Transformer substation system dynamics safety assessment method considering mutual verification

Abstract

The invention relates to a transformer substation system dynamics safety assessment method considering mutual verification. The method comprises the following steps: acquiring a plurality of mutual verification characteristic variables corresponding to key equipment in a transformer substation system; based on the maximum mutual information coefficient and grey correlation analysis, obtaining a strong correlation mutual verification set; variables in the mutual verification set serve as independent variables, variables to be verified mutually serve as dependent variables, and the relation between the dependent variables and the independent variables is built through a ridge regression method; constructing a multi-dimensional comprehensive fault probability function and a fault probability function of mutual influence between devices by calculating a univariate error; and dynamic safety evaluation of the transformer substation system is realized by constructing a system dynamic flow diagram. According to the method, the implicit incidence relation between the monitoring variables is mined through the method of combining feature optimization, regression analysis and system dynamics, the utilization rate of the monitoring variables is effectively improved, the operation state of the transformer substation monitoring equipment is evaluated from the perspective of data, and the accuracy and reliability of safety evaluation are improved.

Description

Technical Field

[0001] The invention relates to the technical field of substation safety monitoring, and in particular to a substation system dynamics safety assessment method considering mutual verification. Background Art

[0002] With the rapid development of digital substations, a wide variety of monitoring devices have been introduced into the power system. By comprehensively analyzing a large amount of monitoring data from electrical and non-electrical equipment, safety accidents can be prevented more effectively. However, most of these monitoring devices are currently independent of each other, and some devices only evaluate the safety of equipment operation based on a single monitoring variable, failing to achieve comprehensive analysis of multiple variables. In addition, it is an important research task to explore the implicit relationship model between rich monitoring variables and apply it to the comprehensive evaluation of equipment safety.

[0003] Chinese patent application number CN 117893032 A discloses a substation operation and maintenance health analysis method and system based on digital twins. The original database is constructed based on the historical data of the electrical variables of the power system and the operation simulation, and the dynamic safety assessment model of the power system is constructed using genetic algorithms and BP neural networks to conduct power system safety assessment. However, this method does not consider the important impact of non-electrical variables, including environmental variables, on the power system. Construct a digital twin model of the substation, build a relationship mapping for each virtual device; obtain the physical parameters and real-time operation data of the physical device, and display the dynamic data through the virtual device to monitor the operation status of the physical device. However, this method focuses on the relationship between devices, the analysis of the monitoring data is not comprehensive enough, and the relationship between the monitoring variables is not fully considered.

[0004] In summary, there is currently a lack of a substation system dynamics safety assessment method to solve or partially solve the above-mentioned problems. Summary of the invention

[0005] The purpose of the present invention is to overcome the defects of the above-mentioned prior art and to provide a substation system dynamic safety assessment method taking mutual verification into consideration, so as to solve or partially solve the problem that the monitoring devices in the existing detection system are independent of each other and lack consideration of the implicit correlation between the characteristic variables.

[0006] The purpose of the present invention can be achieved by the following technical solutions:

[0007] The present invention provides a substation system dynamics safety assessment method considering mutual verification, comprising the following steps:

[0008] Step S1, obtaining multiple mutual verification characteristic variables corresponding to key equipment in the substation system;

[0009] Step S2, based on the maximum mutual information coefficient and grey correlation analysis, a strongly correlated mutual verification set is obtained;

[0010] Step S3, taking the variables in the mutual verification set as independent variables and the variables to be mutually verified as dependent variables, and constructing the relationship between the dependent variables and the independent variables by using the ridge regression method;

[0011] Step S4, constructing a mutual verification fault probability function by calculating the single variable error, combining it with the multi-dimensional comprehensive fault probability function and the mutual influence fault probability function between devices to form a substation safety assessment fault probability function;

[0012] Step S5, realizing the substation system dynamics safety assessment by constructing a system dynamics flow diagram.

[0013] As a preferred technical solution, the step S2 includes the following sub-steps:

[0014] Step S201, calculating the grey correlation coefficient and the maximum mutual information coefficient between each mutual verification feature variable;

[0015] Step S202, weighting the grey correlation coefficient and the maximum mutual information coefficient to obtain a weighted correlation between mutual verification feature variables;

[0016] Step S203: construct a mutual verification set based on the weighted association degree.

