CN118249471A - Robot charging method and device - Google Patents
Robot charging method and device Download PDFInfo
- Publication number
- CN118249471A CN118249471A CN202410649585.3A CN202410649585A CN118249471A CN 118249471 A CN118249471 A CN 118249471A CN 202410649585 A CN202410649585 A CN 202410649585A CN 118249471 A CN118249471 A CN 118249471A
- Authority
- CN
- China
- Prior art keywords
- charging
- parameters
- robot
- fluctuation prediction
- result
- Prior art date
- Legal status (The legal status 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 status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 40
- 238000012549 training Methods 0.000 claims abstract description 13
- 238000012545 processing Methods 0.000 claims description 28
- 239000013598 vector Substances 0.000 claims description 23
- 238000000926 separation method Methods 0.000 claims description 8
- 238000000605 extraction Methods 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000013507 mapping Methods 0.000 claims description 6
- 238000000354 decomposition reaction Methods 0.000 claims description 5
- 238000007781 pre-processing Methods 0.000 claims description 5
- 238000004590 computer program Methods 0.000 claims description 3
- 239000003990 capacitor Substances 0.000 description 6
- 230000006870 function Effects 0.000 description 6
- 230000001419 dependent effect Effects 0.000 description 4
- 238000010408 sweeping Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 230000006978 adaptation Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000011217 control strategy Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J7/00—Circuit arrangements for charging or depolarising batteries or for supplying loads from batteries
- H02J7/007—Regulation of charging or discharging current or voltage
- H02J7/00712—Regulation of charging or discharging current or voltage the cycle being controlled or terminated in response to electric parameters
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J19/00—Accessories fitted to manipulators, e.g. for monitoring, for viewing; Safety devices combined with or specially adapted for use in connection with manipulators
- B25J19/005—Accessories fitted to manipulators, e.g. for monitoring, for viewing; Safety devices combined with or specially adapted for use in connection with manipulators using batteries, e.g. as a back-up power source
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/10—Pre-processing; Data cleansing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
- H01M10/00—Secondary cells; Manufacture thereof
- H01M10/42—Methods or arrangements for servicing or maintenance of secondary cells or secondary half-cells
- H01M10/4285—Testing apparatus
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
- H01M10/00—Secondary cells; Manufacture thereof
- H01M10/42—Methods or arrangements for servicing or maintenance of secondary cells or secondary half-cells
- H01M10/44—Methods for charging or discharging
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E60/00—Enabling technologies; Technologies with a potential or indirect contribution to GHG emissions mitigation
- Y02E60/10—Energy storage using batteries
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Chemical Kinetics & Catalysis (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- General Chemical & Material Sciences (AREA)
- Electrochemistry (AREA)
- Manufacturing & Machinery (AREA)
- Chemical & Material Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Mechanical Engineering (AREA)
- Robotics (AREA)
- Power Engineering (AREA)
- Charge And Discharge Circuits For Batteries Or The Like (AREA)
Abstract
The invention provides a robot charging method and a robot charging device. The method comprises the following steps: acquiring state parameters of the robot when the robot is charged by a charging system; extracting the characteristics of the state parameters to obtain characteristic data; inputting the characteristic data into a fluctuation prediction model to obtain a fluctuation prediction result; the fluctuation prediction model is obtained by training a preset network model by utilizing historical robot charging data; obtaining a charging adjustment parameter according to the real-time electric energy parameter of the charging system, the fluctuation prediction result and the target charging condition; and controlling the charging system to adjust the charging parameters according to the charging adjustment parameters. According to the invention, whether the robot fluctuates in the charging process is predicted by using the acquired state parameters of the charging system, and the charging system is controlled to adjust the charging parameters according to the calculated charging adjustment parameters, so that constant charging conditions are achieved, the charging efficiency and the service life of the robot are improved, and the method has the advantage of high safety.
Description
Technical Field
The invention relates to the technical field of robot charging, and also relates to a robot charging method and device.
Background
With the continuous progress of technology, robots have become part of people's lives as an intelligent device. They are widely used in the fields of industry, medical treatment, military, etc., and bring a lot of convenience to the production and life of people. The robot uses a battery as an energy source to power it. In order to ensure continuous operation of the robot, charging is an indispensable link. However, due to unstable power quality and lack of intelligent control strategy, the charging parameters cannot be adjusted according to actual conditions when the robot is charged, so as to maintain constant charging conditions (such as stable charging voltage, stable charging current, charging power and the like), which not only reduces the charging efficiency of the robot, but also affects the service life of the robot.
