Power grid problem analysis and determination method and device, computer equipment, readable storage medium and program product
By collecting real-time data of power grid equipment and using causal multi-attention maps and data mining algorithms, the problem of insufficient efficiency and accuracy of traditional power grid problem analysis methods is solved, and the rapid identification and analysis of power grid problems is realized, and the safety of power grid operation is improved. Sex and stability.
Patent Information
- Application Number
- CN202411326053.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-23
- Publication Date
- 2025-01-14
AI Technical Summary
Traditional grid problem analysis methods rely on manual experience, slow analysis speed and limited accuracy, making it difficult to process massive data and complex grid structures, resulting in insufficient efficiency and quality.
By collecting real-time operation data of power grid equipment, generating causal multi-attention maps, using data mining algorithms and logistic regression algorithms to extract and analyze effective data, and achieve rapid and accurate identification of power grid problems.
It significantly improves the accuracy and efficiency of power grid problem analysis, reduces reliance on manual experience, and enhances the safety and stability of power grid operation.
Smart Images
Figure CN119312288A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of power grid problem analysis, and in particular to a power grid problem analysis and determination method, apparatus, computer equipment, readable storage medium and program product. Background Art
[0002] With the increasing demand for electricity and the continuous expansion of the power grid, power grid problems have become increasingly complex, and traditional power grid problem analysis methods can no longer meet the actual needs of modern power grid management.
[0003] At present, power grid problem analysis mainly relies on human experience and expert knowledge, which not only leads to slow analysis speed, but also limits the accuracy of analysis and is easily affected by personal experience differences and subjective judgment. In addition, existing analysis methods have obvious deficiencies in processing massive power grid data and complex power grid structures, which further restricts the efficiency and quality of power grid problem analysis and processing.
[0004] Therefore, developing an intelligent technology that can quickly and accurately identify and analyze power grid problems has important practical significance and application value for improving the safety and stability of power grid operation. Summary of the invention
[0005] Based on this, it is necessary to provide a power grid problem analysis and determination method, device, computer equipment, readable storage medium and program product that can quickly and accurately identify and analyze power grid problems in response to the above technical problems.
[0006] In a first aspect, the present application provides a method for analyzing and determining power grid problems, the method comprising:
[0007] Collect real-time operation data of power grid equipment; real-time operation data includes temperature, appearance, vibration, voltage and current;
[0008] Generate a causal multi-attention graph based on real-time operation data, and determine the problem data of power grid equipment based on the causal multi-attention graph;
[0009] According to the calibrated operating parameters, the data mining algorithm is used to extract valid data from the problem data of the power grid equipment; the valid data includes temperature abnormality data, appearance abnormality data, abnormal vibration data, abnormal voltage data and abnormal current data; the calibrated operating parameters include the outgoing line interval of the substation, the main transformer capacity, the outgoing line voltage, the feeder length, the main transformer load, the feeder load and the distribution transformer capacity;
[0010] Clean the valid data to obtain the target valid data;
[0011] The target valid data is analyzed based on the logistic regression algorithm to identify power grid problems.
[0012] In one embodiment, generating a causal multi-attention graph based on real-time operation data includes:
[0013] Based on the causal attention mechanism, the real-time operation data is fused through the multimodal data fusion algorithm to obtain fused data;
[0014] According to the fused data, a causal multi-attention graph is generated by combining the multi-head attention mechanism and the structural causal model.
[0015] In one embodiment, according to the calibrated operating parameters, a data mining algorithm is used to extract valid data from the problem data of the power grid equipment, including:
[0016] Based on the calibrated operating parameters, classification algorithm, association rule mining algorithm and anomaly detection algorithm are used to extract valid data from the problem data of power grid equipment.
[0017] In one embodiment, the valid data is cleaned to obtain target valid data, including:
[0018] Based on historical operation data, the decision tree algorithm is used to preliminarily screen the effective data to obtain preliminary screening data;
[0019] Compare the preliminary screening data with the historical question data in the preset question library for further screening to obtain the target valid data.
[0020] In one embodiment, the method further comprises:
[0021] Based on the target effective data, it is compared with the corresponding problem data in the preset problem type matching table to determine the power grid problem.
[0022] In one embodiment, the method further comprises:
[0023] The grid problems are sent to the user terminal in the form of data tables.
[0024] In a second aspect, the present application provides a power grid problem analysis and determination device, the device comprising:
[0025] Operation data acquisition module, used to collect real-time operation data of power grid equipment; real-time operation data includes temperature, appearance, vibration, voltage and current;
[0026] A problem data determination module is used to generate a causal multi-attention graph based on real-time operation data, and determine the problem data of the power grid equipment based on the causal multi-attention graph;
[0027] The effective data extraction module is used to extract effective data from the problem data of power grid equipment according to the calibrated operating parameters and using data mining algorithms; the effective data includes temperature abnormality data, appearance abnormality data, abnormal vibration data, abnormal voltage data and abnormal current data; the calibrated operating parameters include the outgoing line interval of the substation, the main transformer capacity, the outgoing line voltage, the feeder length, the main transformer load, the feeder load and the distribution transformer capacity;
[0028] Data cleaning module, used to clean valid data and obtain target valid data;
[0029] The problem determination module is used to analyze the target valid data according to the logistic regression algorithm and determine the power grid problems.
[0030] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the method in the above embodiment when executing the computer program.
[0031] In a fourth aspect, the present application further provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the steps of the method in the above embodiment are implemented.
[0032] In a fifth aspect, the present application also provides a computer program product, including a computer program, which implements the steps of the method in the above embodiment when the computer program is executed by a processor.
[0033] The above-mentioned power grid problem analysis and determination method, device, computer equipment, readable storage medium and program product have at least the following beneficial effects:
[0034] By collecting the operating data of power grid equipment in real time and using multimodal data fusion technology and causal multi-attention graph generation methods, potential problems in the equipment can be accurately identified. By extracting valid data through data mining algorithms and cleaning the data, and finally using logistic regression algorithms to diagnose problems, this series of steps significantly improves the accuracy and efficiency of power grid problem analysis, reduces dependence on manual experience, and enhances the safety and stability of power grid operation. BRIEF DESCRIPTION OF THE DRAWINGS
[0035] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.
[0036] FIG1 is a diagram of an application environment of a method for analyzing and determining power grid problems in one embodiment;
[0037] FIG2 is a schematic diagram of a flow chart of a method for analyzing and determining power grid problems in one embodiment;
[0038] FIG3 is a structural block diagram of a device for analyzing and determining power grid problems in one embodiment;
[0039] FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION
[0040] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.
[0041] The power grid problem analysis and determination method provided in the embodiment of the present application can be applied to the application environment shown in Figure 1. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or it can be placed on the cloud or other network servers. The server 102 collects real-time operation data of the power grid equipment; the real-time operation data includes temperature, appearance, vibration, voltage and current; according to the real-time operation data, a causal multi-attention graph is generated, and the problem data of the power grid equipment is determined according to the causal multi-attention graph; according to the calibrated operation parameters, the data mining algorithm is used to extract the valid data from the problem data of the power grid equipment; the valid data includes temperature abnormality data, appearance abnormality data, abnormal vibration data, abnormal voltage data and abnormal current data; the calibrated operation parameters include the outgoing line interval, main transformer capacity, outgoing line voltage, feeder length, main transformer load, feeder load and distribution transformer capacity of the substation; the valid data is cleaned to obtain the target valid data; the target valid data is analyzed according to the logistic regression algorithm to determine the power grid problem. The terminal 102 may be, but is not limited to, a camera, an infrared sensor, an ultrasonic wave, a feeder monitoring terminal (FTU), a distribution transformer monitoring and metering terminal, and other intelligent devices or sensors. The server 104 may be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services.
[0042] In an exemplary embodiment, as shown in FIG2 , a method for analyzing and determining power grid problems is provided, which is described by taking the method applied to the server 102 in FIG1 as an example, and includes the following steps S202 to S206 . Among them:
[0043] S202, collecting real-time operating data of power grid equipment; the real-time operating data includes temperature, appearance, vibration, voltage and current.
[0044] Among them, real-time operating data of power grid equipment such as temperature, appearance, vibration, voltage and current can be collected through intelligent devices or sensors such as cameras, infrared sensors, ultrasound, feeder monitoring terminals (FTU), distribution transformer monitoring and metering terminals, etc.
[0045] S204, generating a causal multi-attention graph based on the real-time operation data, and determining the problem data of the power grid equipment based on the causal multi-attention graph.
[0046] For example, the temperature, shape, voltage, current and other data of power grid equipment are collected in real time through devices such as cameras, infrared sensors, ultrasonic sensors, feeder monitoring terminals (FTUs) and distribution transformer monitoring and metering terminals. And the multimodal data fusion technology is used to integrate these data and generate a causal multi-attention graph in combination with the multi-head attention mechanism and the structural causal model. For example, if the infrared sensor detects that the temperature of a device is abnormally high, and the ultrasonic sensor simultaneously captures an abnormal sound inside the device, these data will be associated in the causal multi-attention graph to form a focus. By combining the multi-head attention mechanism and the structural causal model, a causal multi-attention graph is generated. These graphs can highlight which factors are most likely to cause problems with the device. For example, if the infrared sensor detects that the temperature of the device is abnormal, and the ultrasonic sensor detects that there is an abnormal sound inside the device, these factors will be associated in the causal multi-attention graph to form a focus, indicating that these factors may jointly cause problems with the device. By analyzing the causal multi-attention graph, the system can identify which data is a sign of potential problems with the device. For example, if the causal multi-attention graph shows that the temperature of the device is abnormally high and is associated with abnormal internal sounds, the system will mark these data as problem data.
[0047] S206, based on the calibrated operating parameters, using the data mining algorithm, extract valid data from the problem data of the power grid equipment; the valid data includes temperature abnormality data, appearance abnormality data, abnormal vibration data, abnormal voltage data and abnormal current data; the calibrated operating parameters include the outgoing line interval of the substation, the main transformer capacity, the outgoing line voltage, the feeder length, the main transformer load, the feeder load and the distribution transformer capacity.
[0048] Exemplarily, by obtaining the calibrated operating parameters including the outgoing line interval, main transformer capacity, outgoing line voltage, feeder length, main transformer load, feeder load and distribution transformer capacity of the substation, the calibrated operating parameters are used to characterize the parameters of the normal operation of the power grid equipment. With the calibrated operating parameters as the benchmark, data mining algorithms such as association rule mining and anomaly detection are used to process the collected data to identify data that does not conform to the normal operation status of the equipment. For example, when the temperature of a distribution transformer is monitored to continuously exceed the predetermined safety threshold, and its load is close to or exceeds its calibrated capacity, the system identifies this temperature record as abnormal temperature data; if the visual sensor detects obvious deformation or damage on the surface of the distribution box, it is marked as appearance abnormal data; and when the vibration frequency or intensity detected by the vibration sensor exceeds the normal range, it is regarded as abnormal vibration data; for voltage and current data, if the instantaneous voltage or current value is monitored to deviate significantly from the historical average or exceed the safety range, it will be classified as abnormal voltage or current data. In this way, the system can filter out effective fault warning information from the massive power grid equipment operation data.
[0049] S208, cleaning the valid data to obtain target valid data.
[0050] Exemplarily, based on all the identified abnormal data, such as abnormal temperature, abnormal appearance, abnormal vibration, abnormal voltage and abnormal current data, data cleaning technology is used to remove duplicate, erroneous or irrelevant information. For example, if the system records abnormal fluctuations in the temperature of the equipment in the same time period multiple times, only the most representative records are retained; if a sensor produces an erroneous reading due to a fault, the erroneous data is corrected or deleted by verifying the data of other sensors; if it is found that some abnormal data is irrelevant to the current power grid operation status (such as a one-time fluctuation caused by external temporary factors), these data are excluded. Through such a cleaning process, it can be ensured that the final target effective data set only contains problem data that really need to be paid attention to, thereby improving the accuracy and efficiency of problem diagnosis.
[0051] S210, analyzing target effective data according to a logistic regression algorithm to determine power grid problems.
[0052] Exemplarily, the cleaned valid data (such as abnormal temperature, abnormal appearance, abnormal vibration, abnormal voltage and abnormal current data) are used as input features and analyzed using a pre-trained logistic regression model. For example, if the system detects that the temperature of a transformer rises abnormally, and at the same time records that the voltage fluctuation of the transformer exceeds the preset threshold, the logistic regression model will calculate the probability that the transformer is in an "overloaded" state based on these features, and judge whether there is an overload problem based on this. For example, if it is detected that there is only one main transformer in the substation, it is a single main transformer problem; if the load rate of the main transformer is greater than or equal to 80% and less than 100%, the main transformer is overloaded; if the load rate of the main transformer is less than or equal to 20%, the main transformer is lightly loaded. If the main transformer is greater than or equal to 100%, the main transformer is overloaded, etc.; if the current ambient temperature is too high, there are problems with objects or geology that affect power supply, etc., there are safety hazards, etc. In this way, the specific problem types of power grid equipment can be accurately identified based on the logistic regression algorithm.
[0053] The above-mentioned power grid problem analysis and determination method can accurately identify potential problems in equipment by collecting the operating data of power grid equipment in real time and using multimodal data fusion technology and causal multi-attention graph generation methods. By extracting effective data through data mining algorithms and cleaning the data, and finally using logistic regression algorithms to diagnose problems, this series of steps significantly improves the accuracy and efficiency of power grid problem analysis, reduces dependence on manual experience, and enhances the safety and stability of power grid operation.
[0054] In an exemplary embodiment, generating a causal multi-attention graph based on real-time operation data includes:
[0055] Based on the causal attention mechanism, the real-time running data is fused through the multimodal data fusion algorithm to obtain the fused data.
[0056] For example, a multimodal data fusion algorithm based on the causal attention mechanism is implemented. For example, when the infrared sensor detects an abnormal increase in the temperature of a certain power equipment, this may indicate that the equipment is at risk of overheating; at the same time, the ultrasonic sensor captures abnormal sounds from inside the equipment, suggesting that there may be a mechanical failure. The data of these two modes - temperature increase and abnormal sound, are integrated through multimodal data fusion technology, and the multi-head attention mechanism is used to enable the system to pay attention to the correlation between different data sources, and then the structural causal model is combined to analyze the causal relationship behind these correlations, thereby generating a causal multi-attention graph. In this graph, the temperature increase and the abnormal sound are associated to form a focus, indicating that the two may jointly point to a specific problem of the equipment. In this way, through the fusion analysis of real-time operation data, the system can not only identify the potential failure of the equipment, but also intelligently predict the cause of the failure, improving the accuracy of problem identification and response speed.
[0057] According to the fused data, a causal multi-attention graph is generated by combining the multi-head attention mechanism and the structural causal model.
[0058] For example, after integrating the data of abnormal temperature rise of the equipment detected by the infrared sensor and the data of abnormal sound inside the equipment captured by the ultrasonic sensor through multimodal data fusion technology, the multi-head attention mechanism is used to focus on the multiple associations between these data. The multi-head attention mechanism allows the system to focus on these data from different angles (or heads), such as the relationship between temperature rise and equipment load, and the relationship between abnormal sound and changes in the internal structure of the equipment. Then, the structural causal model (SCM) is used to explore the possible causal relationship behind these associations. For example, if the temperature rise is caused by the increase in load, the abnormal sound may be caused by overheating that causes the expansion or deformation of the internal parts of the equipment. In this way, a causal multi-attention graph is generated, which highlights the causal relationship between temperature rise and abnormal sound, forming a focus, indicating that these factors may jointly cause problems with the equipment. By generating such a causal multi-attention graph, the system can more accurately identify and diagnose potential problems with the equipment.
[0059] In this embodiment, by collecting the operation data of power grid equipment in real time and using multimodal data fusion technology and causal multi-attention graph, comprehensive monitoring and intelligent analysis of equipment status are achieved. This method can not only detect abnormal conditions of equipment in a timely manner, such as overheating risks and mechanical failures, but also reveal potential causal links by analyzing the complex relationship between different data sources, thereby accurately locating the root cause of the problem, providing strong support for preventive maintenance, reducing the probability of sudden failures, and improving the reliability and operation efficiency of the system.
[0060] In an exemplary embodiment, according to the calibrated operating parameters, using a data mining algorithm, extracting valid data from the problem data of the power grid equipment includes:
[0061] Based on the calibrated operating parameters, classification algorithm, association rule mining algorithm and anomaly detection algorithm are used to extract valid data from the problem data of power grid equipment.
[0062] For example, when the system detects that the temperature of a transformer exceeds the preset safety threshold (one of the calibrated operating parameters), the system uses a classification algorithm to identify whether the temperature anomaly belongs to a known problem mode; at the same time, the association rule mining algorithm is used to find the relationship between temperature anomaly and equipment load, such as temperature anomaly is more frequent under high load; and then the anomaly detection algorithm is used to identify whether the equipment voltage or current fluctuation exceeds the normal range. Through the application of this series of algorithms, the system can filter out truly meaningful abnormal data from a large number of monitoring data, such as temperature anomaly, load anomaly, or voltage and current fluctuation anomaly, thereby generating an effective data set and providing accurate data support for subsequent problem diagnosis.
[0063] In this embodiment, by combining calibrated operating parameters and a variety of data mining algorithms, effective problem data can be accurately extracted from the real-time operating data of power grid equipment, which not only improves the accuracy and efficiency of problem identification.
[0064] In an exemplary embodiment, cleaning the valid data to obtain target valid data includes:
[0065] Based on historical operation data, the decision tree algorithm is used to preliminarily screen the effective data to obtain preliminary screening data;
[0066] Exemplarily, historical data of equipment voltage fluctuations over a period of time in the past are collected and analyzed using a decision tree algorithm. The decision tree algorithm identifies the association between voltage fluctuations and specific events (such as nearby construction activities) by learning patterns and regularities in historical data. For example, if the system finds that abnormal fluctuations in equipment voltage only occurred once during a certain construction period and returned to normal after the construction, the system will mark this fluctuation as an accidental event and exclude it from further analysis. In this way, the decision tree algorithm can not only predict and make decisions, but also learn from the data which fluctuations are accidental, non-influential or non-problematic data, thereby achieving preliminary screening of valid data and ensuring that the final problem list is more accurate and refined.
[0067] Compare the preliminary screening data with the historical question data in the preset question library for further screening to obtain the target valid data.
[0068] Exemplarily, the system compares the data initially screened by the decision tree algorithm with the historical problem data in the preset problem library to identify those problems that have been confirmed by historical data to be non-problems or have been solved. For example, if the initial screening data contains an abnormal fluctuation in equipment voltage, but the preset problem library shows that the fluctuation was caused by temporary construction in the past and returned to normal after the construction was completed, the system will exclude this fluctuation and no longer include it in further processing. In this way, the system can further filter out the problem data that really needs attention and form a final list of problems to ensure that the list only contains valid problems that need to be dealt with immediately.
[0069] In this embodiment, by combining historical operation data and decision tree algorithm to conduct preliminary screening of valid data, and further comparing with historical problem data in a preset problem library, it is possible to effectively identify and exclude accidental, non-influential or resolved problem data, thereby ensuring that the final generated problem list is more accurate and refined, and improving the efficiency and reliability of problem diagnosis.
[0070] In an exemplary embodiment, the method further comprises:
[0071] Based on the target effective data, it is compared with the corresponding problem data in the preset problem type matching table to determine the power grid problem.
[0072] Exemplarily, for problems that cannot be directly identified, the target valid data obtained through preliminary screening is compared with the preset problem type matching table to identify the specific problem type. If it is found that the voltage fluctuation of a certain device is associated with the "construction of nearby facilities" in the preset problem type matching table, that is, the fluctuation occurs during the construction activity, and the fluctuation characteristics are consistent with the typical fluctuations caused by the construction activity, then the system marks the problem as "voltage fluctuation caused by construction of nearby facilities"; if the monitored terrain changes are associated with geological disasters, it is marked as "problems caused by geological disasters." In this way, the system can ensure that all problems can be accurately identified and classified, thereby forming a final list of problems.
[0073] In this embodiment, by comparing the target valid data with the preset problem type matching table, various problems occurring in the power grid can be accurately identified and classified. In particular, those problems that cannot be directly identified through automated analysis can be effectively identified and classified based on preset matching rules, which not only improves the accuracy and comprehensiveness of problem diagnosis, but also ensures the accuracy and practicality of the problem list, thereby improving the efficiency and effectiveness of power grid maintenance and ensuring the safety and stability of power grid operation.
[0074] In an exemplary embodiment, the method further comprises:
[0075] The grid problems are sent to the user terminal in the form of data tables.
[0076] In this embodiment, by sending power grid problems to user terminals in the form of data tables, maintenance personnel can receive and view specific problems of power grid equipment in real time, improving the timeliness and accuracy of problem handling, thereby enhancing the reliability of power grid operation and maintenance efficiency.
[0077] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.
[0078] Based on the same inventive concept, the embodiment of the present application also provides a power grid problem analysis and determination device for implementing the power grid problem analysis and determination method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more power grid problem analysis and determination device embodiments provided below can refer to the limitations of the power grid problem analysis and determination method above, and will not be repeated here.
[0079] In an exemplary embodiment, as shown in FIG3 , a power grid problem analysis and determination device is provided, comprising: an operation data acquisition module 302 , a problem data determination module 304 , a valid data extraction module 306 , a data cleaning module 308 and a problem determination module 310 , wherein:
[0080] Operation data collection module 302, used to collect real-time operation data of power grid equipment; real-time operation data includes temperature, appearance, vibration, voltage and current;
[0081] A problem data determination module 304 is used to generate a causal multi-attention graph based on the real-time operation data, and determine the problem data of the power grid equipment based on the causal multi-attention graph;
[0082] The effective data extraction module 306 is used to extract effective data from the problem data of the power grid equipment according to the calibrated operation parameters and using the data mining algorithm; the effective data includes temperature abnormality data, appearance abnormality data, abnormal vibration data, abnormal voltage data and abnormal current data; the calibrated operation parameters include the outgoing line interval of the substation, the main transformer capacity, the outgoing line voltage, the feeder length, the main transformer load, the feeder load and the distribution transformer capacity;
[0083] The data cleaning module 308 is used to clean the valid data to obtain the target valid data;
[0084] The problem determination module 310 is used to analyze the target effective data according to the logistic regression algorithm to determine the power grid problem.
[0085] In an exemplary embodiment, the problem data determination module 304 includes:
[0086] A data fusion unit is used to fuse the real-time running data through a multimodal data fusion algorithm based on a causal attention mechanism to obtain fused data;
[0087] The graph generation unit is used to generate a causal multi-attention graph based on the fused data, combining the multi-head attention mechanism and the structural causal model.
[0088] In an exemplary embodiment, the valid data extraction module 306 includes:
[0089] The effective data extraction unit is used to extract effective data from the problem data of the power grid equipment based on the calibrated operating parameters by using a classification algorithm, an association rule mining algorithm and an anomaly detection algorithm.
[0090] In an exemplary embodiment, the data cleaning module 308 includes:
[0091] A data preliminary screening unit is used to perform preliminary screening of valid data based on historical operation data using a decision tree algorithm to obtain preliminary screening data;
[0092] The target valid data determination unit is used to compare the preliminary screening data with the historical question data in the preset question library for further screening to obtain the target valid data.
[0093] In an exemplary embodiment, the problem determination module 310 is further used to compare the target effective data with the corresponding problem data in the preset problem type matching table to determine the power grid problem.
[0094] In an exemplary embodiment, the above-mentioned power grid problem analysis and determination device further includes:
[0095] The data sending module is used to send power grid problems to the user terminal in the form of a data table.
[0096] Each module in the above-mentioned power grid problem analysis and determination device can be implemented in whole or in part by software, hardware and a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.
[0097] In an exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be shown in FIG4. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected via a system bus, and the communication interface is connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store real-time operating data of power grid equipment. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for analyzing and determining power grid problems is implemented.
[0098] Those skilled in the art will understand that the structure shown in FIG. 4 is merely a block diagram of a partial structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.
[0099] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.
[0100] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above method embodiments are implemented.
[0101] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.
[0102] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.
[0103] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.
[0104] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be construed as limiting the scope of the present application. It should be noted that, for a person of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.
Claims
1. A method for analyzing and determining power grid problems, characterized in that: The method comprises: Collecting real-time operating data of power grid equipment; the real-time operating data includes temperature, appearance, vibration, voltage and current; Generate a causal multi-attention graph according to the real-time operation data, and determine the problem data of the power grid equipment according to the causal multi-attention graph; According to the calibrated operating parameters, the valid data in the problem data of the power grid equipment is extracted by using a data mining algorithm; the valid data includes temperature abnormality data, appearance abnormality data, abnormal vibration data, abnormal voltage data and abnormal current data; the calibrated operating parameters include the outgoing line interval, main transformer capacity, outgoing line voltage, feeder length, main transformer load, feeder load and distribution transformer capacity of the substation; Cleaning the valid data to obtain target valid data; The target valid data is analyzed according to a logistic regression algorithm to determine the power grid problem.
2. The method for analyzing and determining power grid problems according to claim 1, characterized in that: Generating a causal multi-attention graph according to the real-time operation data includes: Based on the causal attention mechanism, the real-time operation data is fused through a multimodal data fusion algorithm to obtain fused data; According to the fused data, a causal multi-attention graph is generated by combining a multi-head attention mechanism and a structural causal model.
3. The method for analyzing and determining power grid problems according to claim 1, characterized in that: The extracting valid data from the problem data of the power grid equipment by using a data mining algorithm according to the calibrated operating parameters includes: Based on the calibrated operating parameters, a classification algorithm, an association rule mining algorithm and an anomaly detection algorithm are used to extract valid data from the problem data of the power grid equipment.
4. The method for analyzing and determining power grid problems according to claim 1, characterized in that: The step of cleaning the valid data to obtain target valid data includes: Based on the historical operation data, a decision tree algorithm is used to preliminarily screen the valid data to obtain preliminary screening data; The preliminary screening data is compared with the historical question data in the preset question library for further screening to obtain the target valid data.
5. The method for analyzing and determining power grid problems according to claim 1, characterized in that: The method further comprises: Based on the target valid data, the corresponding problem data in the preset problem type matching table is compared to determine the power grid problem.
6. The method for analyzing and determining power grid problems according to claim 1, characterized in that: The method further comprises: The power grid problem is sent to the user terminal in the form of a data table.
7. A device for analyzing and determining power grid problems, characterized in that: The device comprises: An operation data acquisition module is used to collect real-time operation data of power grid equipment; the real-time operation data includes temperature, appearance, vibration, voltage and current; A problem data determination module, used to generate a causal multi-attention graph according to the real-time operation data, and determine the problem data of the power grid equipment according to the causal multi-attention graph; An effective data extraction module is used to extract effective data from the problem data of the power grid equipment according to the calibrated operating parameters and using a data mining algorithm; the effective data includes temperature abnormality data, appearance abnormality data, abnormal vibration data, abnormal voltage data and abnormal current data; the calibrated operating parameters include the outgoing line interval, main transformer capacity, outgoing line voltage, feeder length, main transformer load, feeder load and distribution transformer capacity of the substation; A data cleaning module, used for cleaning the valid data to obtain target valid data; The problem determination module is used to analyze the target valid data according to a logistic regression algorithm to determine the power grid problem.
8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.
9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.
10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.