CN114662556A - Fault diagnosis method for security intelligent operation and maintenance equipment - Google Patents
Fault diagnosis method for security intelligent operation and maintenance equipment Download PDFInfo
- Publication number
- CN114662556A CN114662556A CN202210125151.4A CN202210125151A CN114662556A CN 114662556 A CN114662556 A CN 114662556A CN 202210125151 A CN202210125151 A CN 202210125151A CN 114662556 A CN114662556 A CN 114662556A
- Authority
- CN
- China
- Prior art keywords
- maintenance
- equipment
- fault
- maintenance equipment
- diagnosed
- 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.)
- Pending
Links
- 238000012423 maintenance Methods 0.000 title claims abstract description 164
- 238000000034 method Methods 0.000 title claims abstract description 32
- 238000003745 diagnosis Methods 0.000 title claims abstract description 31
- 238000003062 neural network model Methods 0.000 claims description 17
- 238000012549 training Methods 0.000 claims description 16
- 230000008569 process Effects 0.000 claims description 11
- 239000000428 dust Substances 0.000 claims description 3
- 239000002023 wood Substances 0.000 claims description 3
- 241000533950 Leucojum Species 0.000 claims description 2
- 238000007726 management method Methods 0.000 description 31
- 238000004458 analytical method Methods 0.000 description 9
- 238000007689 inspection Methods 0.000 description 9
- 238000013528 artificial neural network Methods 0.000 description 8
- 230000006870 function Effects 0.000 description 8
- 230000009286 beneficial effect Effects 0.000 description 7
- 230000008439 repair process Effects 0.000 description 7
- 238000012545 processing Methods 0.000 description 6
- 238000011156 evaluation Methods 0.000 description 4
- 238000010801 machine learning Methods 0.000 description 4
- 238000003860 storage Methods 0.000 description 4
- 230000005540 biological transmission Effects 0.000 description 3
- 238000013079 data visualisation Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000009826 distribution Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 239000003795 chemical substances by application Substances 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000002427 irreversible effect Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000000704 physical effect Effects 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000012384 transportation and delivery Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
Images
Classifications
-
- 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
- G06F18/211—Selection of the most significant subset of features
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M99/00—Subject matter not provided for in other groups of this subclass
- G01M99/008—Subject matter not provided for in other groups of this subclass by doing functionality tests
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention relates to a fault diagnosis method for security and protection intelligent operation and maintenance equipment, and belongs to the field of security and protection system intelligent operation and maintenance. The method comprises the steps of collecting attribute information of traditional equipment of the operation and maintenance equipment to be diagnosed and historical fault data of the operation and maintenance equipment of the same type in a set range around the geographical position of the operation and maintenance equipment to be diagnosed, inputting the data serving as input quantity into an operation and maintenance equipment fault diagnosis model corresponding to the trained operation and maintenance equipment to be diagnosed, and predicting the fault type of the operation and maintenance equipment to be diagnosed. The invention considers the historical fault data of the operation and maintenance equipment of the same type near the operation and maintenance equipment to be diagnosed, also considers the geographic position of the operation and maintenance equipment of the same type around the operation and maintenance equipment to be diagnosed in the time-space characteristic information of the fault, considers the influence of the factors in the fault diagnosis method, and improves the accuracy of fault diagnosis of the operation and maintenance equipment to be diagnosed.
Description
Technical Field
The invention relates to a fault diagnosis method for security and protection intelligent operation and maintenance equipment, and belongs to the field of security and protection system intelligent operation and maintenance.
Background
In the security system, operation, maintenance and management are important works, and in the security system of large-scale mechanical equipment applied to the fields of aerospace and industrial process maintenance in the prior art, due to the characteristics of high specificity, high research and development cost and the like, operation and maintenance equipment in the security system is generally only overhauled and is not replaced. However, in the civil field of the security system, the cost of each operation and maintenance device is not high, so the operation and maintenance devices can be replaced after a period of overhaul. In the process of replacing the operation and maintenance equipment, the performance of the operation and maintenance equipment of different models and batches is different, and the fault data of the operation and maintenance equipment of different models and batches is also different, so that the operation and maintenance equipment cannot be detected and maintained by using the same detection method of the operation and maintenance equipment all the time.
At present, researchers apply a machine learning algorithm to operation and maintenance equipment of a security system, and when a machine learning algorithm model is designed, the input of the machine learning algorithm model only includes information of faulty operation and maintenance equipment. Correspondingly, when the designed machine learning algorithm model is used for fault diagnosis of a certain operation and maintenance device, only the data of the operation and maintenance device is collected and input into the designed model, so as to judge whether the operation and maintenance device has a fault or not. However, due to the limitation of space in a civil security system, a plurality of security devices of the same type may exist in a smaller distance range, and interference may exist between the security devices of the same type to cause a failure of the security device, so that the failure condition of the operation and maintenance device is determined only by using the data of the operation and maintenance device to be diagnosed, and the failure result of the operation and maintenance device is determined inaccurately.
Disclosure of Invention
The invention aims to provide a fault diagnosis method for security and protection intelligent operation and maintenance equipment, which is used for solving the problem that in the fault diagnosis process of the operation and maintenance equipment, only fault data of the operation and maintenance equipment to be diagnosed is collected for judgment, so that the judgment result is inaccurate.
In order to achieve the purpose, the technical scheme and the corresponding beneficial effects of the invention comprise that:
the invention relates to a fault diagnosis method of security intelligent operation and maintenance equipment, which comprises the following steps:
1) acquiring traditional equipment attribute information of the operation and maintenance equipment to be diagnosed and fault spatiotemporal feature information of nearby operation and maintenance equipment which is located in a set range near the operation and maintenance equipment to be diagnosed and has the same type as the operation and maintenance equipment to be diagnosed, wherein the fault spatiotemporal feature information comprises a geographical position, fault time and a fault type;
2) and inputting the acquired attribute information of the traditional equipment and the time-space characteristic information of the faults of the nearby operation and maintenance equipment into the fault diagnosis model of the operation and maintenance equipment corresponding to the type of the operation and maintenance equipment to be diagnosed to obtain the fault type of the operation and maintenance equipment to be diagnosed.
The beneficial effects of the above technical scheme are: in order to improve the accuracy of fault diagnosis of the operation and maintenance equipment to be diagnosed, the invention collects the traditional equipment attribute information of the operation and maintenance equipment to be diagnosed and historical fault data of the operation and maintenance equipment of the same type within a set range around the geographical position of the operation and maintenance equipment to be diagnosed, and inputs the data serving as input quantity into an operation and maintenance equipment fault diagnosis model corresponding to the trained operation and maintenance equipment to be diagnosed, so that the fault type of the operation and maintenance equipment to be diagnosed can be predicted.
In the invention, besides the information of the equipment to be diagnosed, the historical fault data of the same type of operation and maintenance equipment near the equipment to be diagnosed is also considered, so that for the security system, certain faults have certain regularity in space-time distribution, especially for the influence of similarity of factors such as power faults and thunderstorm weather on the security equipment in the whole area, and for the consideration, when the fault diagnosis model of the operation and maintenance equipment is designed, the input of the model also comprises the fault space-time characteristic information of the nearby equipment. The fault spatiotemporal characteristic information comprises a geographical position, and the geographical position is set in a way that the closer the fault spatiotemporal characteristic information is to the equipment to be diagnosed, the greater the influence on the equipment to be diagnosed. Therefore, the invention takes the influence of various factors into consideration, and improves the accuracy of fault diagnosis of the operation and maintenance equipment to be diagnosed.
Further, in the step 2), in the process of training the operation and maintenance equipment fault diagnosis model, the training data is the latest data within a set time period from the current time.
The beneficial effects of the above technical scheme are: in the process of training the model, the data is ensured to be the latest training data, and the processing is that the latest training data has the maximum reference value, and the accuracy and precision of model training can be improved by using the latest training data.
Further, the operation and maintenance equipment fault diagnosis model is an RNN neural network model.
Further, the conventional device attribute information includes at least two kinds of information of purchase time of the operation and maintenance device, use time of the operation and maintenance device, manufacturer of the operation and maintenance device, model of the operation and maintenance device, geographical location of the operation and maintenance device, and external characteristic information of the operation and maintenance device, and the external characteristic information includes at least one kind of information of temperature, humidity, dust content, vibration, noise, and electromagnetic interference.
Further, if the operation and maintenance equipment to be diagnosed is a camera, the attribute information of the conventional equipment further includes at least one of snow noise rate, black screen times and duration within a set time range, and interference time of a picture vertical bar or a wood grain bar.
The beneficial effects of the above technical scheme are: if the operation and maintenance equipment to be diagnosed is a camera, the specific data of the camera is used as a reference quantity, so that the accuracy of camera fault diagnosis is improved.
Further, if the operation and maintenance equipment to be diagnosed is a gate, the conventional equipment attribute information further includes at least one of motor speed curve data and current curve data.
The beneficial effects of the above technical scheme are: if the operation and maintenance equipment to be diagnosed is a gate, the specific data of the gate is used as a reference quantity, so that the accuracy of gate fault diagnosis is improved.
Further, if the operation and maintenance device to be diagnosed is a fingerprint access control device, the attribute information of the conventional device further includes an error rate.
The beneficial effects of the above technical scheme are: if the operation and maintenance equipment to be diagnosed is an entrance guard, the specific data of the entrance guard are used as reference quantity, and the accuracy of entrance guard fault diagnosis is improved.
Further, the method also comprises the step of carrying out one-bit effective coding on the acquired traditional equipment attribute information of the operation and maintenance equipment to be diagnosed and the fault spatiotemporal characteristic information of the nearby equipment.
The beneficial effects of the above technical scheme are: all information is coded, so that the computer can conveniently process and operate.
Drawings
FIG. 1 is an overall framework diagram of the security intelligent operation and maintenance system of the present invention;
FIG. 2 is a schematic diagram of a fault diagnosis method for the security intelligent operation and maintenance device according to the present invention;
FIG. 3 is a schematic diagram of the RNN neural network structure of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples.
Example (b):
the security protection intelligent operation and maintenance system provided by the invention is integrally divided into a management object layer, an acquisition layer, a convergence processing layer and an application layer as shown in figure 1. The management object layer is all manageable facilities, including all software and hardware facilities, data, log files, network streams and the like, and specifically comprises the following steps: monitoring system, infrared detector, fingerprint entrance guard and floodgate machine. The acquisition layer requires the manageable facilities of each management object layer to upload static indexes, the static indexes comprise host names and IP addresses of the manageable facilities, and the running state information of the equipment is reported. The convergence processing layer analyzes and processes the information acquired by the acquisition layer, and mainly comprises three functions of resource management, an analysis engine and service management. The resource management mainly realizes the processing of the running state data of the software and hardware facilities. And the analysis engine forms sequence data for the equipment state characteristics according to time, fault analysis and life cycle management are carried out through the RNN neural network, and an online learning mechanism is used for enabling the analysis engine to adapt to the characteristics of the operation and maintenance system. And the service management layer is responsible for issuing and processing maintenance work order information. The application layer only needs to realize the visual display of the states, structures and the like of manageable facilities and data in the system based on a high-precision map, and finally realizes various functions of the security intelligent operation and maintenance system capable of operation and maintenance.
The application layer specifically comprises platform deployment, job management, interface management, system evaluation analysis, life cycle management, document management, online warranty APP, a data visualization platform, terminal management and authority management. The platform deployment application is implemented on a cloud computing platform and comprises physical equipment, a virtual host and the like, and has an abnormal alarm notification function. The operation management application realizes personnel scheduling, routing inspection plan management and spare part management. The interface management subsystem application provides standard interface for other systems to call after platform application and approval, and the function includes: the system comprises an asset information issuing interface, a work order information issuing interface, an equipment alarm information issuing interface, an online interface description document, a statistical data issuing interface, interface approval management and inquiry and interface calling management. The system evaluation analysis application function is used for formulating evaluation indexes and realizing cost accounting, and the specific evaluation comprises the following steps: the personnel and vehicles on duty condition and daily operation and maintenance basic data are subjected to statistical analysis, and the access rate, the online rate, the completion rate, the workload and the like of the equipment are quantized. The life cycle management application records and manages the whole life cycle process from equipment installation, construction, delivery, use, maintenance to final abandonment. The document management application realizes the unified management of the operation and maintenance related document data of the security intelligent operation and maintenance system, including uploading, inquiring, deleting and the like of the document. The method specifically comprises the following steps: the uploading, the query and the full-text retrieval of the documents are realized according to the areas, the streets, the intersections and the equipment where the equipment is located. The online repair APP realizes on-site work order processing and realizes the functions of displaying the positions, the running states and the asset details of equipment such as a gate, a video monitor and an intelligent access control in a mobile phone GIS map mode, receiving a shift scheduling plan, receiving a routing inspection task, uploading a routing inspection report and the like on the intelligent mobile phone. The data visualization platform realizes the visualization display of operation and maintenance data, the acquisition, aggregation, cleaning and analysis of operation and maintenance big data, and realizes the perception of system operation quality, fault warning and tracking. The terminal management realizes the management of the intelligent operation and maintenance terminal equipment installed at the front end, reports the data of equipment temperature, humidity, the state of a cabinet door, power supply, network, video and the like through the installed intelligent operation and maintenance terminal, and collects various alarm information from the intelligent operation and maintenance terminal. And the authority management application realizes the management of the account number, the role and the authority of the platform.
Based on the security intelligent operation and maintenance system, the fault diagnosis method of the security intelligent operation and maintenance equipment provided by the invention can be realized through the analysis engine, and as shown in fig. 2, the fault diagnosis method comprises the following steps.
1) And acquiring the information of the operation and maintenance equipment.
Firstly, acquiring attribute information of each operation and maintenance traditional device in a management object layer in a security intelligent operation and maintenance system, specifically comprising: the purchase time of the equipment, the service time of the equipment, the manufacturer of the equipment, the model of the equipment, the geographical position (including longitude and latitude and altitude) of the equipment, and the external characteristics (including temperature, humidity, dust, vibration, noise, electromagnetic interference and the like) of the equipment.
Specific legacy device attribute information is also obtained for a specific operation and maintenance device. When the operation and maintenance equipment is a camera, the specific traditional equipment attribute information of the camera comprises a snowflake noise rate, the number and duration of black screen within a period of time, and the duration of vertical bar or wood grain-shaped interference of a picture. When the operation and maintenance device is a gate, the gate-specific conventional device attribute information includes a motor speed curve and a current curve. When the operation and maintenance equipment is fingerprint access control, the specific traditional equipment attribute information of the fingerprint access control comprises an error rate.
Besides the traditional device attribute information of the operation and maintenance device, it is also necessary to obtain the fault spatiotemporal feature information of the same operation and maintenance device within the range of the geographical location of the operation and maintenance device that needs fault diagnosis, where the fault spatiotemporal feature information includes the geographical location (including longitude, latitude and altitude), the time when the fault occurs, and the type of the fault device. Over time, the fault spatiotemporal feature information will increase. And the operation and maintenance equipment faults have certain regularity in space-time distribution, and factors such as power faults and thunderstorm weather can generate similar influences on the operation and maintenance equipment in the region, so that the fault space-time characteristics are used as input quantity to be applied to the security intelligent operation and maintenance system to achieve better performance.
2) And carrying out fault diagnosis and prediction by using the RNN neural network model.
After the information of the operation and maintenance equipment is acquired in the step 1), the information of the operation and maintenance equipment is encoded in a one-hot (one-bit effective encoding) manner, and as another embodiment, an encoding manner such as target encoding or leave-one-out encoding may also be adopted. Each type of operation and maintenance equipment corresponds to one RNN neural network model, information of the operation and maintenance equipment is coded and then correspondingly input to the RNN neural network model corresponding to the operation and maintenance equipment type for fault diagnosis and prediction, and the fault type of the operation and maintenance equipment is obtained (generally, the fault type comprises normal data in the case of non-fault). At this time, the corresponding RNN neural network model is the RNN neural network model which is trained, and the specific training process is as follows;
the RNN neural network structure used in the present invention is shown in fig. 3, where X is a vector, and represents that the latest value of the encoded information of the operation and maintenance device is input to the RNN neural network as an input value for training; s is a vector representing the value of the hidden layer; u is the weight matrix from the input layer to the hidden layer; o is a vector which represents that the fault type of the operation and maintenance equipment at the current moment is taken as an output quantity; v is the activation function of the hidden layer to the output layer; w is the value of the layer above the hidden layer as the weight of this input. In the RNN neural network, the neurons of the hidden layers are weighted with weights W, as the sequence is continuously advanced, the hidden layers in the front will influence the hidden layers in the back, and the loss function is continuously accumulated as the sequence is recommended. Wherein W, U and V are the same value.
Taking a camera as an example, when an RNN neural network model is trained, historical fault information related to the camera A is collected, wherein the historical fault information comprises traditional equipment attribute information when the camera A has a certain fault at a certain moment, fault conditions of the camera B, the camera C, the camera D and the camera E near the camera A, and the traditional equipment attribute information when the camera A has a certain fault, and the latest state data in the fault space-time characteristic information of the camera B, the camera C, the camera D and the camera E are used as the input quantity of the RNN neural network model, and setting the fault type of the camera A at the fault occurrence time as an output quantity corresponding to the input quantity, and training an RNN neural network model by using all input quantity data and the output quantity data corresponding to the input quantity data as training data so as to obtain hidden layer data and weight in the RNN neural network. Continuously updating n latest state data in traditional equipment attribute information and fault space-time characteristic information related to the camera as input quantity, correspondingly updating the fault condition of the camera at the corresponding moment, setting the fault condition as an output value, and continuously and circularly training until the hidden layer data and the weight in the RNN neural network model reach an ideal state, wherein the RNN neural network model of the corresponding camera is trained. After training is finished, acquiring traditional equipment attribute information and fault spatiotemporal feature information of the camera and inputting the traditional equipment attribute information and the fault spatiotemporal feature information into an RNN neural network model of the camera, wherein the RNN neural network model of the camera outputs a predicted fault type of the camera. The RNN neural network model of other operation and maintenance equipment is similar to that of the camera.
The security protection intelligent operation and maintenance system has adaptivity to the updating of operation and maintenance equipment. Specifically, the operation and maintenance equipment is continuously updated in an iterative manner, products in different stages have different physical properties and electrical characteristics, and equipment of the same brand, the same model and different batches of equipment also have differences. For example, when the security intelligent operation and maintenance system changes the camera into a low power consumption version, a power consumption curve is decreased, and the signal noise is increased, so that the traditional analysis engine is easy to misjudge or the model needs to be retrained. This difference is even more pronounced as the operation and maintenance equipment is faster to change. Therefore, in the RNN neural network model, whether the operation and maintenance equipment is replaced or not, the input quantity of the RNN neural network always acquires the latest n pieces of traditional equipment attribute information and fault spatiotemporal feature information as the input quantity, and the input data which is used in the RNN neural network model training is deleted to reduce the system memory.
Everybody of the inspection personnel is equipped with a handheld terminal, and the handheld terminal is provided with an online repair APP corresponding to the intelligent operation and maintenance system. After the fault of the operation and maintenance equipment is predicted by using the RNN neural network, the data information is sent to an online repair APP, and the inspection personnel receive tasks assigned by the system by using the online repair APP. The data visualization platform projects the position information of the operation and maintenance equipment needing to be repaired or replaced to a GIS map, and the patrol personnel acquire the position information of the operation and maintenance equipment on the map through an online repair APP. And after finding the operation and maintenance equipment, the inspection personnel acquires the equipment ID through the external two-dimensional code of the operation and maintenance equipment and confirms the operation and maintenance equipment again. The inspection personnel access the historical maintenance record of the operation and maintenance equipment through the online repair APP, and the historical maintenance information of the operation and maintenance equipment is downloaded through the network to help the inspection personnel to maintain the operation and maintenance equipment. After the maintenance of the operation and maintenance equipment is completed, the inspection personnel input the maintenance result information through the online repair reporting APP, and submit the life cycle management for auditing, so that the whole maintenance process of the operation and maintenance equipment is completed.