Disclosure of Invention
The invention aims to provide a robot charging method and device so as to meet constant charging conditions during robot charging.
In order to solve the technical problems, the technical scheme of the invention is as follows:
A robot charging method, comprising:
acquiring state parameters of the robot when the robot is charged by a charging system;
extracting the characteristics of the state parameters to obtain characteristic data;
inputting the characteristic data into a fluctuation prediction model to obtain a fluctuation prediction result; the fluctuation prediction model is obtained by training a preset network model by utilizing historical robot charging data;
Obtaining a charging adjustment parameter according to the real-time electric energy parameter of the charging system, the fluctuation prediction result and the target charging condition;
And controlling the charging system to adjust the charging parameters according to the charging adjustment parameters.
Optionally, extracting the characteristics of the state parameter to obtain characteristic data includes:
preprocessing the state parameters to obtain preprocessed state parameters;
performing eigenvalue decomposition processing on the preprocessed state parameters to obtain eigenvalues and corresponding eigenvectors;
sorting the characteristic values to obtain a sorting result;
And carrying out feature extraction according to the sorting result and the feature vector to obtain feature data.
Optionally, inputting the feature data into a fluctuation prediction model to obtain a fluctuation prediction result, including:
inputting the characteristic data into an input layer of a fluctuation prediction model for processing to obtain a first output result;
inputting the first output result into a first processing layer of a fluctuation prediction model for mapping processing to obtain a second output result;
Inputting the second output result into a second processing layer of the fluctuation prediction model for separation processing to obtain separation data;
And inputting the separated data into an output layer of the fluctuation prediction model to obtain a fluctuation prediction result.
Optionally, obtaining the charging adjustment parameter according to the real-time electric energy parameter of the charging system, the fluctuation prediction result and the target charging condition includes:
Acquiring a target charging condition; the target charging conditions comprise target charging current, target charging voltage and target charging power when the robot is charged;
acquiring real-time electric energy parameters of a charging system; the real-time electric energy parameters comprise real-time voltage parameters, real-time current parameters and real-time power parameters;
Judging according to the real-time electric energy parameters of the charging system and the fluctuation prediction result to obtain a judgment result of whether the charging parameters need to be adjusted;
obtaining a charging adjustment parameter according to the judging result, the fluctuation predicting result and the target charging condition; the charge adjustment parameters include a charge current, a charge voltage, and a charge power.
Optionally, obtaining the charging adjustment parameter according to the judging result, the fluctuation predicting result and the target charging condition includes:
obtaining an error value according to the judging result, the fluctuation predicting result and the target charging condition;
Performing deviation solving and conducting calculation according to the error value and a preset initialization charging adjustment parameter to obtain a gradient vector;
And updating the preset initialization charging adjustment parameters according to the gradient vector until a preset stopping condition is reached, so as to obtain the charging adjustment parameters.
Optionally, according to the charging adjustment parameter, controlling the charging system to adjust the charging parameter includes:
and outputting the charging adjustment parameters to the charging system, so that the charging system adjusts the charging parameters according to the charging adjustment parameters to achieve the target charging condition.
Optionally, the method further comprises:
Storing real-time electric energy parameters, the fluctuation prediction result, the target charging condition and the charging adjustment parameters of the charging system;
And transmitting the real-time electric energy parameters, the fluctuation prediction result, the target charging condition and the charging adjustment parameters of the charging system to a robot management platform.
In a second aspect of the present invention, there is provided a robot charging apparatus comprising:
The acquisition module is used for acquiring state parameters of the robot when the robot is charged by the charging system;
The extraction module is used for extracting the characteristics of the state parameters to obtain characteristic data;
The prediction module is used for inputting the characteristic data into a fluctuation prediction model to obtain a fluctuation prediction result; the fluctuation prediction model is obtained by training a preset network model by utilizing historical robot charging data;
the processing module is used for obtaining a charging adjustment parameter according to the real-time electric energy parameter of the charging system, the fluctuation prediction result and the target charging condition;
And the control module is used for controlling the charging system to adjust the charging parameters according to the charging adjustment parameters.
In a third aspect of the present invention, there is provided a computing device comprising: a processor, a memory storing a computer program which, when executed by the processor, performs a method as described in the first aspect.
In a fourth aspect of the invention, there is provided a computer readable storage medium storing instructions that when executed on a computer cause the computer to perform the method of the first aspect.
