Nothing Special   »   [go: up one dir, main page]

WO2021212496A1 - 一种电池检测的方法和装置 - Google Patents

一种电池检测的方法和装置 Download PDF

Info

Publication number
WO2021212496A1
WO2021212496A1 PCT/CN2020/086781 CN2020086781W WO2021212496A1 WO 2021212496 A1 WO2021212496 A1 WO 2021212496A1 CN 2020086781 W CN2020086781 W CN 2020086781W WO 2021212496 A1 WO2021212496 A1 WO 2021212496A1
Authority
WO
WIPO (PCT)
Prior art keywords
failure
battery
degree
message
state parameter
Prior art date
Application number
PCT/CN2020/086781
Other languages
English (en)
French (fr)
Inventor
程康
王甲佳
朱泽敏
Original Assignee
华为技术有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 华为技术有限公司 filed Critical 华为技术有限公司
Priority to EP20932184.3A priority Critical patent/EP4130766A4/en
Priority to PCT/CN2020/086781 priority patent/WO2021212496A1/zh
Priority to CN202080004896.4A priority patent/CN112639495A/zh
Priority to JP2022564504A priority patent/JP2023522468A/ja
Priority to KR1020227040401A priority patent/KR20230006855A/ko
Publication of WO2021212496A1 publication Critical patent/WO2021212496A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
    • G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
    • G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
    • G01R31/392—Determining battery ageing or deterioration, e.g. state of health
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60L—PROPULSION OF ELECTRICALLY-PROPELLED VEHICLES; SUPPLYING ELECTRIC POWER FOR AUXILIARY EQUIPMENT OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRODYNAMIC BRAKE SYSTEMS FOR VEHICLES IN GENERAL; MAGNETIC SUSPENSION OR LEVITATION FOR VEHICLES; MONITORING OPERATING VARIABLES OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRIC SAFETY DEVICES FOR ELECTRICALLY-PROPELLED VEHICLES
    • B60L3/00—Electric devices on electrically-propelled vehicles for safety purposes; Monitoring operating variables, e.g. speed, deceleration or energy consumption
    • B60L3/0023—Detecting, eliminating, remedying or compensating for drive train abnormalities, e.g. failures within the drive train
    • B60L3/0046—Detecting, eliminating, remedying or compensating for drive train abnormalities, e.g. failures within the drive train relating to electric energy storage systems, e.g. batteries or capacitors
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60L—PROPULSION OF ELECTRICALLY-PROPELLED VEHICLES; SUPPLYING ELECTRIC POWER FOR AUXILIARY EQUIPMENT OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRODYNAMIC BRAKE SYSTEMS FOR VEHICLES IN GENERAL; MAGNETIC SUSPENSION OR LEVITATION FOR VEHICLES; MONITORING OPERATING VARIABLES OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRIC SAFETY DEVICES FOR ELECTRICALLY-PROPELLED VEHICLES
    • B60L58/00—Methods or circuit arrangements for monitoring or controlling batteries or fuel cells, specially adapted for electric vehicles
    • B60L58/10—Methods or circuit arrangements for monitoring or controlling batteries or fuel cells, specially adapted for electric vehicles for monitoring or controlling batteries
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60L—PROPULSION OF ELECTRICALLY-PROPELLED VEHICLES; SUPPLYING ELECTRIC POWER FOR AUXILIARY EQUIPMENT OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRODYNAMIC BRAKE SYSTEMS FOR VEHICLES IN GENERAL; MAGNETIC SUSPENSION OR LEVITATION FOR VEHICLES; MONITORING OPERATING VARIABLES OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRIC SAFETY DEVICES FOR ELECTRICALLY-PROPELLED VEHICLES
    • B60L58/00—Methods or circuit arrangements for monitoring or controlling batteries or fuel cells, specially adapted for electric vehicles
    • B60L58/10—Methods or circuit arrangements for monitoring or controlling batteries or fuel cells, specially adapted for electric vehicles for monitoring or controlling batteries
    • B60L58/16—Methods or circuit arrangements for monitoring or controlling batteries or fuel cells, specially adapted for electric vehicles for monitoring or controlling batteries responding to battery ageing, e.g. to the number of charging cycles or the state of health [SoH]
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
    • G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
    • G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
    • G01R31/367—Software therefor, e.g. for battery testing using modelling or look-up tables
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
    • G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
    • G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
    • G01R31/382—Arrangements for monitoring battery or accumulator variables, e.g. SoC
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
    • G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
    • G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
    • G01R31/382—Arrangements for monitoring battery or accumulator variables, e.g. SoC
    • G01R31/3842—Arrangements for monitoring battery or accumulator variables, e.g. SoC combining voltage and current measurements
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
    • G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
    • G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
    • G01R31/385—Arrangements for measuring battery or accumulator variables
    • G01R31/387—Determining ampere-hour charge capacity or SoC
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
    • G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
    • G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
    • G01R31/389—Measuring internal impedance, internal conductance or related variables
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
    • G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
    • G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
    • G01R31/396—Acquisition or processing of data for testing or for monitoring individual cells or groups of cells within a battery
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60L—PROPULSION OF ELECTRICALLY-PROPELLED VEHICLES; SUPPLYING ELECTRIC POWER FOR AUXILIARY EQUIPMENT OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRODYNAMIC BRAKE SYSTEMS FOR VEHICLES IN GENERAL; MAGNETIC SUSPENSION OR LEVITATION FOR VEHICLES; MONITORING OPERATING VARIABLES OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRIC SAFETY DEVICES FOR ELECTRICALLY-PROPELLED VEHICLES
    • B60L2240/00—Control parameters of input or output; Target parameters
    • B60L2240/40—Drive Train control parameters
    • B60L2240/54—Drive Train control parameters related to batteries
    • B60L2240/547—Voltage
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60L—PROPULSION OF ELECTRICALLY-PROPELLED VEHICLES; SUPPLYING ELECTRIC POWER FOR AUXILIARY EQUIPMENT OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRODYNAMIC BRAKE SYSTEMS FOR VEHICLES IN GENERAL; MAGNETIC SUSPENSION OR LEVITATION FOR VEHICLES; MONITORING OPERATING VARIABLES OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRIC SAFETY DEVICES FOR ELECTRICALLY-PROPELLED VEHICLES
    • B60L2240/00—Control parameters of input or output; Target parameters
    • B60L2240/40—Drive Train control parameters
    • B60L2240/54—Drive Train control parameters related to batteries
    • B60L2240/549—Current
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60L—PROPULSION OF ELECTRICALLY-PROPELLED VEHICLES; SUPPLYING ELECTRIC POWER FOR AUXILIARY EQUIPMENT OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRODYNAMIC BRAKE SYSTEMS FOR VEHICLES IN GENERAL; MAGNETIC SUSPENSION OR LEVITATION FOR VEHICLES; MONITORING OPERATING VARIABLES OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRIC SAFETY DEVICES FOR ELECTRICALLY-PROPELLED VEHICLES
    • B60L2250/00—Driver interactions
    • B60L2250/10—Driver interactions by alarm
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60L—PROPULSION OF ELECTRICALLY-PROPELLED VEHICLES; SUPPLYING ELECTRIC POWER FOR AUXILIARY EQUIPMENT OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRODYNAMIC BRAKE SYSTEMS FOR VEHICLES IN GENERAL; MAGNETIC SUSPENSION OR LEVITATION FOR VEHICLES; MONITORING OPERATING VARIABLES OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRIC SAFETY DEVICES FOR ELECTRICALLY-PROPELLED VEHICLES
    • B60L2250/00—Driver interactions
    • B60L2250/16—Driver interactions by display