The data uploading line of the security intelligent operation and maintenance system adopts a tree topology structure. The tree-type topology structure is formed by the evolution of bus topology, is similar to the shape of a tree, and is easy to isolate faults and convenient to expand. The system data is accessed by default through https, the security risk of malicious man-in-the-middle service hijacking is reduced through a credit granting certificate, and information leakage caused by data sniffing in the process of transmitting information plaintext is protected through https encryption transmission. By means of the agent access platform and the configuration of encryption algorithm access meeting the safety requirements, direct external exposure of an internal service port is reduced, and service safety is improved. The service only responds to the access of the trust IP and defends against cross-site attack and malicious access of a non-trust server. Each component stores independent encryption, and the keys are respectively kept and isolated from each other, so that the security of the data stored by other components is not influenced even if a small number of component security keys are broken. The high-sensitivity security data such as the user password and the like are stored by adopting an anti-tampering and irreversible encryption algorithm, so that the security and the non-tampering of the original password are guaranteed. The front end requests the back end, the sensitive description transmission adopts https, and the data is encrypted and transmitted by using an asymmetric encryption algorithm, so that the security of data transmission is further guaranteed. The key storage uses a security box of a company to perform encryption storage management. And when the platform accesses the storage and the equipment, the platform accesses the storage and the equipment by adopting respective security authentication.
Claims (8)
1. A fault diagnosis method for security intelligent operation and maintenance equipment is characterized by comprising the following steps:
1) acquiring traditional equipment attribute information of the operation and maintenance equipment to be diagnosed and fault spatiotemporal feature information of the adjacent operation and maintenance equipment which is located in a set range near the operation and maintenance equipment to be diagnosed and has the same type as the operation and maintenance equipment to be diagnosed, wherein the fault spatiotemporal feature information comprises a geographical position, fault time and a fault type;
2) and inputting the acquired attribute information of the traditional equipment and the time-space characteristic information of the faults of the nearby operation and maintenance equipment into the fault diagnosis model of the operation and maintenance equipment corresponding to the type of the operation and maintenance equipment to be diagnosed to obtain the fault type of the operation and maintenance equipment to be diagnosed.
2. The method for diagnosing the fault of the security intelligent operation and maintenance device according to claim 1, wherein in the step 2), in the process of training the fault diagnosis model of the operation and maintenance device, the training data is the latest data within a set time period from the current time.
3. The method for diagnosing the fault of the security intelligent operation and maintenance equipment according to claim 1, wherein the operation and maintenance equipment fault diagnosis model is an RNN neural network model.
4. The method for diagnosing the failure of the security intelligent operation and maintenance device according to claim 1, wherein the conventional device attribute information includes at least two kinds of information selected from a purchase time of the operation and maintenance device, a use time of the operation and maintenance device, a manufacturer of the operation and maintenance device, a model of the operation and maintenance device, a geographical location of the operation and maintenance device, and external characteristic information of the operation and maintenance device, and the external characteristic information includes at least one kind of information selected from temperature, humidity, dust content, vibration, noise, and electromagnetic interference.
5. The method for diagnosing the fault of the security intelligent operation and maintenance device according to claim 4, wherein if the operation and maintenance device to be diagnosed is a camera, the attribute information of the traditional device further comprises at least one of a snowflake noise rate, the number and duration of black screens within a set time range, and the interference time of vertical bars or wood stripes of a picture.
6. The method for diagnosing the failure of the security intelligent operation and maintenance device according to claim 4, wherein if the operation and maintenance device to be diagnosed is a gate, the conventional device attribute information further includes at least one of motor speed curve data and current curve data.
7. The method for diagnosing the faults of the security intelligent operation and maintenance equipment according to claim 4, wherein if the operation and maintenance equipment to be diagnosed is a fingerprint access control, the attribute information of the traditional equipment further comprises an error rate.
8. The method for diagnosing the faults of the security intelligent operation and maintenance equipment according to any one of claims 1 to 7, further comprising a step of performing one-bit effective coding on the acquired attribute information of the traditional equipment of the operation and maintenance equipment to be diagnosed and the fault spatiotemporal feature information of the nearby equipment.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210125151.4A CN114662556A (en) | 2022-02-10 | 2022-02-10 | Fault diagnosis method for security intelligent operation and maintenance equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210125151.4A CN114662556A (en) | 2022-02-10 | 2022-02-10 | Fault diagnosis method for security intelligent operation and maintenance equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114662556A true CN114662556A (en) | 2022-06-24 |
Family
ID=82026125
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210125151.4A Pending CN114662556A (en) | 2022-02-10 | 2022-02-10 | Fault diagnosis method for security intelligent operation and maintenance equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114662556A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108629430A (en) * | 2018-05-14 | 2018-10-09 | 西安交通大学 | A kind of substantial equipment intelligence operation management system |
| CN110535711A (en) * | 2019-09-17 | 2019-12-03 | 河南骏德信息科技有限责任公司 | A kind of video monitoring fault diagnosis system and diagnostic method |
| CN111757096A (en) * | 2020-06-23 | 2020-10-09 | 广州红贝科技有限公司 | Video operation and maintenance management system and method |
| CN113691801A (en) * | 2021-08-17 | 2021-11-23 | 国网安徽省电力有限公司检修分公司 | Video monitoring equipment fault monitoring method and system based on video image analysis |
-
2022
- 2022-02-10 CN CN202210125151.4A patent/CN114662556A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108629430A (en) * | 2018-05-14 | 2018-10-09 | 西安交通大学 | A kind of substantial equipment intelligence operation management system |
| CN110535711A (en) * | 2019-09-17 | 2019-12-03 | 河南骏德信息科技有限责任公司 | A kind of video monitoring fault diagnosis system and diagnostic method |
| CN111757096A (en) * | 2020-06-23 | 2020-10-09 | 广州红贝科技有限公司 | Video operation and maintenance management system and method |
| CN113691801A (en) * | 2021-08-17 | 2021-11-23 | 国网安徽省电力有限公司检修分公司 | Video monitoring equipment fault monitoring method and system based on video image analysis |
Non-Patent Citations (2)
| Title |
|---|
| 唐建, 张梅军, 夏志高: "基于BP网络的闸门典型故障诊断", 解放军理工大学学报(自然科学版), no. 04, 25 August 2004 (2004-08-25) * |
| 徐春玲: "校园安防运维系统的现状及应用", 中国安防, no. 3, 1 March 2018 (2018-03-01), pages 43 - 47 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112102111B (en) | Intelligent processing system for power plant data | |
| CN109656793A (en) | A kind of information system performance stereoscopic monitoring method based on multi-source heterogeneous data fusion | |
| CN105553957A (en) | Network safety situation awareness early-warning method and system based big data | |
| CN112785458A (en) | Intelligent management and maintenance system for bridge health big data | |
| CN106888205A (en) | A kind of non-intrusion type is based on the PLC method for detecting abnormality of power consumption analysis | |
| CN101459537A (en) | Network security situation sensing system and method based on multi-layer multi-angle analysis | |
| US20240142063A1 (en) | Method for troubleshooting potential safety hazards of compressor in smart gas pipeline network and internet of things system thereof | |
| CN101436967A (en) | Method and system for evaluating network safety situation | |
| CN110866642A (en) | Security monitoring method and device, electronic equipment and computer readable storage medium | |
| CN108198408B (en) | Self-adaptive anti-electricity-stealing monitoring method and system based on electricity information acquisition system | |
| CN108650139A (en) | A kind of powerline network monitoring system | |
| CN115378711B (en) | Intrusion detection method and system for industrial control network | |
| CN117439916A (en) | Network security test evaluation system and method | |
| CN112488877A (en) | Industrial energy consumption visualization system for energy service platform | |
| CN100412993C (en) | System for intelligent maintaince of muclear power paltn based on state monitoring | |
| Chen et al. | AI maintenance: a robustness perspective | |
| Kummerow et al. | Cyber-physical data stream assessment incorporating Digital Twins in future power systems | |
| CN118313812A (en) | Electric power big data acquisition and processing method based on machine learning | |
| CN115296933B (en) | Industrial production data risk level assessment method and system | |
| CN114061728B (en) | Remote metering and monitoring system for dynamic truck scale | |
| CN118230553B (en) | Traffic flow data analysis system based on expressway | |
| CN114662556A (en) | Fault diagnosis method for security intelligent operation and maintenance equipment | |
| CN118521264A (en) | Forestry resource dynamic monitoring and asset assessment integrated technology | |
| CN103795585A (en) | Method and system for monitoring website based on black list | |
| CN117828304A (en) | Electric power energy monitoring and analyzing method and system based on big data |
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 |