The scheme of the invention at least comprises the following beneficial effects:
According to the scheme, whether the robot fluctuates in the charging process is predicted by using the acquired state parameters of the charging system, so that the charging adjustment parameters are calculated, and the charging system is controlled to adjust the charging parameters according to the charging adjustment parameters, so that the constant charging condition is achieved, the charging efficiency and the service life of the robot are improved, and the charging system has the advantage of high safety.
Drawings
Fig. 1 is a flow chart of a robot charging method in an embodiment of the invention;
fig. 2 is a circuit diagram of a robot when charged in an embodiment of the present invention;
Fig. 3 is a schematic structural view of a robot charging apparatus in an embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present invention are shown in the drawings, it should be understood that the present invention may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.
As shown in fig. 1, an embodiment of the present invention proposes a robot charging method, including the steps of:
Step 101, acquiring state parameters of a robot when the robot is charged by a charging system;
102, extracting the characteristics of the state parameters to obtain characteristic data;
step 103, inputting the characteristic data into a fluctuation prediction model to obtain a fluctuation prediction result; the fluctuation prediction model is obtained by training a preset network model by utilizing historical robot charging data;
104, obtaining a charging adjustment parameter according to the real-time electric energy parameter of the charging system, the fluctuation prediction result and the target charging condition;
And 105, controlling the charging system to adjust the charging parameters according to the charging adjustment parameters.
According to the robot charging method provided by the embodiment of the invention, whether the robot fluctuates in the charging process is predicted by the acquired state parameters of the robot when the robot is charged by the charging system, so that the charging adjustment parameters are calculated, and the charging system is controlled to adjust the charging parameters according to the charging adjustment parameters, so that the constant charging condition is achieved, the charging efficiency and the service life of the robot are improved, and the robot charging method has the advantage of high safety.
The robot in this embodiment includes, but is not limited to, a sweeping robot, and a circuit diagram of a sweeping robot when charging is shown in fig. 2. One end of the resistor R4 is connected with the capacitor C3 and 220V alternating current, the other end of the resistor R4 is connected with the other end of the capacitor C3 and the port 1 of the rectifier bridge T, the port 2 of the rectifier bridge T is connected with the capacitor C4 and the anode of the diode D1, the cathode of the diode D1 is connected with the collector of the triode V4, the anode of the storage battery E and the resistor R4, the other end of the capacitor C4 is connected with the cathode of the storage battery E, the port 4 of the rectifier bridge T, the sweeping robot A, the potentiometer RP1, the capacitor C2 and the pin 2 of the chip IC1, the other end of the switch S1 is connected with the resistor R1, the emitter of the triode V1 and the emitter of the triode V2, the base of the triode V2 is connected with the resistor R2, the other end of the resistor R4 is connected with the collector of the triode V1, the base of the triode V1 and the capacitor C1, the base of the other end of the triode V1 is connected with the other end of the resistor R3, and the collector of the triode C2 of the sweeping robot A.
Specifically, above-mentioned charging circuit simple structure, components and parts are few, have the function of dual supply power to utilize voltage detection circuit and switch triode's combination, set up undervoltage protection module in the circuit, can also provide the protection to the condition of load short circuit simultaneously, consequently have that the function is various, convenient to use and control accurate advantage.
In an alternative embodiment of the present invention, step 102 includes:
Step 1021, preprocessing the state parameters to obtain preprocessed state parameters;
specifically, the preprocessing mode may include removing repeated, erroneous or incomplete data, performing normalization, standardization processing and the like, so as to eliminate dimension differences and numerical range differences between different data, and be beneficial to improving accuracy of results.
Step 1022, performing eigenvalue decomposition processing on the preprocessed state parameters to obtain eigenvalues and corresponding eigenvectors;
Specifically, the preprocessed state parameters can be decomposed into feature values and corresponding feature vectors through feature value decomposition, the magnitude of the feature values represents the importance degree of the corresponding feature vectors, and the feature vectors represent the directions of the original features in the new feature space.
Step 1023, sorting the characteristic values to obtain a sorting result;
Specifically, after the feature values and the corresponding feature vectors are obtained, the feature values need to be ranked, typically, the feature values are ranked from large to small, and since the feature values and the feature vectors are in a corresponding relationship, the larger the feature value corresponding to the feature vector after ranking, the more important the feature vector.
And step 1024, extracting features according to the sorting result and the feature vector to obtain feature data.
Specifically, according to the sorting result of the feature values, the feature vectors corresponding to the first N feature values are selected as main components, the main components represent linear combinations of the original features in the low-dimensional space, and most of information in the preprocessed state parameters can be reserved by selecting proper main components.