Definitions

  • This application relates to the field of battery technology, and more specifically, to a method, device and chip system for battery detection.
  • Lithium-ion power battery accidents usually manifest themselves as temperature rise, smoke, fire or even explosion with thermal runaway as the core.
  • the lithium-ion power battery accident on electric vehicles threatens the safety of people’s lives and property, and seriously hinders the large-scale industrial application of electric vehicles.
  • the thermal runaway of the power battery is not an instant process, but a gradually spreading process. If we can detect battery failure at an early stage, and take preventive measures in advance or warn car owners to hurry up to repair, we can avoid the development of thermal runaway and cause personal and property losses. Therefore, how to accurately assess the degree of battery failure and provide countermeasures is a problem that needs to be solved urgently.
  • the present application provides a method and device for battery detection.
  • a service system including a failure model obtained by training
  • the failure degree is obtained, and the failure degree is sent to the vehicle-mounted equipment and/or terminal equipment. It is helpful to accurately assess the failure risk of the battery and reduce the loss caused by the failure of the battery.
  • a method for battery detection includes: acquiring a first battery state parameter of the battery; and determining a first failure degree according to the first battery state parameter and a failure model, wherein the first The degree of failure is used to indicate the degree of failure of the battery corresponding to the first battery state parameter, and the failure model is trained based on the second battery state parameter and a second degree of failure, and the second degree of failure is obtained through testing.
  • the failure degree of the battery of the same specification under the second battery state parameter, the battery state parameter includes at least one of the following parameters: discharge voltage, discharge current, charging temperature; sending a first message, the first message including the first A degree of failure.
  • the failure degree is obtained, and the failure degree is sent to the on-board equipment and/or terminal equipment, which is conducive to accurately assessing the failure risk of the battery and reducing the battery Loss caused by failure.
  • the determining the first failure degree according to the first battery state parameter and the failure model specifically includes: according to the discharge included in the first battery state parameter At least one parameter of voltage, discharge current, and charging temperature determines the internal resistance of the battery, and the internal resistance of the battery is used to determine the first degree of failure.
  • the accuracy of battery failure detection can be improved.
  • a second message is sent, and the second message is used to instruct the battery There is a risk of failure.
  • the personal and property losses caused by the battery failure can be reduced.
  • the method before the first degree of failure is determined according to the first battery state parameter and the failure model, the method further includes: receiving a third message, so The third message is used to request detection of the battery.
  • the user experience can be improved, and the user's need for battery detection at any time can be met.
  • the sending the first message specifically includes: sending the first message within a first preset time after the first battery state parameter is acquired.
  • the effect of periodically detecting the battery can be achieved, and the user experience is improved.
  • the method further includes: inputting the second battery state parameter into the original model to obtain a third degree of failure; and adjusting the parameters of the original model to Make the deviation of the third degree of failure and the second degree of failure within a preset range; use the modulated original model as the failure model.
  • Adjusting the failure model through the original model can effectively improve the accuracy of the failure model, thereby improving the accuracy of battery detection.
  • a method for battery detection includes: sending a first message, the first message being used to request battery detection; and receiving a second message, the second message including the first degree of failure , Wherein the first degree of failure is used to indicate the degree of failure of the battery corresponding to the first battery state parameter, the failure model is trained based on the second battery state parameter and the second degree of failure, the first The second failure degree is the failure degree of the battery of the same specification obtained through detection under the second battery state parameter, and the battery state parameter includes at least one of the following parameters: discharge voltage, discharge current, and charge temperature.
  • the failure degree based on the failure model can be obtained, the risk of battery failure can be accurately understood, and the loss caused by the thermal runaway of the battery can be reduced.
  • the first message may be sent by a vehicle-mounted device, a terminal device, or an application APP in the terminal device.
  • a third message is received, the third message is used to indicate that the battery has a risk of failure, and the third message is that the service system or the terminal device is in the Sent when the first failure degree is greater than or equal to the first threshold.
  • the method further includes: taking a mandatory action according to the third message.
  • the method further includes: displaying the second message and/or the third message through a display device.
  • the method further includes: sending a first battery state parameter to the service system, where the first battery state parameter includes at least one of the following parameters: Discharge voltage, discharge current, charging temperature.
  • a battery detection device in a third aspect, includes: a first acquisition module for acquiring a first battery state parameter of a battery; a first processing module for acquiring a first battery state parameter according to the first battery state parameter A model to determine a first degree of failure, wherein the first degree of failure is used to indicate the degree of failure of the battery corresponding to the first battery state parameter, and the failure model is based on the second battery state parameter and the second degree of failure Obtained by training, the second degree of failure is the degree of failure of batteries of the same specification obtained through testing under the second battery state parameter, and the battery state parameter includes at least one of the following parameters: discharge voltage, discharge current, and charge temperature;
  • the first sending module is configured to send a first message, where the first message includes the first degree of failure.
  • the processing module is specifically configured to: determine according to at least one of the discharge voltage, the discharge current, and the charging temperature included in the first battery state parameter The internal resistance of the battery is used to determine the first degree of failure.
  • the first sending module is further configured to: send a second message when the first degree of failure is greater than or equal to a preset first threshold, so The second message is used to indicate that the battery has a risk of failure.
  • the device further includes: a first receiving module, configured to receive a third message, the third message being used to request detection of the battery.
  • the first sending module is specifically configured to: send the first message within a first preset time after acquiring the first battery state parameter .
  • the first processing module is further configured to: input the second battery state parameter to the original model to obtain a third degree of failure; Parameters so that the deviation between the third degree of failure and the second degree of failure is within a preset range; and the original model after the modulation is used as the failure model.
  • a battery detection device in a fourth aspect, includes: a second sending module, configured to send a first message, the first message being used to request battery detection; and a second receiving module, configured to receive A second message, where the second message includes a first degree of failure, wherein the first degree of failure is used to indicate the degree of failure of the battery corresponding to the first battery state parameter, and the failure model is based on the second battery
  • the state parameter and the second failure degree are obtained through training, the second failure degree is the failure degree of the same specification battery under the second battery state parameter obtained after testing, and the battery state parameter includes at least one of the following parameters: discharge voltage , Discharge current, charging temperature.
  • the second receiving module is further configured to: receive a third message, where the third message is used to indicate that the battery has a risk of failure, and the third The message is sent by the service system or the terminal device when the first degree of failure is greater than or equal to the first threshold.
  • the device further includes: a second processing module, configured to take a mandatory action according to the third message.
  • the device further includes: a display module configured to display the second message and/or the third message through the display device.
  • the second sending module is further configured to send a first battery state parameter, where the first battery state parameter includes at least one of the following parameters: discharge Voltage, discharge current, charging temperature.
  • a computer-readable storage medium including a computer program, which when running on a computer device, causes the processing unit in the computer device to execute the first aspect or any possible implementation of the first aspect The method in the way.
  • a computer-readable storage medium including a computer program, which when running on a computer device, causes the processing unit in the computer device to execute any possible implementation such as the second aspect or the second aspect The method in the way.
  • a computer program product including a computer program, which, when run on a computer device, causes the processing unit in the computer device to execute the first aspect or any possible implementation manner of the first aspect The method described.
  • a computer program product including a computer program, which, when run on a computer device, causes the processing unit in the computer device to execute the second aspect or any possible implementation manner of the second aspect The method described.
  • a chip in a ninth aspect, includes a processor and a memory, the memory is used to store a computer program, and the processor is used to call and run the computer program stored in the memory to execute the first aspect Or a method in any possible implementation of the first aspect.
  • a chip in a tenth aspect, includes a processor and a memory, the memory is used to store a computer program, and the processor is used to call and run the computer program stored in the memory to execute the second aspect Or a method in any possible implementation of the second aspect.
  • a chip system in an eleventh aspect, includes at least one processor.
  • the at least one processor When a program instruction is executed in the at least one processor, the at least one processor is caused to perform the battery detection described above. Methods.
  • Fig. 1 is a schematic diagram of a battery detection method in the prior art.
  • Figure 2 is a schematic structural diagram of a system architecture provided by an embodiment of the present application.
  • FIG. 3 is a schematic diagram of battery detection according to a convolutional neural network model provided by an embodiment of the present application.
  • Fig. 4 is a schematic diagram of a chip hardware structure provided by an embodiment of the present application.
  • Fig. 5 is a schematic diagram of a battery detection method according to an embodiment of the present application.
  • Fig. 6 is a schematic diagram of another battery detection method according to an embodiment of the present application.
  • FIG. 7 is a schematic diagram of the principle of battery failure detection according to an embodiment of the present application.
  • FIG. 8 is a schematic diagram of a system architecture of an embodiment of the present application.
  • Fig. 9 is a schematic diagram of module interaction in an embodiment of the present application.
  • Fig. 10 is a schematic diagram of a battery detection device according to an embodiment of the present application.
  • FIG. 11 is a schematic diagram of another battery detection device according to an embodiment of the present application.
  • the embodiments of the present application can be used for battery failure detection of electric vehicles, and can also be used for battery failure detection of various objects driven by power batteries such as electric bicycles.
  • the prior art provides a method for detecting the internal short-circuit condition of the battery based on voltage.
  • management system collects the terminal voltage of each battery in the battery pack and compares the terminal voltage with the average voltage. When the deviation between the terminal voltage and the average voltage is greater than the safety threshold, it is determined that the battery has a potential safety hazard.
  • the method of detecting the battery by voltage does not need to use the least square method for calculation, which reduces the requirements of the battery detection method for hardware devices.
  • the terminal voltage of the battery is not only related to the internal resistance of the battery, but is also easily affected by many other factors, resulting in low accuracy and easy misjudgment.
  • This application provides a method for battery detection.
  • the failure degree is obtained, and the failure degree is sent to the vehicle-mounted equipment and/or terminal equipment, which is beneficial to Accurately assess the risk of battery failure and reduce the loss caused by battery failure.
  • a neural network can be composed of neural units.
  • a neural unit can refer to an arithmetic unit that takes x s and intercept 1 as inputs.
  • the output of the arithmetic unit can be:
  • s 1, 2,...n, n is a natural number greater than 1
  • W s is the weight of x s , where W and x are both vectors
  • b is the bias of the neural unit.
  • f is the activation function of the neural unit, which is used to introduce nonlinear characteristics into the neural network to convert the input signal in the neural unit into an output signal.
  • the output signal of the activation function can be used as the input of the next convolutional layer, and the activation function can be a sigmoid function.
  • a neural network is a network formed by connecting multiple above-mentioned single neural units together, that is, the output of one neural unit can be the input of another neural unit.
  • the input of each neural unit can be connected with the local receptive field of the previous layer to extract the characteristics of the local receptive field.
  • the local receptive field can be a region composed of several neural units.
  • Deep neural network also known as multi-layer neural network
  • the DNN is divided according to the positions of different layers.
  • the neural network inside the DNN can be divided into three categories: input layer, hidden layer, and output layer.
  • the first layer is the input layer
  • the last layer is the output layer
  • the number of layers in the middle are all hidden layers.
  • the layers are fully connected, that is to say, any neuron in the i-th layer must be connected to any neuron in the i+1th layer.
  • DNN looks complicated, it is not complicated in terms of the work of each layer. Simply put, it is the following linear relationship expression: in, Is the input vector, Is the output vector, Is the offset vector, W is the weight matrix (also called coefficient), and ⁇ () is the activation function.
  • Each layer is just the input vector After such a simple operation, the output vector is obtained Due to the large number of DNN layers, the coefficient W and the offset vector The number is also relatively large.
  • DNN The definition of these parameters in DNN is as follows: Take coefficient W as an example: Suppose in a three-layer DNN, the linear coefficients from the fourth neuron in the second layer to the second neuron in the third layer are defined as The superscript 3 represents the number of layers where the coefficient is located, and the subscript corresponds to the third layer index 2 of the output and the second layer index 4 of the input.
  • the coefficient from the kth neuron in the L-1th layer to the jth neuron in the Lth layer is defined as
  • Convolutional neural network (convolutional neuron network, CNN) is a deep neural network with a convolutional structure.
  • the convolutional neural network contains a feature extractor composed of a convolutional layer and a sub-sampling layer.
  • the feature extractor can be regarded as a filter.
  • the convolutional layer refers to the neuron layer that performs convolution processing on the input signal in the convolutional neural network.
  • a neuron can be connected to only part of the neighboring neurons.
  • a convolutional layer usually contains several feature planes, and each feature plane can be composed of some rectangularly arranged neural units. Neural units in the same feature plane share weights, and the shared weights here are the convolution kernels.
  • Sharing weight can be understood as the way of extracting image information has nothing to do with location.
  • the convolution kernel can be initialized in the form of a matrix of random size. In the training process of the convolutional neural network, the convolution kernel can obtain reasonable weights through learning. In addition, the direct benefit of sharing weights is to reduce the connections between the layers of the convolutional neural network, and at the same time reduce the risk of overfitting.
  • Recurrent Neural Networks are used to process sequence data.
  • the layers are fully connected, and the nodes in each layer are disconnected.
  • this ordinary neural network has solved many problems, it is still powerless for many problems. For example, if you want to predict what the next word of a sentence will be, you generally need to use the previous word, because the preceding and following words in a sentence are not independent. The reason why RNN is called recurrent neural network is that the current output of a sequence is also related to the previous output.
  • RNN can process sequence data of any length.
  • the training of RNN is the same as the training of traditional CNN or DNN.
  • the neural network can use the back propagation (BP) algorithm to modify the size of the parameters in the initial neural network model during the training process, so that the reconstruction error loss of the neural network model becomes smaller and smaller. Specifically, forwarding the input signal to the output will cause error loss, and the parameters in the initial neural network model are updated by backpropagating the error loss information, so that the error loss is converged.
  • the back-propagation algorithm is a back-propagation motion dominated by error loss, and aims to obtain the optimal parameters of the neural network model, such as the weight matrix.
  • an embodiment of the present application provides a system architecture 200.
  • a data collection device 260 is used to collect training data.
  • the training data may include battery state parameters and the degree of failure corresponding to the battery state parameters.
  • the data collection device 260 stores the training data in the database 230, and the training device 220 trains to obtain the target model/rule 201 based on the training data maintained in the database 230.
  • the training device 220 processes the input battery state parameters and the original failure degree, and compares the output failure degree with the original failure degree until the training device 220 The difference between the output failure degree and the original failure degree is less than a certain threshold, thereby completing the training of the target model/rule 101.
  • the above-mentioned target model/rule 201 can be used to implement the battery detection method of the embodiment of the present application, that is, the battery state parameter is input into the target model/rule 201 after relevant preprocessing, and then the failure degree result can be obtained.
  • the target model/rule 201 in the embodiment of the present application may specifically be a neural network.
  • the training data maintained in the database 230 may not all come from the collection of the data collection device 260, and may also be received from other devices.
  • the training device 220 does not necessarily perform the training of the target model/rule 201 completely based on the training data maintained by the database 230. It may also obtain training data from the cloud or other places for model training. The above description should not be used as a reference to this application. Limitations of the embodiment.
  • the target model/rule 201 trained according to the training device 220 can be applied to different systems or devices, such as the execution device 210 shown in FIG. 2, which can be a terminal, such as a mobile phone terminal, a tablet computer, notebook computers, augmented reality (AR) AR/virtual reality (VR), vehicle-mounted terminals, etc., can also be servers or clouds.
  • the execution device 210 is configured with an input/output (input/output, I/O) interface 212 for data interaction with external devices.
  • the user can input data to the I/O interface 212 through the client device 240.
  • the input data in the embodiment of the present application may include: battery state parameters and the degree of failure corresponding to the battery state parameters.
  • the preprocessing module 213 and the preprocessing module 214 are used to perform preprocessing according to the input data (such as battery state parameters) received by the I/O interface 212.
  • the preprocessing module 213 and the preprocessing module may not be provided. 214 (there may only be one preprocessing module), and the calculation module 211 is directly used to process the input data.
  • the execution device 210 When the execution device 210 preprocesses input data, or when the calculation module 211 of the execution device 210 performs calculations and other related processing, the execution device 210 can call data, codes, etc. in the data storage system 250 for corresponding processing. , The data, instructions, etc. obtained by corresponding processing may also be stored in the data storage system 150.
  • the I/O interface 212 returns the processing result, as described above, to the client device 240 to provide the user with the degree of failure.
  • the training device 220 can generate corresponding target models/rules 201 based on different training data for different goals or tasks, and the corresponding target models/rules 201 can be used to achieve the above goals or complete The above tasks provide users with the desired results.
  • the user can manually set input data, and the manual setting can be operated through the interface provided by the I/O interface 212.
  • the client device 240 can automatically send input data to the I/O interface 212. If the client device 240 is required to automatically send the input data and the user's authorization is required, the user can set the corresponding authority in the client device 240. The user can view the result output by the execution device 210 on the client device 240, and the specific presentation form may be a specific manner such as display, sound, and action.
  • the client device 240 can also be used as a data collection terminal to collect the input data of the input I/O interface 212 and the output result of the output I/O interface 212 as new sample data, and store it in the database 230 as shown in the figure.
  • the I/O interface 212 directly uses the input data input to the I/O interface 212 and the output result of the output I/O interface 212 as a new sample as shown in the figure. The data is stored in the database 230.
  • FIG. 2 is only a schematic diagram of a system architecture provided by an embodiment of the present application, and the positional relationship between the devices, devices, modules, etc. shown in the figure does not constitute any limitation.
  • the data The storage system 250 is an external memory relative to the execution device 210. In other cases, the data storage system 250 may also be placed in the execution device 210.
  • the target model/rule 201 is obtained by training according to the training device 220.
  • the target model/rule 201 may be the neural network in this application in the embodiment of the application.
  • the neural network provided in the embodiment of the application is It can be CNN, deep convolutional neural networks (DCNN), recurrent neural network (RNNS) and so on.
  • CNN is a very common neural network
  • the structure of CNN will be introduced in detail below in conjunction with Figure 3.
  • a convolutional neural network is a deep neural network with a convolutional structure. It is a deep learning architecture.
  • the deep learning architecture refers to the algorithm of machine learning. Multi-level learning is carried out on the abstract level of.
  • CNN is a feed-forward artificial neural network. Each neuron in the feed-forward artificial neural network can respond to the input image.
  • a convolutional neural network (CNN) 300 may include an input layer 310, a convolutional layer/pooling layer 320 (the pooling layer is optional), and a neural network layer 330.
  • CNN convolutional neural network
  • the convolutional layer/pooling layer 320 may include layers 321-326, for example: in one implementation, layer 321 is a convolutional layer, layer 322 is a pooling layer, and layer 323 is a convolutional layer. Layers, 324 is a pooling layer, 325 is a convolutional layer, and 326 is a pooling layer; in another implementation, 321 and 322 are convolutional layers, 323 is a pooling layer, and 324 and 325 are convolutional layers. Layer, 326 is the pooling layer. That is, the output of the convolutional layer can be used as the input of the subsequent pooling layer, or as the input of another convolutional layer to continue the convolution operation.
  • the convolution layer 321 can include many convolution operators.
  • the convolution operator is also called a kernel. Its function in battery detection is equivalent to a filter that extracts specific information from the input battery state parameters and other information.
  • the sub can essentially be a weight matrix. This weight matrix is usually pre-defined. In the process of convolution on the battery state parameters, the weight matrix is usually processed one by one in the input battery state parameters to complete the slave battery. The work of extracting specific features from state parameters.
  • the size of the weight matrix should be related to the size of the battery state parameters. It should be noted that the depth dimension of the weight matrix and the depth dimension of the input battery state parameters are the same. During the convolution operation, the weight The matrix will extend to the full depth of the input battery state parameters.
  • convolution with a single weight matrix will produce a single depth dimension convolution output, but in most cases, a single weight matrix is not used, but multiple weight matrices of the same size (row ⁇ column) are applied. That is, multiple homogeneous matrices.
  • the output of each weight matrix is stacked to form the depth dimension of the convolutional battery state parameter, where the dimension can be understood as determined by the "multiple" mentioned above.
  • Different weight matrices can be used to extract different characteristics of battery state parameters. For example, one weight matrix is used to extract discharge voltage data, another weight matrix is used to extract discharge current data, and another weight matrix is used to extract charging temperature.
  • weight values in these weight matrices need to be obtained through a lot of training in practical applications.
  • the weight matrices formed by the weight values obtained through training can be used to extract information from the input battery state parameters, so that the convolutional neural network 300 performs correctly. Prediction.
  • the initial convolutional layer (such as 321) often extracts more general features, which can also be called low-level features; with the convolutional neural network
  • the features extracted by the subsequent convolutional layers (for example, 326) become more and more complex, such as features such as high-level semantics, and features with higher semantics are more suitable for the problem to be solved.
  • the convolutional layer can be a convolutional layer followed by a layer.
  • the pooling layer can also be a multi-layer convolutional layer followed by one or more pooling layers. In the battery detection process, the sole purpose of the pooling layer is to reduce the space size of the battery state parameters.
  • Neural network layer 330
  • the convolutional neural network 300 After processing by the convolutional layer/pooling layer 320, the convolutional neural network 300 is not enough to output the required output information. Because as mentioned above, the convolutional layer/pooling layer 320 only extracts features and reduces the parameters brought by the input state parameters. However, in order to generate final output information (required class information or other related information), the convolutional neural network 300 needs to use the neural network layer 330 to generate one or a group of required classes of output. Therefore, the neural network layer 330 can include multiple hidden layers (331, 332 to 33n as shown in FIG. 3) and an output layer 340. The parameters contained in the multiple hidden layers can be based on specific task types. The relevant training data is obtained by pre-training.