[0017] As a preferred technical solution, in step S202, the weighted correlation degree is calculated using the following formula:

[0018]

[0019] Among them, J i is the weighted correlation of the ith mutual verification feature variable, n is the total number of mutual verification feature variables, MIC i (A,B i ) is the mutual verification dependent variable A and the mutual verification characteristic variable B i The maximum mutual information coefficient between i (A,B i ) is the mutual verification dependent variables A and B i Grey correlation coefficient between .

[0020] As a preferred technical solution, in step S203, the process of constructing a mutual verification set includes:

[0021] The mutual verification feature variables are arranged according to the weighted correlation, and a feature with the largest weighted correlation is selected each time to be added to the preferred set to realize the construction of the mutual verification set.

[0022] As a preferred technical solution, the step S3 includes:

[0023] Through ridge regression analysis, variables with linear relationships in the mutual verification set are extracted. The variables in the mutual verification set are used as independent variables, and the variables to be mutually verified are used as dependent variables. The regression coefficients are obtained through regression analysis to realize the construction of the relationship between the dependent variable and the independent variable.

[0024] As a preferred technical solution, the univariate error p k The calculation is done using the following formula:

[0025]

[0026] Among them, ξ k is the kth mutual verification characteristic variable verification difference, ξ k ′ is the threshold value of the kth mutual verification feature variable verification difference, X k is the monitoring value of the kth mutual verification characteristic variable, is the check value of the kth mutual check characteristic variable, when ξ k Greater than the test threshold ξ k ', it is determined that the monitored variable is abnormal, and at the same time, an alarm is issued to the monitoring device corresponding to the monitored variable.

[0027] As a preferred technical solution, in step S4, the process of constructing the multi-dimensional comprehensive fault probability function and the fault probability function of mutual influence between devices includes the following steps:

[0028] Step S401, constructing a single variable failure probability function for the device from the electrical signal dimension, the device status index dimension and the operating environment index dimension;

[0029] Step S402, based on the single variable failure probability function of the device, calculate the comprehensive failure probability function corresponding to each device by series connection;

[0030] Step S403, based on the comprehensive failure probability function corresponding to each device, calculate the mutual influence failure probability function between devices.

[0031] As a preferred technical solution, the following steps are also included:

[0032] Step S6, building a substation safety assessment system based on a microservice framework.

[0033] As a preferred technical solution, in step S1, key equipment includes transformers, busbars, cable lines and circuit breakers.

[0034] As a preferred technical solution, in the step S1, the mutual verification characteristic variables include electrical signals, equipment status indicators and operating environment indicators, wherein the electrical signals include load current, operating voltage and switch signals, the equipment status indicators specifically include circulating current, core grounding current, clamp grounding current, partial discharge, main transformer oil temperature, main transformer oil level height, main transformer oil level ratio, equipment temperature and SF6 gas pressure, and the operating environment indicators specifically include water level, humidity, temperature and equipment air chamber temperature.

[0035] Compared with the prior art, the present invention has at least one of the following beneficial effects:

[0036] (1) Fully explore the implicit correlation between each characteristic variable: The implicit correlation between monitoring variables is explored by combining feature optimization and regression analysis with system dynamics, which effectively improves the utilization rate of monitoring variables, evaluates the operating status of substation monitoring equipment from a data perspective, and improves the accuracy and reliability of safety assessment.

[0037] (2) Breaking the independence of monitoring devices: A substation operation safety assessment system based on system dynamics was established, breaking the barriers between equipment assessment and substation assessment, achieving a transition from individual to overall, from equipment to network, solving the problem of independence between substation online monitoring systems and difficulty in integrating monitoring information, realizing joint prevention and control of power equipment, preventing substation safety accidents caused by multiple accidental factors, and effectively improving the safety level of power grid operation. Combining data analysis and system dynamics for substation safety assessment can effectively combine various monitoring systems and solve the problem of independent information islands between monitoring systems. At the same time, the comprehensive analysis of various monitoring data using system dynamics methods improves the comprehensiveness of substation safety assessment and can effectively solve the problem of accidental failures occurring in multiple conditions at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 A schematic diagram of the overall framework of security assessment in the embodiment;

[0039] Figure 2 It is a flow chart of the feature optimization steps in the embodiment;

[0040] Figure 3 Construct a flow chart for the chain guard system dynamics equation in the embodiment;

[0041] Figure 4 It is a safety assessment flow chart in the embodiment;

[0042] Figure 5 Schematic diagram of the physical framework of the substation safety monitoring system in the embodiment. DETAILED DESCRIPTION

[0043] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0044] Example 1

[0045] In response to the problem of mutual independence between existing monitoring systems in substations and the problem of insufficient exploration of implicit correlations between monitoring variables, this embodiment provides a substation system dynamics safety assessment method that takes mutual verification into consideration, which fully considers the mutual influence between monitoring variables in the substation, the influence of each variable on the safety level of substation equipment, and the topological relationship between each device. Through comprehensive analysis of substation operation data, this method can effectively associate multi-dimensional data, improve data utilization efficiency, and deeply explore the correlation between data, realizing a comprehensive safety assessment of substation primary equipment and auxiliary control equipment, thereby significantly improving the overall safety level of power grid operation.

[0046] See also Figure 1 , the method comprises the following steps:

[0047] Step S1, select important equipment for substation safety assessment and build a monitoring variable system. Specifically, this step includes the following sub-steps:

[0048] Step S101, selecting the most representative and most critical equipment of the substation: transformer, busbar, cable line and circuit breaker;

[0049] Step S102, selecting the most representative key monitoring feature of the equipment in step S101.

[0050] Specifically, the key features cover three dimensions: electrical signals, equipment status indicators, and operating environment indicators. The key features of the gas signal dimension are load current, operating voltage, and switch signal; the equipment status indicator dimension is specifically circulating current, core grounding current, clamp grounding current, partial discharge, main transformer oil temperature, main transformer oil level height, main transformer oil level ratio, equipment temperature, and SF6 gas pressure; the operating environment indicator dimension is specifically water level, humidity, temperature, and equipment gas chamber temperature.

[0051] Step S2, determining a variable set with a larger correlation relationship based on the maximum mutual information coefficient and the characteristic variable optimization method of grey correlation analysis. Specifically, this step includes the following sub-steps:

[0052] Step S201, calculating the grey correlation coefficient and the maximum mutual information coefficient between each feature variable;

[0053] Mutually check the dependent variable A and the characteristic variable B i The maximum mutual information coefficient between i (A,B i ); A and B i The grey correlation coefficient is recorded as r i (A,B i );

[0054] Step S202, calculating the weighted correlation between the variables;

[0055] Since the maximum mutual information coefficient measures the influence of the characteristic variable on the mutual verification dependent variable, its weight reflects the effectiveness of the characteristic variable, and the grey correlation degree quantifies the consistency between the characteristic variable and the mutual verification dependent variable, the maximum mutual information weight is combined with the grey correlation degree, and the feature optimization method based on weighted correlation degree is adopted. The steps for optimizing the mutual verification characteristic variables based on weighted correlation degree are as follows: Figure 1 As shown in Figure 2, the calculation formula for weighted association is:

[0056]

[0057] Where: J i is the weighted correlation of the ith mutual verification feature variable; n is the total number of mutual verification feature variables.

[0058] Arrange the calculated weighted correlations in descending order, select a feature with the largest weighted correlation each time and add it to the preferred set, and remove it from the set to be preferred. The weight formula for feature selection is:

[0059]

[0060] Where: J s is the sum of the weighted correlations of the mutual verification features in the preferred set; i is the weight of the i-th feature optimization. When this value is less than the threshold α, it is considered that the mutual verification feature screening is completed.

[0061] Step S203: establishing a mutual verification set.

[0062] In view of the importance of characteristic variables to the transformer and the results of the correlation calculation in the previous section, seven characteristic variables, including the operating temperature, oil temperature, ambient temperature, oil level, oil level ratio, clamp grounding current, and core grounding current of the transformer, were selected for mutual verification. The weighted correlation between each characteristic variable was calculated to perform feature optimization. According to the actual operation data calculation results of a transformer, the weight of the weighted correlation was taken as 0.12, which means that when the weight of the feature optimization is less than 0.12, the correlation between the two characteristic variables can be ignored.

[0063] From the feature optimization results, the optimal set of feature variables for each variable can be obtained as follows:

[0064] S1={X4,X5,X8,X2,X3,X9,X 11};S2={X4,X5,X8,X1,X3,X9,X7};

[0065] S3={X8,X2,X1,X4,X5,X9}; S4={X2,X1,X9,X5,X3,X8,X7};

[0066] S5={X2,X1,X9,X 12 ,X8,X4,X3}; S6={X7,X5,X 10 ,X2,X1,X9};

[0067] S7={X5,X 10 ,X6,X9,X1,X2,X4}.

[0068] Among them, X1~X 12 They represent 12 variables respectively, namely operating temperature, oil temperature, ambient temperature, oil level height, oil level ratio, clamp grounding current, core grounding current, on-load ventilator temperature, main ventilator temperature, high current value, main ventilator humidity, and on-load ventilator humidity; S1~S7 respectively represent the feature optimization set of 7 mutually verified variables, namely transformer operating temperature, oil temperature, ambient temperature, oil level height, oil level ratio, clamp grounding current, and core grounding current.

[0069] Step S3, using the ridge regression method to establish a functional relationship model between monitoring variables.

[0070] Due to the high degree of collinearity between variables, the ridge regression method is used to establish a model between mutually verified variables, so as to avoid the interference of multicollinearity between variables. The specific steps are as follows: First, for variables with linear relationships, ridge regression analysis is used to check the multicollinearity of mutually verified feature variables, and the variables in the feature optimization set are used as independent variables, and the variables to be verified are used as dependent variables. Regression fitting analysis is performed to obtain the corresponding regression coefficients, and the optimal regression model of the variables to be verified is determined, which is then applied to the system dynamics model. The dependent variable values ​​predicted by the regression model are compared with the monitored dependent variable values ​​to obtain the mutual verification results.

[0071] See Table 1 for the coefficient matrix of the regression model.

[0072] Table 1 Coefficient matrix of regression model

[0073]

[0074] According to the regression coefficients in the coefficient matrix, the regression model function of the mutual verification dependent variable is obtained as follows:

[0075] X1=8.958+0.462X2+0.292X3+0.062X4+0.071X5+0.092X8-0.01X9+0.04X 11 (3)

[0076] The regression model expressions of other mutual verification dependent variables are similar and will not be repeated here.

[0077] Step S4, establish the mutual verification function between variables, the single variable to equipment failure probability function, the multi-variable comprehensive failure probability function and the mutual influence failure probability function between equipment, and the failure probability function of the substation system. Specifically, this step includes the following sub-steps:

[0078] Step S401, constructing a mutual verification function between variables.

[0079] For the fault inference of auxiliary control equipment, the predicted value of the variable is compared with the actual monitoring value according to the regression model function expression in c. The maximum difference between the predicted value and the actual monitoring value during normal operation is obtained by analyzing the historical data to determine the difference threshold. The mutual verification function between variables obtained by the single variable error is:

[0080]

[0081] Where ξ k is the kth variable check difference, ξ′ k is the threshold value of the k-th variable check difference, X k is the monitoring value of the kth variable, is the check value of the kth variable, when ξ k Greater than the test threshold ξ′ k , it is determined that the monitored variable is abnormal, and at the same time, an alarm is issued to the monitoring device corresponding to the monitored variable.

[0082] Step S402: constructing a single variable failure probability function for the equipment.

[0083] Construct the fault probability function in the electrical signal dimension;

[0084] If the load current and operating voltage of the equipment in the station exceed a certain threshold, the equipment will be damaged or even burned; if the switch signal value in the station is 1, it means the equipment is normal, and if it is 0, it means the equipment is faulty. Therefore, the fault probability functions of the three electrical signal characteristics of load current, operating voltage and switch signal are pf1(t), pf2(t), and pf3(t) respectively:

[0085]

[0086]

[0087] In the formula are the operating thresholds of the load current and operating voltage of the equipment s in the station, are the load current and operating voltage of the equipment s in the station at time t, a s (t) is the switch signal value of device s in the station at time t.

[0088] According to the component failure probability theory, based on the results of equations (5), (6), and (7), the failure probability function pf(t) in the electrical signal dimension is obtained as follows:

[0089] pf(t)=1-(1-pf1(t))(1-pf2(t))(1-pf3(t))(8)

[0090] Construct the failure probability function of the equipment status indicator dimension;

[0091] The deviation between the health status indicators of different equipment and the standard value is used to indicate the impact of the indicator on the equipment. r '(t) means:

[0092]

[0093] In the formula is the working threshold of the i-th device status indicator of the device s in the station; is the value of the i-th device status indicator at time t; there are m device status indicators in a station, B i is the influence coefficient of the i-th equipment status indicator.

[0094] There is an aging process in the actual operation of the equipment, so the equipment failure rate l(t) is:

[0095] l(t)=Ke -100C·μ(t)·HI′(t) (10)

[0096] Where K and C are proportional coefficients, and μ(t) is the equipment aging coefficient.

[0097] According to the survey, the typical failure rate is related to the equipment health index of 0.8, while the lowest failure rate corresponds to the perfect health of the equipment, that is, the health index is 1. By analyzing historical data, the average failure rate of each device in the substation can be determined, and the lowest failure rate is set between 10% and 20% of the average failure rate. According to formula (10), the relationship between the failure rate and the probability of failure is obtained, and the failure probability function of the equipment status indicator dimension is obtained as follows:

[0098] pl(t)=1-e-l(t) (11)

[0099] Where pl(t) is the probability of equipment failure at time t.

[0100] Construct the failure probability function of the operating environment indicator dimension.

[0101] The function design of environmental factors mostly adopts low-complexity and practical exponential models, and has achieved ideal results in scientific research analysis. In order to reasonably construct the failure probability function of operating environment indicators, a piecewise function is introduced to improve the existing exponential empirical function, namely:

[0102]

[0103] Where M is the unknown coefficient of the model, which can be obtained based on objective historical data and expert experience; min y is the starting value of the equipment affected in the station; max is the maximum value for normal operation of the equipment; j (t) is the equipment failure rate caused by the jth environmental influencing factor at time t.

[0104] The failure probability of the equipment caused by the external environment is obtained by the piecewise exponential function of the environmental factor in formula (12):

[0105]

[0106] Where: pe j (t) is the probability of equipment failure caused by the jth environmental influencing factor at time t.

[0107] Considering the impact of operating environment factors on the equipment, the failure probability function pe(t) of the operating environment dimension is obtained as follows:

[0108]

[0109] Where b is the number of operating environment indicators.

[0110] Step S403: comprehensive failure probability function of multiple variables.

[0111] For fault inference of electrical equipment, any abnormality in any dimension of electrical signal, equipment status index and operating environment index will cause an alarm, and the indicators are coupled with each other. The failure probability function X of the multi-dimensional monitoring characteristics of the equipment is obtained according to the series model based on the execution results of steps d01) and d02). g1 (t):

[0112] X g1 (t) = 1-(1-pf g (t))(1-pl g (t))(1-peg (t)) (15)

[0113] Step S404: mutual influence failure probability function between devices.

[0114] For electrical equipment failure inference, through the coupling analysis of the electrical relationship between the equipment in the substation, the failure probability of the main equipment at this level will be affected by the failure probability of the upper main equipment. The failure probability of the equipment at this level can be obtained by integrating n high-level equipment. g2 (t) is:

[0115]

[0116] Step S5, constructing a system dynamics flow chart for substation system safety assessment, and conducting a safety assessment on the substation system. Specifically, this step includes:

[0117] Build a system dynamics flow diagram based on the electrical relationship between substation variables, between variables and equipment, and between equipment, such as Figure 2 The functional relationship in the above step S4 is input into the functional relationship of the system dynamics flow chart, and the system dynamics equation for substation safety assessment is designed. The system dynamics equation is combined with the flow chart to finally form a substation safety assessment model. The final safety assessment flow chart is as follows: Figure 3 shown.

[0118] Step S6( Figure 1 (not shown in the figure), combined with Vensim, Python and other technologies, using the SpringCloud microservice framework, design and develop a substation safety assessment system. Specifically, this step includes the following sub-steps:

[0119] Step S601, constructing the application architecture and physical architecture of the substation safety assessment application system, and determining the main functions of the application system.

[0120] Step S602, design the database to realize the monitoring, query and preprocessing functions of collecting electrical and non-electrical characteristic data, perform status verification of the data acquisition device, push alarms for verification abnormalities, and realize the access of substation real-time monitoring information, display of system dynamics model, ledger configuration and other functions.

[0121] Step S603, using Vensim and Python technology to complete the development and implementation of the substation safety assessment model, realize the substation safety monitoring function, and issue alarm information when the monitoring results show abnormalities. The system physical architecture is as follows Figure 4 shown.

[0122] This method has the following beneficial effects:

[0123] (1) By combining feature optimization and regression analysis with system dynamics, the implicit correlation between monitoring variables is mined, which effectively improves the utilization rate of monitoring variables, evaluates the operating status of substation monitoring equipment from a data perspective, and improves the accuracy and reliability of safety assessment.

[0124] (2) A substation operation safety assessment system based on system dynamics was established, breaking down the barriers between equipment assessment and substation assessment, achieving a transition from individual to overall, from equipment to network, and solving the problems of mutual independence between substation online monitoring systems and difficulty in integrating monitoring information. This enabled joint prevention and control of power equipment, prevented substation safety accidents caused by multiple accidental factors, and effectively improved the safety level of power grid operation.

[0125] (3) Combining data analysis and system dynamics for substation safety assessment can effectively combine various monitoring systems and solve the problem of independent information islands between monitoring systems. At the same time, the comprehensive analysis of various monitoring data using system dynamics methods improves the comprehensiveness of substation safety assessment and can effectively solve the problem of accidental failures occurring in multiple conditions at the same time.

[0126] Example 2

[0127] Based on Example 1, see Figure 5 This embodiment provides a substation safety monitoring system, which mainly includes four modules: system dynamics flow chart model construction, data acquisition, basic configuration and safety monitoring. The system uses one or more of the technical middle platform (GIS map), real-time measurement center, business middle platform (topological relationship / equipment ledger), and substation auxiliary control system as input to achieve safety monitoring.

[0128] Specifically, the system dynamics flow chart model construction part includes two sub-parts: the construction of the cause-effect relationship flow chart and the construction of the system dynamics function relationship, which is achieved by the method in Example 1.

[0129] The data acquisition part includes electrical data and auxiliary control data access, data acquisition monitoring and data management.

[0130] The basic configuration section includes ledger configuration, alarm level configuration, and data collection point configuration.

[0131] The security monitoring part includes online security monitoring and dynamic security alarms.

[0132] Example 3

[0133] This embodiment provides an electronic device, including: one or more processors and a memory, wherein the memory stores one or more programs, and the one or more programs include instructions for executing the substation system dynamic safety assessment method considering mutual verification as described in Example 1.

[0134] Example 4

[0135] This embodiment provides a computer-readable storage medium, including one or more programs for execution by one or more processors of an electronic device, wherein the one or more programs include instructions for executing the substation system dynamic safety assessment method considering mutual verification as described in Example 1.

[0136] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A method for dynamic safety assessment of substation system considering mutual verification, characterized in that: The steps include: Step S1, obtaining multiple mutual verification characteristic variables corresponding to key equipment in the substation system; Step S2, based on the maximum mutual information coefficient and grey correlation analysis, a strongly correlated mutual verification set is obtained; Step S3, taking the variables in the mutual verification set as independent variables and the variables to be mutually verified as dependent variables, and constructing the relationship between the dependent variables and the independent variables by using the ridge regression method; Step S4, constructing a mutual verification fault probability function by calculating the single variable error, combining it with the multi-dimensional comprehensive fault probability function and the mutual influence fault probability function between devices to form a substation safety assessment fault probability function; Step S5, realizing the substation system dynamics safety assessment by constructing a system dynamics flow diagram.

2. A method for dynamic safety assessment of a substation system considering mutual verification according to claim 1, characterized in that: The step S2 includes the following sub-steps: Step S201, calculating the grey correlation coefficient and the maximum mutual information coefficient between each mutual verification feature variable; Step S202, weighting the grey correlation coefficient and the maximum mutual information coefficient to obtain a weighted correlation between mutual verification feature variables; Step S203: construct a mutual verification set based on the weighted association degree.

3. A method for dynamic safety assessment of a substation system considering mutual verification according to claim 2, characterized in that: In step S202, the weighted correlation degree is calculated using the following formula: Among them, J i is the weighted correlation of the ith mutual verification feature variable, n is the total number of mutual verification feature variables, MIC i (A,B i ) is the mutual verification dependent variable A and the mutual verification characteristic variable B i The maximum mutual information coefficient between i (A,B i ) is the mutual verification dependent variables A and B i Grey correlation coefficient between .

4. A method for dynamic safety assessment of a substation system considering mutual verification according to claim 2, characterized in that: In step S203, the process of constructing a mutual verification set includes: The mutual verification feature variables are arranged according to the weighted correlation, and a feature with the largest weighted correlation is selected each time to be added to the preferred set to realize the construction of the mutual verification set.

5. A method for dynamic safety assessment of a substation system considering mutual verification according to claim 1, characterized in that: The step S3 comprises: Through ridge regression analysis, variables with linear relationships in the mutual verification set are extracted. The variables in the mutual verification set are used as independent variables, and the variables to be mutually verified are used as dependent variables. The regression coefficients are obtained through regression analysis to realize the construction of the relationship between the dependent variable and the independent variable.

6. A method for dynamic safety assessment of a substation system considering mutual verification according to claim 1, characterized in that: The univariate error p k The calculation is done using the following formula: Among them, ξ k is the kth mutual verification characteristic variable verification difference, ξ k ′ is the threshold value of the kth mutual verification feature variable verification difference, X k is the monitoring value of the kth mutual verification characteristic variable, is the check value of the kth mutual check characteristic variable, when ξ k Greater than the test threshold ξ k ′, it is judged that the monitored variable is abnormal, and at the same time, an alarm is issued to the monitoring device corresponding to the monitored variable.

7. A method for dynamic safety assessment of a substation system considering mutual verification according to claim 1, characterized in that: In step S4, the process of constructing the multi-dimensional comprehensive fault probability function and the fault probability function of mutual influence between devices includes the following steps: Step S401, constructing a single variable failure probability function for the device from the electrical signal dimension, the device status index dimension and the operating environment index dimension; Step S402, based on the single variable failure probability function of the device, calculate the comprehensive failure probability function corresponding to each device by series connection; Step S403, based on the comprehensive failure probability function corresponding to each device, calculate the mutual influence failure probability function between devices.

8. A method for dynamic safety assessment of a substation system considering mutual verification according to claim 1, characterized in that: The following steps are also included: Step S6, building a substation safety assessment system based on a microservice framework.

9. A method for dynamic safety assessment of a substation system considering mutual verification according to claim 1, characterized in that: In the step S1, key equipment includes transformers, busbars, cable lines and circuit breakers.

10. A method for dynamic safety assessment of a substation system considering mutual verification according to claim 1, characterized in that: In the step S1, the mutual verification characteristic variables include electrical signals, equipment status indicators and operating environment indicators, wherein the electrical signals include load current, operating voltage and switch signals, the equipment status indicators specifically include circulating current, core grounding current, clamp grounding current, partial discharge, main transformer oil temperature, main transformer oil level height, main transformer oil level ratio, equipment temperature and SF6 gas pressure, and the operating environment indicators specifically include water level, humidity, temperature and equipment air chamber temperature.

Images