In an alternative embodiment of the present invention, step 103 includes:
Step 10311, inputting the characteristic data into an input layer of a fluctuation prediction model for processing to obtain a first output result;
specifically, through the input layer, the feature data can be converted into a format that can be processed by the fluctuation prediction model.
Step 10312, inputting the first output result into a first processing layer of the fluctuation prediction model for mapping processing to obtain a second output result;
Specifically, the mapping function y=f (X; θ) may be used to map the first output result to obtain the second output result. Where Y is the second output, f is the functional form of the mapping function, X is the first output, and θ is the unknown parameter.
Step 10313, inputting the second output result into a second processing layer of the fluctuation prediction model for separation processing to obtain separation data;
specifically, for each data in the second output result, calculating the distance from the second output result to the hyperplane, and judging the category of each data according to the distance and the hyperplane direction, so as to obtain the separated data.
And step 10314, inputting the separated data into an output layer of the fluctuation prediction model to obtain a fluctuation prediction result.
Specifically, the fluctuation prediction result may be a specific current, voltage and power fluctuation value, and may also be a description of fluctuation trend or range.
In an alternative embodiment of the present invention, the training process of the wave motion prediction model in step 103 includes:
In step 10321, historical robot charging data associated with the fluctuation is obtained, and the historical robot charging data is used as an independent variable (characteristic) and a dependent variable (target value), for example, the independent variable includes parameters such as charging current, charging voltage, charging power, temperature and the like, and the dependent variable is fluctuation amount (for example, fluctuation of current or voltage or power).
Step 10322, selecting characteristics with significant influence on fluctuation from the historical robot charging data, such as charging current data, charging voltage data and charging power data in the historical robot charging data if fluctuation of current or voltage or power needs to be considered;
step 10323, selecting a predetermined network model as Where y is the dependent variable, i.e. the amount of fluctuation to be predicted,、、Is an argument, n is the number of arguments, such as: is the charging current which is used to charge the battery, Is the charging voltage of the battery,Is the charging power of the battery,Is the intercept term, i.e., the predicted value of the dependent variable when the independent variable is 0,Is thatIs used for the coefficient of (a),Is thatIs used for the coefficient of (a),Is thatAre obtained by a training process.
Step 10324, dividing the historical robot charging data into training set and test set according to the preset proportion, training the preset network model by using the training set, and finding the optimal coefficient value (i.e、、……、Values of (2), which need to be passed throughMinimizing an error between the predicted value and the actual value, wherein L is the error between the predicted value and the actual value,In order to be able to predict the value,For the actual value, n is the number of data lines in the training set.
Step 10325, after finding the optimal coefficient value, obtaining an initial fluctuation prediction model, testing the initial fluctuation prediction model by using a test set, evaluating the performance of the initial fluctuation prediction model, and adjusting the initial fluctuation prediction model by using indexes such as calculation prediction error, accuracy and the like to obtain a final fluctuation prediction model.
In an alternative embodiment of the present invention, step 104 includes:
Step 1041, obtaining a target charging condition; the target charging conditions comprise a target current, a target charging voltage and a target charging power when the robot is charged;
step 1042, obtaining real-time electric energy parameters of the charging system; the real-time electric energy parameters comprise real-time voltage parameters, real-time current parameters and real-time power parameters;
Specifically, the current, the voltage and the power are important parameters for ensuring that the robot has a constant charging condition in the charging process, so that the target current, the target charging voltage and the target charging power of the robot in the target charging condition are required to be obtained, and the real-time voltage parameter, the real-time current parameter and the real-time power parameter of the charging system are used as the basis for subsequently adjusting the charging parameters and ensuring the constant charging condition when the robot is charged by using the charging system.
Step 1043, judging according to the real-time electric energy parameter of the charging system and the fluctuation prediction result to obtain a judgment result of whether the charging parameter needs to be adjusted;
Specifically, the current, voltage and power fluctuation values in the fluctuation prediction result can be correspondingly compared with the real-time voltage parameter, the real-time current parameter and the real-time power parameter of the charging system, and if the difference exists, the charging parameters need to be adjusted.
Step 1044, obtaining a charging adjustment parameter according to the determination result, the fluctuation prediction result and the target charging condition; the charge adjustment parameters include a charge current, a charge voltage, and a charge power.
Specifically, through adjusting charging current, charging voltage and charging power, current, voltage and power are in invariable state always when guaranteeing that the robot utilizes charging system to charge, reduce undulant, guarantee the battery safety of robot, extension battery and the life of robot.