  • the output layer 340 After the multiple hidden layers in the neural network layer 330, that is, the final layer of the entire convolutional neural network 300 is the output layer 340.
  • the output layer 340 has a loss function similar to the classification cross entropy, which is specifically used to calculate the prediction error.
  • the convolutional neural network 300 shown in FIG. 3 is only used as an example of a convolutional neural network. In specific applications, the convolutional neural network may also exist in the form of other network models.
  • FIG. 4 is a hardware structure of a chip provided by an embodiment of the application, and the chip includes a neural network processor 40.
  • the chip can be set in the execution device 210 as shown in FIG. 2 to complete the calculation work of the calculation module 211.
  • the chip can also be set in the training device 220 shown in FIG. 2 to complete the training work of the training device 220 and output the target model/rule 201.
  • the algorithms of each layer in the convolutional neural network as shown in FIG. 3 can be implemented in the chip as shown in FIG. 4.
  • the neural network processor NPU 40 NPU is mounted as a coprocessor to a main central processing unit (central processing unit, CPU) (host CPU), and the main CPU distributes tasks.
  • the core part of the NPU is the arithmetic circuit 40.
  • the controller 404 controls the arithmetic circuit 403 to extract data from the memory (weight memory or input memory) and perform calculations.
  • the arithmetic circuit 403 includes multiple processing units (process engines, PE). In some implementations, the arithmetic circuit 403 is a two-dimensional systolic array. The arithmetic circuit 403 may also be a one-dimensional systolic array or other electronic circuit capable of performing mathematical operations such as multiplication and addition. In some implementations, the arithmetic circuit 403 is a general-purpose matrix processor.
  • the input matrix A in this embodiment of the application can be a matrix of battery state parameters, a weight matrix B, and an output matrix C.
  • the output matrix still being developed in this embodiment of the application can be a matrix of failure degree .
  • the arithmetic circuit fetches the data corresponding to matrix B from the weight memory 402 and caches it on each PE in the arithmetic circuit.
  • the arithmetic circuit fetches the matrix A data and matrix B from the input memory 401 to perform matrix operations, and the partial result or final result of the obtained matrix is stored in an accumulator 408.
  • the vector calculation unit 407 can perform further processing on the output of the arithmetic circuit, such as vector multiplication, vector addition, exponential operation, logarithmic operation, size comparison, and so on.
  • the vector calculation unit 407 can be used for network calculations in the non-convolutional/non-FC layer of the neural network, such as pooling, batch normalization, local response normalization, etc. .
  • the vector calculation unit 407 can store the processed output vector in the unified buffer 406.
  • the vector calculation unit 407 may apply a nonlinear function to the output of the arithmetic circuit 403, such as a vector of accumulated values, to generate the activation value.
  • the vector calculation unit 407 generates a normalized value, a combined value, or both.
  • the processed output vector can be used as an activation input to the arithmetic circuit 403, for example for use in subsequent layers in a neural network.
  • the unified memory 406 is used to store input data and output data.
  • the weight data directly transfers the input data in the external memory to the input memory 401 and/or the unified memory 406 through the storage unit access controller 405 (direct memory access controller, DMAC), and stores the weight data in the external memory into the weight memory 402, And the data in the unified memory 406 is stored in the external memory.
  • DMAC direct memory access controller
  • the bus interface unit (BIU) 410 is used to implement interaction between the main CPU, the DMAC, and the fetch memory 409 through the bus.
  • An instruction fetch buffer 409 connected to the controller 404 is used to store instructions used by the controller 404;
  • the controller 404 is used to call the instructions cached in the memory 409 to control the working process of the computing accelerator.
  • the unified memory 406, the input memory 401, the weight memory 402, and the instruction fetch memory 409 are all on-chip (On-Chip) memories.
  • the external memory is a memory external to the NPU.
  • the external memory can be a double data rate synchronous dynamic random access memory.
  • Memory double data rate synchronous dynamic random access memory, DDR SDRAM), high bandwidth memory (HBM) or other readable and writable memory.
  • each layer in the convolutional neural network shown in FIG. 3 may be executed by the arithmetic circuit 403 or the vector calculation unit 407.
  • Fig. 5 shows a schematic diagram of a battery detection method according to an embodiment of the present application. As shown in Fig. 5, the method includes steps S510 to S530. These three steps are described in detail below.
  • S510 The service system obtains the first battery state parameter of the battery.
  • the service system may request the vehicle-mounted system to send the first battery state parameter of the battery by sending a message to the vehicle-mounted system, or the service system may retrieve the previously stored battery state data from the storage module.
  • the vehicle-mounted system in the embodiments of the present application can obtain the state parameters of the vehicle battery.
  • the battery state parameters may include: mileage, current battery SOC, rechargeable battery temperature, time, discharge voltage, discharge current, battery model, etc.
  • S520 The service system determines the first degree of failure according to the first battery state parameter and the failure model.
  • the service system may display the detection result on the device after obtaining the above-mentioned first failure degree, and the display form may be voice, text, etc.
  • the first degree of failure indicates the degree of failure in the current state of the battery
  • the failure model is obtained by training based on the second battery state parameter and the second degree of failure
  • the second degree of failure is the same as that obtained through detection.
  • the failure degree of the specification battery under the second battery state parameter, and the battery state parameter includes at least one of the following parameters: discharge voltage, discharge current, and charge temperature.
  • battery failure is a gradual spreading process, for example, it can be divided into three stages: the initial stage of internal short circuit, the middle stage of internal short circuit, and the final stage of internal short circuit (thermal runaway).
  • the battery's electrical characteristics such as voltage, current
  • thermal characteristics temperature
  • the battery's electrical characteristics such as voltage, current
  • thermal characteristics temperature
  • the above-mentioned second battery state parameter may be the acquired measurement data of a real battery of the same specification.
  • the second degree of failure may be the first degree of battery failure that is actually recorded when the battery is working normally. 2.
  • the failure degree corresponding to the battery state parameter or it can be the actual recorded failure degree when the battery fails; or the test data can also be the test data obtained after the vehicle battery is simulated in a laboratory environment. For example, set the battery discharge temperature, load, etc. for discharge test, and record the battery discharge voltage, temperature, internal resistance and other test values.
  • the second failure degree can be the failure recorded during the normal operation of the battery under the simulation test.
  • the degree can also be the failure degree data recorded when the battery fails under the simulation test.
  • the failure degree of the battery can be obtained, and the risk of battery failure can be accurately assessed, thereby reducing the personal and property losses caused by the thermal runaway of the battery.
  • the above failure model is obtained based on algorithm training, which includes: inputting the second battery state parameter to the original model to obtain the third failure degree; adjusting the parameters of the original model so that the first The deviation between the third failure degree and the second failure degree is within a preset range; and the original model after the modulation is used as the failure model.
  • the aforementioned failure model may be obtained from the system shown in FIG. 2.
  • the failure model in the embodiment of the present application may be obtained through training by the remote service itself, or may also be obtained from other devices.
  • the service system may also detect the failure degree of the battery according to the internal resistance of the battery.
  • the determining the first failure degree according to the first battery state parameter and the failure model specifically includes: according to at least one of the discharge voltage, the discharge current, and the charging temperature included in the first battery state parameter , Determine the internal resistance of the battery, and the internal resistance of the battery is used to determine the first degree of failure.
  • the service system of the embodiment of the present application may detect the battery after receiving the request message sent by the vehicle-mounted device and/or the terminal device. Specifically, according to the first battery state parameter and the failure model, Before determining the first degree of failure, the method further includes: receiving a third message, where the third message is used to request detection of the battery.
  • the service system may obtain the third message before obtaining the first battery state parameter, or may also obtain the third message before the service system determines the degree of failure according to the state parameter and the failure model.
  • the user's need to detect the battery at any time can be met, and the user experience can be improved.
  • the service system in the embodiment of the present application may be installed inside the vehicle, or, when the vehicle or the object using the power battery cannot meet the hardware requirements, optionally, the service system in the embodiment of the present application may also be independent of the vehicle. Or remote service system of other objects.
  • S530 The service system sends a first message, where the first message includes the first degree of failure.
  • the service system can send the first degree of failure.
  • Application APP or you can send the message to the manufacturer’s service center and share it with other application modules on the remote server.
  • the service system may also send a reminder message.
  • a reminder message when the first degree of failure is greater than or equal to a preset first threshold, a second message is sent, and the second message is used to indicate the battery There is a risk of failure.
  • the second message may include a warning message, such as reminding the user to repair or replace the battery, or include a message for instructing the vehicle to take compulsory measures, such as forcing the vehicle to decelerate or stop.
  • the user can judge the current battery failure.
  • the user can deal with the vehicle battery according to his needs, such as repairing, etc., and at the same time Sending an alarm when the threshold is exceeded can further protect the personal and property safety of the user.
  • the service system can also perform internal short-circuit detection on the battery according to a preset time.
  • the sending the first message specifically includes: sending the first message within a first preset time after acquiring the first battery state parameter.
  • the service system can send periodic battery detection information to vehicle-mounted equipment or terminal equipment, which improves user experience and reduces losses due to battery failure.
  • Fig. 6 shows a schematic diagram of another battery detection method according to an embodiment of the present application. As shown in Figure 6, the method includes steps S610 and S620. These two steps are described in detail below.
  • S610 Send a first message, where the first message is used to request detection of the battery.
  • S620 Receive a second message, where the second message includes the first degree of failure.
  • the first degree of failure is used to indicate the degree of failure of the battery corresponding to the first battery state parameter
  • the failure model is trained based on the second battery state parameter and the second degree of failure
  • the first The second failure degree is the failure degree of the battery of the same specification under the second battery state parameter obtained through detection
  • the battery state parameter includes at least one of the following parameters: discharge voltage, discharge current, and charge temperature.
  • the subject sending the first message may be a vehicle-mounted device, or a terminal device, or a mobile APP in the terminal device, which is not limited in the embodiment of the present application.
  • the in-vehicle device or terminal device or application APP can receive reminder messages, etc., specifically, receive a third message, the third message is used to indicate that the battery is at risk of failure, and the third message is a service system Or sent by the terminal device when the first degree of failure is greater than or equal to a first threshold.
  • the third message can be used to instruct the in-vehicle device to take mandatory measures, such as forced deceleration, forced parking, etc., or the third message can also be used to remind the user to perform battery maintenance as soon as possible Or replace and so on.
  • the in-vehicle device, terminal device, or application APP can display the second message or the third message, for example, in the form of a display screen or voice.
  • the second message and the third message can be displayed on the display device. /Or the third message.
  • the in-vehicle device may send a battery state parameter to the service system before requesting the service system to perform battery detection.
  • the in-vehicle device sends a first battery state parameter, where the first battery state parameter includes at least one of the following Parameters: discharge voltage, discharge current, charging temperature.
  • FIG. 7 shows a schematic diagram of the principle of battery failure detection according to an embodiment of the present application.
  • the schematic diagram mainly includes a battery state parameter acquisition part, a failure model part, and a result output part.
  • the battery state parameter acquisition part may include: battery state parameters and internal resistance estimation.
  • the battery state parameters may include: discharge voltage, discharge current, current charging temperature and other state parameters.
  • the above-mentioned battery state parameters are sent by the vehicle-mounted system to the service system, and the service system may obtain the state parameters by sending a request to the vehicle-mounted system, or alternatively, the service system may also retrieve the stored battery state parameters from the storage module.
  • the service system can input these status parameters to the failure model for battery detection.
  • the battery state parameter input to the failure model may also include the internal resistance of the battery.
  • the service system may obtain the current internal resistance value of the battery through a state estimation algorithm according to at least one of the above-mentioned battery state parameters.
  • the estimation algorithm can be: Kalman filter, Bayesian filter, hidden markov model (HMM) or other algorithms to estimate the internal resistance of the battery.
  • HMM hidden markov model
  • the failure model part may include: acquiring test battery data, where the test battery data may also be the second battery state parameter involved in the above application embodiment, where the test battery data may be the acquired test data of the real battery, or the test
  • the data can also be the test data obtained after the vehicle battery is subjected to a simulation test on the vehicle battery in a laboratory environment, such as setting the battery discharge temperature, load, etc. for discharge testing, and recording the battery discharge voltage, temperature, internal resistance, etc. Test value; the failure model part can also include failure model estimation.
  • the algorithm module of the service system can be based on the above test data, according to neural network, long-short-term memory (LSTM), random forest, HMM, etc.
  • the algorithm constructs a failure model about the parameters of the battery discharge state.
  • the neural network shown in Fig. 2 or 3 can be used to obtain the failure model, and the threshold of the degree of battery failure can be obtained.
  • the service system can then output the battery detection result according to the above-mentioned battery state parameters and failure model. Further, an alarm message can also be sent according to the degree of failure threshold.
  • the failure degree of the battery can be obtained, which can accurately assess the risk of battery failure, and then reduce the loss caused by battery failure.
  • FIG. 8 shows a schematic diagram of a system architecture according to an embodiment of the present application.
  • the system architecture of the embodiment of the present application may include a service system 810 and an in-vehicle system 820.
  • the vehicle-mounted system 820 can collect battery-related data (including but not limited to: mileage, current battery SOC, battery temperature, time, discharge voltage, discharge current, battery model, etc.), and send it to the service system through a designated protocol .
  • the vehicle-mounted system 820 may include a data collection module, a data reporting module, a service request module, and a data display module.
  • the service system 810 may include 3 layers, and the first layer may include: a data collection module, a data processing module, and a data storage module.
  • the second layer can include: data analysis module, algorithm module and failure model module.
  • the third layer can include: battery failure detection application module.
  • the service system 810 may have the following functions: after receiving the battery data, the service system parses the data packet, and then sorts and stores it according to the vehicle identification number or other identification; the service system is based on the test battery data, and can use the algorithm module based on the algorithm Generate the relevant failure model and save the model to the failure model module; the service system can receive the detection request from the in-vehicle system or terminal device, or other applications, such as the mobile phone application APP, to perform internal short-circuit detection on the specified battery; service The system sends the detection result to the relevant in-vehicle system or terminal device (such as a mobile phone or mobile APP, etc.), or other application services for data display.
  • the data display mode can be voice, text, etc.
  • the service system 810 can be installed in the car, or can be a remote service system independent of the existence of the car. Setting the service system in the remote service system independent of the existence of the car can overcome the problem of high hardware requirements for the service system.
  • the battery failure detection application module may also include an information interaction module and an internal short circuit detection module.
  • Fig. 9 shows a schematic diagram of module interaction in an embodiment of the present application.
  • the information interaction module receives a battery detection service request sent by the car or the terminal device.
  • the internal short circuit detection module receives a detection instruction from the information interaction module, and calls the data analysis module to obtain battery data.
  • the internal short circuit detection module can be configured with battery discharge characteristics that need to be detected, such as discharge voltage data, discharge current data, and charging temperature data.
  • the data analysis module obtains the current battery state parameters.
  • the service system may send a message to obtain the latest battery data, or the service system may also obtain stored battery state data from the storage module.
  • the car battery data stored in the storage module may include a variety of data, while the internal short-circuit detection may only require a few specific data.
  • the data analysis module can be based on the battery status configured in the internal short-circuit detection module.
  • Parameter type extracts state parameters, and only extracts state parameters for battery detection.
  • the service system can receive service requests from multiple objects.
  • the data analysis module can first identify the vehicle that needs to be tested, and then obtain the battery status of the vehicle battery parameter.
  • the data storage module may also be based on the acquired battery data, such as at least one of the following: discharge voltage data, discharge current data, discharge temperature data, etc., using a state estimation algorithm Obtain the internal resistance of the battery.
  • the failure module receives the state parameter processed by the data analysis module.
  • S950 The failure module detects based on the battery state parameter, obtains the battery failure degree in the current state, and returns it to the information interaction module.
  • S960 The information interaction module returns the detection result to the car, terminal device or mobile phone APP.
  • the information interaction module may also send an alarm message.
  • the alarm message may include: maintenance prompt , Slow down, stop prompt, etc.
  • the information interaction module can also send the invalidation result to other related services, such as the manufacturer's service center.
  • FIG. 10 shows a schematic diagram of a battery detection device according to an embodiment of the present application.
  • the device 1000 includes a first acquiring module 1001, a first processing module 1002, and a first sending module 1003.
  • the device 1000 can be used to implement the battery detection function involved in any of the foregoing method embodiments.
  • the device 1000 may be a service system.
  • the network element or network function may be a network element in a hardware device, a software function running on dedicated hardware, or a virtualization function instantiated on a platform (for example, a cloud platform).
  • the device 1000 can be used as a service system to detect the battery, and execute the steps processed by the service system in the foregoing method embodiment.
  • the first receiving module 1001 and the first sending module 1003 can be used to support the device 1000 to communicate, for example, to perform the sending/receiving actions performed by the service system in FIG. 5 and FIG. 6, the first processing module 1002 can be used to
  • the support device 1000 executes the processing actions in the foregoing method, for example, executes the processing actions executed by the service system in FIG. 5 or FIG. 6. Specifically, you can refer to the following description:
  • the first obtaining module 1001 is used to obtain the first battery state parameter of the battery; the first processing module 1002 is used to determine the first failure degree according to the first battery state parameter and the failure model, wherein the first failure degree is used In order to indicate the degree of failure of the battery corresponding to the first battery state parameter, the failure model is obtained by training based on the second battery state parameter and a second degree of failure, and the second degree of failure is the same specification obtained after testing.
  • the battery state parameter includes at least one of the following parameters: discharge voltage, discharge current, and charging temperature; the first sending module 1003 is configured to send a first message, the first message Including the first degree of failure.
  • the processing module is specifically configured to determine the internal resistance of the battery and the internal resistance of the battery according to at least one of the discharge voltage, discharge current, and charging temperature included in the first battery state parameter.
  • the resistance is used to determine the first degree of failure.
  • the first sending module is further configured to send a second message when the first degree of failure is greater than or equal to a preset first threshold, and the second message is used to indicate that the battery has a failure. risk.
  • the device further includes: a first receiving module, configured to receive a third message, the third message being used to request detection of the battery.
  • the first sending module is specifically configured to send the first message within a first preset time after acquiring the first battery state parameter.
  • the first processing module is further configured to: input the second battery state parameter to the original model to obtain a third failure degree; and adjust the parameters of the original model so that the third failure degree and The deviation of the second failure degree is within a preset range; and the original model after the modulation is used as the failure model.
  • FIG. 11 shows a schematic diagram of a battery detection device according to an embodiment of the present application.
  • the device 1100 includes a second sending module 1101 and a second receiving module 1102.
  • the device 1100 can be used to implement the battery detection function involved in any of the foregoing method embodiments.
  • the device 1100 can be used as a service system to detect the battery, and execute the steps processed by the vehicle-mounted device in the foregoing method embodiment.
  • the second sending module 1101 and the second receiving module 1102 can be used to support the device 1100 to communicate, for example, to perform the sending/receiving actions performed by the in-vehicle device in FIG. 5 and FIG. 6.
  • the device 1100 may further include a second processing module 1103, which may be used to support the device 1100 to execute the processing actions in the foregoing method, for example, execute the processing actions executed by the vehicle-mounted device in FIGS. 2 and 6.
  • the second sending module 1101 is used to send a first message, the first message is used to request the service system to detect the battery; the second receiving module 1102 is used to receive a second message, the second message includes the first failure Degree, wherein the first degree of failure is used to indicate the degree of failure of the battery corresponding to the first battery state parameter, the failure model is trained based on the second battery state parameter and the second degree of failure, the The second degree of failure is the degree of failure of batteries of the same specification under the second battery state parameter obtained through detection, and the battery state parameter includes at least one of the following parameters: discharge voltage, discharge current, and charge temperature.
  • the second receiving module is further configured to: receive a third message, the third message being used to indicate that the battery has a risk of failure, and the third message is that the service system or the terminal device is in the first Sent when the failure degree is greater than or equal to the first threshold.
  • the device further includes: a second processing module, configured to take a mandatory action according to the third message.
  • a second processing module configured to take a mandatory action according to the third message.
  • the device further includes: a display module, configured to display the second message and/or the third message through the display device.
  • a display module configured to display the second message and/or the third message through the display device.
  • the second sending module is further configured to send a first battery state parameter, where the first battery state parameter includes at least one of the following parameters: discharge voltage, discharge current, and charge temperature.
  • the disclosed system, device, and method can be implemented in other ways.
  • the device embodiments described above are merely illustrative, for example, the division of the units is only a logical function division, and there may be other divisions in actual implementation, for example, multiple units or components may be combined or It can be integrated into another system, or some features can be ignored or not implemented.
  • the displayed or discussed mutual coupling or direct coupling or communication connection may be indirect coupling or communication connection through some interfaces, devices or units, and may be in electrical, mechanical or other forms.
  • the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the objectives of the solutions of the embodiments.
  • the functional units in the various embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units may be integrated into one unit.
  • the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer readable storage medium.
  • the technical solution of the present application essentially or the part that contributes to the existing technology or the part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including Several instructions are used to make a computer device (which may be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the methods described in the various embodiments of the present application.
  • the aforementioned storage media include: U disk, mobile hard disk, read-only memory (read-only memory, ROM), random access memory (random access memory, RAM), magnetic disks or optical disks and other media that can store program codes. .

