Fault diagnosis method and device for power system
By using a fault identification model trained by multiple sets of sample data, automatic fault diagnosis is realized, the problem of low reliability of manual analysis in the existing technology is solved, and the efficiency and reliability of fault diagnosis of power system is improved. .
Patent Information
- Application Number
- CN202310645221.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2023-05-31
- Publication Date
- 2024-12-03
AI Technical Summary
In the prior art, power system fault diagnosis relies on manual analysis by experienced experts, resulting in low reliability.
By obtaining fault-related data of the power system, using the fault identification model trained by multiple sets of sample data to process the data, obtain fault identification information and fault cause information, thereby realizing automated fault diagnosis.
Improves the efficiency and reliability of power system fault diagnosis and reduces dependence on experienced experts.
Smart Images

Figure CN119066413A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of power system fault diagnosis, and in particular to a power system fault diagnosis method and device. Background Art
[0002] The power system is a complex and large-scale network, and its operation stability is crucial. However, due to various reasons, power systems may fail. In order to ensure the reliable operation of the power system, real-time detection and diagnosis of power system faults are particularly important. However, traditional fault diagnosis methods usually rely on manual analysis by experienced experts, which is time-consuming and has limited accuracy.
[0003] With regard to the problem that the above-mentioned related technologies usually rely on manual analysis by experienced experts when diagnosing faults in power systems, and the reliability is low, no effective solution has been proposed so far. Summary of the invention
[0004] The embodiment of the present invention provides a method and device for diagnosing faults in an electric power system, so as to at least solve the technical problem in the related art that fault diagnosis of an electric power system usually relies on manual analysis by experienced experts, which results in low reliability.
[0005] According to one aspect of an embodiment of the present invention, a fault diagnosis method for an electric power system is provided, comprising: obtaining fault-related data of a target electric power system, wherein the target electric power system is a power system to be diagnosed for fault, and the fault-related data includes at least: historical fault reports of the target electric power system, relay protection action record information of the target electric power system, and equipment status information of electric equipment in the target electric power system; inputting the fault-related data into a fault identification model to process the fault-related data using the fault identification model, wherein the fault identification model is a model obtained by training using multiple groups of sample data, each of the multiple groups of sample data includes: sample fault-related data and sample fault diagnosis results corresponding to the sample fault-related data, the sample fault-related data is the input of the fault identification model, and the sample fault diagnosis result is the output of the fault identification model; obtaining the output result of the fault identification model, wherein the output result includes at least: fault identification information and fault cause information; and determining that the output result is the fault information of the target electric power system.
[0006] Optionally, the fault-related data is input into a fault identification model so as to process the fault-related data using the fault identification model, including: preprocessing the fault-related data to obtain the preprocessed fault-related data, wherein the preprocessing includes at least the following operations: data cleaning operation, data standardization operation, data feature extraction operation; inputting the preprocessed fault-related data into the fault identification model so as to process the preprocessed fault-related data using the fault identification model.
[0007] Optionally, before inputting the fault-related data into a fault identification model to process the fault-related data using the fault identification model, the fault diagnosis method of the power system also includes: acquiring a plurality of the sample fault-related data within a historical time period and a plurality of the sample fault diagnosis results corresponding to the sample fault-related data; training a natural language processing model using a plurality of groups of sample data including a plurality of the sample fault-related data and a plurality of the sample fault diagnosis results to obtain the fault identification model.
[0008] Optionally, the fault-related data is input into a fault identification model so as to process the fault-related data using the fault identification model, including at least one of the following: after determining that the fault-related data is input into the fault identification model, the fault-related data is processed using the fault identification model to obtain the fault identification information, wherein the fault identification information includes at least: fault type, fault location and fault time; after determining that the fault-related data is input into the fault identification model, the fault-related data is processed using the fault identification model to obtain the fault cause information.
[0009] Optionally, after determining that the output result is the fault information of the target power system, the fault diagnosis method of the power system further includes at least: displaying the fault information; generating a new fault report based on the fault information; and saving the fault report.
[0010] Optionally, after determining that the output result is the fault information of the target power system, the fault diagnosis method of the power system also includes: obtaining actual fault information of the target power system; comparing the actual fault information with the fault information to obtain a comparison result; and determining the accuracy of the fault information based on the similarity between the actual fault information and the fault information in the comparison result.
[0011] Optionally, after determining that the output result is the fault information of the target power system, the fault diagnosis method of the power system further includes: optimizing the fault identification model using the comparison result to obtain the optimized fault identification model.