In an alternative embodiment of the present invention, step 1044 includes:
Step 10441, obtaining an error value according to the judging result, the fluctuation predicting result and the target charging condition;
specifically, if the determination result is that the charging parameter needs to be adjusted, calculating an error value of the fluctuation prediction result and the target charging condition, where the overall target is that the smaller the error value between the fluctuation prediction result and the target charging condition is, the better, so the following objective function may be set:
Wherein the fluctuation prediction result and the parameters (charge adjustment parameters) in the target charge condition are the same, such as all including current parameters, voltage parameters, power parameters, etc., For an error value between the fluctuation prediction result and the target charging condition (such as an error value of the current parameter in the fluctuation prediction result and the current parameter of the target charging condition),For the target charging condition of the i-th parameter,For the fluctuation prediction result of the ith parameter, m is the number of parameters in the fluctuation prediction result and the target charging condition (if both the fluctuation prediction result and the target charging condition include the current parameter, the voltage parameter, and the power parameter, m is 3),For parameters (such as current parameters or voltage parameters or power parameters), i is an index variable used to traverse each parameter, and the value ranges from 1 to m.
Step 10442, performing bias derivative calculation according to the error value and a preset initialization charging adjustment parameter to obtain a gradient vector;
Specifically, a set of initial values is selected as the preset initialization charge adjustment parameters for the charge adjustment parameters, and the preset initialization charge adjustment parameters are continuously updated in the subsequent calculation process. And calculating deviation of a preset initialization charging adjustment parameter by using the objective function, and calculating a mean gradient by the following formula:
Then the gradient vector is obtained by the following formula ：
Wherein,Is the j-th eigenvalue of the i-th parameter.
Step 10443, updating the preset initialization charging adjustment parameter according to the gradient vector until reaching a preset stop condition, thereby obtaining the charging adjustment parameter.
Specifically, the preset initialization charging adjustment parameter is updated according to the opposite direction of the gradient vector, which can be specifically realized by subtracting the gradient vector from the current value of the charging adjustment parameter and multiplying the current value by a learning rate, wherein the formula is as follows:
Wherein, In order to update the charge adjustment parameters,Is the j-th charge adjustment parameter,For the learning rate, it determines the distance moved at each update,As an average factor of the values of the coefficients,As a result of fluctuation prediction of the kth parameter (charge adjustment parameter),For a target charging condition of the kth parameter,Is the j-th eigenvalue of the k-th parameter.
In an alternative embodiment of the present invention, step 105 includes:
and outputting the charging adjustment parameters to the charging system, so that the charging system adjusts the charging parameters according to the charging adjustment parameters to achieve the target charging condition.
Specifically, the target charging conditions include a target charging current, a target charging voltage and a target charging power when the robot is charged, and the charging adjustment parameters are output to the charging system, so that the charging system adjusts the charging parameters according to the charging adjustment parameters, the real-time current, the real-time voltage and the real-time power reach the target charging current, the target charging voltage and the target charging power in the target charging conditions, the charging requirement of the robot is met, fluctuation in the charging process of the robot is avoided, the charging efficiency is improved, and the service life of the robot is prolonged.
In an alternative embodiment of the present invention, the robot charging method further includes the steps of:
step 106, storing the real-time electric energy parameters, the fluctuation prediction result, the target charging condition and the charging adjustment parameters of the charging system;
specifically, the content is stored, so that the subsequent upgrading and maintenance of the charging system are facilitated.
And step 107, transmitting the real-time electric energy parameters of the charging system, the fluctuation prediction result, the target charging condition and the charging adjustment parameters to a robot management platform.
Specifically, the content is wirelessly and remotely sent to a robot management platform, so that maintenance and upgrading of the robot are facilitated, and fault backtracking is facilitated.
As shown in fig. 3, an embodiment of the present invention provides a robot charging apparatus 200 including:
An obtaining module 201, configured to obtain a state parameter of the robot when the robot is charged by using the charging system;
the extracting module 202 is configured to perform feature extraction on the state parameter to obtain feature data;
The prediction module 203 is configured to input the feature data into a fluctuation prediction model to obtain a fluctuation prediction result; the fluctuation prediction model is obtained by training a preset network model by utilizing historical robot charging data;
The processing module 204 is configured to obtain a charging adjustment parameter according to the real-time electric energy parameter of the charging system, the fluctuation prediction result and the target charging condition;
The control module 205 is configured to control the charging system to adjust the charging parameter according to the charging adjustment parameter.