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Power Engineering (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Sustainable Development (AREA)
  • Sustainable Energy (AREA)
  • Transportation (AREA)
  • Mechanical Engineering (AREA)
  • Secondary Cells (AREA)
  • Tests Of Electric Status Of Batteries (AREA)
  • Charge And Discharge Circuits For Batteries Or The Like (AREA)

Abstract

一种电池检测的方法和装置，其中方法包括：获取电池的第一电池状态参数（S510）；根据第一电池状态参数和失效模型，确定第一失效程度（S520）；发送第一消息，第一消息包括第一失效程度（S530）。通过将电池的状态参数输入至包括训练得到的失效模型的服务系统中，得到失效程度，并将失效程度发送给车载设备和/或终端设备，有利于准确地评估电池的失效风险，并减少电池失效带来的损失。

Description

一种电池检测的方法和装置 技术领域
本申请涉及电池技术领域，并且更具体地，涉及一种电池检测的方法、装置及芯片系统。
背景技术
随着电动汽车的广泛推广使用，锂离子动力电池的安全性事故时有发生。锂离子动力电池事故通常表现为以热失控为核心的温度骤升、冒烟、起火甚至爆炸等现象。电动汽车上的锂离子动力电池事故威胁着人民群众的生命财产安全，严重阻碍了电动汽车的大规模产业化应用。
动力电池的热失控，并不是一个瞬发过程，而是逐渐蔓延的过程。如果我们能够在早期就探测到电池失效情况，并提前采取防治措施或警示车主赶紧去维修，就可以避免发展为热失控而带来人身与财产损失。因此，如何准确地评估电池失效程度并提供应对措施是急需解决的问题。
发明内容
本申请提供一种电池检测的方法和装置，通过将电池的状态参数输入至包括训练得到的失效模型的服务系统中，得到失效程度，并将失效程度发送给车载设备和/或终端设备，有利于准确地评估电池的失效风险，并减少电池失效带来的损失。
第一方面，提供了一种电池检测的方法，该方法包括：获取电池的第一电池状态参数；根据所述第一电池状态参数和失效模型，确定第一失效程度，其中，所述第一失效程度用于指示所述电池对应于所述第一电池状态参数的失效程度，所述失效模型基于第二电池状态参数和第二失效程度训练得到的，所述第二失效程度是经检测获得的同规格电池在所述第二电池状态参数下的失效程度，电池状态参数包括以下至少一种参数：放电电压、放电电流、充电温度；发送第一消息，所述第一消息包括所述第一失效程度。
通过将电池的状态参数输入至包括训练得到的失效模型的服务系统中，得到失效程度，并将失效程度发送给车载设备和/或终端设备，有利于准确地评估电池的失效风险，并减少电池失效带来的损失。
结合第一方面，在第一方面的某些实现方式中，所述根据所述第一电池状态参数和失效模型，确定第一失效程度，具体包括：根据所述第一电池状态参数包括的放电电压、放电电流、充电温度中的至少一种参数，确定所述电池的内阻，所述电池的内阻用于确定所述第一失效程度。
通过将包括电池内阻在内的多维度电池状态参数输入至失效模型并得到失效程度，可以提高电池失效检测的准确性。
结合第一方面，在第一方面的某些实现方式中，当所述第一失效程度大于或等于预设 的第一阈值时，发送第二消息，所述第二消息用于指示所述电池存在失效风险。
通过在电池失效程度大于预设阈值时发送消息提醒用户该电池存在失效风险，如警告用户或者指示车辆采取强制措施，可以减少因电池失效带来的人身和财产方面的损失。
结合第一方面，在第一方面的某些实现方式中，在所述根据所述第一电池状态参数和失效模型，确定第一失效程度之前，所述方法还包括：接收第三消息，所述第三消息用于请求对所述电池进行检测。
通过接收请求消息并对电池进行检测，可以提高用户的体验，满足用户随时对电池进行检测的需求。
结合第一方面，在第一方面的某些实现方式中，所述发送第一消息具体包括：在获取所述第一电池状态参数后的第一预设时间内，发送所述第一消息。
通过根据预设的时间，如一定的时间间隔，对电池进行检测并发送检测结果，可以达到定期对电池进行检测的效果，提高了用户的体验。
结合第一方面，在第一方面的某些实现方式中，所述方法还包括：将所述第二电池状态参数输入至原始模型，得到第三失效程度；调整所述原始模型的参数，以使所述第三失效程度和所述第二失效程度的偏差在预设范围内；将经过所述调制的原始模型作为所述失效模型。
通过原始模型来调整失效模型，可以有效的提高失效模型的准确性，从而提高电池检测的准确性。
第二方面，提供了一种电池检测的方法，该方法包括：发送第一消息，所述第一消息用于请求对电池进行检测；接收第二消息，所述第二消息包括第一失效程度，其中，所述第一失效程度用于指示所述电池对应于所述第一电池状态参数的失效程度，所述失效模型基于第二电池状态参数和第二失效程度训练得到的，所述第二失效程度是经检测获得的同规格电池在所述第二电池状态参数下的失效程度，电池状态参数包括以下至少一种参数：放电电压、放电电流、充电温度。
通过向服务系统发送用于检测电池的请求消息，得到基于失效模型的失效程度，可以准确地了解电池失效的风险，并减少电池热失控带来的损失。可选地，发送第一消息的可以是车载设备，也可以是终端设备，还可以是终端设备中的应用APP等。
结合第二方面，在第二方面的某些实现方式中，接收第三消息，所述第三消息用于指示所述电池存在失效风险，所述第三消息是服务系统或终端设备在所述第一失效程度大于或等于第一阈值时发送的。
通过接收在电池失效程度超过阈值时发送的警告消息或者指示消息，可以提前对电池采取措施，如维修、更换等，从而减少因电池失效带来的人身和财产的损失。
结合第二方面，在第二方面的某些实现方式中，所述方法还包括：根据所述第三消息采取强制动作。
根据服务系统发送的消息采取强制措施，如减速、停车等，可以有效地减少因电池失效带来的人身和财产的损失。
结合第二方面，在第二方面的某些实现方式中，所述方法还包括：通过显示装置显示所述第二消息和/或第三消息。
通过将服务系统发送的消息进行显示，可以提高用户的体验。
结合第二方面，在第二方面的某些实现方式中，所述方法还包括：向所述服务系统发送第一电池状态参数，所述第一电池状态参数包括以下中的至少一种参数：放电电压、放电电流、充电温度。
第三方面，提供了一种电池检测的装置，该装置包括：第一获取模块，用于获取电池的第一电池状态参数；第一处理模块，用于根据所述第一电池状态参数和失效模型，确定第一失效程度，其中，所述第一失效程度用于指示所述电池对应于所述第一电池状态参数的失效程度，所述失效模型基于第二电池状态参数和第二失效程度训练得到的，所述第二失效程度是经检测获得的同规格电池在所述第二电池状态参数下的失效程度，电池状态参数包括以下至少一种参数：放电电压、放电电流、充电温度；第一发送模块，用于发送第一消息，所述第一消息包括所述第一失效程度。
结合第三方面，在第三方面的某些实现方式中，所述处理模块具体用于：根据所述第一电池状态参数包括的放电电压、放电电流、充电温度中的至少一种参数，确定所述电池的内阻，所述电池的内阻用于确定所述第一失效程度。
结合第三方面，在第三方面的某些实现方式中，所述第一发送模块还用于：当所述第一失效程度大于或等于预设的第一阈值时，发送第二消息，所述第二消息用于指示所述电池存在失效风险。
结合第三方面，在第三方面的某些实现方式中，所述装置还包括：第一接收模块，用于接收第三消息，所述第三消息用于请求对所述电池进行检测。
结合第三方面，在第三方面的某些实现方式中，所述第一发送模块具体用于：在获取所述第一电池状态参数后的第一预设时间内，发送所述第一消息。
结合第三方面，在第三方面的某些实现方式中，所述第一处理模块还用于：所述第二电池状态参数输入至原始模型，得到第三失效程度；调整所述原始模型的参数，以使所述第三失效程度和所述第二失效程度的偏差在预设范围内；将经过所述调制的原始模型作为所述失效模型。
第四方面，提供了一种电池检测的装置，该装置包括：第二发送模块，用于发送第一消息，所述第一消息用于请求对电池进行检测；第二接收模块，用于接收第二消息，所述第二消息包括第一失效程度，其中，所述第一失效程度用于指示所述电池对应于所述第一电池状态参数的失效程度，所述失效模型基于第二电池状态参数和第二失效程度训练得到的，所述第二失效程度是经检测获得的同规格电池在所述第二电池状态参数下的失效程度，电池状态参数包括以下至少一种参数：放电电压、放电电流、充电温度。
结合第四方面，在第四方面的某些实现方式中，所述第二接收模块还用于：接收第三消息，所述第三消息用于指示所述电池存在失效风险，所述第三消息是服务系统或终端设备在所述第一失效程度大于或等于第一阈值时发送的。
结合第四方面，在第四方面的某些实现方式中，所述装置还包括：第二处理模块，用于根据所述第三消息采取强制动作。
结合第四方面，在第四方面的某些实现方式中，所述装置还包括：显示模块，用于通过显示装置显示所述第二消息和/或第三消息。
结合第四方面，在第四方面的某些实现方式中，所述第二发送模块还用于：发送第一电池状态参数，所述第一电池状态参数包括以下中的至少一种参数：放电电压、放电电流、 充电温度。
第五方面，提供了一种计算机可读存储介质，包括计算机程序，当其在计算机设备上运行时，使得所述计算机设备中的处理单元执行如第一方面或第一方面的任意可能的实现方式中的方法。
第六方面，提供了一种计算机可读存储介质，包括计算机程序，当其在计算机设备上运行时，使得所述计算机设备中的处理单元执行如第二方面或第二方面的任意可能的实现方式中的方法。
第七方面，提供了一种计算机程序产品，包括计算机程序，当其在计算机设备上运行时，使得所述计算机设备中的处理单元执行如第一方面或第一方面的任意可能的实现方式中所述的方法。
第八方面，提供了一种计算机程序产品，包括计算机程序，当其在计算机设备上运行时，使得所述计算机设备中的处理单元执行如第二方面或第二方面的任意可能的实现方式中所述的方法。
第九方面，提供了一种芯片，所述芯片包括处理器和存储器，所述存储器用于存储计算机程序，所述处理器用于调用并运行所述存储器中存储的计算机程序，以执行第一方面或第一方面的任意可能的实现方式中的方法。
第十方面，提供了一种芯片，所述芯片包括处理器和存储器，所述存储器用于存储计算机程序，所述处理器用于调用并运行所述存储器中存储的计算机程序，以执行第二方面或第二方面的任意可能的实现方式中的方法。
第十一方面，提供了一种芯片系统，该芯片系统包括至少一个处理器，当程序指令在所述至少一个处理器中执行时，使得所述至少一个处理器执行前文中所述的电池检测的方法。
附图说明
图1是现有技术中的一种电池检测方法的示意图。
图2是本申请实施例提供的系统架构的结构示意图。
图3是本申请实施例提供的根据卷积神经网络模型进行电池检测的示意图。
图4是本申请实施例提供的一种芯片硬件结构示意图。
图5是本申请实施例的一个电池检测方法的示意图。
图6是本申请实施例的另一个电池检测方法的示意图。
图7是本申请实施例的电池失效检测原理示意图。
图8是本申请实施例的一个系统架构示意图。
图9是本申请实施例的模块交互示意图。
图10是本申请实施例的一个电池检测装置的示意图。
图11是本申请实施例的另一个电池检测装置的示意图。
具体实施方式
下面将结合图，对本申请中的技术方案进行描述。
本申请实施例可以用于电动汽车的电池失效检测，也可以用于电动自行车等基于动力 电池驱动的各种对象的电池失效检测。
为了判断电池的内短路程度，减少电池热失控带来的损失，现有技术中提供了一种基于电压来检测电池内短路情况的方法，如图1所示，该方法通过电池管理系统(battery management system，BMS)采集电池包中的每个电池的端电压，并将端电压与平均电压进行比较，当端电压与平均电压的偏差值大于安全门限时，确定电池存在安全隐患。现有技术中通过电压检测电池的方法无需采用最小二乘法进行运算，降低了电池检测方法对于硬件设备的要求。
但是在这种方法中，电池的端电压不仅仅和电池的内阻相关，而且也容易受到其他多方面的因素的影响，造成其准确性比较低，容易出现误判。
本申请提供了一种电池检测的方法，通过将电池的状态参数输入至包括训练得到的失效模型的服务系统中，得到失效程度，并将失效程度发送给车载设备和/或终端设备，有利于准确地评估电池的失效风险，并减少电池失效带来的损失。
由于本申请实施例涉及大量神经网络的应用，为了便于理解，下面先对本申请实施例可能涉及的神经网络的相关术语和概念进行介绍。
(1)神经网络
神经网络可以是由神经单元组成的，神经单元可以是指以x s和截距1为输入的运算单元，该运算单元的输出可以为：
Figure PCTCN2020086781-appb-000001
其中，s＝1、2、……n，n为大于1的自然数，W s为x s的权重，其中W和x均为向量，b为神经单元的偏置。f为神经单元的激活函数(activation functions)，用于将非线性特性引入神经网络中，来将神经单元中的输入信号转换为输出信号。该激活函数的输出信号可以作为下一层卷积层的输入，激活函数可以是sigmoid函数。神经网络是将多个上述单一的神经单元联结在一起形成的网络，即一个神经单元的输出可以是另一个神经单元的输入。每个神经单元的输入可以与前一层的局部接受域相连，来提取局部接受域的特征，局部接受域可以是由若干个神经单元组成的区域。
(2)深度神经网络
深度神经网络(deep neural network，DNN)，也称多层神经网络，可以理解为具有多层隐含层的神经网络。按照不同层的位置对DNN进行划分，DNN内部的神经网络可以分为三类：输入层，隐含层，输出层。一般来说第一层是输入层，最后一层是输出层，中间的层数都是隐含层。层与层之间是全连接的，也就是说，第i层的任意一个神经元一定与第i+1层的任意一个神经元相连。
虽然DNN看起来很复杂，但是就每一层的工作来说，其实并不复杂，简单来说就是如下线性关系表达式：
Figure PCTCN2020086781-appb-000002
其中，
Figure PCTCN2020086781-appb-000003
是输入向量，
Figure PCTCN2020086781-appb-000004
是输出向量，
Figure PCTCN2020086781-appb-000005
是偏移向量，W是权重矩阵(也称系数)，α()是激活函数。每一层仅仅是对输入向量
Figure PCTCN2020086781-appb-000006
经过如此简单的操作得到输出向量
Figure PCTCN2020086781-appb-000007
由于DNN层数多，系数W和偏移向量
Figure PCTCN2020086781-appb-000008
的数量也比较多。这些参数在DNN中的定义如下所述：以系数W为例：假设在一个三层的DNN中，第二层的第4个神经元到第三层的第2个神经元的线性系数定义为
Figure PCTCN2020086781-appb-000009
上标3代表系数所在的层数，而下标对应的是输出的第三层索引2和输入的第二层索引4。
综上，第L-1层的第k个神经元到第L层的第j个神经元的系数定义为
Figure PCTCN2020086781-appb-000010
需要注意的是，输入层是没有W参数的。在深度神经网络中，更多的隐含层让网络更能够刻画现实世界中的复杂情形。理论上而言，参数越多的模型复杂度越高，“容量”也就越大，也就意味着它能完成更复杂的学习任务。训练深度神经网络的也就是学习权重矩阵的过程，其最终目的是得到训练好的深度神经网络的所有层的权重矩阵(由很多层的向量形成的权重矩阵)。
(3)卷积神经网络
卷积神经网络(convolutional neuron network，CNN)是一种带有卷积结构的深度神经网络。卷积神经网络包含了一个由卷积层和子采样层构成的特征抽取器，该特征抽取器可以看作是滤波器。卷积层是指卷积神经网络中对输入信号进行卷积处理的神经元层。在卷积神经网络的卷积层中，一个神经元可以只与部分邻层神经元连接。一个卷积层中，通常包含若干个特征平面，每个特征平面可以由一些矩形排列的神经单元组成。同一特征平面的神经单元共享权重，这里共享的权重就是卷积核。共享权重可以理解为提取图像信息的方式与位置无关。卷积核可以以随机大小的矩阵的形式初始化，在卷积神经网络的训练过程中卷积核可以通过学习得到合理的权重。另外，共享权重带来的直接好处是减少卷积神经网络各层之间的连接，同时又降低了过拟合的风险。
(4)循环神经网络