[0012] According to the above embodiment of the present invention, there is also provided a fault diagnosis device for an electric power system, comprising: a first acquisition unit, used to acquire fault-related data of a target electric power system, wherein the target electric power system is a power system to be diagnosed for fault, and the fault-related data at least includes: historical fault reports of the target electric power system, relay protection action record information of the target electric power system, and equipment status information of electric equipment in the target electric power system; a processing unit, used to input the fault-related data into a fault identification model so as to process the fault-related data using the fault identification model, wherein the fault identification model is a model obtained by training using multiple groups of sample data, each of the multiple groups of sample data includes: sample fault-related data and sample fault diagnosis results corresponding to the sample fault-related data, the sample fault-related data is the input of the fault identification model, and the sample fault diagnosis result is the output of the fault identification model; a second acquisition unit, used to acquire the output result of the fault identification model, wherein the output result at least includes: fault identification information and fault cause information; a determination unit, used to determine that the output result is the fault information of the target electric power system.
[0013] Optionally, the processing unit includes: a preprocessing module, used to preprocess the fault-related data to obtain the preprocessed fault-related data, wherein the preprocessing includes at least the following operations: data cleaning operation, data standardization operation, data feature extraction operation; a first processing module, used to input the preprocessed fault-related data into the fault identification model to process the preprocessed fault-related data using the fault identification model.
[0014] Optionally, the fault diagnosis device of the power system also includes: a third acquisition unit, used to acquire a plurality of the sample fault-related data within a historical time period and a plurality of the sample fault diagnosis results corresponding to the sample fault-related data before inputting the fault-related data into the fault identification model to process the fault-related data using the fault identification model; a training unit, used to train the natural language processing model using multiple groups of sample data including a plurality of the sample fault-related data and a plurality of the sample fault diagnosis results to obtain the fault identification model.
[0015] Optionally, the processing unit includes at least one of the following: a second processing module, used to process the fault-related data using the fault identification model to obtain the fault identification information after determining that the fault-related data is input into the fault identification model, wherein the fault identification information includes at least: fault type, fault location and fault time; a third processing module, used to process the fault-related data using the fault identification model to obtain the fault cause information after determining that the fault-related data is input into the fault identification model.
[0016] Optionally, the fault diagnosis device of the power system also includes at least: a display unit, used to display the fault information after determining that the output result is the fault information of the target power system; a generation unit, used to generate a new fault report based on the fault information; and a storage unit, used to store the fault report.
[0017] Optionally, the fault diagnosis device of the power system also includes: a fourth acquisition unit, used to acquire actual fault information of the target power system after determining that the output result is the fault information of the target power system; a comparison unit, used to compare the actual fault information with the fault information to obtain a comparison result; and the determination unit, used to determine the accuracy of the fault information based on the similarity between the actual fault information and the fault information in the comparison result.
[0018] Optionally, the fault diagnosis device of the power system further includes: an optimization unit, which is used to optimize the fault identification model using the comparison result after determining that the output result is the fault information of the target power system, so as to obtain the optimized fault identification model.
[0019] According to the above embodiment of the present invention, a computer-readable storage medium is further provided, wherein the computer-readable storage medium includes a stored program, wherein the program executes any one of the above-mentioned methods for diagnosing faults in a power system.
[0020] According to the above embodiment of the present invention, a processor is further provided, and the processor is used to run a program, wherein the program executes any one of the above-mentioned methods for diagnosing faults in a power system when running.
[0021] In an embodiment of the present invention, fault-related data of a target power system is obtained, wherein the target power system is a power system to be diagnosed for faults, and the fault-related data at least includes: historical fault reports of the target power system, relay protection action record information of the target power system, and equipment status information of power equipment in the target power system; the fault-related data is input into a fault identification model to process the fault-related data using the fault identification model, wherein the fault identification model is a model obtained by training with multiple groups of sample data, each of the multiple groups of sample data includes: sample fault-related data and sample fault diagnosis results corresponding to the sample fault-related data, the sample fault-related data is the input of the fault identification model, and the sample fault diagnosis results are the output of the fault identification model; the output result of the fault identification model is obtained, wherein the output result at least includes: fault identification information and fault cause information; and the output result is determined to be the fault information of the target power system. Through the technical solution provided by the present invention, the purpose of diagnosing faults in the power system through the fault identification model trained by machine learning is achieved, so that the fault information of the power system can be obtained in a relatively intelligent way, the efficiency and reliability of fault diagnosis of the power system are improved, and the technical problem of low reliability that the related technology usually relies on manual analysis by experienced experts when diagnosing faults in the power system is solved. BRIEF DESCRIPTION OF THE DRAWINGS
[0022] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:
[0023] Figure 1 It is a hardware structure block diagram of a mobile terminal of a method for diagnosing a fault in an electric power system according to an embodiment of the present invention;
[0024] Figure 2 is a flow chart of a fault diagnosis method for a power system according to an embodiment of the present invention;
[0025] Figure 3 is a schematic diagram of a fault diagnosis device for an electric power system according to an embodiment of the present invention. DETAILED DESCRIPTION
[0026] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.