Optionally, extracting the characteristics of the state parameter to obtain characteristic data includes:
preprocessing the state parameters to obtain preprocessed state parameters;
performing eigenvalue decomposition processing on the preprocessed state parameters to obtain eigenvalues and corresponding eigenvectors;
sorting the characteristic values to obtain a sorting result;
And carrying out feature extraction according to the sorting result and the feature vector to obtain feature data.
Optionally, inputting the feature data into a fluctuation prediction model to obtain a fluctuation prediction result, including:
inputting the characteristic data into an input layer of a fluctuation prediction model for processing to obtain a first output result;
inputting the first output result into a first processing layer of a fluctuation prediction model for mapping processing to obtain a second output result;
Inputting the second output result into a second processing layer of the fluctuation prediction model for separation processing to obtain separation data;
And inputting the separated data into an output layer of the fluctuation prediction model to obtain a fluctuation prediction result.
Optionally, obtaining the charging adjustment parameter according to the real-time electric energy parameter of the charging system, the fluctuation prediction result and the target charging condition includes:
Acquiring a target charging condition; the target charging conditions comprise a target current, a target charging voltage and a target charging power when the robot is charged;
acquiring real-time electric energy parameters of a charging system; the real-time electric energy parameters comprise real-time voltage parameters, real-time current parameters and real-time power parameters;
Judging according to the real-time electric energy parameters of the charging system and the fluctuation prediction result to obtain a judgment result of whether the charging parameters need to be adjusted;
obtaining a charging adjustment parameter according to the judging result, the fluctuation predicting result and the target charging condition; the charge adjustment parameters include a charge current, a charge voltage, and a charge power.
Optionally, obtaining the charging adjustment parameter according to the judging result, the fluctuation predicting result and the target charging condition includes:
obtaining an error value according to the judging result, the fluctuation predicting result and the target charging condition;
Performing deviation solving and conducting calculation according to the error value and a preset initialization charging adjustment parameter to obtain a gradient vector;
And updating the preset initialization charging adjustment parameters according to the gradient vector until a preset stopping condition is reached, so as to obtain the charging adjustment parameters.
Optionally, according to the charging adjustment parameter, controlling the charging system to adjust the charging parameter includes:
and outputting the charging adjustment parameters to the charging system, so that the charging system adjusts the charging parameters according to the charging adjustment parameters to achieve the target charging condition.
Optionally, the apparatus further includes:
A storage module 206, configured to store the real-time electric energy parameter, the fluctuation prediction result, the target charging condition, and the charging adjustment parameter of the charging system;
And the sending module 207 is configured to send the real-time electric energy parameter of the charging system, the fluctuation prediction result, the target charging condition and the charging adjustment parameter to a robot management platform.
According to the robot charging device provided by the embodiment of the invention, whether the robot fluctuates in the charging process is predicted by the acquired state parameters of the robot when the robot is charged by the charging system, so that the charging adjustment parameters are calculated, and the charging system is controlled to adjust the charging parameters according to the charging adjustment parameters, so that the constant charging condition is achieved, the charging efficiency and the service life of the robot are improved, and the robot charging device has the advantage of high safety.
It should be noted that, the device is a device corresponding to the above method, and all implementation manners in the above method embodiments are applicable to the embodiment of the device, so that the same technical effects can be achieved. In this embodiment, details are not described again.
The embodiment of the invention also provides a computing device, which comprises: a processor, a memory storing a computer program which, when executed by the processor, performs a method as in any of the above embodiments. All the implementation manners in the method embodiment are applicable to the embodiment of the device, and the same technical effect can be achieved. In this embodiment, details are not described again.
Embodiments of the present invention also provide a computer-readable storage medium having stored thereon instructions which, when run on a computer, cause the computer to perform a method according to any of the above embodiments. All the implementation manners in the method embodiment are applicable to the embodiment of the device, and the same technical effect can be achieved. In this embodiment, details are not described again.
While the foregoing is directed to the preferred embodiments of the present invention, it will be appreciated by those skilled in the art that various modifications and adaptations can be made without departing from the principles of the present invention, and such modifications and adaptations are intended to be comprehended within the scope of the present invention.
Claims (10)
1.A robot charging method, comprising:
acquiring state parameters of the robot when the robot is charged by a charging system;
extracting the characteristics of the state parameters to obtain characteristic data;
inputting the characteristic data into a fluctuation prediction model to obtain a fluctuation prediction result; the fluctuation prediction model is obtained by training a preset network model by utilizing historical robot charging data;
Obtaining a charging adjustment parameter according to the real-time electric energy parameter of the charging system, the fluctuation prediction result and the target charging condition;
And controlling the charging system to adjust the charging parameters according to the charging adjustment parameters.
2. The robot charging method according to claim 1, wherein the feature extraction of the state parameter to obtain feature data includes:
preprocessing the state parameters to obtain preprocessed state parameters;
performing eigenvalue decomposition processing on the preprocessed state parameters to obtain eigenvalues and corresponding eigenvectors;
sorting the characteristic values to obtain a sorting result;
And carrying out feature extraction according to the sorting result and the feature vector to obtain feature data.
3. The robot charging method according to claim 1, wherein inputting the characteristic data into a fluctuation prediction model to obtain a fluctuation prediction result comprises:
inputting the characteristic data into an input layer of a fluctuation prediction model for processing to obtain a first output result;
inputting the first output result into a first processing layer of a fluctuation prediction model for mapping processing to obtain a second output result;
Inputting the second output result into a second processing layer of the fluctuation prediction model for separation processing to obtain separation data;
And inputting the separated data into an output layer of the fluctuation prediction model to obtain a fluctuation prediction result.
4. The robot charging method according to claim 1, wherein obtaining the charging adjustment parameter according to the real-time power parameter of the charging system, the fluctuation prediction result, and the target charging condition comprises:
Acquiring a target charging condition; the target charging conditions comprise target charging current, target charging voltage and target charging power when the robot is charged;
acquiring real-time electric energy parameters of a charging system; the real-time electric energy parameters comprise real-time voltage parameters, real-time current parameters and real-time power parameters;
Judging according to the real-time electric energy parameters of the charging system and the fluctuation prediction result to obtain a judgment result of whether the charging parameters need to be adjusted;
obtaining a charging adjustment parameter according to the judging result, the fluctuation predicting result and the target charging condition; the charge adjustment parameters include a charge current, a charge voltage, and a charge power.
5. The method according to claim 4, wherein obtaining the charge adjustment parameter based on the determination result, the fluctuation prediction result, and the target charge condition includes:
obtaining an error value according to the judging result, the fluctuation predicting result and the target charging condition;
Performing deviation solving and conducting calculation according to the error value and a preset initialization charging adjustment parameter to obtain a gradient vector;
And updating the preset initialization charging adjustment parameters according to the gradient vector until a preset stopping condition is reached, so as to obtain the charging adjustment parameters.
6. The robot charging method of claim 1, wherein controlling the charging system to adjust the charging parameters according to the charging adjustment parameters comprises:
and outputting the charging adjustment parameters to the charging system, so that the charging system adjusts the charging parameters according to the charging adjustment parameters to achieve the target charging condition.
7. The robot charging method according to claim 1, further comprising:
Storing real-time electric energy parameters, the fluctuation prediction result, the target charging condition and the charging adjustment parameters of the charging system;
And transmitting the real-time electric energy parameters, the fluctuation prediction result, the target charging condition and the charging adjustment parameters of the charging system to a robot management platform.
8. A robotic charging device, comprising:
The acquisition module is used for acquiring state parameters of the robot when the robot is charged by the charging system;
The extraction module is used for extracting the characteristics of the state parameters to obtain characteristic data;
The prediction module is used for inputting the characteristic data into a fluctuation prediction model to obtain a fluctuation prediction result; the fluctuation prediction model is obtained by training a preset network model by utilizing historical robot charging data;
the processing module is used for obtaining a charging adjustment parameter according to the real-time electric energy parameter of the charging system, the fluctuation prediction result and the target charging condition;
And the control module is used for controlling the charging system to adjust the charging parameters according to the charging adjustment parameters.
9. A computing device, comprising: a processor, a memory storing a computer program which, when executed by the processor, performs the method of any one of claims 1 to 7.