循环神经网络(recurrent neural networks，RNN)是用来处理序列数据的。在传统的神经网络模型中，是从输入层到隐含层再到输出层，层与层之间是全连接的，而对于每一层层内之间的各个节点是无连接的。这种普通的神经网络虽然解决了很多难题，但是却仍然对很多问题无能无力。例如，你要预测句子的下一个单词是什么，一般需要用到前面的单词，因为一个句子中前后单词并不是独立的。RNN之所以称为循环神经网路，即一个序列当前的输出与前面的输出也有关。具体的表现形式为网络会对前面的信息进行记忆并应用于当前输出的计算中，即隐含层本层之间的节点不再无连接而是有连接的，并且隐含层的输入不仅包括输入层的输出还包括上一时刻隐含层的输出。理论上，RNN能够对任何长度的序列数据进行处理。对于RNN的训练和对传统的CNN或DNN的训练一样。
既然已经有了卷积神经网络，为什么还要循环神经网络？原因很简单，在卷积神经网络中，有一个前提假设是：元素之间是相互独立的，输入与输出也是独立的，比如猫和狗。但现实世界中，很多元素都是相互连接的，比如股票随时间的变化，再比如一个人说了：我喜欢旅游，其中最喜欢的地方是云南，以后有机会一定要去。这里填空，人类应该都知道是填“云南”。因为人类会根据上下文的内容进行推断，但如何让机器做到这一步？RNN就应运而生了。RNN旨在让机器像人一样拥有记忆的能力。因此，RNN的输出就需要依赖当前的输入信息和历史的记忆信息。
(5)损失函数
在训练深度神经网络的过程中，因为希望深度神经网络的输出尽可能的接近真正想要预测的值，所以可以通过比较当前网络的预测值和真正想要的目标值，再根据两者之间的差异情况来更新每一层神经网络的权重向量(当然，在第一次更新之前通常会有初始化的过程，即为深度神经网络中的各层预先配置参数)，比如，如果网络的预测值高了，就调整权重向量让它预测低一些，不断地调整，直到深度神经网络能够预测出真正想要的目标值或与真正想要的目标值非常接近的值。因此，就需要预先定义“如何比较预测值和目标 值之间的差异”，这便是损失函数(loss function)或目标函数(objective function)，它们是用于衡量预测值和目标值的差异的重要方程。其中，以损失函数举例，损失函数的输出值(loss)越高表示差异越大，那么深度神经网络的训练就变成了尽可能缩小这个loss的过程。
(6)反向传播算法
神经网络可以采用误差反向传播(back propagation，BP)算法在训练过程中修正初始的神经网络模型中参数的大小，使得神经网络模型的重建误差损失越来越小。具体地，前向传递输入信号直至输出会产生误差损失，通过反向传播误差损失信息来更新初始的神经网络模型中参数，从而使误差损失收敛。反向传播算法是以误差损失为主导的反向传播运动，旨在得到最优的神经网络模型的参数，例如权重矩阵。
如图2所示，本申请实施例提供了一种系统架构200。在图2中，数据采集设备260用于采集训练数据。针对本申请实施例的电池检测方法来说，训练数据可以包括电池状态参数以及电池状态参数对应的失效程度。
在采集到训练数据之后，数据采集设备260将这些训练数据存入数据库230，训练设备220基于数据库230中维护的训练数据训练得到目标模型/规则201。
下面对训练设备220基于训练数据得到目标模型/规则201进行描述，训练设备220对输入的电池状态参数和原始失效程度进行处理，将输出的失效程度与原始失效程度进行对比，直到训练设备220输出的失效程度与原始失效程度的差值小于一定的阈值，从而完成目标模型/规则101的训练。
上述目标模型/规则201能够用于实现本申请实施例的电池检测方法，即，将电池状态参数通过相关预处理后输入该目标模型/规则201，即可得到失效程度结果。本申请实施例中的目标模型/规则201具体可以为神经网络。需要说明的是，在实际的应用中，所述数据库230中维护的训练数据不一定都来自于数据采集设备260的采集，也有可能是从其他设备接收得到的。另外需要说明的是，训练设备220也不一定完全基于数据库230维护的训练数据进行目标模型/规则201的训练，也有可能从云端或其他地方获取训练数据进行模型训练，上述描述不应该作为对本申请实施例的限定。
根据训练设备220训练得到的目标模型/规则201可以应用于不同的系统或设备中，如应用于图2所示的执行设备210，所述执行设备210可以是终端，如手机终端，平板电脑，笔记本电脑，增强现实(augmented reality，AR)AR/虚拟现实(virtual reality，VR)，车载终端等，还可以是服务器或者云端等。在图2中，执行设备210配置输入/输出(input/output，I/O)接口212，用于与外部设备进行数据交互，用户可以通过客户设备240向I/O接口212输入数据，所述输入数据在本申请实施例中可以包括：电池状态参数及电池状态参数对应的失效程度。
预处理模块213和预处理模块214用于根据I/O接口212接收到的输入数据(如电池状态参数)进行预处理，在本申请实施例中，也可以没有预处理模块213和预处理模块214(也可以只有其中的一个预处理模块)，而直接采用计算模块211对输入数据进行处理。
在执行设备210对输入数据进行预处理，或者在执行设备210的计算模块211执行计算等相关的处理过程中，执行设备210可以调用数据存储系统250中的数据、代码等以用 于相应的处理，也可以将相应处理得到的数据、指令等存入数据存储系统150中。
最后，I/O接口212将处理结果，如上述得到的失效程度返回给客户设备240，从而提供给用户。
值得说明的是，训练设备220可以针对不同的目标或称不同的任务，基于不同的训练数据生成相应的目标模型/规则201，该相应的目标模型/规则201即可以用于实现上述目标或完成上述任务，从而为用户提供所需的结果。
在图2中所示情况下，用户可以手动给定输入数据，该手动给定可以通过I/O接口212提供的界面进行操作。另一种情况下，客户设备240可以自动地向I/O接口212发送输入数据，如果要求客户设备240自动发送输入数据需要获得用户的授权，则用户可以在客户设备240中设置相应权限。用户可以在客户设备240查看执行设备210输出的结果，具体的呈现形式可以是显示、声音、动作等具体方式。客户设备240也可以作为数据采集端，采集如图所示输入I/O接口212的输入数据及输出I/O接口212的输出结果作为新的样本数据，并存入数据库230。当然，也可以不经过客户设备140进行采集，而是由I/O接口212直接将如图所示输入I/O接口212的输入数据及输出I/O接口212的输出结果，作为新的样本数据存入数据库230。
值得注意的是，图2仅是本申请实施例提供的一种系统架构的示意图，图中所示设备、器件、模块等之间的位置关系不构成任何限制，例如，在图2中，数据存储系统250相对执行设备210是外部存储器，在其它情况下，也可以将数据存储系统250置于执行设备210中。
如图2所示，根据训练设备220训练得到目标模型/规则201，该目标模型/规则201在本申请实施例中可以是本申请中的神经网络，具体的，本申请实施例提供的神经网络可以CNN，深度卷积神经网络(deep convolutional neural networks，DCNN)，循环神经网络(recurrent neural network，RNNS)等等。
由于CNN是一种非常常见的神经网络，下面结合图3重点对CNN的结构进行详细的介绍。如上文的基础概念介绍所述，卷积神经网络是一种带有卷积结构的深度神经网络，是一种深度学习(deep learning)架构，深度学习架构是指通过机器学习的算法，在不同的抽象层级上进行多个层次的学习。作为一种深度学习架构，CNN是一种前馈(feed-forward)人工神经网络，该前馈人工神经网络中的各个神经元可以对输入其中的图像做出响应。
如图3所示，卷积神经网络(CNN)300可以包括输入层310，卷积层/池化层320(其中池化层为可选的)，以及神经网络层330。下面对这些层的相关内容做详细介绍。
卷积层/池化层320：
如图3所示卷积层/池化层320可以包括如示例321-326层，举例来说：在一种实现中，321层为卷积层，322层为池化层，323层为卷积层，324层为池化层，325为卷积层，326为池化层；在另一种实现方式中，321、322为卷积层，323为池化层，324、325为卷积层，326为池化层。即卷积层的输出可以作为随后的池化层的输入，也可以作为另一个卷积层的输入以继续进行卷积操作。
下面将以卷积层321为例，介绍一层卷积层的内部工作原理。
卷积层321可以包括很多个卷积算子，卷积算子也称为核，其在电池检测中的作用相 当于一个从输入电池状态参数等信息中提取特定信息的过滤器，卷积算子本质上可以是一个权重矩阵，这个权重矩阵通常被预先定义，在对电池状态参数进行卷积操作的过程中，权重矩阵通常在输入电池状态参数中一个接着一个数据进行处理，从而完成从电池状态参数中提取特定特征的工作。该权重矩阵的大小应该与电池状态参数的大小相关，需要注意的是，权重矩阵的纵深维度(depth dimension)和输入电池状态参数的纵深维度是相同的，在进行卷积运算的过程中，权重矩阵会延伸到输入电池状态参数的整个深度。因此，和一个单一的权重矩阵进行卷积会产生一个单一纵深维度的卷积化输出，但是大多数情况下不使用单一权重矩阵，而是应用多个尺寸(行×列)相同的权重矩阵，即多个同型矩阵。每个权重矩阵的输出被堆叠起来形成卷积电池状态参数的纵深维度，这里的维度可以理解为由上面所述的“多个”来决定。不同的权重矩阵可以用来提取电池状态参数中不同的特征，例如一个权重矩阵用来提取放电电压数据，另一个权重矩阵用来提取放电电流数据，又一个权重矩阵用来提取充电温度等。
这些权重矩阵中的权重值在实际应用中需要经过大量的训练得到，通过训练得到的权重值形成的各个权重矩阵可以用来从输入电池状态参数中提取信息，从而使得卷积神经网络300进行正确的预测。
当卷积神经网络300有多个卷积层的时候，初始的卷积层(例如321)往往提取较多的一般特征，该一般特征也可以称之为低级别的特征；随着卷积神经网络300深度的加深，越往后的卷积层(例如326)提取到的特征越来越复杂，比如高级别的语义之类的特征，语义越高的特征越适用于待解决的问题。
池化层：
由于常常需要减少训练参数的数量，因此卷积层之后常常需要周期性的引入池化层，在如图3中320所示例的321-326各层，可以是一层卷积层后面跟一层池化层，也可以是多层卷积层后面接一层或多层池化层。在电池检测过程中，池化层的唯一目的就是减少电池状态参数的空间大小。
神经网络层330：
在经过卷积层/池化层320的处理后，卷积神经网络300还不足以输出所需要的输出信息。因为如前所述，卷积层/池化层320只会提取特征，并减少输入状态参数带来的参数。然而为了生成最终的输出信息(所需要的类信息或其他相关信息)，卷积神经网络300需要利用神经网络层330来生成一个或者一组所需要的类的数量的输出。因此，在神经网络层330中可以包括多层隐含层(如图3所示的331、332至33n)以及输出层340，该多层隐含层中所包含的参数可以根据具体的任务类型的相关训练数据进行预先训练得到。
在神经网络层330中的多层隐含层之后，也就是整个卷积神经网络300的最后层为输出层340，该输出层340具有类似分类交叉熵的损失函数，具体用于计算预测误差，一旦整个卷积神经网络300的前向传播(如图3由310至340方向的传播为前向传播)完成，反向传播(如图3由340至310方向的传播为反向传播)就会开始更新前面提到的各层的权重值以及偏差，以减少卷积神经网络300的损失，及卷积神经网络300通过输出层输出的结果和理想结果之间的误差。
需要说明的是，如图3所示的卷积神经网络300仅作为一种卷积神经网络的示例，在 具体的应用中，卷积神经网络还可以以其他网络模型的形式存在。
图4为本申请实施例提供的一种芯片硬件结构，该芯片包括神经网络处理器40。该芯片可以被设置在如图2所示的执行设备210中，用以完成计算模块211的计算工作。该芯片也可以被设置在如图2所示的训练设备220中，用以完成训练设备220的训练工作并输出目标模型/规则201。如图3所示的卷积神经网络中各层的算法均可在如图4所示的芯片中得以实现。
神经网络处理器NPU 40NPU作为协处理器挂载到主中央处理器(central processing unit，CPU)(host CPU)上，由主CPU分配任务。NPU的核心部分为运算电路40，控制器404控制运算电路403提取存储器(权重存储器或输入存储器)中的数据并进行运算。
在一些实现中，运算电路403内部包括多个处理单元(process engine，PE)。在一些实现中，运算电路403是二维脉动阵列。运算电路403还可以是一维脉动阵列或者能够执行例如乘法和加法这样的数学运算的其它电子线路。在一些实现中，运算电路403是通用的矩阵处理器。
举例来说，假设有输入矩阵A，本申请实施例中输入矩阵A可以是电池状态参数的矩阵，权重矩阵B，输出矩阵C，本申请实施例还在弄的输出矩阵可以是失效程度的矩阵。运算电路从权重存储器402中取矩阵B相应的数据，并缓存在运算电路中每一个PE上。运算电路从输入存储器401中取矩阵A数据与矩阵B进行矩阵运算，得到的矩阵的部分结果或最终结果，保存在累加器(accumulator)408中。
向量计算单元407可以对运算电路的输出做进一步处理，如向量乘，向量加，指数运算，对数运算，大小比较等等。例如，向量计算单元407可以用于神经网络中非卷积/非FC层的网络计算，如池化(pooling)，批归一化(batch normalization)，局部响应归一化(local response normalization)等。
在一些实现种，向量计算单元能407将经处理的输出的向量存储到统一缓存器406。例如，向量计算单元407可以将非线性函数应用到运算电路403的输出，例如累加值的向量，用以生成激活值。在一些实现中，向量计算单元407生成归一化的值、合并值，或二者均有。在一些实现中，处理过的输出的向量能够用作到运算电路403的激活输入，例如用于在神经网络中的后续层中的使用。
统一存储器406用于存放输入数据以及输出数据。
权重数据直接通过存储单元访问控制器405(direct memory access controller，DMAC)将外部存储器中的输入数据搬运到输入存储器401和/或统一存储器406、将外部存储器中的权重数据存入权重存储器402，以及将统一存储器406中的数据存入外部存储器。
总线接口单元(bus interface unit，BIU)410，用于通过总线实现主CPU、DMAC和取指存储器409之间进行交互。
与控制器404连接的取指存储器(instruction fetch buffer)409，用于存储控制器404使用的指令；
控制器404，用于调用指存储器409中缓存的指令，实现控制该运算加速器的工作过程。
入口：可以根据实际发明说明这里的数据是说明数据，比如探测到车辆速度？障碍物距离等
一般地，统一存储器406，输入存储器401，权重存储器402以及取指存储器409均为片上(On-Chip)存储器，外部存储器为该NPU外部的存储器，该外部存储器可以为双倍数据率同步动态随机存储器(double data rate synchronous dynamic random access memory，DDR SDRAM)、高带宽存储器(high bandwidth memory，HBM)或其他可读可写的存储器。
其中，图3所示的卷积神经网络中各层的运算可以由运算电路403或向量计算单元407执行。
图5示出了本申请实施例的一个电池检测方法的示意图。如图5所示，该方法包括步骤S510至S530。下面对这三个步骤进行详细介绍。
S510，服务系统获取电池的第一电池状态参数。
可选地，服务系统可以通过向车载系统发送消息，请求车载系统发送电池的第一电池状态参数，或者，服务系统可以从存储模块中调取之前存储的电池状态数据。
应理解，本申请实施例中的车载系统可以获取车辆电池的状态参数，电池状态参数可以包括：已行驶里程、当前电池SOC、充电电池温度、时间、放电电压、放电电流、电池型号等。
S520，服务系统根据所述第一电池状态参数和失效模型，确定第一失效程度。
应理解，服务系统在得到上述第一失效程度后可以在设备上显示检测结果，显示形式可以为语音、文字等。
作为一个实施例，所述第一失效程度表示电池当前状态的失效程度，所述失效模型基于第二电池状态参数和第二失效程度训练得到的，所述第二失效程度是经检测获得的同规格电池在所述第二电池状态参数下的失效程度，电池状态参数包括以下中的至少一种参数：放电电压、放电电流、充电温度。
应理解，电池失效是一个逐步蔓延的过程，例如，其可以分为内短路初期、内短路中期和内短路末期(热失控)三个阶段。在每个阶段中，电池电特征(如电压、电流)和热特征(温度)等都会有不同的表现，比如在内短路末期可以表现为电压消失、急剧产热等特征，对于锂离子电池来说，可以按照是否有明显自生热、是否达到隔膜失效温度这两个特征来划分三个阶段，然后将三个阶段分别对应不同的失效程度(如30％、80％等)，本申请对电池失效阶段的划分并不做限定。
可选地，上述第二电池状态参数可以是获取的同规格真实电池的测量数据，这种情况下，按照不同阶段对应的电池失效程度，第二失效程度可以是真实记录的电池正常工作时第二电池状态参数对应的失效程度，或者也可以是真实记录地电池失效时的失效程度；或者测试数据也可以是在实验室环境下，对车辆电池进行工况模拟测试后等得到的测试数据，比如设定电池的放电温度、负载等进行放电测试，并记录电池放电电压、温度、内阻等测试值，这种情况下，第二失效程度可以是模拟测试下，电池正常工作时记录的失效程度，也可以是模拟测试下，电池失效时记录的失效程度数据。
通过将电池的状态参数输入至失效模型，得到电池的失效程度，可以准确地评估电池失效的风险，继而减少电池热失控带来的人身和财产的损失。
作为一个实施例，上述失效模型是基于算法训练得到的，其中包括：将所述第二电池状态参数输入至原始模型，得到第三失效程度；调整所述原始模型的参数，以使所述第三 失效程度和所述第二失效程度的偏差在预设范围内；将经过所述调制的原始模型作为所述失效模型。可选地，上述失效模型可以是由图2中所示的系统得到的。
应理解，通过将原始模型得到的第三失效程度和真实测试得到的电池的第二失效程度进行比较，并将两者得到的偏差控制在预设范围内，可以得到与真实情况更加符合的失效模型，从而提高了电池失效检测的准确性。
可选地，本申请实施例中的失效模型可以是远程服务自身通过训练得到的，或者也可以是从其他设备获取的。
可选地，除上述第一电池状态参数包括的参数外，服务系统还可以根据电池内阻对电池进行失效程度的检测。具体地，所述根据所述第一电池状态参数和失效模型，确定第一失效程度，具体包括：根据所述第一电池状态参数包括的放电电压、放电电流、充电温度中的至少一种参数，确定所述电池的内阻，所述电池的内阻用于确定第一失效程度。
应理解，上述电池内阻可以通过滤波的方法得到，该方法属于现有技术，本申请实施例不做过多赘述。
可选地，本申请实施例的服务系统可以在接收到车载设备和/或终端设备发送的请求消息之后对电池进行检测，具体地，在所述根据所述第一电池状态参数和失效模型，确定第一失效程度之前，所述方法还包括：接收第三消息，所述第三消息用于请求对所述电池进行检测。可选地，服务系统可以在获取第一电池状态参数之前获取该第三消息，或者也可以在所述服务系统根据状态参数和失效模型确定失效程度之前获得该第三消息。
通过接收车载设备和/或终端设备发送的请求消息后对电池进行检测，可以满足用户随时想对电池进行检测的需求，提高用户体验。
应理解，本申请实施例中的服务系统可以设置于车辆内部，或者，当车辆或者使用动力电池的对象满足不了硬件要求时，可选地，本申请实施例的服务系统也可以是独立于车辆或其他对象的远程服务系统。
S530，服务系统发送第一消息，所述第一消息包括所述第一失效程度。
作为一个实施例，服务系统在得到第一失效程度后，可以将第一失效程度发出，可选地，可以发送给所属汽车的车载设备，也可以发送给终端设备(如手机，终端设备上的应用APP)等，或者也可以将该消息发送给厂家服务中心，并共享至远程服务器上的其他应用模块。
作为一个实施例，服务系统还可以发送提醒消息，具体地，当所述第一失效程度大于或等于预设的第一阈值时，发送第二消息，所述第二消息用于指示所述电池存在失效风险。可选地，该第二消息可以包括警告消息，如提醒用户进行维修或更换电池等，或者包括用于指示车辆采取强制措施的消息，如强制车辆进行减速、停车等。
通过将检测结果发送给车载设备或者终端设备、手机APP等，可以使得用户对当前电池的失效情况进行判断，用户可以根据自己的需求对车辆电池进行相应的处理，比如维修等，同时在失效程度超过阈值时发送告警，可以进一步保障用户的人身和财产安全。
可选地，服务系统也可以根据预设时间，对电池进行内短路检测。具体地，所述发送第一消息具体包括：在获取所述第一电池状态参数后的第一预设时间内，发送所述第一消息。
通过为服务系统设定预设的定时，可以让服务系统向车载设备或终端设备发送定期的 电池检测信息，提高了用户体验，减少因电池失效带来的损失。
图6示出了本申请实施例的另一个电池检测方法的示意图。如图6所示，该方法包括步骤S610和S620。下面对这两个步骤进行详细介绍。
S610，发送第一消息，所述第一消息用于请求对电池进行检测。
S620，接收第二消息，所述第二消息包括第一失效程度。
作为一个实施例，所述第一失效程度用于指示所述电池对应于第一电池状态参数的失效程度，所述失效模型基于第二电池状态参数和第二失效程度训练得到的，所述第二失效程度是经检测获得的同规格电池在所述第二电池状态参数下的失效程度，电池状态参数包括以下中的至少一种参数：放电电压、放电电流、充电温度。
可选地，发送第一消息的主体可以是车载设备，或者是终端设备，或者是终端设备中的移动APP等，本申请实施例对此不做限定。
作为一个实施例，车载设备或终端设备或应用APP可以接收提醒消息等，具体地，接收第三消息，所述第三消息用于指示所述电池存在失效风险，所述第三消息是服务系统或终端设备在所述第一失效程度大于或等于第一阈值时发送的。
可选地，当该发送主体是车载设备时，该第三消息可以用于指示车载设备采取强制措施，如强制减速、强制停车等，或者该第三消息还可以用于提醒用户尽快进行电池维修或者更换等。
可选地，车载设备、终端设备或者应用APP等可以对第二消息或第三消息进行显示，例如可以通过显示屏或者语音的形式进行显示，具体地，通过显示装置显示所述第二消息和/或第三消息。
可选地，车载设备在请求服务系统进行电池检测之前，可以向服务系统发送电池状态参数，具体地，车载设备发送第一电池状态参数，所述第一电池状态参数包括以下中的至少一种参数：放电电压、放电电流、充电温度。
其余步骤与图5中相同，本申请实施例不再做过多赘述。
图7示出了本申请实施例的电池失效检测原理示意图。如图7所示，该示意图主要包括电池状态参数获取部分、失效模型部分以及结果输出部分。
其中，电池状态参数获取部分中可以包括：电池状态参数和内阻估计。其中电池状态参数可以包括：放电电压、放电电流、当前充电温度及其他状态参数。上述电池状态参数是车载系统发送给服务系统的，服务系统可以通过向车载系统发送请求获取状态参数，或者可选地，服务系统也可以从存储模块中调取存储的电池状态参数。服务系统可以将这些状态参数输入至失效模型进行电池检测。可选地，输入失效模型的电池状态参数还可以包括电池内阻，具体地，服务系统可以根据上述电池状态参数中的至少一种，通过状态估计算法得到当前电池的内阻值，其中，状态估计算法可以为：卡尔曼滤波、贝叶斯滤波、隐马尔科夫模型(hidden markov model，HMM)或者其他算法来估计得到电池的内阻值。根据状态估计算法得到电池内阻值的方法属于现有技术，本申请对此不作过多赘述。
失效模型部分中可以包括：获取测试电池数据，此处的测试电池数据也可以是上述申请实施例中涉及的第二电池状态参数，其中测试电池数据可以是获取的真实电池的测试数据，或者测试数据也可以是在实验室环境下，对车辆电池进行工况模拟测试后等得到的测试数据，比如设定电池的放电温度、负载等进行放电测试，并记录电池放电电压、温度、 内阻等测试值；失效模型部分还可以包括失效模型估计，具体地，服务系统的算法模块可以基于上述测试数据，根据神经网络、长短期记忆网络(long short-term memory，LSTM)、随机森林、HMM等算法构建关于电池放电状态参数的失效模型，例如可以利用图2或3所示的神经网络获得失效模型，并获得电池失效的程度阈值。
随后服务系统可以根据上述电池状态参数和失效模型输出电池检测结果。进一步地，还可以根据失效的程度阈值，发出告警消息。
通过利用包括电池内阻值在内的多种实时电池状态参数，以及基于训练得到的失效模型，来获得电池的失效程度，可以准确的评估电池失效的风险，继而减少电池失效带来的损失。
图8示出了本申请实施例的一种系统架构示意图。如图8所示，本申请实施例的系统架构可以包括服务系统810和车载系统820。
其中车载系统820可以进行电池相关数据的采集(包括但不限于：已行驶里程、当前电池SOC、电池温度、时间、放电电压、放电电流、电池型号等)，并通过指定的协议发送至服务系统。车载系统820可以包括数据采集模块、数据上报模块、服务请求模块以及数据显示模块。
服务系统810可以包括3层，第一层可以包括：数据收集模块、数据处理模块和数据存储模块。第二层可以包括：数据分析模块、算法模块以及失效模型模块。第三层可以包括：电池失效检测应用模块。
服务系统810可以具有以下功能：服务系统在接收到电池数据后，对数据包进行解析等工作后，按照车辆识别号或者其他标识进行分类存储；服务系统基于测试电池数据，可以利用算法模块基于算法生成相关的失效模型，并将模型保存到失效模型模块中；服务系统可以接收到车载系统或者终端设备，或者其他应用，例如手机应用APP发出的检测请求，对指定的电池进行内短路检测；服务系统将检测结果发送到相关的车载系统或者终端设备(如手机或移动APP等)，或者其他应用服务进行数据显示，可选地，数据显示方式可以为语音、文字等。可选地，服务系统810可以设置于汽车中，也可以是独立于汽车存在的远程服务系统，将服务系统设置于独立于汽车存在的远程服务系统，可以克服服务系统硬件需求较高的问题。
其中电池失效检测应用模块还可以包括信息交互模块和内短路检测模块。
图9示出了本申请实施例的模块交互示意图。如图9所示，S910，信息交互模块接收到汽车或者终端设备发出的电池检测服务请求。S920，内短路检测模块接收服务请求。
S930，内短路检测模块接收信息交互模块的检测指示，并调用数据分析模块获取电池数据。其中，内短路检测模块可以配置需要进行检测的电池放电特征种类，如放电电压数据、放电电流数据、充电温度数据等。数据分析模块获取当前电池的状态参数，可选地，服务系统可以发送消息来获取最新的电池数据，或者服务系统也可以从存储模块中获取存储的电池的状态数据。应理解，存储模块中存储的汽车电池数据可以包括多种数据，而内短路检测可能只需要几种特定的数据，在这种情况下，数据分析模块可以根据内短路检测模块中配置的电池状态参数种类进行状态参数提取，只提取用于电池检测的状态参数。可选地，当服务系统独立于车载系统时，服务系统可以接收多个对象的服务请求，在这种情况下，数据分析模块可以先识别需要进行检测的车辆，然后获取该车辆电池的电池状态参 数。可选地，当进行检测的电池数据包括电池内阻时，数据存储模块还可以基于获取的电池数据，如以下至少一种：放电电压数据、放电电流数据、放电温度数据等，利用状态估计算法得到电池的内阻值。
S940，失效模块接收数据分析模块处理得到的状态参数。S950，失效模块基于电池状态参数进行检测，得到当前状态下的电池失效程度并返回给信息交互模块。S960，信息交互模块将检测结果返回给汽车、终端设备或者手机APP，可选地，当检测结果中的失效程度超过程度阈值时，信息交互模块还可以发送告警消息，告警消息可以包括：维修提示、减速、停车提示等。可选地，信息交互模块还可以将失效结果发送给其他相关服务使用，如厂家服务中心等。
图10示出了本申请实施例的电池检测的装置示意图。如图10所示，该装置1000包括第一获取模块1001、第一处理模块1002以及第一发送模块1003。该装置1000可以用于实现上述任一方法实施例中涉及的电池检测的功能。例如，该装置1000可以是服务系统。该网元或者网络功能既可以是硬件设备中的网络元件，也可以是在专用硬件上运行的软件功能，或者是平台(例如，云平台)上实例化的虚拟化功能。
该装置1000可以作为服务系统对电池进行检测，并执行上述方法实施例中由所述服务系统进行处理的步骤。所述第一接收模块1001和第一发送模块1003可用于支持该装置1000进行通信，例如执行图5和图6中由服务系统执行的发送/接收的动作，所述第一处理模块1002可用于支持装置1000执行上述方法中的处理动作，例如执行图5或图6中由服务系统执行的处理动作。具体地，可以参考如下描述：
第一获取模块1001用于获取电池的第一电池状态参数；第一处理模块1002用于根据所述第一电池状态参数和失效模型，确定第一失效程度，其中，所述第一失效程度用于指示所述电池对应于所述第一电池状态参数的失效程度，所述失效模型基于第二电池状态参数和第二失效程度训练得到的，所述第二失效程度是经检测获得的同规格电池在所述第二电池状态参数下的失效程度，电池状态参数包括以下至少一种参数：放电电压、放电电流、充电温度；第一发送模块1003用于发送第一消息，所述第一消息包括所述第一失效程度。
可选地，所述处理模块具体用于：根据所述第一电池状态参数包括的放电电压、放电电流、充电温度中的至少一种参数，确定所述电池的内阻，所述电池的内阻用于确定所述第一失效程度。
可选地，所述第一发送模块还用于：当所述第一失效程度大于或等于预设的第一阈值时，发送第二消息，所述第二消息用于指示所述电池存在失效风险。
可选地，所述装置还包括：第一接收模块，用于接收第三消息，所述第三消息用于请求对所述电池进行检测。
可选地，所述第一发送模块具体用于：在获取所述第一电池状态参数后的第一预设时间内，发送所述第一消息。
可选地，所述第一处理模块还用于：将所述第二电池状态参数输入至原始模型，得到第三失效程度；调整所述原始模型的参数，以使所述第三失效程度和所述第二失效程度的偏差在预设范围内；将经过所述调制的原始模型作为所述失效模型。
图11示出了本申请实施例的电池检测的装置示意图。如图11所示，该装置1100包括第二发送模块1101、第二接收模块1102。该装置1100可以用于实现上述任一方法实施 例中涉及的电池检测的功能。
该装置1100可以作为服务系统对电池进行检测，并执行上述方法实施例中由车载设备进行处理的步骤。所述第二发送模块1101和第二接收模块1102可用于支持该装置1100进行通信，例如执行图5和图6中由车载设备执行的发送/接收的动作。可选地，装置1100还可以包括第二处理模块1103，所述处理模块1103可用于支持装置1100执行上述方法中的处理动作，例如执行图2和图6中由车载设备执行的处理动作。具体地，可以参考如下描述：
第二发送模块1101用于发送第一消息，所述第一消息用于请求所述服务系统对电池进行检测；第二接收模块1102用于接收第二消息，所述第二消息包括第一失效程度，其中，所述第一失效程度用于指示所述电池对应于所述第一电池状态参数的失效程度，所述失效模型基于第二电池状态参数和第二失效程度训练得到的，所述第二失效程度是经检测获得的同规格电池在所述第二电池状态参数下的失效程度，电池状态参数包括以下至少一种参数：放电电压、放电电流、充电温度。
可选地，所述第二接收模块还用于：接收第三消息，所述第三消息用于指示所述电池存在失效风险，所述第三消息是服务系统或终端设备在所述第一失效程度大于或等于第一阈值时发送的。
可选地，所述装置还包括：第二处理模块，用于根据所述第三消息采取强制动作。
可选地，所述装置还包括：显示模块，用于通过显示装置显示所述第二消息和/或第三消息。
可选地，所述第二发送模块还用于：发送第一电池状态参数，所述第一电池状态参数包括以下中的至少一种参数：放电电压、放电电流、充电温度。
本领域普通技术人员可以意识到，结合本文中所公开的实施例描述的各示例的单元及算法步骤，能够以电子硬件、或者计算机软件和电子硬件的结合来实现。这些功能究竟以硬件还是软件方式来执行，取决于技术方案的特定应用和设计约束条件。专业技术人员可以对每个特定的应用来使用不同方法来实现所描述的功能，但是这种实现不应认为超出本申请的范围。
所属领域的技术人员可以清楚地了解到，为描述的方便和简洁，上述描述的系统、装置和单元的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。
在本申请所提供的几个实施例中，应该理解到，所揭露的系统、装置和方法，可以通过其它的方式实现。例如，以上所描述的装置实施例仅仅是示意性的，例如，所述单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个单元或组件可以结合或者可以集成到另一个系统，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口，装置或单元的间接耦合或通信连接，可以是电性，机械或其它的形式。
所述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外，在本申请各个实施例中的各功能单元可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中。
所述功能如果以软件功能单元的形式实现并作为独立的产品销售或使用时，可以存储在一个计算机可读取存储介质中。基于这样的理解，本申请的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质中，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)执行本申请各个实施例所述方法的全部或部分步骤。而前述的存储介质包括：U盘、移动硬盘、只读存储器(read-only memory，ROM)、随机存取存储器(random access memory，RAM)、磁碟或者光盘等各种可以存储程序代码的介质。
以上所述，仅为本申请的具体实施方式，但本申请的保护范围并不局限于此，任何熟悉本技术领域的技术人员在本申请揭露的技术范围内，可轻易想到变化或替换，都应涵盖在本申请的保护范围之内。因此，本申请的保护范围应以所述权利要求的保护范围为准。

Claims (23)

  1. 一种电池检测的方法，其特征在于，包括：
    获取电池的第一电池状态参数；
    根据所述第一电池状态参数和失效模型，确定第一失效程度，其中，所述第一失效程度用于指示所述电池对应于所述第一电池状态参数的失效程度，所述失效模型基于第二电池状态参数和第二失效程度训练得到的，所述第二失效程度是经检测获得的同规格电池在所述第二电池状态参数下的失效程度，电池状态参数包括以下至少一种参数：
    放电电压、放电电流、充电温度；
    发送第一消息，所述第一消息包括所述第一失效程度。
  2. 根据权利要求1所述的方法，其特征在于，所述根据所述第一电池状态参数和失效模型，确定第一失效程度，具体包括：
    根据所述第一电池状态参数包括的放电电压、放电电流、充电温度中的至少一种参数，确定所述电池的内阻，所述电池的内阻用于确定所述第一失效程度。
  3. 根据权利要求1或2所述的方法，其特征在于，所述方法还包括：
    当所述第一失效程度大于或等于预设的第一阈值时，发送第二消息，所述第二消息用于指示所述电池存在失效风险。
  4. 根据权利要求1-3中任一项所述的方法，其特征在于，在所述根据所述第一电池状态参数和失效模型，确定第一失效程度之前，所述方法还包括：
    接收第三消息，所述第三消息用于请求对所述电池进行检测。
  5. 根据权利要求1-4中任一项所述的方法，其特征在于，所述发送第一消息具体包括：
    在获取所述第一电池状态参数后的第一预设时间程度内，发送所述第一消息。
  6. 根据权利要求1-5中任一项所述的方法，其特征在于，所述方法还包括：
    将所述第二电池状态参数输入至原始模型，得到第三失效程度；
    调整所述原始模型的参数，以使所述第三失效程度和所述第二失效程度的偏差在预设范围内；
    将经过所述调制的原始模型作为所述失效模型。
  7. 一种电池检测方法，其特征在于，包括：
    发送第一消息，所述第一消息用于请求对电池进行检测；
    接收第二消息，所述第二消息包括第一失效程度，其中，所述第一失效程度用于指示所述电池对应于所述第一电池状态参数的失效程度，所述失效模型基于第二电池状态参数和第二失效程度训练得到的，所述第二失效程度是经检测获得的同规格电池在所述第二电池状态参数下的失效程度，电池状态参数包括以下至少一种参数：
    放电电压、放电电流、充电温度。
  8. 根据权利要求7所述的方法，其特征在于，所述方法还包括：
    接收第三消息，所述第三消息用于指示所述电池存在失效风险，所述第三消息是服务系统或终端设备在所述第一失效程度大于或等于第一阈值时发送的。
  9. 根据权利要求8所述的方法，其特征在于，所述方法还包括：
    根据所述第三消息采取强制动作。
  10. 根据权利要求9所述的方法，其特征在于，所述方法还包括：
    通过显示装置显示所述第二消息和/或第三消息。
  11. 根据权利要求7-10中任一项所述的方法，其特征在于，所述方法还包括：
    发送第一电池状态参数，所述第一电池状态参数包括以下中的至少一种参数：放电电压、放电电流、充电温度。
  12. 一种电池检测的装置，其特征在于，包括：
    第一获取模块，用于获取电池的第一电池状态参数；
    第一处理模块，用于根据所述第一电池状态参数和失效模型，确定第一失效程度，其中，所述第一失效程度用于指示所述电池对应于所述第一电池状态参数的失效程度，所述失效模型基于第二电池状态参数和第二失效程度训练得到的，所述第二失效程度是经检测获得的同规格电池在所述第二电池状态参数下的失效程度，电池状态参数包括以下至少一种参数：
    放电电压、放电电流、充电温度；
    第一发送模块，用于发送第一消息，所述第一消息包括所述第一失效程度。
  13. 根据权利要求12所述的装置，其特征在于，所述处理模块具体用于：
    根据所述第一电池状态参数包括的放电电压、放电电流、充电温度中的至少一种参数，确定所述电池的内阻，所述电池的内阻用于确定所述第一失效程度。
  14. 根据权利要求12或13所述的装置，其特征在于，所述第一发送模块还用于：
    当所述第一失效程度大于或等于预设的第一阈值时，发送第二消息，所述第二消息用于指示所述电池存在失效风险。
  15. 根据权利要求12-14中任一项所述的装置，其特征在于，所述装置还包括：
    第一接收模块，用于接收第三消息，所述第三消息用于请求对所述电池进行检测。
  16. 根据权利要求12-15中任一项所述的装置，其特征在于，所述第一发送模块具体用于：
    在获取所述第一电池状态参数后的第一预设时间内，发送所述第一消息。
  17. 根据权利要求12-16中任一项所述的装置，其特征在于，所述第一处理模块还用于：
    将所述第二电池状态参数输入至原始模型，得到第三失效程度；
    调整所述原始模型的参数，以使所述第三失效程度和所述第二失效程度的偏差在预设范围内；
    将经过所述调制的原始模型作为所述失效模型。
  18. 一种电池检测的装置，其特征在于，包括：
    第二发送模块，用于发送第一消息，所述第一消息用于请求对电池进行检测；
    第二接收模块，用于接收第二消息，所述第二消息包括第一失效程度，其中，所述第一失效程度用于指示所述电池对应于所述第一电池状态参数的失效程度，所述失效模型基于第二电池状态参数和第二失效程度训练得到的，所述第二失效程度是经检测获得的同规格电池在所述第二电池状态参数下的失效程度，电池状态参数包括以下至少一种参数：
    放电电压、放电电流、充电温度。
  19. 根据权利要求18所述的装置，其特征在于，所述第二接收模块还用于：
    接收第三消息，所述第三消息用于指示所述电池存在失效风险，所述第三消息是服务系统或终端设备在所述第一失效程度大于或等于第一阈值时发送的。
  20. 根据权利要求19所述的装置，其特征在于，所述装置还包括：
    第二处理模块，用于根据所述第三消息采取强制动作。
  21. 根据权利要求20所述的装置，其特征在于，所述装置还包括：
    显示模块，用于通过显示装置显示所述第二消息和/或第三消息。
  22. 根据权利要求18-21中任一项所述的装置，其特征在于，所述第二发送模块还用于：
    发送第一电池状态参数，所述第一电池状态参数包括以下中的至少一种参数：放电电压、放电电流、充电温度。
  23. 一种芯片系统，其特征在于，所述芯片系统包括至少一个处理器，当程序指令在所述至少一个处理器中执行时，使得所述至少一个处理器执行如权利要求1-11中任一项所述的电池检测的方法。
PCT/CN2020/086781 2020-04-24 2020-04-24 一种电池检测的方法和装置 WO2021212496A1 (zh)

