Substation hidden danger point risk index model construction method, system, equipment and medium

Abstract

The invention discloses a transformer substation hidden danger point risk index model construction method, system and device and a medium, and belongs to the technical field of transformer substation risk assessment, and the method comprises the steps: collecting multi-dimensional data related to the operation of a target transformer substation; screening key factors influencing the risk of the hidden danger point, and determining the weight of each key factor; analyzing the multi-dimensional data by using a machine learning model, and identifying hidden danger points; constructing a risk assessment model and calculating risk indexes according to the weights of the key factors and the identified hidden danger points; and outputting the risk level of the hidden danger point and corresponding early warning information based on the risk index. By combining multi-dimensional data and utilizing a machine learning algorithm, the equipment operation state can be comprehensively analyzed, potential hidden dangers can be deeply mined, a large amount of historical data can be efficiently processed and analyzed, potential hidden danger points can be automatically recognized, the hidden danger point recognition accuracy is remarkably improved, early warning is ensured, equipment faults are effectively prevented, and the method is suitable for popularization and application. The operation risk of the substation is reduced.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of substation risk assessment, and particularly relates to a substation hidden danger point risk index model construction method, system, device and medium. BACKGROUND

[0002] The substation is an important node of the power transmission and distribution system, and the safety of its operation directly affects the stability of the power grid and the power supply quality. With the expansion of the power system scale, the traditional manual inspection and maintenance method has been unable to meet the growing demand, and there are certain limitations in its accuracy and timeliness. Therefore, how to use modern data analysis, machine learning and intelligent algorithm to construct an efficient and accurate risk assessment model is the key to improving the safe operation level of the substation.

[0003] Although the prior art can realize the prediction and early warning of substation flood prevention risk, it cannot construct a scientific risk assessment and control system, accurately identify hidden danger points of substation equipment, predict potential risks, and formulate corresponding risk warning and control measures to ensure the safe and stable operation of substation equipment, reduce faults and improve management efficiency by using multi-dimensional data analysis and advanced algorithm technology. SUMMARY

[0004] To solve the above technical problems, a substation hidden danger point risk index model construction method is proposed, which includes collecting multi-dimensional data related to the operation of the target substation; screening key factors affecting the risk of hidden danger points and determining the weight of each key factor; using a machine learning model to analyze the multi-dimensional data and identify hidden danger points; constructing a risk assessment model and calculating a risk index according to the weight of the key factors and the identified hidden danger points; and outputting the risk level of the hidden danger points and the corresponding warning information based on the risk index.

[0005] As a preferred scheme of the substation hidden danger point risk index model construction method, before screening the key factors affecting the risk of hidden danger points, the method further includes preprocessing the multi-dimensional data; the preprocessing includes but is not limited to missing value processing, noise data removal and scale unification processing.

[0006] As a preferred scheme of the substation hidden danger point risk index model construction method, the multi-dimensional data includes but is not limited to real-time operation data, environmental monitoring data, equipment maintenance history, inspection records and fault logs.

[0007] As a preferred scheme of the substation hidden danger point risk index model construction method, wherein: the missing value processing includes mean filling or interpolation filling based on similar samples; the noise data removal includes based on experience threshold rejection or using an abnormal detection algorithm to remove abnormal points.

[0008] As a preferred scheme of the substation hidden danger point risk index model construction method, wherein: the weight of each key factor is determined, including based on the equipment working characteristics and historical failure data, establishing a hierarchical structure model including target layer, criterion layer and scheme layer; inviting experts to compare the factors of the criterion layer and constructing a judgment matrix; calculating the weight vector of each factor by geometric mean method, and performing consistency test on the judgment matrix.

[0009] As a preferred scheme of the substation hidden danger point risk index model construction method, wherein: the training of the machine learning model includes using historical data containing known hidden danger point labels, inputting data of each influencing factor, and outputting corresponding hidden danger point existence state; using support vector machine, decision tree or neural network algorithm for training, support vector machine is suitable for high-dimensional small sample data, decision tree is used for rule explanation, and neural network is used for identifying complex nonlinear relationship; after training, the model is applied to new real-time operation data to identify potential hidden danger points.

[0010] As a preferred scheme of the substation hidden danger point risk index model construction method, wherein: the risk level is divided based on the calculated risk index, at least three levels are set, and when the comprehensive risk score exceeds the set threshold, a warning is triggered.

[0011] Another object of the present application is to provide a substation hidden danger point risk index model construction system, which can effectively solve the problem of being unable to construct a scientific risk assessment and control system, and accurately identify the hidden danger points of substation equipment by using multi-dimensional data analysis and advanced algorithm technology.

[0012] As a preferred scheme of the substation hidden danger point risk index model construction system, characterized in that, comprising: a data acquisition module for collecting multi-dimensional data related to the operation of the target substation; a weight calculation module for screening key factors affecting hidden danger point risk and determining the weight of each key factor; a hidden danger analysis module for analyzing the multi-dimensional data using a machine learning model to identify hidden danger points; a risk assessment module for constructing a risk assessment model and calculating a risk index based on the weight of the key factors and the identified hidden danger points; a risk warning module for outputting the risk level of the hidden danger point and the corresponding warning information based on the risk index.

[0013] A computer device comprises a memory and a processor, the memory stores a computer program, and the processor implements the steps of the substation hidden danger point risk index model construction method when executing the computer program.

[0014] A computer readable storage medium stores a computer program, and the computer program implements the steps of the substation hidden danger point risk index model construction method when executed by a processor.

[0015] The present application has the following advantages: by combining multi-dimensional data such as real-time operation data, environmental monitoring data, fault logs, etc., and using advanced machine learning algorithms, the device operation state can be comprehensively analyzed, potential hidden dangers can be deeply mined, a large amount of historical data can be efficiently processed and analyzed, potential hidden danger points can be automatically identified, the accuracy of hidden danger point identification can be significantly improved, early warning can be ensured and equipment failure can be effectively prevented, and the operation risk of the substation can be reduced.

[0016] The multi-dimensional evaluation method of analytic hierarchy process and grey correlation analysis is used, and the weight is quantified by combining expert scoring method, so that the scientificity and objectivity of each influencing factor in the evaluation process are ensured, the expert scoring method ensures the full use of professional knowledge, the analytic hierarchy process makes the relationship between factors more clear and the hierarchy more clear, the grey correlation analysis further reveals the correlation between hidden danger points, improves the comprehensiveness of evaluation, reduces the deviation of human judgment, makes the risk evaluation result more accurate, and improves the reliability and effectiveness of decision-making.

[0017] Through the control strategy formulated based on the comprehensive risk evaluation result, the scheme can realize the priority maintenance of high-risk equipment and the timely replacement of aging equipment, reduce the equipment failure rate, and at the same time, through regular risk evaluation and optimization adjustment, it can ensure that the risk model always keeps consistent with the actual operation state, so that the substation can predict and respond to potential risks in advance, reduce the occurrence of sudden failures, improve the emergency response speed and the refinement degree of equipment management, improve the safety of equipment, prolong the service life of equipment, and optimize the overall operation efficiency. BRIEF DESCRIPTION OF DRAWINGS

[0018] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiment description. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without creative labor.

[0019] Fig. 1 A substation hidden danger point risk index model construction method provided by an embodiment of the present application is provided.

[0020] Fig. 2 Another flowchart of a substation hidden danger point risk index model construction method provided for an embodiment of the present application. DETAILED DESCRIPTION

[0021] In order to make the above objectives, characteristics and advantages of the present application more apparent, obvious and easy to understand, the specific embodiments of the present application will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor should fall within the scope of protection of the present application.

[0022] Embodiment 1, with reference to Figs. 1-2 For the first embodiment of the present application, the embodiment provides a substation hidden danger point risk index model construction method, comprising:

[0023] Step 1: Collect multi-dimensional data related to the operation of the target substation;

[0024] In this embodiment, the multi-dimensional data of a substation is collected, including real-time operation data such as voltage, current, power, etc., environmental monitoring data such as temperature, humidity, wind speed, etc., equipment maintenance history such as repair time, replacement parts, etc., inspection records such as equipment appearance, abnormal sound, etc. recorded by the inspection personnel, and fault logs such as past fault occurrence time, faulty equipment, fault cause, etc.

[0025] It should be noted that the collected data may have missing values, noise and other problems, so data preprocessing is performed.

[0026] In an optional embodiment of the present application, for missing values, the mean filling method is used for filling, for noise data, by setting a threshold to remove obvious abnormal noise points, and then after standardization and normalization processing of the data, these high-quality data will be fully put into the subsequent substation hidden danger point risk index model construction process,

[0027] In a preferred embodiment of the present application, during the model training stage, complete and scale-unified data enables the model to more accurately learn the complex correlation patterns between the dimensions of data and the risk of hidden danger points, avoiding training bias caused by poor data quality. During the model verification stage, the preprocessed data can generate reliable evaluation indicators, accurately reflecting the performance of the model and providing a strong basis for model optimization. In the actual application stage, by inputting the preprocessed real-time data into the trained model, the risk assessment results of the hidden danger points of the substation equipment can be quickly and accurately obtained, potential risks can be discovered in a timely manner, and timely and accurate information support can be provided for the subsequent risk control measures, effectively ensuring the stable operation of the substation and improving the overall safety management level. The different dimensions of data have the same scale, avoiding the influence of different dimensions on the training effect of the subsequent model.

[0028] Further, by collecting multi-dimensional data and preprocessing, the accuracy and stability of the substation hidden danger point risk index model can be improved. The missing value filling guarantees the integrity of the data, the noise removal eliminates abnormal interference, and the data standardization and normalization ensure that the data of different dimensions have the same scale, so that the model can more effectively identify potential risks, optimize the evaluation results, and improve the accuracy of hidden danger point prediction and the scientificity of decision-making. This lays a solid data foundation for subsequent steps such as factor screening and weighting, hidden danger point identification, etc.

[0029] Step 2: Screen the key factors affecting the risk of hidden danger points and determine the weight of each key factor;

[0030] Based on the working characteristics and historical failure data of the substation equipment, factors influencing the risk of hidden trouble points are screened out, for example, for transformer equipment, factors such as oil temperature, oil level, winding temperature and load rate are screened out as factors influencing the risk of hidden trouble points, a multi-dimensional evaluation method combining analytic hierarchy process, grey correlation analysis and expert scoring method is used, first, a hierarchical structure model is established, the target layer is set as the risk evaluation of hidden trouble points of substation transformer equipment, factors such as oil temperature, oil level, winding temperature and load rate are screened out as the criterion layer, the scheme layer is the measures of hidden trouble points with different risk levels or the risk level division, experts are invited to compare and score the factors in the criterion layer two by two, a judgment matrix is constructed, the weight vector is calculated by geometric mean method and consistency check is carried out, the weight of each factor is determined, then grey correlation analysis is carried out, the ideal optimal hidden trouble point risk state is selected as the reference sequence, and different hidden trouble points or period data are used as the comparison sequence, after dimensionless processing of the data, the grey correlation coefficient and the grey correlation degree are calculated, which reflect the correlation degree of the comparison sequence and the reference sequence, finally, the weight determined by the analytic hierarchy process and the grey correlation degree obtained by the grey correlation analysis are combined, the comprehensive risk score is calculated, the risk level of the hidden trouble point is divided, a scientific and objective basis is provided for subsequent hidden trouble point identification and risk evaluation, the reliability and accuracy of decision-making are improved, the model accurately focuses on key factors, and the risk evaluation efficiency and effect are improved.

[0031] Step 3: analyzing the multi-dimensional data by using a machine learning model to identify hidden trouble points;

[0032] In one preferred embodiment of the present application, a machine learning algorithm is used to train historical data to identify potential hidden trouble points. Taking support vector machine as an example, the data in the collected historical data that is known to have hidden trouble points is used as the training set, where the input is the data of each influencing factor and the output is the label of whether there is a hidden trouble point. After training the support vector machine model, it is applied to new real-time operation data to classify the operation state of the substation equipment and determine whether there is a hidden trouble point.

[0033] In an optional embodiment of the present application, a decision tree algorithm can also be used to quickly determine hidden trouble points according to the value range of each factor and the decision rule, for example, when the oil temperature exceeds a certain threshold and the load rate is high, it is determined that there may be an overheating hidden trouble point. In addition, a neural network algorithm can also be used to automatically identify potential hidden trouble points through learning a large amount of historical data, thereby achieving efficient and accurate identification of hidden trouble points of substation equipment.

[0034] In a preferred embodiment of the present application, the machine learning algorithm (taking the support vector machine as an example) is suitable for processing high-dimensional data and small sample data sets. In the identification of hidden danger points in a substation, when the collected influence factor data has a high dimension and the sample size is relatively moderate, the support vector machine can effectively construct a classification model. It finds a hyperplane to maximize the classification interval to distinguish the data of hidden danger points and non-hidden danger points. This method is particularly suitable for scenarios with complex data characteristics and high-precision classification requirements.

[0035] In another optional embodiment of the present application, a decision tree algorithm can be used to identify hidden danger points. The decision tree algorithm is suitable for scenarios with obvious hierarchical structure of data characteristics and high requirements for rule interpretability. In the identification of hidden danger points in a substation, if there is a clear logical relationship between each influence factor and the hidden danger point, and quick judgment and intuitive explanation are required, the decision tree algorithm can quickly judge the hidden danger points according to the preset rules. For example, when the oil temperature exceeds a certain threshold and the load rate is high, the decision tree can quickly judge that there may be an overheating hidden danger point. The advantage of this method is that the decision-making process is transparent, easy to understand and explain.

[0036] In another optional embodiment of the present application, a neural network algorithm can be used to identify hidden danger points. The neural network algorithm is suitable for processing a large amount of complex data and nonlinear relationships. It can automatically learn complex patterns and associations in data. In the identification of hidden danger points in a substation, when a large amount of historical data is collected and there are complex nonlinear relationships in the data, the neural network algorithm can automatically identify potential hidden danger points through learning a large amount of historical data. This method is particularly suitable for scenarios with complex data relationships that are difficult to describe with simple models, and can achieve efficient and accurate identification of hidden danger points in substation equipment.

[0037] It should be noted that the use of advanced machine learning algorithms can comprehensively analyze the operating state of equipment, deeply mine potential hidden dangers, efficiently process and analyze a large amount of historical data, automatically identify potential hidden danger points, significantly improve the accuracy of hidden danger point identification, ensure early warning and effectively prevent equipment failure, reduce the operating risk of a substation, and provide accurate hidden danger point information for subsequent risk assessment model construction.

[0038] Step 4: Construct a risk assessment model and calculate a risk index according to the weights of the key factors and the identified hidden danger points;

[0039] In step 4, a comprehensive risk assessment model is constructed based on a multi-dimensional evaluation method. The collected multi-dimensional data is integrated into a unified data platform or database, including real-time operating data, environmental monitoring data, equipment maintenance history, inspection records, and fault logs, etc. to ensure the completeness and consistency of the data, and necessary cleaning and preprocessing are performed to eliminate noise and missing values.

[0040] In a preferred embodiment of the present application, the weights of the evaluation factors are first determined by the analytic hierarchy process, such as the weight of the equipment failure rate being 0.4, the weight of the environmental factor being 0.3, etc., and then the gray correlation analysis is used to analyze the correlation between different hidden danger points, for example, it is found that there is a strong correlation between the equipment aging and the overheating hidden danger point, such as the probability of overheating rising by 30% for every 20% increase in the aging degree. The weights of the factors are determined by the analytic hierarchy process, such as the weight of the equipment aging being 0.4, the weight of the overheating hidden danger point being 0.3, etc. The correlation between the two is quantified by the gray correlation analysis, and the gray correlation degree is 0.7. The comprehensive risk score is obtained by multiplying the scores of each factor by the weight and then summing them up, such as the equipment aging score of a certain equipment hidden danger point being 0.6, the overheating hidden danger point score being 0.8, and the other factor score being 0.5, and the comprehensive risk score being 0.6*0.4+0.8*0.3+0.5*0.3=0.6, which is divided into medium risk according to the standard. Different risk levels of hidden danger points correspond to different control measures, high risk needs to be handled first, medium risk needs to be monitored regularly, and low risk needs to be normally inspected, which provides a quantitative basis for subsequent risk control and ensures the safe operation of the substation.

[0041] In a preferred embodiment of the present application, the steps of gray correlation analysis are as follows: first, determine the reference sequence (the sequence reflecting the main behavior of the system) and the comparison sequence (the sequence of each factor affecting the behavior of the system), then perform non-dimensionalization processing on the original data to eliminate the influence of dimension and order of magnitude, then calculate the gray correlation coefficient of each comparison sequence and the reference sequence at each time point, and finally calculate the average correlation coefficient of each comparison sequence and the reference sequence, the larger the average correlation coefficient, the higher the correlation degree of the factor with the reference sequence.

[0042] In a preferred embodiment of the present application, the steps of the analytic hierarchy process include: constructing the decision hierarchy structure, which is the first step of the analytic hierarchy process, and the purpose is to decompose the complex problem into different levels, including the target layer, the criterion layer and the scheme layer. Through the hierarchical relationship of each factor, the foundation is laid for the subsequent steps.

[0043] After constructing the decision hierarchy structure, a judgment matrix needs to be constructed, which is obtained by comparing the scheme layer based on the criterion layer, and these comparison values reflect the relative importance of each factor.

[0044] After constructing the judgment matrix, the weight values of each factor are calculated by the eigenvector method, geometric mean method, etc., and the weight values reflect the relative importance of each factor in the target decision, which provides a quantitative basis for the subsequent decision.

[0045] Consistency check is performed to ensure that the judgment matrix has logical consistency. The consistency index (CI) and the consistency ratio (CR) are calculated. If the CR is less than 0.1, it is considered that the judgment matrix has acceptable consistency, otherwise the judgment matrix needs to be adjusted.

[0046] It should be noted that the combination of the analytic hierarchy process and the grey correlation analysis can effectively improve the accuracy and comprehensive evaluation ability of the risk index model of the substation hidden danger points. The analytic hierarchy process determines the weight of each evaluation factor and reasonably quantifies the influence degree of each factor, providing a scientific basis for risk assessment. The grey correlation analysis is used to analyze the correlation between different hidden danger points and reveal the potential relationship between the hidden danger points, thereby more comprehensively evaluating the risk, improving the precision of risk assessment, helping to better identify potential hidden dangers, optimizing safety management and decision-making processes, and providing strong support for subsequent risk early warning and control strategy formulation.

[0047] Step 5: Based on the risk index, output the risk level of the hidden danger point and the corresponding early warning information.

[0048] According to the output results of the constructed risk assessment model, set the risk threshold, for example, set the system to automatically issue a warning when the comprehensive risk score of the hidden danger point exceeds 0.7, reminding the operation and maintenance personnel to pay attention and handle it in time. At the same time, based on historical risk data, trend analysis and prediction model construction are carried out to predict future risk trends.

[0049] If it is found that the risk of hidden danger points of a certain device shows a gradually rising trend, take corresponding preventive measures in advance, such as arranging maintenance plans in advance, preparing spare parts, etc. In terms of risk control, for high-risk equipment, priority is given to maintenance, potential hazards are discovered and eliminated in time, for equipment with high aging degree, replacement plan is made, gradual replacement and update are carried out, and risk assessment model is optimized and adjusted regularly, so that it can better adapt to the actual operation condition of substation equipment, continuously improve the safety management level of substation, and ensure its stable operation.

[0050] Through the control strategy formulated based on the comprehensive risk assessment results, the priority maintenance of high-risk equipment and the timely replacement of aging equipment can be realized, and the equipment failure rate can be reduced. At the same time, through regular risk assessment and optimization adjustment, it can ensure that the risk model always keeps consistent with the actual operation condition, so that the substation can foresee and respond to potential risks in advance, reduce the occurrence of sudden failures, improve the speed of emergency response and the degree of refinement of equipment management, improve the safety of equipment, prolong the service life of equipment, and optimize the overall operation efficiency. In addition, based on the trend analysis and prediction model of historical risk data, the forward-looking and early warning ability of the risk index model of substation hidden danger points can be effectively improved, providing a scientific basis for future risk trends, enhancing the initiative and preventive nature of risk management, and improving the safety guarantee level of the substation.

[0051] Embodiment 2, which is a second embodiment of the present application, differs from the previous embodiment in that:

[0052] The functions described can be implemented in software, firmware, hardware, or any combination thereof. If implemented in software and as an independent application, it can be stored in a one or more computer-readable storage media, such as a floppy disk, a hard disk, a CD-ROM, a DVD, a ROM, a RAM, a magnetic tape, a magneto-optical disk, or the like. The computer-readable storage media is distributed among computers to be used to distribute the computer program.

[0053] The logic and / or steps represented in the flowcharts and / or described herein, for example, can be considered as a sequence of instructions to cause a processor to perform a function. The logic and / or steps can be embodied in a computer-readable medium to cause a processor to perform the logic and / or steps. The computer-readable medium can be a machine-readable storage device, a machine-readable storage medium, or a memory device. The memory device can include, but is not limited to, any suitable device for storing data, including floppy disks, hard disks, optical storage devices, tape, nonvolatile solid-state memory, and the like. The memory device can store data which to be communicated using the present application. The computer-readable medium can be a machine-readable signal medium or a machine-readable transmission medium. The computer-readable signal medium can include a computer-readable storage medium and / or a computer-readable transmission medium. The computer-readable storage medium can include any suitable device for storing data to be transmitted using the present application. The computer-readable transmission medium can include, but is not limited to, carrier waves, transmissions through the Internet, wireless-based transmissions, and the like.

[0054] More specific examples (a non-exhaustive list) of the computer-readable medium include the following: an electrical connection (electronic) having one or more wires, a portable computer diskette (magnetic), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, and a portable compact disc read-only memory (CD-ROM). Additionally, the computer-readable medium can also be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, for example, via optical scanning of the paper or other medium, then compiled, interpreted, or otherwise processed in a suitable manner, if necessary, and then stored in a computer memory.

[0055] It should be understood that various parts of the present application can be realized in hardware, software, firmware, or a combination thereof. In the above-described embodiments, a plurality of steps or methods can be realized with software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if realized in hardware, and as in another embodiment, it can be realized with a combination of any of the following technologies known in the art: discrete logic circuitry having logic gates for implementing logic functions on data signals, application specific integrated circuits having appropriate combinational logic gates, programmable gate arrays (PGA), field programmable gate arrays (FPGA), and the like.

[0056] Embodiment 3, a third embodiment of the present application, which provides a substation hidden danger point risk index model construction system, comprising.

[0057] A data collection module is configured to collect multi-dimensional data related to the operation of the target substation.

[0058] A weight calculation module is configured to screen key factors affecting the risk of hidden danger points and determine the weights of the key factors.

[0059] A hidden danger analysis module is configured to analyze the multi-dimensional data using a machine learning model to identify hidden danger points.

[0060] A risk assessment module is configured to construct a risk assessment model and calculate a risk index based on the weights of the key factors and the identified hidden danger points.

[0061] A risk warning module is configured to output the risk level of the hidden danger points and corresponding warning information based on the risk index.

[0062] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present application and are not limiting. Although the present application has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solutions of the present application can be modified or replaced equivalently without departing from the spirit and scope of the technical solutions of the present application, and they should be covered in the scope of the claims of the present application.

Claims

1. A method for constructing a risk indicator model for potential danger points in a substation, characterized by: include, Collect multi-dimensional data related to the target substation operation; Screen the key factors that affect the risk of hidden danger points and determine the weight of each key factor; Analyze the multi-dimensional data using a machine learning model to identify potential risks; Based on the weights of key factors and identified hidden dangers, a risk assessment model is constructed and risk indicators are calculated; Based on the risk indicators, the risk level of the hidden danger point and the corresponding early warning information are output.

2. The method for constructing a risk indicator model for potential danger points in a substation according to claim 1, wherein: Before screening the key factors that affect the risk of hidden danger points, it also includes: Preprocessing the multi-dimensional data; The preprocessing includes but is not limited to missing value processing, noise data removal and scale unification processing.

3. The method for constructing a risk indicator model for potential danger points in a substation according to claim 2, wherein: The multi-dimensional data includes but is not limited to real-time operation data, environmental monitoring data, equipment maintenance history, inspection records and fault logs.

4. The method for constructing a risk indicator model for potential danger points in a substation according to claim 3, wherein: The missing value processing includes filling with mean value or interpolation based on similar samples; The noise data removal includes removing outliers based on an empirical threshold or using an outlier detection algorithm.

5. The method for constructing a risk indicator model for potential danger points in a substation according to claim 4, characterized in that: The weight of each key factor is determined as follows: Based on equipment operating characteristics and historical fault data, a hierarchical model consisting of a target layer, a criterion layer, and a solution layer is established; Invite experts to compare the factors at the criterion level and construct a judgment matrix; The weight vector of each factor was calculated by the geometric mean method, and the judgment matrix was tested for consistency.

6. The method for constructing a risk indicator model for potential danger points in a substation according to claim 5, characterized in that: The training of the machine learning model includes, Use historical data containing known hidden danger point labels, input the data of various influencing factors, and output the corresponding hidden danger point existence status; Support vector machines, decision trees, or neural network algorithms are used for training. Support vector machines are suitable for high-dimensional small sample data, decision trees are used for rule interpretation, and neural networks are used to identify complex nonlinear relationships. After training is complete, the model is applied to new real-time operational data to identify potential risk points.

7. The method for constructing a risk indicator model for potential danger points in a substation according to claim 6, characterized in that: The risk level division is based on the calculated risk indicators, with at least three levels set, and when the comprehensive risk score exceeds a set threshold, an early warning is triggered.

8. A system for constructing a risk indicator model for a potential danger point in a substation, applying the method for constructing a risk indicator model for a potential danger point in a substation as claimed in any one of claims 1 to 7, characterized in that: include: Data acquisition module, used to collect multi-dimensional data related to the operation of the target substation; The weight calculation module is used to screen the key factors that affect the risk of hidden danger points and determine the weight of each key factor; A hidden danger analysis module is used to analyze the multi-dimensional data using a machine learning model to identify hidden danger points; The risk assessment module is used to build a risk assessment model and calculate risk indicators based on the weights of key factors and identified potential hazards; The risk warning module is used to output the risk level of hidden danger points and corresponding warning information based on risk indicators.

9. 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 for constructing a substation hidden danger point risk indicator model according to any one of claims 1 to 7 are implemented.

10. 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 a method for constructing a substation hidden danger point risk indicator model according to any one of claims 1 to 7 are implemented.

Images