10. A computer readable storage medium storing instructions which, when run on a computer, cause the computer to perform the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410649585.3A CN118249471B (en) | 2024-05-24 | 2024-05-24 | Robot charging method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410649585.3A CN118249471B (en) | 2024-05-24 | 2024-05-24 | Robot charging method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118249471A true CN118249471A (en) | 2024-06-25 |
| CN118249471B CN118249471B (en) | 2024-07-26 |
Family
ID=91551258
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410649585.3A Active CN118249471B (en) | 2024-05-24 | 2024-05-24 | Robot charging method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118249471B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120223579A1 (en) * | 2010-01-20 | 2012-09-06 | Sanyo Electric Co., Ltd. | Electrical charging and discharging system and charge and discharge control device |
| CN112733426A (en) * | 2020-12-16 | 2021-04-30 | 国创新能源汽车智慧能源装备创新中心(江苏)有限公司 | Pulse charging frequency optimization method and device for electric automobile |
| CN113258154A (en) * | 2021-07-16 | 2021-08-13 | 苏州浪潮智能科技有限公司 | Battery charging method, device, equipment and medium |
| CN116865400A (en) * | 2023-07-17 | 2023-10-10 | 湖州顺为能源科技有限公司 | Intelligent lithium battery charger and control system thereof |
| CN117554821A (en) * | 2023-11-20 | 2024-02-13 | 符宗卓 | Energy storage battery on-line monitoring management method and system based on deep learning network |
| CN117614060A (en) * | 2023-10-30 | 2024-02-27 | 郭宇琦 | Wireless charging method |
-
2024
- 2024-05-24 CN CN202410649585.3A patent/CN118249471B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120223579A1 (en) * | 2010-01-20 | 2012-09-06 | Sanyo Electric Co., Ltd. | Electrical charging and discharging system and charge and discharge control device |
| CN112733426A (en) * | 2020-12-16 | 2021-04-30 | 国创新能源汽车智慧能源装备创新中心(江苏)有限公司 | Pulse charging frequency optimization method and device for electric automobile |
| CN113258154A (en) * | 2021-07-16 | 2021-08-13 | 苏州浪潮智能科技有限公司 | Battery charging method, device, equipment and medium |
| CN116865400A (en) * | 2023-07-17 | 2023-10-10 | 湖州顺为能源科技有限公司 | Intelligent lithium battery charger and control system thereof |
| CN117614060A (en) * | 2023-10-30 | 2024-02-27 | 郭宇琦 | Wireless charging method |
| CN117554821A (en) * | 2023-11-20 | 2024-02-13 | 符宗卓 | Energy storage battery on-line monitoring management method and system based on deep learning network |
Non-Patent Citations (1)
| Title |
|---|
| KAIWEN CHEN 等: "A High-Interoperability Optimal Frequency Control Method for the AGV Dynamic Wireless Charging Systems Without Communication", IEEE TRANSACTIONS ON POWER ELECTRONICS, vol. 39, no. 3, 31 March 2024 (2024-03-31), pages 3797 - 3808 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118249471B (en) | 2024-07-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112699913A (en) | Transformer area household variable relation abnormity diagnosis method and device | |
| CN112132351A (en) | Electric vehicle charging load clustering prediction method and device | |
| Li et al. | Diagnosis for PEMFC systems: A data-driven approach with the capabilities of online adaptation and novel fault detection | |
| US20230118702A1 (en) | Method, device and computer readable storage medium for estimating SOC of lithium battery | |
| CN110766320A (en) | Method and device for evaluating operation safety of airport intelligent power grid | |
| CN113537525A (en) | Self-adaptive early warning method for fault state of battery energy storage system | |
| CN110766313A (en) | Cable tunnel comprehensive state evaluation method based on operation and maintenance system | |
| CN112541634B (en) | Method and device for predicting top-layer oil temperature and discriminating false alarm and storage medium | |
| CN115983134B (en) | Battery power state prediction method and system based on neural network | |
| CN118249471B (en) | Robot charging method and device | |
| CN114781875A (en) | Micro-grid economic operation state evaluation method based on deep convolutional network | |
| CN114814707A (en) | Intelligent ammeter stress error analysis method, equipment, terminal and readable medium | |
| Zhang et al. | State-of-charge estimation for lead-acid battery using isolation forest algorithm and long short term memory network with attention mechanism | |
| CN111277221A (en) | Photovoltaic fault diagnosis method and device | |
| CN117455725A (en) | Building energy consumption management method and system based on BIM (building information modeling) building | |
| CN117368789A (en) | Power failure co-location method and system based on multi-source heterogeneous data | |
| CN117713116A (en) | Voltage multistage regulating method and system based on reactive compensation | |
| CN114047372B (en) | Voltage characteristic-based platform region topology identification system | |
| CN115693916A (en) | Intelligent online monitoring method and system for direct-current power supply of transformer substation | |
| CN115863712A (en) | Water management method and system for fuel cell | |
| Qiao et al. | Transient stability assessment for ac-dc hybrid systems based on bayesian optimization xgboost | |
| CN109828170B (en) | Power distribution station gear identification method and device and storage medium | |
| CN116661522B (en) | Intelligent temperature regulation and control method for temperature change test box based on data processing | |
| CN114397519B (en) | Steady-state load identification method based on improved TOPSIS algorithm | |
| CN115511326A (en) | Grid-connected power supply adjustable performance evaluation method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |