Power grid operation and maintenance monitoring method and device and digital power grid operation and maintenance monitoring system

Abstract

The invention provides a power grid operation and maintenance monitoring method and device and a digital power grid operation and maintenance monitoring system. The method comprises the steps of obtaining related information of a power grid; a first model is constructed, the first model is obtained by training through a target algorithm by using multiple groups of training data, each group of training data in the multiple groups of training data comprises historical related information acquired in a historical time period and a historical detection result corresponding to the historical related information, and the historical detection result corresponds to the historical related information; the historical detection result is used for representing whether a fault occurs in the power grid in a historical time period, and the target algorithm comprises one or more of RNN, LSTM, CNN and DNN; and inputting the related information into the first model to obtain a detection result corresponding to the related information. According to the scheme, the problem that in the prior art, the accuracy of power grid fault detection is low is solved.

Description

Technical Field

[0001] The present application relates to the technical field of power grid operation and maintenance, and in particular to a power grid operation and maintenance monitoring method, a power grid operation and maintenance monitoring device, a computer program product, and a digital power grid operation and maintenance monitoring system. Background Art

[0002] With the development of society, the demand for electricity is also increasing, so ensuring the stable operation of the power grid has become the key to power grid monitoring. In the prior art, the equipment status and power parameters of the power equipment in the power grid are generally detected, and the data obtained by the detection are analyzed using a general power grid fault detection model to analyze the fault situation of the power grid, thereby realizing the operation and maintenance monitoring of the power grid. However, the fault situation of the power grid is analyzed only by these two parameters, and the data is relatively single, which makes the accuracy of fault detection of the power grid low. Summary of the invention

[0003] The main purpose of the present application is to provide a power grid operation and maintenance monitoring method, a power grid operation and maintenance monitoring device, a computer program product and a digital power grid operation and maintenance monitoring system, so as to at least solve the problem of low accuracy of fault detection in the power grid in the prior art.

[0004] In order to achieve the above-mentioned purpose, according to one aspect of the present application, a method for operation and maintenance monitoring of a power grid is provided, comprising: obtaining relevant information of the power grid, wherein the relevant information includes one or more of power detection information, device status information, device type information, connection attribute information and topology type information, wherein the power detection information is information about the voltage, current and power of the power equipment of the power grid, the device status information is information about the temperature, load and vibration of the power equipment of the power grid, the device type information is information about the type of the power equipment of the power grid, the connection attribute information is information about whether the power equipment of the power grid is connected and the connection relationship, and the connection relationship includes series connection, One or more of parallel connection and series-parallel connection, the topology structure type information is the information of the topological connection relationship between the multiple power devices in the power grid; constructing a first model, wherein the first model is obtained by training with a target algorithm using multiple sets of training data, each set of training data in the multiple sets of training data includes historical related information obtained in a historical time period, and historical detection results corresponding to the historical related information, wherein the historical detection results are used to characterize whether the power grid in the historical time period has a fault, wherein the target algorithm includes one or more of RNN, LSTM, CNN and DNN; inputting the relevant information into the first model to obtain the detection results corresponding to the relevant information.

[0005] In order to achieve the above-mentioned purpose, according to one aspect of the present application, there is provided a method for obtaining relevant information of a power grid, including: generating a topological connection diagram according to the equipment type information and the connection attribute information of the power equipment; searching a target database for a topological connection template diagram with the highest similarity to the topological connection diagram according to the topological connection diagram, and obtaining a target topological connection template diagram, wherein the target database includes a plurality of the topological connection template diagrams, and the topological connection template diagrams correspond to the topological structure types one by one; determining the topological structure type information of the power grid according to the target topological connection template diagram.

[0006] Optionally, after acquiring relevant information of the power grid, the method further includes: encrypting the relevant information to obtain encrypted data; and sending the encrypted data to a server so that the server decrypts the encrypted data.

[0007] Optionally, the relevant information is encrypted to obtain encrypted data, including: obtaining operation and maintenance information, wherein the operation and maintenance information includes request time information, personnel identification information and equipment identification information, the request time information is information about the time for requesting operation and maintenance monitoring of the power grid, the personnel identification information is information about the identity of the operation and maintenance personnel, and the equipment identification information is information about the unique identification of the power equipment; encoding the operation and maintenance information according to a Base64 encoding table to obtain encoded information; performing hash calculation on the relevant information according to the encoded information to obtain the encrypted data.

[0008] Optionally, after obtaining relevant information of the power grid, the method further includes: obtaining feature information, wherein the feature information includes one or more of first feature information, second feature information, third feature information, fourth feature information and fifth feature information, the first feature information is a feature corresponding to the power detection information, the second feature information is a feature corresponding to the device status information, the third feature information is a feature corresponding to the device type information, the fourth feature information is a feature corresponding to the connection attribute information, and the fifth feature information is a feature corresponding to the topology type information; performing feature fusion on the feature information to obtain fused feature information, wherein the fusion method includes attention mechanism fusion and / or weighted fusion; constructing a second model, wherein the second model is trained using multiple sets of training data, each set of the multiple sets of training data includes historical fused feature information obtained within a historical time period and historical detection results corresponding to the historical fused feature information; inputting the fused feature information into the second model to obtain the detection results corresponding to the fused feature information.

[0009] Optionally, obtaining feature information includes: constructing a first feature extraction model, wherein the first feature extraction model is obtained by training with a first algorithm using multiple sets of training data, each set of training data in the multiple sets of training data includes historical power detection information obtained within a historical time period, and historical first feature information corresponding to the historical power detection information, wherein the first algorithm includes RNN and / or LSTM; inputting the power detection information into the first feature extraction model to obtain the first feature information corresponding to the power detection information; constructing a second feature extraction model, wherein the second feature extraction model is obtained by training with the first algorithm using multiple sets of training data, each set of training data in the multiple sets of training data includes historical device status information obtained within a historical time period, and historical second feature information corresponding to the historical device status information; inputting the device status information into the second feature extraction model to obtain the second feature information corresponding to the device status information.

[0010] Optionally, obtaining feature information includes: constructing a third feature extraction model, wherein the third feature extraction model is obtained by training with a second algorithm using multiple sets of training data, each set of training data in the multiple sets of training data includes historical device type information obtained in a historical time period, and historical third feature information corresponding to the historical device type information, wherein the second algorithm includes CNN and / or DNN; inputting the device type information into the third feature extraction model to obtain the third feature information corresponding to the device type information; constructing a fourth feature extraction model, wherein the fourth feature extraction model is obtained by training with the second algorithm using multiple sets of training data, each set of training data in the multiple sets of training data The data include historical connection attribute information obtained within a historical time period, and historical fourth feature information corresponding to the historical connection attribute information; the connection attribute information is input into the fourth feature extraction model to obtain the fourth feature information corresponding to the connection attribute information; a fifth feature extraction model is constructed, wherein the fifth feature extraction model is obtained by training the second algorithm using multiple sets of training data, and each set of training data in the multiple sets of training data include historical topological structure type information obtained within a historical time period, and historical fifth feature information corresponding to the historical topological structure type information; the topological structure type information is input into the fifth feature extraction model to obtain the fifth feature information corresponding to the topological structure type information.

[0011] According to another aspect of the present application, there is provided an operation and maintenance monitoring device for a power grid, comprising: a first acquisition unit, for acquiring relevant information of the power grid, wherein the relevant information includes one or more of power detection information, device status information, device type information, connection attribute information and topology type information, wherein the power detection information is information on voltage, current and power of the power equipment of the power grid, the device status information is information on temperature, load and vibration of the power equipment of the power grid, the device type information is information on the type of the power equipment of the power grid, the connection attribute information is information on whether the power equipment of the power grid is connected and the connection relationship, and the connection relationship includes one of series connection, parallel connection and series-parallel connection. type or more, the topology structure type information is the information of the topological connection relationship between the multiple power devices in the power grid; a first construction unit, used to construct a first model, wherein the first model is obtained by training with a target algorithm using multiple sets of training data, each set of training data in the multiple sets of training data includes historical related information obtained in a historical time period, and historical detection results corresponding to the historical related information, wherein the historical detection results are used to characterize whether the power grid in the historical time period has a fault, wherein the target algorithm includes one or more of RNN, LSTM, CNN and DNN; a first processing unit, used to input the relevant information into the first model to obtain the detection results corresponding to the relevant information.

[0012] According to another aspect of the present application, a computer program product is provided, comprising a computer program, wherein when the computer program is executed by a processor, the steps of any one of the power grid operation and maintenance monitoring methods are implemented.

[0013] According to another aspect of the present application, a digital power grid operation and maintenance monitoring system is provided, comprising one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors, and the one or more programs include a method for executing any one of the power grid operation and maintenance monitoring methods.

[0014] By applying the technical solution of the present application, multiple parameters can be used to determine whether the power grid is faulty. Compared with the prior art which only detects the equipment status and power parameters in the power equipment of the power grid, this solution uses more parameters for analysis, especially adds the topology type for analysis. The topology type of the power grid represents the physical connection relationship and electrical characteristics between each power equipment or power element in the power grid, which can be used as an important information for power grid fault detection. The first model is then used to realize automatic analysis of the fault. The accuracy of fault detection can be improved through multi-parameter learning analysis. This solution can effectively improve the accuracy of fault detection in the power grid and ensure the normal operation of the power grid. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The drawings constituting part of the present application are used to provide a further understanding of the present application. The exemplary embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0016] Figure 1 A hardware structure block diagram of a mobile terminal for executing an operation and maintenance monitoring method of a power grid provided in an embodiment of the present application is shown;

[0017] Figure 2 A schematic diagram of a flow chart of a method for operation and maintenance monitoring of a power grid provided according to an embodiment of the present application is shown;

[0018] Figure 3 A flow chart of a digital power grid operation and maintenance monitoring method according to an embodiment of the present application is shown;

[0019] Figure 4 A structural block diagram of an operation and maintenance monitoring device for a power grid provided according to an embodiment of the present application is shown;

[0020] Figure 5 A schematic diagram of the structure of a computer system suitable for implementing an electronic device of an embodiment of the present application is shown.

[0021] The above drawings include the following reference numerals:

[0022] 102. Processor; 104. Memory; 106. Transmission device; 108. Input and output device; 500. Computer system; 501. Central processing unit; 502. Read-only memory; 503. Random access memory; 504. Bus; 505. Input / output interface; 506. Input part; 507. Output part; 508. Storage part; 509. Communication part; 510. Drive; 511. Removable media. DETAILED DESCRIPTION

[0023] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0024] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0025] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present application described here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0026] As introduced in the background technology, there is a problem of low accuracy in fault detection of power grids in the prior art. To solve the above problem, the embodiments of the present application provide a power grid operation and maintenance monitoring method, a power grid operation and maintenance monitoring device, a computer program product and a digital power grid operation and maintenance monitoring system.

[0027] 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.

[0028] The method embodiments provided in the embodiments of the present application 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 monitoring operation and maintenance of a power grid 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 1The 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 are shown.

[0029] 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 display method of device information 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.

[0030] In this embodiment, a power grid operation and maintenance monitoring method, a power grid operation and maintenance monitoring device, a computer program product and a digital power grid operation and maintenance monitoring system that run on a mobile terminal, a computer terminal or a similar computing device are 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.

[0031] Figure 2 FIG. 1 is a flow chart of a method for monitoring and controlling an operation and maintenance of a power grid according to an embodiment of the present application. Figure 2 As shown, the method comprises the following steps:

[0032] Step S201, obtaining relevant information of the power grid, wherein the relevant information includes one or more of power detection information, device status information, device type information, connection attribute information and topology type information, wherein the power detection information is information on voltage, current and power of the power equipment of the power grid, the device status information is information on temperature, load and vibration of the power equipment of the power grid, the device type information is information on the type of the power equipment of the power grid, the connection attribute information is information on whether the power equipment of the power grid is connected and the connection relationship, the connection relationship includes one or more of series connection, parallel connection and series-parallel connection, and the topology type information is information on the topological connection relationship between the multiple power equipment of the power grid;

[0033] Specifically, the monitoring request of the operation and maintenance management server is used as a request to trigger the operation and maintenance management client to perform power grid operation and maintenance monitoring operations. The monitoring request may include request time information, personnel identification information of the operation and maintenance personnel, and device identification information of the operation and maintenance management server. The operation and maintenance management client communicates with various power equipment in the power grid to be monitored, as well as sensors or detection devices used to detect information on power equipment in the power grid, to obtain various power grid detection information in the power grid. The above-mentioned power grid detection information may include power detection information in the power grid, equipment status information of each power equipment in the power grid, equipment type information of each power equipment in the power grid, and connection attribute information between each power equipment in the power grid.

[0034] Specifically, the power detection information is the parameter information of the power equipment or various nodes in the power grid, such as voltage, current, power, etc.; the equipment status information of the power equipment includes the parameter information reflecting the equipment status, such as the temperature, load, vibration, etc. of the power equipment; the equipment type information of the power equipment can be the equipment type information corresponding to different power equipment, such as generators, transformers, switchgear, power protection devices, etc. The connection attribute information between power equipment is a kind of information reflecting the important association relationship between power equipment, which can include whether the power equipment is connected and the specific connection relationship, such as series or parallel connection.

[0035] Step S202, constructing a first model, wherein the first model is obtained by training a target algorithm using multiple sets of training data, each set of training data in the multiple sets of training data includes historical related information obtained in a historical time period, and historical detection results corresponding to the historical related information, wherein the historical detection results are used to characterize whether the power grid in the historical time period has a fault, wherein the target algorithm includes one or more of RNN, LSTM, CNN and DNN;

[0036] Specifically, machine learning can be performed through a target algorithm to use a large amount of data training to obtain a first model, and whether a power grid failure occurs can be determined through the first model.

[0037] Step S203: input the above-mentioned relevant information into the above-mentioned first model to obtain the detection results corresponding to the above-mentioned relevant information.

[0038] Specifically, through the first model, it can be determined whether the current power grid fails, and the relevant information of the current power grid is input into the first model to obtain the output of the first model, that is, the detection result.

[0039] Through this embodiment, multiple parameters can be used to determine whether the power grid is faulty. Compared with the prior art that only detects the equipment status and power parameters in the power equipment of the power grid, this solution also uses more parameters for analysis, especially adding the topology type for analysis. The topology type of the power grid represents the physical connection relationship and electrical characteristics between each power equipment or power element in the power grid, which can be used as an important information for power grid fault detection. The first model is then used to realize automatic analysis of the fault. The accuracy of fault detection can be improved through multi-parameter learning analysis. This solution can effectively improve the accuracy of fault detection in the power grid and ensure the normal operation of the power grid.

[0040] Specifically, the digital power grid operation and maintenance monitoring method of this solution includes responding to the monitoring request of the operation and maintenance management service end, obtaining the power detection information in the power grid to be monitored, the equipment status information of each power device in the power grid, the equipment type information of each power device in the power grid, and the connection attribute information between each power device in the power grid; based on the equipment type information and connection attribute information of the power device, determining the topological structure type of the power grid; using the power detection information, equipment status information, equipment type information, connection attribute information and topological structure type as fault analysis data, matching the target power grid fault detection model in the power grid fault detection model library. The technical solution of this solution can effectively improve the accuracy of fault detection in the power grid.

[0041] Specifically, in response to a monitoring request from an operation and maintenance management service end, power detection information in a power grid to be monitored, equipment status information of each power device in the power grid, equipment type information of each power device in the power grid, and connection attribute information between each power device in the power grid are obtained; based on the equipment type information of the power devices and the connection attribute information, a topology structure type of the power grid is determined; the power detection information, the equipment status information, the equipment type information, the connection attribute information, and the topology structure type are used as fault analysis data, and a target power grid fault detection model is matched in a power grid fault detection model library; power grid fault analysis is performed on the fault analysis data based on the target power grid fault detection model to obtain a fault detection result; based on the fault detection result, an operation and maintenance monitoring result of the power grid is generated.

[0042] Specifically, in the technical solutions provided in some embodiments of the present scheme, the topological structure type of the power grid is determined based on the equipment type information and connection attribute information of the power equipment; the power detection information, equipment status information, equipment type information, connection attribute information and topological structure type are used as fault analysis data, and the target power grid fault detection model is matched in the power grid fault detection model library; since the target power grid fault detection model is a power grid fault detection model suitable for the specific fault analysis data including the topological structure type, the data obtained by the detection is analyzed compared with the general power grid fault detection model, and the power grid fault is detected by using the power grid fault detection model dedicated to the fault analysis data, which can effectively improve the accuracy of power grid fault detection, so as to take operation and maintenance measures in time to maintain the power grid fault and ensure the normal operation of the power grid.

[0043] Specifically, in this embodiment, the system architecture applying the technical solution of the present application may include an operation and maintenance management client and an operation and maintenance management server. The operation and maintenance management client may include various electronic devices such as smart phones, tablet computers, laptops, desktop computers, etc. with built-in digital power grid operation and maintenance monitoring methods. The operation and maintenance management server is a server, which may be an independent physical server or a server cluster or distributed system composed of multiple physical servers. Between the operation and maintenance management client and the operation and maintenance management server, there may be communication media of various connection types for providing communication links, such as wired communication links or wireless communication links. The operation and maintenance management client is connected to the operation and maintenance management server for communication. The operation and maintenance management client responds to the monitoring request of the operation and maintenance management server, obtains the monitoring request, obtains the power detection information in the power grid to be monitored, the equipment status information of each power device in the power grid, the equipment type information of each power device in the power grid, and the connection attribute information between each power device in the power grid; determines the topological structure type of the power grid based on the equipment type information and connection attribute information of the power equipment; uses the power detection information, equipment status information, equipment type information, connection attribute information and topological structure type as fault analysis data, and matches the target power grid fault detection model in the power grid fault detection model library; performs power grid fault analysis on the fault analysis data based on the target power grid fault detection model to obtain the fault detection result; generates the operation and maintenance monitoring result of the power grid based on the fault detection result.

[0044] Specifically, in order to reduce the delay of power grid fault detection, the optimal location of the operation and maintenance management server can be determined based on the density distribution of power equipment, the importance of power equipment and the coverage of communication signals.

[0045] Specifically, the distance weighted average method or the nearest neighbor algorithm can be used to determine the optimal site selection location. The optimal site selection location of the operation and maintenance management server can be determined by the above method, so that the overall time of power detection information and equipment status information of each power equipment in the power grid in data transmission is minimized, thereby effectively reducing the delay of power grid fault detection, improving the efficiency of fault detection and processing, and ensuring the safe and stable operation of the power grid.

[0046] Specifically, the power grid fault detection model library contains multiple target power grid fault detection models, wherein each different power grid fault detection model is suitable for detecting power grid detection data under different power grid conditions. Specifically, different power grid conditions refer to the types of power detection information in the power grid, the types of equipment status information of each power device, the equipment type information of each power device, and the types of topological structures. Each power grid fault detection model is obtained by using the power grid detection data under the power grid condition as training sample data to train the power grid fault detection model separately, so the power grid fault detection model has a high accuracy in fault detection of the power grid under the power grid condition. It can be understood that the fault analysis data reflects the power grid condition data of the power grid, and the power grid fault detection model library pre-establishes the mapping relationship between different power grid condition data and the power grid fault detection model corresponding to the power grid condition, and then can quickly match the corresponding target power grid fault detection model in the power grid fault detection model library according to different fault analysis data.

[0047] The existing method does not consider the topological structure information of the power grid, which makes the accuracy of fault detection of the power grid low. This solution has made improvements on this. In the specific implementation process, the relevant information of the power grid can be obtained through the following steps: generating a topological connection diagram based on the above-mentioned equipment type information and the above-mentioned connection attribute information of the above-mentioned power equipment; searching for the topological connection template diagram with the highest similarity to the above-mentioned topological connection diagram in the target database according to the above-mentioned topological connection diagram, and obtaining the target topological connection template diagram, wherein the above-mentioned target database includes multiple above-mentioned topological connection template diagrams, and the above-mentioned topological connection template diagrams correspond to the topological structure types one by one; determining the above-mentioned topological structure type information of the above-mentioned power grid according to the above-mentioned target topological connection template diagram.

[0048] In this scheme, the topology connection template map database includes multiple topology connection template maps, which are generated based on power grids of multiple different topology types. By comparing the similarity between the generated topology connection map and each topology connection template map in the topology connection template map database, the topology connection template map with the highest similarity is found, thereby achieving accurate determination of the topology structure type of the power grid.

[0049] Specifically, based on the equipment type information of each power device in the above-mentioned power grid and the connection attribute information between each power device in the above-mentioned power grid, a topological connection diagram is generated; based on the above-mentioned topological connection diagram, the topological connection template diagram with the highest similarity is matched in the topological connection template diagram database; based on the above-mentioned topological connection template diagram, the topological structure type of the above-mentioned power grid is determined.

[0050] Specifically, in order to more accurately analyze the fault conditions of the power grid, it is necessary to determine the topological structure type of the power grid based on the equipment type information and connection attribute information of the power equipment. The topological structure type of the power grid represents the physical connection relationship and electrical characteristics between each power equipment or power element in the power grid, which can be used as an important information for power grid fault detection.

[0051] Specifically, a topological connection diagram reflecting the connection mode, connection strength, connection density and other information between the various power devices in the power grid can be generated based on the device type information and connection attribute information of the power equipment. The topological connection template diagram database includes multiple topological connection template diagrams, and the multiple topological connection template diagrams are generated based on power grids of multiple different topological types. By comparing the similarity of the generated topological connection diagram with each topological connection template diagram in the topological connection template diagram database, the topological connection template diagram with the highest similarity is found, thereby determining the topological structure type of the power grid. For example, the topological structure type may include star structure, ring structure, mesh structure, linear structure and other types. Of course, it can also include a combination of the above multiple topological structure types or be divided into other more fine-grained topological structure types, which are not specifically limited here.

[0052] Since power detection information, device status information, device type information, connection attribute information, and topology type are relatively important data information, in order to improve data security, the above data can be encrypted. In some embodiments, after obtaining relevant information of the power grid, the above method also includes the following steps: encrypting the above relevant information to obtain encrypted data; sending the above encrypted data to the server, so that the above server decrypts the above encrypted data.

[0053] In this solution, by encrypting and decrypting relevant information, the security of data can be guaranteed to be better.

[0054] Specifically, the above-mentioned monitoring request includes request time information, personnel identification information of the operation and maintenance personnel, and device identification information of the above-mentioned operation and maintenance management server. The above-mentioned power detection information, the above-mentioned equipment status information, the above-mentioned equipment type information, the above-mentioned connection attribute information, and the above-mentioned topology structure type are used as fault analysis data, and the target power grid fault detection model is matched in the power grid fault detection model library, including: obtaining the above-mentioned personnel identification information, the above-mentioned equipment identification information, and the above-mentioned request time information; determining the target encryption algorithm based on the above-mentioned personnel identification information, the above-mentioned equipment identification information, and the above-mentioned request time information; encrypting the above-mentioned fault analysis data based on the above-mentioned target encryption algorithm to generate encrypted data; sending the above-mentioned encrypted data to the above-mentioned operation and maintenance management server, so that the above-mentioned operation and maintenance management server matches the target power grid fault detection model in the power grid fault detection model library based on the above-mentioned encrypted data; and receiving the above-mentioned target power grid fault detection model from the above-mentioned operation and maintenance management server.

[0055] During the specific implementation process, the above-mentioned relevant information is encrypted to obtain encrypted data, which can be achieved through the following steps: obtaining operation and maintenance information, wherein the above-mentioned operation and maintenance information includes request time information, personnel identification information and equipment identification information, the above-mentioned request time information is the information of the time for requesting operation and maintenance monitoring of the above-mentioned power grid, the above-mentioned personnel identification information is the identity information of the operation and maintenance personnel, and the above-mentioned equipment identification information is the unique identification information of the above-mentioned power equipment; encoding the above-mentioned operation and maintenance information according to the Base64 encoding table to obtain the encoded information; performing hash calculation on the above-mentioned relevant information according to the above-mentioned encoded information to obtain the above-mentioned encrypted data.

[0056] In this solution, encryption processing can be performed more efficiently through the Base64 encoding table, ensuring better encryption specificity and better encryption security.

[0057] Specifically, the request time information is encoded through a standard Base64 encoding table to obtain encoded characters; the total number of characters corresponding to the first category of characters contained in the encoded characters and the total number of characters corresponding to the second category of characters contained therein are determined; the corresponding first encoding table is determined in a first encoding table database based on the total number of characters corresponding to the first category of characters, and the corresponding second encoding table is determined in a second encoding table database based on the total number of characters corresponding to the second category of characters, wherein the first encoding table database stores the correspondence between the total number of characters corresponding to the first category of characters and the first encoding table, and the second encoding table database stores the correspondence between the total number of characters corresponding to the second category of characters and the second encoding table; the personnel identification information is encoded based on the first encoding table to obtain the first encoding information, and the device identification information is encoded based on the second encoding table to obtain the second encoding information; based on the first encoding information and the second encoding information, a target encryption algorithm is determined.

[0058] Specifically, a hash calculation is performed based on the first coding information and the second coding information to obtain a target hash value; the number of characters of different attribute characters is determined from all characters included in the target hash value; the attribute character with the largest number of characters is determined as the target attribute character; for the encryption algorithm package corresponding to each encryption algorithm, the number of target attribute characters is determined from the character string stored at a specific position of the encryption algorithm package; the encryption algorithm corresponding to the encryption algorithm package with the largest number of target attribute characters is selected as the target encryption algorithm.

[0059] Specifically, the personnel identification information can be the name or work number of the operation and maintenance personnel, and the device identification information of the operation and maintenance management server can be the device number or device serial number, which is not limited here. The target encryption algorithm in this solution is the encryption method agreed upon by the operation and maintenance management server and the operation and maintenance management client.

[0060] Specifically, a specific target encryption algorithm is determined based on the public information between the operation and maintenance management client and the operation and maintenance management server, such as the request time information, the personnel identification information of the operation and maintenance personnel, and the device identification information of the operation and maintenance management server; and the fault analysis data is encrypted based on the specific target encryption algorithm to generate encrypted data; the encrypted data is sent to the operation and maintenance management server, and the operation and maintenance management server only needs to generate a decryption password corresponding to or the same as the encryption password based on the above algorithm rules corresponding to the operation and maintenance management client, so as to decrypt the encrypted data according to the decryption password to correctly obtain the fault analysis data, so that the operation and maintenance management server can match the target power grid fault detection model in the power grid fault detection model library based on the encrypted data; the operation and maintenance management client receives the target power grid fault detection model from the operation and maintenance management server, and since the power detection information, equipment status information, equipment type information, connection attribute information, and topology structure type are transmitted in ciphertext, the leakage of these important data can be effectively avoided, thereby improving data security.

[0061] Specifically, in order to improve the specificity and randomness of the determined target encryption algorithm, the standard Base64 encoding table includes 64 sequence numbers and 64 encoding characters, and the encoding characters include numbers and uppercase and lowercase English letters. The first type of characters and the second type of characters can be any two of numeric characters, lowercase English letters and uppercase English letters, respectively, without limitation. It can be understood that the first encoding table in the first encoding table database and the second encoding table in the second encoding table database are both encoding data tables agreed upon between the operation and maintenance management client and the operation and maintenance management server.

[0062] Specifically, after obtaining the first coding information and the second coding information, an encryption algorithm can be selected from multiple different encryption algorithms based on the first coding information and the second coding information to encrypt the fault analysis data and generate encrypted data to effectively improve the specificity and randomness of the determined target encryption algorithm.

[0063] Specifically, different attribute characters refer to different attribute characters such as numeric characters, lowercase English letters and uppercase English letters;

[0064] Specifically, each encryption algorithm may be an existing encryption algorithm, or may be a specific encryption algorithm agreed upon by the operation and maintenance management client and the operation and maintenance management server, which is different from the existing general encryption algorithm and is not limited here.

[0065] Specifically, in the technical solution of the embodiment of the present application, since the power detection information, device status information, device type information, connection attribute information and topology structure type are transmitted in ciphertext, the leakage of these important data can be effectively avoided, thereby improving data security; at the same time, in the process of determining the target encryption algorithm based on the personnel identification information, device identification information and request time information, the request time information is first encoded to obtain specific coding characters, and the personnel identification information and device identification information are secondary encoded, hashed and analyzed according to the specific coding characters, and the corresponding target encryption algorithm is selected from multiple encryption algorithms based on the results of the secondary encoding, hashing and character analysis. Through the multi-layer nested complex logic setting, the specificity and randomness of the selected encryption algorithm can be fully guaranteed, thereby effectively improving the difficulty of data cracking, reducing the risk of data leakage and improving data security.

[0066] Specifically, the target power grid fault detection model can be a model based on machine learning, deep learning, or a model built based on physical laws, which is not limited here; by inputting power detection information, equipment status information, equipment type information, connection attribute information and topology structure type into the target power grid fault detection model, the fault detection results for the power grid can be obtained, and the fault detection results may include fault type, fault location, fault severity and fault impact range, etc., which are not limited here.

[0067] In some embodiments, after obtaining relevant information of the power grid, the method further includes the following steps: obtaining feature information, wherein the feature information includes one or more of first feature information, second feature information, third feature information, fourth feature information and fifth feature information, the first feature information is a feature corresponding to the power detection information, the second feature information is a feature corresponding to the device status information, the third feature information is a feature corresponding to the device type information, the fourth feature information is a feature corresponding to the connection attribute information, and the fifth feature information is a feature corresponding to the topology type information; performing feature fusion on the feature information to obtain fused feature information, wherein the fusion method includes attention mechanism fusion and / or weighted fusion; constructing a second model, wherein the second model is obtained by training using multiple sets of training data, and each set of training data in the multiple sets of training data includes historical fused feature information obtained within a historical time period and historical detection results corresponding to the historical fused feature information; inputting the fused feature information into the second model to obtain the detection results corresponding to the fused feature information.

[0068] In this scheme, the accuracy of fault detection can be improved through multi-parameter learning analysis. This scheme can further effectively improve the accuracy of fault detection in the power grid and ensure the normal operation of the power grid.

[0069] Specifically, the power detection information includes power detection information within a specified time period, the device status information includes device status information within a specified time period, and the fault analysis data is subjected to power grid fault analysis based on the target power grid fault detection model to obtain a fault detection result, including: generating power information time series data based on the power detection information within the specified time period; generating device status time series data based on the device status information within the specified time period; performing feature extraction on the power information time series data and the device status time series data based on the first sub-network structure in the target power grid fault detection model, respectively, to generate a first feature corresponding to the power information time series data and a second feature corresponding to the device status time series data; performing feature extraction on the device type information, the connection attribute information and the topology type based on the second sub-network structure in the target power grid fault detection model, respectively, to generate a third feature corresponding to the device type information, a fourth feature corresponding to the connection attribute information and a fifth feature corresponding to the topology type; performing feature fusion on the first feature, the second feature, the third feature, the fourth feature and the fifth feature to obtain a fused feature; processing the fused feature based on the detection sub-network structure in the target power grid fault detection model to obtain a fault detection result.

[0070] In the specific implementation process, the feature information can be obtained through the following steps: constructing a first feature extraction model, wherein the first feature extraction model is obtained by training with a first algorithm using multiple sets of training data, and each set of training data in the multiple sets of training data includes historical power detection information obtained within a historical time period, and historical first feature information corresponding to the historical power detection information, wherein the first algorithm includes RNN and / or LSTM; inputting the power detection information into the first feature extraction model to obtain the first feature information corresponding to the power detection information; constructing a second feature extraction model, wherein the second feature extraction model is obtained by training with the first algorithm using multiple sets of training data, and each set of training data in the multiple sets of training data includes historical device status information obtained within a historical time period, and historical second feature information corresponding to the historical device status information; inputting the device status information into the second feature extraction model to obtain the second feature information corresponding to the device status information.

[0071] In this solution, both the first feature extraction model and the second feature extraction model can process time series data. Therefore, these two models can be used to extract features from the first feature information and the second feature information, ensuring that the extracted features better meet data requirements.

[0072] Specifically, when the fault analysis data is subjected to a power grid fault analysis based on the target power grid fault detection model to obtain a fault detection result, it can be achieved through a machine learning model. It can be understood that the target power grid fault detection model in this embodiment includes a first sub-network structure for extracting features from the power information time series data and the device status time series data, respectively. The first sub-network structure can specifically be a model for processing time series data, such as a model sub-network structure composed of a recurrent neural network (RNN) model, a model sub-network structure composed of a long short-term memory network (LSTM) model, or other model sub-network structures derived from a recurrent neural network model or a long short-term memory network model, which are not limited here.

[0073] In some embodiments, obtaining feature information can be achieved through the following steps: constructing a third feature extraction model, wherein the third feature extraction model is obtained by training with a second algorithm using multiple sets of training data, and each set of training data in the multiple sets of training data includes historical device type information obtained within a historical time period, and historical third feature information corresponding to the historical device type information, wherein the second algorithm includes CNN and / or DNN; inputting the device type information into the third feature extraction model to obtain the third feature information corresponding to the device type information; constructing a fourth feature extraction model, wherein the fourth feature extraction model is obtained by training with the second algorithm using multiple sets of training data, and each set of training data in the multiple sets of training data includes historical device type information obtained within a historical time period, and historical third feature information corresponding to the historical device type information, wherein the second algorithm includes CNN and / or DNN; inputting the device type information into the third feature extraction model to obtain the third feature information corresponding to the device type information; and constructing a fourth feature extraction model, wherein the fourth feature extraction model is obtained by training with the second algorithm using multiple sets of training data, and each set of training data in the multiple sets of training data includes historical device type information obtained within a historical time period, and historical third feature information corresponding to the historical device type information. Each set of training data includes historical connection attribute information obtained within a historical time period and historical fourth feature information corresponding to the historical connection attribute information; the connection attribute information is input into the fourth feature extraction model to obtain the fourth feature information corresponding to the connection attribute information; a fifth feature extraction model is constructed, wherein the fifth feature extraction model is obtained by training the second algorithm using multiple sets of training data, and each set of training data in the multiple sets of training data includes historical topological structure type information obtained within a historical time period and historical fifth feature information corresponding to the historical topological structure type information; the topological structure type information is input into the fifth feature extraction model to obtain the fifth feature information corresponding to the topological structure type information.

[0074] In this solution, the third feature extraction model, the fourth feature extraction model and the fifth feature extraction model can all be used to directly extract features. The limitation on the time series is not mandatory. Therefore, direct extraction is sufficient. By constructing the models separately through the second algorithm, more accurate features can be extracted.

[0075] Specifically, a training set sample data is obtained for training a machine learning model to be trained, wherein each sample data in the training set sample data includes power detection information, device status information, device type information, connection attribute information, topology type and corresponding fault detection result; the machine learning model to be trained is trained by using the training set sample data to obtain a trained machine learning model; a test set sample data is obtained for verifying the trained machine learning model, wherein each sample data in the test set sample data includes power detection information, device status information, device type information, connection attribute information, topology type and corresponding fault detection result; the power detection information, device status information, device type information, connection attribute information and topology type of each sample data in the test set sample data are input into the trained machine learning model, and a predicted fault detection result is obtained as output; if the proportion of the number of sample data in the test set sample data whose fault detection result is consistent with the predicted fault detection result accounts for more than a predetermined proportion threshold value of the total number of sample data in the test set sample data, the trained machine learning model is identified as the target power grid fault detection model.

[0076] Specifically, the target power grid fault detection model in this embodiment also includes a second sub-network structure for extracting features of device type information, connection attribute information, and topology structure type respectively. The trained machine learning model in this embodiment can be a convolutional neural network (CNN) model or a deep neural network model, which is not limited here.

[0077] Specifically, when the first feature, the second feature, the third feature, the fourth feature, and the fifth feature are subjected to feature fusion, feature fusion may be achieved by using a feature fusion method with an attention mechanism, or by using a weighted fusion network structure. The detection subnetwork structure in the target power grid fault detection model may detect and obtain the fault detection result of the power grid based on the fusion feature obtained by feature fusion.

[0078] Specifically, the machine learning model to be trained is trained by training set sample data to obtain a trained machine learning model. The process of training the machine learning model is to adjust the coefficients in the network structure corresponding to the machine learning model, so that for the input power detection information, device status information, device type information, connection attribute information, topology type and other information, after the various coefficients in the network structure corresponding to the machine learning model are calculated, the output result is the fault detection result. For the trained machine learning model, it is also necessary to verify it to ensure that the machine learning model can meet the expected requirements in actual application. When verifying the trained machine learning model, the test set sample data for verifying the trained machine learning model can be obtained, wherein each sample data in the test set sample data includes power detection information, device status information, device type information, connection attribute information, topology type and corresponding fault detection result. The power detection information, device status information, device type information, connection attribute information, and topology type of each sample data of the test set sample data are input into the trained machine learning model, and the coefficients in the network structure corresponding to the machine learning model process the power detection information, device status information, device type information, connection attribute information, and topology type contained in each sample data to obtain the predicted fault detection result. If the number of sample data whose fault detection results corresponding to each sample data in the test set sample data are consistent with the predicted fault detection results accounts for more than the predetermined ratio threshold of the total number of sample data in the test set sample data, it means that the machine learning model meets the expected requirements, and the trained machine learning model can be identified as the target power grid fault detection model, otherwise, it needs to continue to be trained through the training set sample data until the machine learning model meets the requirements in actual application. Testing the trained machine learning model through the test set sample data before actual application can effectively ensure that the trained machine learning model meets the requirements of actual application.

[0079] Specifically, after obtaining the fault detection results of the power grid, the operation and maintenance monitoring results of the power grid can be determined according to the fault type, fault location, fault severity and fault impact range, and the operation and maintenance monitoring results can be displayed so that operation and maintenance measures can be taken in time to maintain the power grid fault and ensure the normal operation of the power grid.

[0080] In one embodiment, the fault detection result may include the fault type, fault location, fault severity and fault impact range of the power grid fault. The fault type may include short circuit, open circuit, overload or equipment failure and other types. The fault location is the geographical location information of the fault. The fault severity may include high risk, medium risk, low risk and no risk. The fault impact range can be identified in the form of regional geographical range.

[0081] Specifically, a corresponding fault solution can be generated according to the fault type, fault severity and fault impact range. Optionally, a mapping relationship between the fault type, fault severity and fault impact range and the fault solution can be pre-stored locally, so as to quickly locate the corresponding fault solution according to the fault type, fault severity and fault impact range of the power grid fault, determine the corresponding fault solution, and determine the corresponding fault maintenance personnel according to the fault location, so as to facilitate the fault maintenance personnel to quickly inspect the power grid as soon as possible, so as to quickly and accurately clear the fault, which can significantly improve the efficiency of clearing power grid faults, thereby ensuring that the power grid quickly returns to a normal state, thereby continuously and stably providing power supply.

[0082] Specifically, the topological structure type of the power grid is determined based on the equipment type information and connection attribute information of the power equipment; the power detection information, equipment status information, equipment type information, connection attribute information and topological structure type are used as fault analysis data, and the target power grid fault detection model is matched in the power grid fault detection model library; since the target power grid fault detection model is a power grid fault detection model suitable for the specific fault analysis data including the topological structure type, the detected data is analyzed compared with the general power grid fault detection model, and the power grid detection information, equipment status information, equipment type information, connection attribute information and topological structure type are used as fault analysis data, and the target power grid fault detection model is matched in the power grid fault detection model library, and then the power grid fault detection model specifically corresponding to the fault analysis data is mined to perform fault detection on the power grid, which can effectively improve the accuracy of fault detection on the power grid, so as to take operation and maintenance measures in time to maintain the power grid fault and ensure the normal operation of the power grid.

[0083] In order to enable those skilled in the art to more clearly understand the technical solution of the present application, the implementation process of the power grid operation and maintenance monitoring method of the present application will be described in detail below in combination with specific embodiments.

[0084] This embodiment relates to a specific power grid operation and maintenance monitoring method, such as Figure 3 As shown, the following steps are included:

[0085] S310, in response to a monitoring request from the operation and maintenance management server, obtaining power detection information in the power grid to be monitored, device status information of each power device in the power grid, device type information of each power device in the power grid, and connection attribute information between each power device in the power grid;

[0086] S320, determining a topology type of the power grid based on device type information and connection attribute information of the power device;

[0087] S330, using the power detection information, the device status information, the device type information, the connection attribute information and the topology structure type as fault analysis data, and matching the target power grid fault detection model in the power grid fault detection model library;

[0088] S340, performing power grid fault analysis on the fault analysis data based on the target power grid fault detection model to obtain a fault detection result;

[0089] S350 generates operation and maintenance monitoring results of the power grid based on the fault detection results.

[0090] The embodiment of the present application also provides an operation and maintenance monitoring device for a power grid. It should be noted that the operation and maintenance monitoring device for the power grid of the embodiment of the present application can be used to execute the operation and maintenance monitoring method for the power grid provided in the embodiment of the present application. The device is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the term "module" can implement a combination of software and / or hardware for a predetermined function. Although the device described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceived.

[0091] The following is an introduction to the operation and maintenance monitoring device for the power grid provided in an embodiment of the present application.

[0092] Figure 4 1 is a structural block diagram of a power grid operation and maintenance monitoring device according to an embodiment of the present application. Figure 4 As shown, the device comprises:

[0093] A first acquisition unit 10 is used to acquire relevant information of a power grid, wherein the relevant information includes one or more of power detection information, device status information, device type information, connection attribute information and topology type information, wherein the power detection information is information on voltage, current and power of the power equipment of the power grid, the device status information is information on temperature, load and vibration of the power equipment of the power grid, the device type information is information on the type of the power equipment of the power grid, the connection attribute information is information on whether the power equipment of the power grid is connected and the connection relationship, the connection relationship includes one or more of series connection, parallel connection and series-parallel connection, and the topology type information is information on the topological connection relationship between the multiple power equipment of the power grid;

[0094] A first construction unit 20 is used to construct a first model, wherein the first model is obtained by training a target algorithm using multiple sets of training data, each set of training data in the multiple sets of training data includes historical related information obtained in a historical time period and historical detection results corresponding to the historical related information, wherein the historical detection results are used to characterize whether the power grid in the historical time period has a fault, wherein the target algorithm includes one or more of RNN, LSTM, CNN and DNN;

[0095] The first processing unit 30 is used to input the above-mentioned relevant information into the above-mentioned first model to obtain the detection results corresponding to the above-mentioned relevant information.

[0096] Through this embodiment, multiple parameters can be used to determine whether the power grid is faulty. Compared with the prior art that only detects the equipment status and power parameters in the power equipment of the power grid, this solution also uses more parameters for analysis, especially adding the topology type for analysis. The topology type of the power grid represents the physical connection relationship and electrical characteristics between each power equipment or power element in the power grid, which can be used as an important information for power grid fault detection. The first model is then used to realize automatic analysis of the fault. The accuracy of fault detection can be improved through multi-parameter learning analysis. This solution can effectively improve the accuracy of fault detection in the power grid and ensure the normal operation of the power grid.

[0097] In the specific implementation process, the first acquisition unit includes a generation module, a search module and a determination module. The generation module is used to generate a topology connection diagram according to the above-mentioned equipment type information and the above-mentioned connection attribute information of the above-mentioned power equipment; the search module is used to search for the topology connection template diagram with the highest similarity to the above-mentioned topology connection diagram in the target database according to the above-mentioned topology connection diagram, and obtain the target topology connection template diagram, wherein the above-mentioned target database includes multiple above-mentioned topology connection template diagrams, and the above-mentioned topology connection template diagrams correspond to the topology structure types one by one; the determination module is used to determine the above-mentioned topology structure type information of the above-mentioned power grid according to the above-mentioned target topology connection template diagram.

[0098] In this scheme, the topology connection template map database includes multiple topology connection template maps, which are generated based on power grids of multiple different topology types. By comparing the similarity between the generated topology connection map and each topology connection template map in the topology connection template map database, the topology connection template map with the highest similarity is found, thereby achieving accurate determination of the topology structure type of the power grid.

[0099] In some embodiments, the above-mentioned device also includes an encryption unit and a decryption unit. The encryption unit is used to encrypt the relevant information of the power grid after acquiring the relevant information to obtain encrypted data; the decryption unit is used to send the encrypted data to the server so that the above-mentioned server decrypts the encrypted data.

[0100] In this solution, by encrypting and decrypting relevant information, the security of data can be guaranteed to be better.

[0101] During the specific implementation process, the encryption unit includes an acquisition module, a first processing module and a calculation module. The acquisition module is used to obtain operation and maintenance information, wherein the above-mentioned operation and maintenance information includes request time information, personnel identification information and equipment identification information. The above-mentioned request time information is the information of the time for requesting operation and maintenance monitoring of the above-mentioned power grid, the above-mentioned personnel identification information is the identity information of the operation and maintenance personnel, and the above-mentioned equipment identification information is the unique identification information of the above-mentioned power equipment; the first processing module is used to encode the above-mentioned operation and maintenance information according to the Base64 encoding table to obtain the encoded information; the calculation module is used to perform hash calculation on the above-mentioned related information according to the above-mentioned encoded information to obtain the above-mentioned encrypted data.

[0102] In this solution, encryption processing can be performed more efficiently through the Base64 encoding table, ensuring better encryption specificity and better encryption security.

[0103] In some embodiments, the device further includes a second acquisition unit, a second processing unit, a second construction unit and a third processing unit, wherein the second acquisition unit is used to acquire feature information after acquiring relevant information of the power grid, wherein the feature information includes one or more of the first feature information, the second feature information, the third feature information, the fourth feature information and the fifth feature information, wherein the first feature information is a feature corresponding to the power detection information, the second feature information is a feature corresponding to the device status information, the third feature information is a feature corresponding to the device type information, the fourth feature information is a feature corresponding to the connection attribute information, and the fifth feature information is a feature corresponding to the topology type information; the second processing unit is used to perform feature fusion on the feature information to obtain fused feature information, wherein the fusion method includes attention mechanism fusion and / or weighted fusion; the second construction unit is used to construct a second model, wherein the second model is obtained by training using multiple sets of training data, and each set of training data in the multiple sets of training data includes historical fused feature information obtained in a historical time period and historical detection results corresponding to the historical fused feature information; the third processing unit is used to input the fused feature information into the second model to obtain the detection results corresponding to the fused feature information.

[0104] In this scheme, the accuracy of fault detection can be improved through multi-parameter learning analysis. This scheme can further effectively improve the accuracy of fault detection in the power grid and ensure the normal operation of the power grid.

[0105] In the specific implementation process, the second acquisition unit includes a first construction module, a second processing module, a second construction module and a third processing module. The first construction module is used to construct a first feature extraction model, wherein the first feature extraction model is obtained by training with a first algorithm using multiple sets of training data, and each set of training data in the multiple sets of training data includes historical power detection information obtained within a historical time period, and historical first feature information corresponding to the historical power detection information, wherein the first algorithm includes RNN and / or LSTM; the second processing module is used to input the power detection information into the first feature extraction model to obtain the first feature information corresponding to the power detection information; the second construction module is used to construct a second feature extraction model, wherein the second feature extraction model is obtained by training with the first algorithm using multiple sets of training data, and each set of training data in the multiple sets of training data includes historical device status information obtained within a historical time period, and historical second feature information corresponding to the historical device status information; the third processing module is used to input the device status information into the second feature extraction model to obtain the second feature information corresponding to the device status information.

[0106] In this solution, both the first feature extraction model and the second feature extraction model can process time series data. Therefore, these two models can be used to extract features from the first feature information and the second feature information, ensuring that the extracted features better meet data requirements.

[0107] In some embodiments, the second acquisition unit further includes a third construction module, a fourth processing module, a fourth construction module, a fifth processing module, a fifth construction module and a sixth processing module. The third construction module is used to construct a third feature extraction model, wherein the third feature extraction model is obtained by training the second algorithm using multiple sets of training data, and each set of training data in the multiple sets of training data includes historical device type information obtained within a historical time period, and historical third feature information corresponding to the historical device type information, wherein the second algorithm includes CNN and / or DNN; the fourth processing module is used to input the device type information into the third feature extraction model to obtain the third feature information corresponding to the device type information; the fourth construction module is used to construct a fourth feature extraction model, wherein the fourth feature extraction model is obtained by training the second algorithm using multiple sets of training data, and each set of training data in the multiple sets of training data includes historical time periods. The fifth processing module is used to input the above-mentioned connection attribute information into the above-mentioned fourth feature extraction model to obtain the above-mentioned fourth feature information corresponding to the above-mentioned connection attribute information; the fifth construction module is used to construct the fifth feature extraction model, wherein the above-mentioned fifth feature extraction model is obtained by training the above-mentioned second algorithm using multiple sets of training data, and each set of training data in the above-mentioned multiple sets of training data includes the historical topological structure type information obtained in the historical time period, and the historical fifth feature information corresponding to the above-mentioned historical topological structure type information; the sixth processing module is used to input the above-mentioned topological structure type information into the above-mentioned fifth feature extraction model to obtain the above-mentioned fifth feature information corresponding to the above-mentioned topological structure type information.

[0108] In this solution, the third feature extraction model, the fourth feature extraction model and the fifth feature extraction model can all be used to directly extract features. The limitation on the time series is not mandatory. Therefore, direct extraction is sufficient. By constructing the models separately through the second algorithm, more accurate features can be extracted.

[0109] The above-mentioned power grid operation and maintenance monitoring device includes a processor and a memory. The above-mentioned first acquisition unit, the first construction unit and the first processing unit are all stored in the memory as program units, and the processor executes the above-mentioned program units stored in the memory to realize corresponding functions. The above-mentioned modules are all located in the same processor; or, the above-mentioned modules are located in different processors in any combination.

[0110] The processor includes a kernel, and the kernel retrieves the corresponding program unit from the memory. One or more kernels can be provided, and the problem of low accuracy in fault detection of the power grid in the prior art can be solved by adjusting kernel parameters.

[0111] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0112] An embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute the operation and maintenance monitoring method of the power grid.

[0113] An embodiment of the present invention provides a processor, and the processor is used to run a program, wherein the operation and maintenance monitoring method of the power grid is executed when the program is run.

[0114] An embodiment of the present invention provides a device, the device including a processor, a memory, and a program stored in the memory and executable on the processor, and when the processor executes the program, at least the following steps are implemented:

[0115] The devices in this article can be servers, PCs, PADs, mobile phones, etc.

[0116] A computer program product includes a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above method in each embodiment of the present application are implemented.

[0117] An embodiment of the present invention provides a digital power grid operation and maintenance monitoring system, comprising one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors, and the one or more programs include methods for executing any one of the above-mentioned power grid operation and maintenance monitoring methods.

[0118] Figure 5 A schematic diagram of the structure of a computer system suitable for implementing an electronic device of an embodiment of the present application is shown.

[0119] It should be noted that Figure 5 The computer system 500 of the electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0120] like Figure 5As shown, the computer system 500 includes a central processing unit 501 (CPU), which can perform various appropriate actions and processes according to the program stored in the read-only memory 502 (ROM) or the program loaded from the storage part 508 to the random access memory 503 (RAM), such as executing the above-mentioned method in the above-mentioned embodiment. In the RAM, various programs and data required for system operation are also stored. The CPU, ROM and RAM are connected to each other through a bus 504. An input / output interface 505 (I / O) is also connected to the bus 504.

[0121] The following components are connected to the I / O interface: an input section 506 including a keyboard, a mouse, etc.; an output section 507 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker; a storage section 508 including a hard disk, etc.; and a communication section 509 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 509 performs communication processing via a network such as the Internet. A drive 510 is also connected to the I / O interface as needed. A removable medium 511, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 510 as needed so that a computer program read therefrom is installed into the storage section 508 as needed.

[0122] Obviously, those skilled in the art should understand that the above modules or steps of the present invention can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order than here, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0123] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0124] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0125] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0126] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0127] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0128] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0129] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0130] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0131] From the above description, it can be seen that the above embodiments of the present application achieve the following technical effects:

[0132] 1) A power grid operation and maintenance monitoring method of the present application can use multiple parameters to determine whether the power grid is faulty. Compared with the prior art that only detects the equipment status and power parameters in the power equipment of the power grid, this scheme also uses more parameters for analysis, especially adding the topology type for analysis. The topology type of the power grid represents the physical connection relationship and electrical characteristics between each power equipment or power element in the power grid, which can be used as an important information for power grid fault detection. The first model is then used to realize automatic analysis of the fault. The accuracy of fault detection can be improved through multi-parameter learning analysis. This scheme can effectively improve the accuracy of fault detection in the power grid and ensure the normal operation of the power grid.

[0133] 2) The operation and maintenance monitoring device of a power grid of the present application can use multiple parameters to determine whether the power grid is faulty. Compared with the prior art which only detects the equipment status and power parameters in the power equipment of the power grid, this scheme also uses more parameters for analysis, especially adds the topology structure type for analysis. The topology structure type of the power grid represents the physical connection relationship and electrical characteristics between each power equipment or power element in the power grid, which can be used as an important information for power grid fault detection. The first model is then used to realize automatic analysis of the fault. The accuracy of fault detection can be improved through multi-parameter learning analysis. This scheme can effectively improve the accuracy of fault detection in the power grid and ensure the normal operation of the power grid.

[0134] The above description is only the preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method for monitoring operation and maintenance of a power grid, characterized in that: include: Obtaining relevant information of a power grid, wherein the relevant information includes one or more of power detection information, device status information, device type information, connection attribute information, and topology type information, wherein the power detection information is information about voltage, current, and power of the power equipment of the power grid, the device status information is information about temperature, load, and vibration of the power equipment of the power grid, the device type information is information about the type of the power equipment of the power grid, the connection attribute information is information about whether the power equipment of the power grid is connected and the connection relationship, the connection relationship includes one or more of series connection, parallel connection, and series-parallel connection, and the topology type information is information about the topological connection relationship between multiple power equipment of the power grid; Constructing a first model, wherein the first model is obtained by training with a target algorithm using multiple sets of training data, each set of training data in the multiple sets of training data includes historical related information obtained in a historical time period and historical detection results corresponding to the historical related information, wherein the historical detection results are used to characterize whether the power grid in the historical time period has a fault, wherein the target algorithm includes one or more of RNN, LSTM, CNN and DNN; The relevant information is input into the first model to obtain the detection result corresponding to the relevant information.

2. The method according to claim 1, characterized in that Obtain information about the power grid, including: Generate a topological connection diagram according to the device type information and the connection attribute information of the power device; According to the topology connection graph, searching a target database for a topology connection template graph having the highest similarity to the topology connection graph to obtain a target topology connection template graph, wherein the target database includes a plurality of the topology connection template graphs, and the topology connection template graphs correspond to topology structure types one by one; The topology structure type information of the power grid is determined according to the target topology connection template graph.

3. The method according to claim 1, characterized in that After obtaining the relevant information of the power grid, the method further includes: Encrypting the relevant information to obtain encrypted data; The encrypted data is sent to a server so that the server decrypts the encrypted data.

4. The method according to claim 3, characterized in that The relevant information is encrypted to obtain encrypted data, including: Acquire operation and maintenance information, wherein the operation and maintenance information includes request time information, personnel identification information and device identification information, the request time information is information of the time for requesting operation and maintenance monitoring of the power grid, the personnel identification information is information of the identity of the operation and maintenance personnel, and the device identification information is information of the unique identification of the power equipment; Encode the operation and maintenance information according to the Base64 encoding table to obtain encoded information; A hash calculation is performed on the relevant information according to the encoding information to obtain the encrypted data.

5. The method according to claim 1, characterized in that After obtaining the relevant information of the power grid, the method further includes: Acquire characteristic information, wherein the characteristic information includes one or more of first characteristic information, second characteristic information, third characteristic information, fourth characteristic information, and fifth characteristic information, the first characteristic information is a characteristic corresponding to the power detection information, the second characteristic information is a characteristic corresponding to the device state information, the third characteristic information is a characteristic corresponding to the device type information, the fourth characteristic information is a characteristic corresponding to the connection attribute information, and the fifth characteristic information is a characteristic corresponding to the topology type information; Performing feature fusion on the feature information to obtain fused feature information, wherein the fusion method includes attention mechanism fusion and / or weighted fusion; Constructing a second model, wherein the second model is trained using multiple sets of training data, each set of training data in the multiple sets of training data includes historical fusion feature information obtained within a historical time period and historical detection results corresponding to the historical fusion feature information; The fused feature information is input into the second model to obtain the detection result corresponding to the fused feature information.

6. The method according to claim 5, characterized in that Get feature information, including: Constructing a first feature extraction model, wherein the first feature extraction model is obtained by training a first algorithm using multiple sets of training data, each set of training data in the multiple sets of training data includes historical power detection information obtained within a historical time period and historical first feature information corresponding to the historical power detection information, wherein the first algorithm includes RNN and / or LSTM; Inputting the power detection information into the first feature extraction model to obtain the first feature information corresponding to the power detection information; Constructing a second feature extraction model, wherein the second feature extraction model is obtained by training the first algorithm using multiple sets of training data, each set of training data in the multiple sets of training data includes historical device status information obtained within a historical time period and historical second feature information corresponding to the historical device status information; The device status information is input into the second feature extraction model to obtain the second feature information corresponding to the device status information.

7. The method according to claim 5, characterized in that Get feature information, including: Constructing a third feature extraction model, wherein the third feature extraction model is obtained by training the second algorithm using multiple sets of training data, each set of training data in the multiple sets of training data includes historical device type information obtained in a historical time period and historical third feature information corresponding to the historical device type information, wherein the second algorithm includes CNN and / or DNN; Inputting the device type information into the third feature extraction model to obtain the third feature information corresponding to the device type information; Constructing a fourth feature extraction model, wherein the fourth feature extraction model is obtained by training the second algorithm using multiple sets of training data, each set of training data in the multiple sets of training data includes historical connection attribute information obtained within a historical time period and historical fourth feature information corresponding to the historical connection attribute information; Inputting the connection attribute information into the fourth feature extraction model to obtain the fourth feature information corresponding to the connection attribute information; Constructing a fifth feature extraction model, wherein the fifth feature extraction model is obtained by training the second algorithm using multiple sets of training data, and each set of training data in the multiple sets of training data includes historical topological structure type information obtained within a historical time period and historical fifth feature information corresponding to the historical topological structure type information; The topological structure type information is input into the fifth feature extraction model to obtain the fifth feature information corresponding to the topological structure type information.

8. A power grid operation and maintenance monitoring device, characterized in that: include: a first acquisition unit, configured to acquire relevant information of a power grid, wherein the relevant information includes one or more of power detection information, device status information, device type information, connection attribute information, and topology type information, wherein the power detection information is information on voltage, current, and power of the power equipment of the power grid, the device status information is information on temperature, load, and vibration of the power equipment of the power grid, the device type information is information on the type of the power equipment of the power grid, the connection attribute information is information on whether the power equipment of the power grid is connected and a connection relationship, the connection relationship includes one or more of series connection, parallel connection, and series-parallel connection, and the topology type information is information on a topological connection relationship between a plurality of the power equipment of the power grid; A first construction unit is used to construct a first model, wherein the first model is obtained by training with a target algorithm using multiple sets of training data, each set of training data in the multiple sets of training data includes historical related information obtained in a historical time period and historical detection results corresponding to the historical related information, wherein the historical detection results are used to characterize whether the power grid in the historical time period has a fault, wherein the target algorithm includes one or more of RNN, LSTM, CNN and DNN; The first processing unit is used to input the relevant information into the first model to obtain the detection result corresponding to the relevant information.

9. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the operation and maintenance monitoring method of the power grid described in any one of claims 1 to 7 are implemented.

10. A digital power grid operation and maintenance monitoring system, characterized in that: include: One or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors, and the one or more programs include a method for executing the operation and maintenance monitoring method of the power grid described in any one of claims 1 to 7.

Images