[0027] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.
[0028] As introduced in the background technology, the related art usually relies on experienced experts to perform manual analysis when diagnosing faults in power systems, which has the defect of low reliability. In the embodiments of the present invention, a method and apparatus for diagnosing faults in power systems, a computer-readable storage medium and a processor are provided.
[0029] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the accompanying drawings in the embodiments of the present invention.
[0030] The method embodiments provided in the embodiments of the present invention can be executed in a mobile terminal, a computer terminal or a similar computing device. Taking running on a mobile terminal as an example, Figure 1 FIG. 1 is a hardware structure block diagram of a mobile terminal of a method for diagnosing a fault in a power system according to an embodiment of the present invention. Figure 1 As shown, the mobile terminal may include one or more ( Figure 1 Only one is shown in the figure) a processor 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data, wherein the mobile terminal may also include a transmission device 106 and an input / output device 108 for communication functions. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the mobile terminal. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations shown.
[0031] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the fault diagnosis method of the power system in the embodiment of the present invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, the above method is implemented. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories can be connected to the mobile terminal via a network. Examples of the above-mentioned network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof. The transmission device 106 is used to receive or send data via a network. The above-mentioned specific examples of the network may include a wireless network provided by a communication provider of the mobile terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.
[0032] According to an embodiment of the present invention, a method embodiment of a fault diagnosis method for an electric power system is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.
[0033] Figure 2 is a flow chart of a fault diagnosis method for a power system according to an embodiment of the present invention. Figure 2 As shown, the fault diagnosis method of the power system includes the following steps:
[0034] Step S202, obtaining fault-related data of the target power system, wherein the target power system is a power system to be diagnosed for fault, and the fault-related data includes at least: historical fault reports of the target power system, relay protection action record information of the target power system, and equipment status information of power equipment in the target power system.
[0035] In this embodiment, data related to the fault of the power system (ie, the target power system) may be collected, including but not limited to: fault reports, relay protection action records, equipment status information, etc.
[0036] Step S204, input the fault-related data into the fault identification model to process the fault-related data using the fault identification model, wherein the fault identification model is a model trained using multiple groups of sample data, each of the multiple groups of sample data includes: sample fault-related data and sample fault diagnosis results corresponding to the sample fault-related data, the sample fault-related data is the input of the fault identification model, and the sample fault diagnosis results are the output of the fault identification model.
[0037] In this embodiment, a pre-trained fault identification model may be used to process fault-related data to obtain identified fault information, such as fault type, fault location, fault time, etc.
[0038] Step S206, obtaining the output result of the fault identification model, wherein the output result at least includes: fault identification information and fault cause information.
[0039] In this embodiment, the output result of the fault identification model may be obtained, such as fault identification information, fault cause information, and the like.
[0040] Step S208: determining that the output result is fault information of the target power system.
[0041] As can be seen from the above, in an embodiment of the present invention, fault-related data of a target power system is obtained, wherein the target power system is a power system to be diagnosed for faults, and the fault-related data includes at least: historical fault reports of the target power system, relay protection action record information of the target power system, and equipment status information of power equipment in the target power system; the fault-related data is input into a fault identification model to process the fault-related data using the fault identification model, wherein the fault identification model is a model obtained by training using multiple groups of sample data, and each of the multiple groups of sample data includes: sample fault-related data and sample fault diagnosis results corresponding to the sample fault-related data, the sample fault-related data is the input of the fault identification model, and the sample fault diagnosis results is the output of the fault identification model; the output result of the fault identification model is obtained, wherein the output result includes at least: fault identification information and fault cause information; the output result is determined to be the fault information of the target power system, thereby achieving the purpose of diagnosing faults in the power system using a fault identification model trained by machine learning, so that the fault information of the power system can be obtained in a relatively intelligent manner, thereby improving the efficiency and reliability of fault diagnosis of the power system.
[0042] Therefore, the technical solution provided by the embodiment of the present invention solves the technical problem in the related art that fault diagnosis of the power system usually relies on manual analysis by experienced experts, which has low reliability.
[0043] According to the above-mentioned embodiment of the present invention, fault-related data is input into a fault identification model so as to process the fault-related data using the fault identification model, including: preprocessing the fault-related data to obtain preprocessed fault-related data, wherein the preprocessing includes at least the following operations: data cleaning operation, data standardization operation, data feature extraction operation; and inputting the preprocessed fault-related data into the fault identification model so as to process the preprocessed fault-related data using the fault identification model.
[0044] In this embodiment, in order to enable the data input into the fault identification model to be recognized and to ensure that the fault identification model can quickly process the data, the fault-related data can be preprocessed before being input into the fault identification model. For example, the collected data can be preprocessed, including cleaning, standardization, and feature extraction, so as to improve the data processing speed of the fault identification model.
[0045] According to the above-mentioned embodiment of the present invention, before inputting the fault-related data into the fault identification model to process the fault-related data using the fault identification model, the fault diagnosis method of the power system may also include: obtaining multiple sample fault-related data within a historical time period and multiple sample fault diagnosis results corresponding to the sample fault-related data; using multiple groups of sample data including multiple sample fault-related data and multiple sample fault diagnosis results to train a natural language processing model to obtain a fault identification model.
[0046] In this embodiment, a large amount of power system fault data set can be used to train and optimize the NLP model so that it can better understand and analyze information related to power system faults.
[0047] According to the above-mentioned embodiment of the present invention, fault-related data is input into a fault identification model so as to process the fault-related data using the fault identification model, including at least one of the following: after determining that the fault-related data is input into the fault identification model, the fault-related data is processed using the fault identification model to obtain fault identification information, wherein the fault identification information includes at least: fault type, fault location and fault time; after determining that the fault-related data is input into the fault identification model, the fault-related data is processed using the fault identification model to obtain fault cause information.
[0048] In this embodiment, the fault identification model can be used to process the fault-related data to obtain fault identification information, such as the fault type, fault location and fault time; the fault-related data can also be processed by the fault identification model to obtain the cause of the fault, that is, the NLP-based fault identification model can be used to analyze the fault characteristics, and combined with the operating laws and actual conditions of the power system, the possible causes of the fault can be inferred.
[0049] According to the above embodiment of the present invention, after determining that the output result is fault information of the target power system, the fault diagnosis method of the power system further includes at least: displaying the fault information; generating a new fault report based on the fault information; and saving the fault report.
[0050] In order to improve the intuitiveness of power system fault diagnosis, fault information can be displayed through a display device, so that the fault diagnosis results can be presented in an intuitive and easy-to-understand manner.
[0051] In addition, in order to facilitate traceability, fault information can also be generated and saved.
[0052] According to the above-mentioned embodiment of the present invention, after determining that the output result is the fault information of the target power system, the fault diagnosis method of the power system may further include: obtaining actual fault information of the target power system; comparing the actual fault information with the fault information to obtain a comparison result; and determining the accuracy of the fault information based on the similarity between the actual fault information and the fault information in the comparison result.
[0053] In this embodiment, actual fault information of the target power system can be obtained, and the actual fault information can be compared with the fault information to determine the difference or similarity between the two, so that the accuracy of the fault information can be determined based on the difference or similarity between the actual fault information and the fault information; in this way, the accuracy of the fault information identified by the fault identification model can be determined, which facilitates the subsequent optimization of the fault identification model so that the fault identification model is more in line with actual needs.
[0054] According to the above embodiment of the present invention, after determining that the output result is fault information of the target power system, the fault diagnosis method of the power system further includes: optimizing the fault identification model using the comparison result to obtain an optimized fault identification model.
[0055] In this embodiment, the fault identification model can be optimized using fault information to obtain an optimized fault identification model; that is, the fault diagnosis method is optimized and iterated according to actual needs and verification results to achieve more efficient and accurate power system fault diagnosis.
[0056] In addition, in the above embodiments of the present invention, the NLP-based fault diagnosis method can be deployed to the cloud through the online real-time fault diagnosis function to realize online real-time fault diagnosis services. And through the fault prediction and prevention function, by analyzing historical fault data and equipment operation status, the NLP technology can be used to predict the type and time of possible equipment failures; the automatic report generation function can also automatically organize the fault diagnosis results into a report format for operation and maintenance personnel to review and manage.
[0057] The following is an embodiment of a method for automatically identifying power system fault characteristics and causes based on natural language processing.
[0058] When a power system fails, relay protection action records, fault reports, and equipment status information are collected and preprocessed. Preprocessing includes data cleaning, data standardization, and feature extraction. Subsequently, the preprocessed data is analyzed using a pretrained NLP model.
[0059] Through NLP model analysis, fault characteristics are automatically identified, such as fault type (short circuit fault), fault location (a certain section of a certain line), fault time (occurred around 2 a.m.), etc. Then, the NLP model is used to further analyze the fault characteristics, and combined with the operation rules and actual conditions of the power system, possible fault causes are inferred, such as short circuit faults caused by insulation damage due to aging equipment.
[0060] Subsequently, the fault diagnosis results are presented in an intuitive and easy-to-understand manner, such as generating a report containing fault characteristics, cause analysis, and treatment suggestions. At the same time, the results are compared with the actual power system operation to verify the accuracy of the analysis results. According to actual needs and verification results, the fault diagnosis method is optimized and iterated to improve the accuracy and efficiency of diagnosis.
[0061] In addition, this method can be further expanded to include online real-time fault diagnosis, fault prediction and prevention, automatic report generation, combination with other AI technologies, cross-domain applications, deployment on mobile devices, integration with existing power system monitoring and dispatching systems, provision of intelligent operation and maintenance recommendations, and integration with power system simulation software.
[0062] The technical solution provided by the above-mentioned embodiment of the present invention has the following functions: 1) Online real-time fault diagnosis: deploy the NLP-based fault diagnosis method to the cloud to realize online real-time fault diagnosis service, so that users can perform fault diagnosis anytime and anywhere; 2) Fault prediction and prevention: by analyzing historical fault data and equipment operation status, use NLP technology to predict the type and time of possible equipment failures, take preventive measures in advance, and reduce the probability of failure; 3) Automatic report generation: automatically organize the fault diagnosis results into a report format, including fault characteristics, cause analysis, processing suggestions, etc., to facilitate operation and maintenance personnel to review and manage; and can be combined with other artificial intelligence technologies: combine the present invention with other AI technologies (such as machine learning, deep learning, graph neural networks, etc.) to improve the accuracy and real-time performance of fault diagnosis; can also be applied across fields: apply the NLP-based power system fault diagnosis method to other fields, such as power system planning, operation scheduling, equipment maintenance, etc., to achieve wider application; and mobile device deployment: based on The NLP-based power system fault diagnosis method is deployed on mobile devices, which is convenient for field engineers to perform fast and convenient fault diagnosis. In addition, it can also be integrated with the existing power system monitoring system: the NLP-based power system fault diagnosis method is integrated with the existing power system monitoring system to realize real-time monitoring and fault diagnosis of power system equipment; and it can be integrated with the power system dispatching system: the NLP-based power system fault diagnosis method is integrated with the power system dispatching system to realize real-time dynamic adjustment of equipment parameters during the operation of the power system, thereby improving the safety and stability of the system; it can also provide intelligent operation and maintenance suggestions: the NLP-based power system fault diagnosis method is used to provide power companies and operation and maintenance personnel with intelligent operation and maintenance and management suggestions to improve the reliability and efficiency of power system operation; in terms of integration, it can also be integrated with power system simulation software: the NLP-based power system fault diagnosis method is integrated with the power system simulation software to realize comparative analysis of fault diagnosis results and simulation results, thereby improving the accuracy of fault diagnosis.
[0063] In the technical solution provided by the above embodiment of the present invention, rapid, accurate and intelligent diagnosis of power system faults can be achieved, providing strong support for the safe and stable operation of the power system. In addition, auxiliary decision-making can be provided for related work such as operation and maintenance, planning and scheduling of the power system, which helps to improve the reliability and operation efficiency of the power system.
[0064] In the power system operation and maintenance scenario, the power system fault diagnosis method based on natural language processing can assist the operation and maintenance personnel to quickly and accurately identify fault characteristics and causes, reduce fault handling time, and improve operation and maintenance efficiency; in the power dispatching center scenario, the power dispatching center can use this method to monitor and diagnose faults in the system in real time, and take quick measures to ensure the stable operation of the power system; for power equipment manufacturers: power equipment manufacturers can integrate this method into their products to provide more intelligent fault diagnosis and operation and maintenance services, and improve the competitiveness of their products; for power engineering design and consulting companies: power engineering design and consulting companies can use this method to provide customers with more comprehensive and accurate fault diagnosis and prevention suggestions, and improve service quality; for power education and training: the power system fault diagnosis method based on natural language processing can be used as an auxiliary tool for power professional education and training, helping students and engineers to better understand and master the principles and methods of power system fault diagnosis; for cross-domain applications: the fault diagnosis method based on natural language processing can be extended to other fields, such as transportation, communications, industrial control, etc.
[0065] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.
[0066] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in each embodiment of the present application.
[0067] According to an embodiment of the present invention, there is also provided a fault diagnosis device for an electric power system for implementing the above-mentioned fault diagnosis method for an electric power system. Figure 3 is a schematic diagram of a fault diagnosis device for a power system according to an embodiment of the present invention. Figure 3 As shown, the device includes: a first acquisition unit 31, a processing unit 33, a second acquisition unit 35 and a determination unit 37. Among them,
[0068] The first acquisition unit 31 is used to acquire fault-related data of the target power system, wherein the target power system is a power system to be diagnosed for fault, and the fault-related data at least includes: historical fault reports of the target power system, relay protection action record information of the target power system, and equipment status information of power equipment in the target power system.
[0069] The processing unit 33 is used to input the fault-related data into the fault identification model so as to process the fault-related data using the fault identification model, wherein the fault identification model is a model trained using multiple groups of sample data, each of the multiple groups of sample data includes: sample fault-related data and sample fault diagnosis results corresponding to the sample fault-related data, the sample fault-related data is the input of the fault identification model, and the sample fault diagnosis results are the output of the fault identification model.
[0070] The second acquisition unit 35 is used to acquire the output result of the fault identification model, wherein the output result at least includes: fault identification information and fault cause information.
[0071] The determination unit 37 is used to determine that the output result is the fault information of the target power system.
[0072] It should be noted here that the above-mentioned first acquisition unit 31, processing unit 33, second acquisition unit 35 and determination unit 37 correspond to steps S202 to S208 in the above-mentioned embodiments, and the four units are the same as the instances and application scenarios implemented by the corresponding steps, but are not limited to the contents disclosed in the above-mentioned embodiments.
[0073] As can be seen from the above, in the scheme recorded in the above embodiment of the present invention, the first acquisition unit can be used to acquire the fault-related data of the target power system, wherein the target power system is the power system to be diagnosed for fault, and the fault-related data at least includes: historical fault reports of the target power system, relay protection action record information of the target power system, and equipment status information of the power equipment in the target power system; then the processing unit is used to input the fault-related data into the fault identification model, so as to process the fault-related data using the fault identification model, wherein the fault identification model is a model obtained by training using multiple groups of sample data, each of the multiple groups of sample data includes: sample fault-related data and sample fault diagnosis results corresponding to the sample fault-related data, the sample fault-related data is the input of the fault identification model, and the sample fault diagnosis result is the output of the fault identification model; and the second acquisition unit is used to acquire the output result of the fault identification model, wherein the output result at least includes: fault identification information and fault cause information; and the determination unit is used to determine that the output result is the fault information of the target power system, thereby achieving the purpose of diagnosing the fault of the power system through the fault identification model trained by machine learning, so that the fault information of the power system can be obtained in a relatively intelligent way, thereby improving the efficiency and reliability of the fault diagnosis of the power system.
[0074] Therefore, the technical solution provided by the embodiment of the present invention solves the technical problem in the related art that fault diagnosis of the power system usually relies on manual analysis by experienced experts, which has low reliability.
[0075] Optionally, the processing unit includes: a preprocessing module, used to preprocess the fault-related data to obtain preprocessed fault-related data, wherein the preprocessing includes at least the following operations: data cleaning operation, data standardization operation, data feature extraction operation; a first processing module, used to input the preprocessed fault-related data into a fault identification model to process the preprocessed fault-related data using the fault identification model.
[0076] Optionally, the fault diagnosis device of the power system also includes: a third acquisition unit, used to acquire multiple sample fault-related data within a historical time period and multiple sample fault diagnosis results corresponding to the sample fault-related data before inputting the fault-related data into the fault identification model to process the fault-related data using the fault identification model; a training unit, used to train the natural language processing model using multiple groups of sample data including multiple sample fault-related data and multiple sample fault diagnosis results to obtain a fault identification model.
[0077] Optionally, the processing unit includes at least one of the following: a second processing module, used to process the fault-related data using the fault identification model after determining that the fault-related data is input into the fault identification model, so as to obtain fault identification information, wherein the fault identification information at least includes: fault type, fault location and fault time; a third processing module, used to process the fault-related data using the fault identification model after determining that the fault-related data is input into the fault identification model, so as to obtain fault cause information.
[0078] Optionally, the fault diagnosis device of the power system further includes at least: a display unit, used to display the fault information after determining that the output result is the fault information of the target power system; a generation unit, used to generate a new fault report based on the fault information; and a storage unit, used to store the fault report.
[0079] Optionally, the fault diagnosis device of the power system also includes: a fourth acquisition unit, used to acquire actual fault information of the target power system after determining that the output result is the fault information of the target power system; a comparison unit, used to compare the actual fault information with the fault information to obtain a comparison result; and a determination unit, used to determine the accuracy of the fault information based on the similarity between the actual fault information and the fault information in the comparison result.
[0080] Optionally, the fault diagnosis device of the power system further includes: an optimization unit, which is used to optimize the fault identification model using the comparison result after determining that the output result is the fault information of the target power system, so as to obtain an optimized fault identification model.
[0081] According to the above embodiment of the present invention, a computer-readable storage medium is further provided. The computer-readable storage medium includes a stored program, wherein the program executes any one of the above-mentioned methods for diagnosing faults in a power system.
[0082] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium including a stored program, wherein the program executes any one of the above-mentioned energy-saving control methods for a water heater.
[0083] Optionally, in this embodiment, the computer-readable storage medium may be located in any one of the computer terminals in a computer terminal group in a computer network, or in any one of the communication devices in a communication device group.
[0084] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for executing the following steps: obtaining fault-related data of a target power system, wherein the target power system is a power system to be diagnosed for fault, and the fault-related data includes at least: historical fault reports of the target power system, relay protection action record information of the target power system, and equipment status information of power equipment in the target power system; inputting the fault-related data into a fault identification model to process the fault-related data using the fault identification model, wherein the fault identification model is a model trained using multiple groups of sample data, each of the multiple groups of sample data includes: sample fault-related data and sample fault diagnosis results corresponding to the sample fault-related data, the sample fault-related data is the input of the fault identification model, and the sample fault diagnosis result is the output of the fault identification model; obtaining the output result of the fault identification model, wherein the output result includes at least: fault identification information and fault cause information; and determining that the output result is the fault information of the target power system.
[0085] Optionally, the fault-related data is input into a fault identification model to process the fault-related data using the fault identification model, including: Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for performing the following steps: preprocessing the fault-related data to obtain preprocessed fault-related data, wherein the preprocessing includes at least the following operations: data cleaning operation, data standardization operation, data feature extraction operation; inputting the preprocessed fault-related data into a fault identification model to process the preprocessed fault-related data using the fault identification model.
[0086] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for performing the following steps: obtaining multiple sample fault-related data within a historical time period and multiple sample fault diagnosis results corresponding to the sample fault-related data; training a natural language processing model using multiple groups of sample data including multiple sample fault-related data and multiple sample fault diagnosis results to obtain a fault identification model.
[0087] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for executing the following steps: after determining that fault-related data is input into a fault identification model, using the fault identification model to process the fault-related data to obtain fault identification information, wherein the fault identification information includes at least: fault type, fault location, and fault time; after determining that fault-related data is input into a fault identification model, using the fault identification model to process the fault-related data to obtain fault cause information.
[0088] Optionally, in this embodiment, the computer-readable storage medium is configured to store program codes for executing the following steps: displaying fault information; generating a new fault report based on the fault information; and saving the fault report.
[0089] Optionally, after determining that the output result is the fault information of the target power system, the fault diagnosis method of the power system also includes: Optionally, in this embodiment, the computer-readable storage medium is configured to store program codes for executing the following steps: obtaining actual fault information of the target power system; comparing the actual fault information with the fault information to obtain a comparison result; determining the accuracy of the fault information based on the similarity between the actual fault information and the fault information in the comparison result.
[0090] Optionally, after determining that the output result is the fault information of the target power system, the fault diagnosis method of the power system also includes: Optionally, in this embodiment, the computer-readable storage medium is configured to store program codes for executing the following steps: optimizing the fault identification model using the comparison results to obtain an optimized fault identification model.
[0091] According to the above embodiment of the present invention, a processor is further provided, and the processor is used to run a program, wherein when the program is run, any one of the above-mentioned methods for diagnosing faults in a power system is executed.
[0092] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.
[0093] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.
[0094] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.
[0095] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.
[0096] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.
[0097] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.
[0098] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.
Claims
1. A fault diagnosis method for a power system, characterized in that: include: Acquire fault-related data of a target power system, wherein the target power system is a power system to be diagnosed for a fault, and the fault-related data includes at least: a historical fault report of the target power system, relay protection action record information of the target power system, and equipment status information of power equipment in the target power system; Inputting the fault-related data into a fault identification model to process the fault-related data using the fault identification model, wherein the fault identification model is a model trained using multiple groups of sample data, each of the multiple groups of sample data includes: sample fault-related data and sample fault diagnosis results corresponding to the sample fault-related data, the sample fault-related data is the input of the fault identification model, and the sample fault diagnosis results are the output of the fault identification model; Obtaining an output result of the fault identification model, wherein the output result at least includes: fault identification information and fault cause information; The output result is determined to be fault information of the target power system.
2. The fault diagnosis method of the power system according to claim 1, characterized in that: Inputting the fault-related data into a fault identification model to process the fault-related data using the fault identification model includes: Preprocessing the fault-related data to obtain the preprocessed fault-related data, wherein the preprocessing at least includes the following operations: data cleaning operation, data standardization operation, and data feature extraction operation; The preprocessed fault-related data is input into the fault identification model, so as to process the preprocessed fault-related data using the fault identification model.
3. The fault diagnosis method for the power system according to claim 1, characterized in that: Before inputting the fault-related data into the fault identification model to process the fault-related data using the fault identification model, the method further includes: Acquire a plurality of the sample fault related data within a historical time period and a plurality of the sample fault diagnosis results corresponding to the sample fault related data; The fault identification model is obtained by training a natural language processing model using multiple groups of sample data including multiple sample fault-related data and multiple sample fault diagnosis results.
4. The fault diagnosis method for the power system according to claim 1, characterized in that: Inputting the fault-related data into a fault identification model to process the fault-related data using the fault identification model includes at least one of the following: After determining that the fault-related data is input into the fault identification model, the fault-related data is processed using the fault identification model to obtain the fault identification information, wherein the fault identification information at least includes: fault type, fault location and fault time; After it is determined that the fault-related data is input into the fault identification model, the fault-related data is processed using the fault identification model to obtain the fault cause information.
5. The fault diagnosis method for an electric power system according to any one of claims 1 to 4, characterized in that: After determining that the output result is the fault information of the target power system, the method further includes: Displaying the fault information; generating a new fault report based on the fault information; The fault report is saved.
6. The fault diagnosis method for an electric power system according to any one of claims 1 to 4, characterized in that: After determining that the output result is the fault information of the target power system, the method further includes: Acquiring actual fault information of the target power system; Comparing the actual fault information with the fault information to obtain a comparison result; The accuracy of the fault information is determined according to the similarity between the actual fault information and the fault information in the comparison result.
7. The fault diagnosis method for the electric power system according to claim 6, characterized in that: After determining that the output result is the fault information of the target power system, the method further includes: The fault identification model is optimized using the comparison result to obtain the optimized fault identification model.
8. A fault diagnosis device for an electric power system, characterized in that: include: A first acquisition unit is used to acquire fault-related data of a target power system, wherein the target power system is a power system to be diagnosed for a fault, and the fault-related data at least includes: a historical fault report of the target power system, relay protection action record information of the target power system, and equipment status information of power equipment in the target power system; a processing unit, configured to input the fault-related data into a fault identification model, so as to process the fault-related data using the fault identification model, wherein the fault identification model is a model obtained by training using multiple groups of sample data, each of the multiple groups of sample data comprising: sample fault-related data and sample fault diagnosis results corresponding to the sample fault-related data, the sample fault-related data being the input of the fault identification model, and the sample fault diagnosis results being the output of the fault identification model; A second acquisition unit is used to acquire an output result of the fault identification model, wherein the output result at least includes: fault identification information and fault cause information; A determination unit is used to determine that the output result is fault information of the target power system.
9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored program, wherein the program executes the fault diagnosis method for the power system according to any one of claims 1 to 7.
10. A processor, characterized in that: The processor is used to run a program, wherein the program, when running, executes the fault diagnosis method for the power system according to any one of claims 1 to 7.
Citation Information
Patent Citations
Power equipment state analysis method and device based on three-layer architecture mode
CN114066163A
Power grid fault diagnosis method, device and equipment based on multi-class information fusion identification
CN115545355A