Priority Applications (5)

Application Number Priority Date Filing Date Title
EP20932184.3A EP4130766A4 (en) 2020-04-24 2020-04-24 BATTERY DETECTION METHOD AND APPARATUS
PCT/CN2020/086781 WO2021212496A1 (zh) 2020-04-24 2020-04-24 一种电池检测的方法和装置
CN202080004896.4A CN112639495A (zh) 2020-04-24 2020-04-24 一种电池检测的方法和装置
JP2022564504A JP2023522468A (ja) 2020-04-24 2020-04-24 バッテリ検出方法及び装置
KR1020227040401A KR20230006855A (ko) 2020-04-24 2020-04-24 배터리 감지 방법 및 장치

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2020/086781 WO2021212496A1 (zh) 2020-04-24 2020-04-24 一种电池检测的方法和装置

Publications (1)

Publication Number Publication Date
WO2021212496A1 true WO2021212496A1 (zh) 2021-10-28

Family

ID=75291261

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/086781 WO2021212496A1 (zh) 2020-04-24 2020-04-24 一种电池检测的方法和装置

Country Status (5)

Country Link
EP (1) EP4130766A4 (zh)
JP (1) JP2023522468A (zh)
KR (1) KR20230006855A (zh)
CN (1) CN112639495A (zh)
WO (1) WO2021212496A1 (zh)

Cited By (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113884924A (zh) * 2021-11-16 2022-01-04 中国科学院电工研究所 基于卷积神经网络的锂离子电池内部短路诊断方法及系统
CN114547966A (zh) * 2022-01-10 2022-05-27 浙江大学 基于硬件特征信息的神经网络加速器故障脆弱性评估方法
CN114839556A (zh) * 2022-05-10 2022-08-02 中国第一汽车股份有限公司 动力电池异常检测方法、装置、存储介质及电子装置
CN115184808A (zh) * 2022-07-05 2022-10-14 东莞新能安科技有限公司 电池热失控风险检测方法、装置、设备及计算机存储介质
CN115308629A (zh) * 2022-08-23 2022-11-08 中国第一汽车股份有限公司 电池性能的测试方法、装置、存储介质及电子设备
CN115320385A (zh) * 2022-07-28 2022-11-11 重庆金康赛力斯新能源汽车设计院有限公司 车辆电池的热失控预警方法、装置、设备和存储介质
CN115902646A (zh) * 2023-01-06 2023-04-04 中国电力科学研究院有限公司 一种储能电池故障识别方法及系统
CN116299038A (zh) * 2023-02-13 2023-06-23 上海玫克生储能科技有限公司 电芯微短路的检测方法、系统、设备及存储介质
CN116520153A (zh) * 2023-04-26 2023-08-01 广东博龙能源科技有限公司 一种锂电池热失控预警保护方法和系统
CN116714437A (zh) * 2023-06-01 2023-09-08 西华大学 基于大数据的氢燃料电池汽车安全监控系统及监控方法
CN117686916A (zh) * 2023-12-12 2024-03-12 中通维易科技服务有限公司 一种实验室数字化管理系统

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113343633B (zh) * 2021-06-10 2022-04-26 上海交通大学 动力锂电池热失控故障分类及风险预测方法、系统
CN114683964B (zh) * 2022-03-29 2024-04-26 北京芯虹科技有限责任公司 一种电池状态信息确定方法及充电设备

Citations (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2006015896A (ja) * 2004-07-02 2006-01-19 Shin Kobe Electric Mach Co Ltd 劣化度推定方法及び劣化度推定装置
CN101010596A (zh) * 2004-08-25 2007-08-01 日本电气株式会社 内阻抗检测设备、内阻抗检测方法、退化程度检测设备和退化程度检测方法
JP2007216707A (ja) * 2006-02-14 2007-08-30 Fujitsu Ten Ltd バッテリ劣化判定装置、およびバッテリ劣化判定方法
CN101512365A (zh) * 2006-09-04 2009-08-19 丰田自动车株式会社 二次电池的内部状态估计装置以及二次电池的内部状态估计方法
CN102043132A (zh) * 2009-10-14 2011-05-04 索尼公司 电池组和用于检测电池劣化的方法
WO2011160258A1 (zh) * 2010-06-24 2011-12-29 松下电器产业株式会社 获取电池的劣化度的方法和系统
CN102313843A (zh) * 2010-06-30 2012-01-11 三洋电机株式会社 电池内阻的检测方法
CN102901928A (zh) * 2011-07-25 2013-01-30 横河电机株式会社 电池劣化确定设备、方法和系统
CN104777431A (zh) * 2015-04-30 2015-07-15 大连楼兰科技股份有限公司 基于obd接口的车辆蓄电池劣化检测设备及方法
CN204758795U (zh) * 2015-06-01 2015-11-11 上海市松江区青少年活动中心 充电电池失效状态检测仪
CN105866551A (zh) * 2016-06-27 2016-08-17 上海电气钠硫储能技术有限公司 一种钠硫电池内阻检测方法
CN106772099A (zh) * 2017-01-23 2017-05-31 合肥国轩高科动力能源有限公司 一种动力锂电池劣化程度估算方法
CN107329088A (zh) * 2016-04-29 2017-11-07 株式会社日立制作所 电池的健康状态诊断装置和方法

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR102357351B1 (ko) * 2015-01-07 2022-01-28 삼성전자주식회사 복수의 배터리 셀들을 포함하는 배터리 팩의 상태를 추정하는 장치 및 방법
CN106680720B (zh) * 2015-11-11 2019-07-02 中国移动通信集团公司 基于车联网的车载蓄电池失效预警系统及方法
US10310022B2 (en) * 2016-10-05 2019-06-04 Samsung Electronics Co., Ltd. Battery state estimation apparatus and method
CN108562855B (zh) * 2017-12-18 2020-02-07 清华大学 电池内短路检测方法、装置和计算机可读存储介质
CN108258338A (zh) * 2017-12-29 2018-07-06 江苏博强新能源科技股份有限公司 电池的管理系统和方法
CN110861531A (zh) * 2019-11-27 2020-03-06 四川野马汽车股份有限公司 一种动力电池失效预警系统及方法

Patent Citations (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2006015896A (ja) * 2004-07-02 2006-01-19 Shin Kobe Electric Mach Co Ltd 劣化度推定方法及び劣化度推定装置
CN101010596A (zh) * 2004-08-25 2007-08-01 日本电气株式会社 内阻抗检测设备、内阻抗检测方法、退化程度检测设备和退化程度检测方法
JP2007216707A (ja) * 2006-02-14 2007-08-30 Fujitsu Ten Ltd バッテリ劣化判定装置、およびバッテリ劣化判定方法
CN101512365A (zh) * 2006-09-04 2009-08-19 丰田自动车株式会社 二次电池的内部状态估计装置以及二次电池的内部状态估计方法
CN102043132A (zh) * 2009-10-14 2011-05-04 索尼公司 电池组和用于检测电池劣化的方法
WO2011160258A1 (zh) * 2010-06-24 2011-12-29 松下电器产业株式会社 获取电池的劣化度的方法和系统
CN102313843A (zh) * 2010-06-30 2012-01-11 三洋电机株式会社 电池内阻的检测方法
CN102901928A (zh) * 2011-07-25 2013-01-30 横河电机株式会社 电池劣化确定设备、方法和系统
CN104777431A (zh) * 2015-04-30 2015-07-15 大连楼兰科技股份有限公司 基于obd接口的车辆蓄电池劣化检测设备及方法
CN204758795U (zh) * 2015-06-01 2015-11-11 上海市松江区青少年活动中心 充电电池失效状态检测仪
CN107329088A (zh) * 2016-04-29 2017-11-07 株式会社日立制作所 电池的健康状态诊断装置和方法
CN105866551A (zh) * 2016-06-27 2016-08-17 上海电气钠硫储能技术有限公司 一种钠硫电池内阻检测方法
CN106772099A (zh) * 2017-01-23 2017-05-31 合肥国轩高科动力能源有限公司 一种动力锂电池劣化程度估算方法

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP4130766A4 *

Cited By (16)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113884924A (zh) * 2021-11-16 2022-01-04 中国科学院电工研究所 基于卷积神经网络的锂离子电池内部短路诊断方法及系统
CN114547966A (zh) * 2022-01-10 2022-05-27 浙江大学 基于硬件特征信息的神经网络加速器故障脆弱性评估方法
CN114839556A (zh) * 2022-05-10 2022-08-02 中国第一汽车股份有限公司 动力电池异常检测方法、装置、存储介质及电子装置
CN115184808A (zh) * 2022-07-05 2022-10-14 东莞新能安科技有限公司 电池热失控风险检测方法、装置、设备及计算机存储介质
CN115320385B (zh) * 2022-07-28 2024-04-30 重庆金康赛力斯新能源汽车设计院有限公司 车辆电池的热失控预警方法、装置、设备和存储介质
CN115320385A (zh) * 2022-07-28 2022-11-11 重庆金康赛力斯新能源汽车设计院有限公司 车辆电池的热失控预警方法、装置、设备和存储介质
CN115308629A (zh) * 2022-08-23 2022-11-08 中国第一汽车股份有限公司 电池性能的测试方法、装置、存储介质及电子设备
CN115902646A (zh) * 2023-01-06 2023-04-04 中国电力科学研究院有限公司 一种储能电池故障识别方法及系统
CN115902646B (zh) * 2023-01-06 2023-06-13 中国电力科学研究院有限公司 一种储能电池故障识别方法及系统
CN116299038A (zh) * 2023-02-13 2023-06-23 上海玫克生储能科技有限公司 电芯微短路的检测方法、系统、设备及存储介质
CN116299038B (zh) * 2023-02-13 2024-04-05 上海玫克生储能科技有限公司 电芯微短路的检测方法、系统、设备及存储介质
CN116520153B (zh) * 2023-04-26 2024-03-26 广东博龙能源科技有限公司 一种锂电池热失控预警保护方法和系统
CN116520153A (zh) * 2023-04-26 2023-08-01 广东博龙能源科技有限公司 一种锂电池热失控预警保护方法和系统
CN116714437A (zh) * 2023-06-01 2023-09-08 西华大学 基于大数据的氢燃料电池汽车安全监控系统及监控方法
CN116714437B (zh) * 2023-06-01 2024-03-26 西华大学 基于大数据的氢燃料电池汽车安全监控系统及监控方法
CN117686916A (zh) * 2023-12-12 2024-03-12 中通维易科技服务有限公司 一种实验室数字化管理系统

Also Published As

Publication number Publication date
KR20230006855A (ko) 2023-01-11
EP4130766A1 (en) 2023-02-08
CN112639495A (zh) 2021-04-09
JP2023522468A (ja) 2023-05-30
EP4130766A4 (en) 2023-06-07

Similar Documents

Publication Publication Date Title
WO2021212496A1 (zh) 一种电池检测的方法和装置
Jiao et al. A yolov3-based learning strategy for real-time uav-based forest fire detection
US20220019855A1 (en) Image generation method, neural network compression method, and related apparatus and device
Zhou et al. Battery health prognosis using improved temporal convolutional network modeling
JP6742554B1 (ja) 情報処理装置およびそれを備えた電子機器
WO2023131065A1 (zh) 一种图像处理方法、一种车道线检测方法及相关设备
WO2024198769A1 (zh) 一种模型的训练方法、功率预测方法及设备
EP4350575A1 (en) Image classification method and related device thereof
WO2022143903A1 (zh) 车用电池的安全评估方法、系统、设备及可读存储介质
CN117251695A (zh) 数据预测模型的训练方法、装置、设备及存储介质
CN118643874A (zh) 训练神经网络的方法和装置
CN117217280A (zh) 神经网络模型优化方法、装置及计算设备
CN113935423A (zh) 耦合模糊控制规则与Elman神经网络的动力电池故障预警方法与系统
Hou et al. A vehicle alarm network for high-temperature fault diagnosis of electric vehicles
Ju et al. A real-time fire detection method from video for electric vehicle-charging stations based on improved YOLOX-tiny
CN116679579A (zh) 一种基于数字孪生的安全控制方法、装置、设备及介质
CN116559680A (zh) 一种电池故障诊断方法、装置、电子设备和存储介质
CN116485135A (zh) 一种智慧商用建筑大数据管理平台
CN115984723A (zh) 道路破损检测方法、系统、装置、存储介质及计算机设备
CN116258190A (zh) 一种量化方法、装置及相关设备
CN118061199B (zh) 校园无人巡逻机器人远程智能控制系统及方法
CN118470649B (zh) 一种基于双层感知的配网电缆环境感知方法及系统
CN117557108B (zh) 电力作业风险智能识别模型的训练方法和装置
Zeng et al. A novel method of aviation safety prediction based on Lstm-Rbf model
WO2023184188A1 (zh) 一种自动驾驶系统中神经网络模型故障监测方法及装置

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20932184

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2022564504

Country of ref document: JP

Kind code of ref document: A

ENP Entry into the national phase

Ref document number: 2020932184

Country of ref document: EP

Effective date: 20221103

ENP Entry into the national phase

Ref document number: 20227040401

Country of ref document: KR

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE