Intelligent state evaluation system and method for secondary equipment of intelligent power grid

Abstract

The invention discloses an intelligent state evaluation system and method for secondary equipment of an intelligent power grid, and belongs to the technical field of equipment state analysis. Index data used for evaluating the health state of the secondary equipment is determined from the operation data through an interval type principal component analysis method through an index data determination module; an index weight calculation module is used for calculating the correlation weight of each index data; setting a health state space of the secondary equipment through a state space construction module, wherein the health state space is divided into T health state levels; a membership value analysis module is used for calculating a membership value of each index data in each health state level; and finally, calculating the trust value of each health state level according to the membership value of each index data in each state level through a trust value calculation module, and evaluating the health state level with the maximum trust value as the health state of the current secondary equipment.

Description

Technical Field

[0001] The present invention relates to the technical field of equipment status analysis, and in particular to a system and method for intelligent status evaluation of secondary equipment in a smart grid. Background Art

[0002] Secondary equipment refers to a series of auxiliary equipment used for monitoring, control, protection, regulation and communication in the power system. It monitors and controls the working status of primary equipment (such as transformers, circuit breakers, transmission lines, etc.). Therefore, the health of secondary equipment directly affects the safe operation of the power grid. Through status assessment, safety hazards can be eliminated in time to prevent the occurrence of safety accidents.

[0003] The invention patent with application number CN202110593619.8 discloses a secondary equipment health status analysis method based on full-business mixed data. Its technical solution is to analyze the health status of secondary equipment by collecting full-business mixed data of the secondary equipment to be analyzed in real time. However, not all operating data can reflect the health status of secondary equipment. The original operating data may contain a large amount of irrelevant or repeated information, which may interfere with the analysis process and lead to erroneous conclusions.

[0004] Therefore, in order to solve the technical problems existing in the prior art, the present invention provides a system and method for intelligent status assessment of secondary equipment in a smart grid. Summary of the invention

[0005] In order to solve the technical problems existing in the prior art, the present invention provides a smart grid secondary equipment state intelligent assessment system, comprising: Data acquisition module, used to obtain the operating data of secondary equipment; An indicator data determination module, used to determine indicator data for evaluating the health status of secondary equipment from the operating data by using an interval-type principal component analysis method; The indicator weight calculation module is used to calculate the correlation weight a of each indicator data; A state space construction module, used to set a health state space of a secondary device, wherein the health state space is divided into T health state levels; The membership value analysis module is used to calculate the membership value ds of each indicator data at each health status level; The trust value calculation module calculates the trust value xrz of each health status level according to the membership value of each indicator data at each status level, and evaluates the health status level with the largest trust value as the health status of the current secondary device. Furthermore, the index data for evaluating the health status of the secondary equipment is determined from the operation data by interval principal component analysis, specifically: Determine the actual measurement matrix based on the operating data ; For the actual measurement matrix Perform preprocessing to obtain a standardized matrix ; Get the normalized matrix The covariance matrix of and the correlation matrix ; Get the correlation matrix The m eigenvalues ​​λ and m eigenvectors of ; Obtain the first k principal components that satisfy the minimum cumulative contribution rate G greater than the first preset threshold for the first time as the preferred principal components; Analyze the load L of various operating data on each preferred principal component; If the absolute value of L is greater than the second preset threshold, the corresponding operating data is the important data of the corresponding preferred principal component. If the number of times the operating data is important data is greater than the third preset threshold, the corresponding operating data is indicator data, and the number of types of indicator data M is counted.

[0006] Furthermore, the actual measurement matrix , represents the jth actual measurement value of the i-th type of operating data, m represents the number of types of operating data, n represents the number of actual measurement values ​​of operating data, and , and They are The left and right values ​​of ; The normalized matrix , yes The preprocessed value of , and They are The left and right values ​​of .

[0007] Furthermore, the calculation of the correlation weight of each indicator data is specifically as follows: Calculate the contribution value g of each preprocessing value corresponding to each indicator data: represents the contribution value of the jth preprocessed value of the i-th indicator data, and They are The left and right values ​​of ; Calculate the entropy value E of each indicator data: and They are The left and right values ​​of ; Calculate the correlation weight a of each indicator data: .

[0008] Furthermore, each health status level has a corresponding limit value interval .

[0009] Furthermore, the calculation of the membership value of each indicator data at each state level is specifically as follows: Each health status level is represented as a status cloud diagram through a cloud model; Obtain the expected Ex, entropy En and super entropy He of each level of state cloud diagram; in, The expectation of the state cloud diagram representing the Tth level, represents the entropy of the state cloud diagram of level T, The hyperentropy of the state cloud diagram representing the Tth level, Indicates the minimum limit value of the state cloud diagram of level T, represents the maximum limit value of the state cloud diagram of level T, and cs represents a preset constant; Each indicator data has T levels of state cloud graphs, and several cloud drops of corresponding indicator data are randomly generated in each state cloud graph. , , ; in, Indicates For expectation, A normal random value generated for the standard deviation, Indicates For expectation, A normal random entropy generated by the standard deviation, represents the natural exponential function, The degree to which each value of the i-th indicator data on the inner contour curve of the T-th level state cloud diagram of the i-th indicator data belongs to the T-th health status level, The degree to which each value of the i-th indicator data on the outer contour curve of the T-th level state cloud diagram of the i-th indicator data belongs to the T-th health state level; Get the membership value ds of each indicator data at each health status level: in, and They are The left and right values ​​of Represents the current actual measurement value of the i-th indicator data.

[0010] Furthermore, the trust value of each state level is calculated according to the membership value of each indicator data at each state level, specifically: Calculate the comprehensive membership value of each indicator data at each health status level: in, It represents the comprehensive membership value of the i-th indicator data at the T-th health status level; In each health status level, first indicator data is screened out respectively, and the number of types yzs corresponding to the first indicator data is counted, and the comprehensive membership value of the first indicator data in each health status level is greater than or equal to a preset membership threshold; Calculate the trust value of each status level: in, represents the first preset weight, Indicates the second preset weight.

[0011] The present invention also provides a method for intelligently evaluating the status of a smart grid secondary device, comprising the following steps: Obtain operating data of secondary equipment; Determining index data for evaluating the health status of secondary equipment from the operating data by using an interval principal component analysis method; Calculate the correlation weight a of each indicator data; Setting a health status space of a secondary device, wherein the health status space is divided into T health status levels; Calculate the membership value ds of each indicator data at each health status level; The trust value xrz of each health status level is calculated according to the membership value of each indicator data at each status level, and the health status level with the largest trust value is evaluated as the health status of the current secondary device.

[0012] Furthermore, determining the indicator data for evaluating the health status of the secondary equipment from the operation data by using interval principal component analysis specifically includes the following steps: Determine the actual measurement matrix based on the operating data ; For the actual measurement matrix Perform preprocessing to obtain a standardized matrix ; Get the normalized matrix The covariance matrix of and the correlation matrix ; Get the correlation matrix The m eigenvalues ​​λ and m eigenvectors of ; Obtain the first k principal components that satisfy the minimum cumulative contribution rate G greater than the first preset threshold for the first time as the preferred principal components; Analyze the load L of various operating data on each preferred principal component; If the absolute value of L is greater than the second preset threshold, the corresponding operating data is the important data of the corresponding preferred principal component. If the number of times the operating data is important data is greater than the third preset threshold, the corresponding operating data is indicator data, and the number of types of indicator data M is counted.

[0013] Furthermore, the calculation of the membership value of each indicator data at each state level specifically includes the following steps: Each health status level is represented as a status cloud diagram through a cloud model; Get the expected Ex, entropy En and super entropy He of each level of state cloud diagram: in, The expectation of the state cloud diagram representing the Tth level, represents the entropy of the state cloud diagram of level T, The hyperentropy of the state cloud diagram representing the Tth level, Indicates the minimum limit value of the state cloud diagram of level T, represents the maximum limit value of the state cloud diagram of level T, and cs represents a preset constant; Each indicator data has T levels of state cloud graphs, and several cloud drops of corresponding indicator data are randomly generated in each state cloud graph. , , ; in, Indicates For expectation, A normal random value generated for the standard deviation, Indicates For expectation, A normal random entropy generated by the standard deviation, represents the natural exponential function, The degree to which each value of the i-th indicator data on the inner contour curve of the T-th level state cloud diagram of the i-th indicator data belongs to the T-th health status level, The degree to which each value of the i-th indicator data on the outer contour curve of the T-th level state cloud diagram of the i-th indicator data belongs to the T-th health state level; Get the membership value ds of each indicator data at each health status level: in, and They are The left and right values ​​of Represents the current actual measurement value of the i-th indicator data.

[0014] Compared with the prior art, the present invention has the following beneficial effects: The present invention determines the index data for evaluating the health status of secondary equipment from the operating data of secondary equipment by using the interval principal component analysis method, effectively processes the multi-dimensional operating data, retains the most important index data by using the dimensionality reduction technology, reduces redundant information, improves the accuracy of the health status evaluation of secondary equipment, and also enhances the robustness and flexibility of the evaluation process; By calculating the correlation weight of each indicator data, the importance of different indicator data can be accurately quantified, which helps to more accurately evaluate the equipment status and avoids the subjective problem of weight determination in traditional evaluation methods; By calculating the membership value of each indicator data at each health status level, the concept of fuzzy mathematics is introduced, which can better handle the fuzziness and uncertainty of data and make the evaluation results closer to the actual situation. By calculating the trust value of each health status level, not only the evaluation results of a single indicator are taken into account, but also the correlation between indicators is integrated to ensure the robustness and reliability of the evaluation results. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention. In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0016] Figure 1 It is a structural block diagram of a state intelligent assessment system of a smart grid secondary device of the present invention; Figure 2 It is a flow chart of a method for intelligently evaluating the status of a secondary device of a smart grid according to the present invention; Figure 3 It is a flow chart of step S2 of a method for intelligently evaluating the status of secondary equipment in a smart grid of the present invention. DETAILED DESCRIPTION

[0017] 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 only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0018] It should be noted that all directional indications (such as up, down, left, right, front, back, etc.) in the embodiments of the present invention are only used to explain the relative position relationship, movement status, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.

[0019] In addition, the descriptions of "first", "second", etc. in the present invention are only used for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in the field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such a combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0020] Embodiment 1 See also Figure 1 As shown, the present invention provides a smart grid secondary equipment state intelligent assessment system, comprising: A data acquisition module, an indicator data determination module, an indicator weight calculation module, a state space construction module, a membership value analysis module and a trust value calculation module, as well as a central processing unit that is communicatively connected with the above modules.

[0021] The data acquisition module is used to obtain the operating data of the secondary equipment.

[0022] The operating data includes but is not limited to voltage, current, temperature, power factor, insulation resistance, communication quality and response time, etc.

[0023] The operating environment of secondary equipment is complex, and there are various uncertainties in the data collection and transmission process. These factors cause the measurement values ​​to not be completely accurate, but to exist within a possible range. Therefore, the operating data of secondary equipment is often expressed as interval data.

[0024] The indicator data determination module is used to determine the indicator data for evaluating the health status of the secondary equipment from the operation data by using the interval principal component analysis method.

[0025] The step of determining the index data for evaluating the health status of the secondary equipment from the operation data by using interval principal component analysis specifically includes the following steps: Determine the actual measurement matrix based on the operating data , , represents the jth actual measurement value of the i-th type of operating data, m represents the number of types of operating data, n represents the number of actual measurement values ​​of operating data, and , and They are The left and right values ​​of ; For the actual measurement matrix Perform preprocessing to obtain a standardized matrix , , yes The preprocessed value of , and They are The left and right values ​​of , for the forward running data, , , for the reverse running data, , ; Positive operation data refers to the operation data whose value increase mostly means better performance or better operation of the device, such as response time. Reverse operation data refers to the operation data whose value decrease mostly means better performance or better operation of the device, such as communication delay. Get the normalized matrix The covariance matrix of and the correlation matrix ; Get the correlation matrix The m eigenvalues ​​λ and m eigenvectors of ; The first k principal components that satisfy the minimum cumulative contribution rate G greater than the first preset threshold for the first time are obtained as the preferred principal components, that is, , k value is the value corresponding to k when G is greater than the first preset threshold for the first time, and They are The left and right values ​​of ; Analyze the load L of various operating data on each preferred principal component; in, represents the load of the i-th operating data on the v-th preferred principal component, represents the eigenvalue associated with the vth preferred principal component, Represents the element of the feature vector corresponding to the i-th running data.

[0026] If the absolute value of L is greater than the second preset threshold, the corresponding operating data is the important data of the corresponding preferred principal component. If the number of times the operating data is important data is greater than the third preset threshold, the corresponding operating data is indicator data, and the number of types of indicator data M is counted. The third preset threshold is set according to the number k of preferred principal components.

[0027] The indicator weight calculation module is used to calculate the correlation weight a of each indicator data.

[0028] The relevance weight of the indicator data reflects the importance of each indicator data relative to the secondary equipment health status assessment result.

[0029] The calculation of the correlation weight of each indicator data is specifically as follows: Calculate the contribution value g of each preprocessing value corresponding to each indicator data: represents the contribution value of the jth preprocessed value of the i-th indicator data, and They are The left and right values ​​of ; Calculate the entropy value E of each indicator data: and They are The left and right values ​​of ; Calculate the correlation weight a of each indicator data: The state space construction module is used to set the health state space of the secondary device. The health state space is divided into T health state levels, and each health state level has a corresponding limit value interval. .

[0030] The boundary value interval of each health status level Determined by the Weibull distribution model.

[0031] The membership value analysis module is used to calculate the membership value ds of each indicator data at each health status level.

[0032] The calculation of the membership value of each indicator data at each state level is specifically as follows: Each health status level is represented as a status cloud diagram through a cloud model; Obtain the expected Ex, entropy En and super entropy He of each level of state cloud diagram; in, The expectation of the state cloud diagram representing the Tth level, represents the entropy of the state cloud diagram of level T, The hyperentropy of the state cloud diagram representing the Tth level, Indicates the minimum limit value of the state cloud diagram of level T, It represents the maximum limit value of the state cloud diagram of the Tth level, and cs represents the preset constant.

[0033] Each indicator data has T levels of state cloud graphs, and several cloud drops of corresponding indicator data are randomly generated in each state cloud graph. , , ; in, Indicates For expectation, A normal random value generated for the standard deviation, Indicates For expectation, A normal random entropy generated by the standard deviation, represents the natural exponential function, The degree to which each value of the i-th indicator data on the inner contour curve of the T-th level state cloud diagram of the i-th indicator data belongs to the T-th health status level, The degree to which each value of the i-th indicator data on the outer contour curve of the T-th level state cloud diagram of the i-th indicator data belongs to the T-th health state level; Get the membership value ds of each indicator data at each health status level: in, and They are The left and right values ​​of Represents the current actual measurement value of the i-th indicator data.

[0034] The trust value calculation module calculates the trust value xrz of each health status level according to the membership value of each indicator data at each status level, and evaluates the health status level with the largest trust value as the health status of the current secondary device.

[0035] The trust value of each state level is calculated according to the membership value of each indicator data at each state level, specifically: Calculate the comprehensive membership value of each indicator data at each health status level: in, It represents the comprehensive membership value of the i-th indicator data at the T-th health status level; In each health status level, first indicator data is screened out respectively, and the number of types yzs corresponding to the first indicator data is counted, and the comprehensive membership value of the first indicator data in each health status level is greater than or equal to a preset membership threshold; Calculate the trust value of each status level: in, represents the first preset weight, Indicates the second preset weight.

[0036] Embodiment 2 See also Figure 2 As shown, the present invention also provides a method for intelligently evaluating the status of a smart grid secondary device, comprising the following steps: S1. Obtaining the operating data of secondary equipment; S2. determining index data for evaluating the health status of secondary equipment from the operation data by using an interval principal component analysis method; S3. Calculate the correlation weight a of each indicator data; S4. Setting a health status space of the secondary device, wherein the health status space is divided into T health status levels; S5, calculating the membership value ds of each indicator data at each health status level; S6. Calculate the trust value xrz of each health status level according to the membership value of each indicator data at each status level, and evaluate the health status level with the largest trust value as the health status of the current secondary device.

[0037] See also Figure 3 As shown, for step S2, the index data for evaluating the health status of the secondary equipment is determined from the operation data by using the interval principal component analysis method, which specifically includes the following steps: T1. Determine the actual measurement matrix based on the operating data ; T2, the actual measurement matrix Perform preprocessing to obtain a standardized matrix ; T3. Get the standardized matrix The covariance matrix of and the correlation matrix ; T4. Get the correlation matrix The m eigenvalues ​​λ and m eigenvectors of ; T5, obtaining the first k principal components whose minimum cumulative contribution rate G is greater than the first preset threshold for the first time as the preferred principal components; T6. Analyze the loads L of various operating data on each preferred principal component; If the absolute value of L is greater than the second preset threshold, the corresponding operating data is the important data of the corresponding preferred principal component. If the number of times the operating data is important data is greater than the third preset threshold, the corresponding operating data is indicator data, and the number of types of indicator data M is counted.

[0038] For step S3, calculating the correlation weight a of each indicator data specifically includes the following steps: Calculate the contribution value g of each preprocessing value corresponding to each indicator data: Calculate the entropy value E of each indicator data according to the contribution value g; The correlation weight a of each indicator data is calculated according to the entropy value E.

[0039] In a method for intelligently evaluating the status of a smart grid secondary device of the present invention, the specific steps of each step and the calculation formula of each parameter correspond to the intelligent evaluation system for the status of a smart grid secondary device in Example 1, and are not repeated here.

[0040] Embodiment 3 The present invention also provides an electronic device, comprising: a processor, a sending device, an input device, an output device and a memory, the memory is used to store computer program code, the computer program code includes computer instructions, when the processor executes the computer instructions, the electronic device executes a method as any one of the possible implementation methods described above.

[0041] Embodiment 4 The present invention also provides a computer-readable storage medium, in which a computer program is stored. The computer program includes program instructions. When the program instructions are executed by a processor of an electronic device, the processor executes a method as described in any possible implementation manner.

[0042] The beneficial effects of the present invention are: The present invention determines the index data for evaluating the health status of secondary equipment from the operating data of secondary equipment by using the interval principal component analysis method, effectively processes the multi-dimensional operating data, retains the most important index data by using the dimensionality reduction technology, reduces redundant information, improves the accuracy of the health status evaluation of secondary equipment, and also enhances the robustness and flexibility of the evaluation process; By calculating the correlation weight of each indicator data, the importance of different indicator data can be accurately quantified, which helps to more accurately evaluate the equipment status and avoids the subjective problem of weight determination in traditional evaluation methods; By calculating the membership value of each indicator data at each health status level, the concept of fuzzy mathematics is introduced, which can better handle the fuzziness and uncertainty of data and make the evaluation results closer to the actual situation. By calculating the trust value of each health status level, not only the evaluation results of a single indicator are taken into account, but also the correlation between indicators is integrated to ensure the robustness and reliability of the evaluation results.

[0043] In the description of the specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0044] The foregoing is merely a specific embodiment of the present invention, which enables those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features claimed herein.

Claims

1. A smart grid secondary equipment status intelligent assessment system, characterized in that: include: Data acquisition module, used to obtain the operating data of secondary equipment; The indicator data determination module is used to determine the indicator data for evaluating the health status of the secondary equipment from the operation data by using the interval principal component analysis method, specifically: Determine the actual measurement matrix based on the operating data ; For the actual measurement matrix Perform preprocessing to obtain a standardized matrix ; Get the normalized matrix The covariance matrix of and the correlation matrix ; Get the correlation matrix The m eigenvalues ​​λ and m eigenvectors of ; Obtain the first k principal components that satisfy the minimum cumulative contribution rate G greater than the first preset threshold for the first time as the preferred principal components; Analyze the load L of various operating data on each preferred principal component; If the absolute value of L is greater than the second preset threshold, the corresponding operating data is the important data of the corresponding preferred principal component. If the number of times the operating data is important data is greater than the third preset threshold, the corresponding operating data is indicator data, and the number of types of indicator data M is counted.

2. The intelligent status assessment system for smart grid secondary equipment according to claim 1, characterized in that: It also includes an indicator weight calculation module for calculating the correlation weight a of each indicator data.

3. The intelligent status assessment system for smart grid secondary equipment according to claim 1 is characterized in that: The actual measurement matrix , represents the jth actual measurement value of the i-th type of operating data, m represents the number of types of operating data, n represents the number of actual measurement values ​​of operating data, and , and They are The left and right values ​​of ; The normalized matrix , yes The preprocessed value of , and They are The left and right values ​​of .

4. The intelligent status assessment system for smart grid secondary equipment according to claim 2, characterized in that: The calculation of the correlation weight of each indicator data is specifically as follows: Calculate the contribution value g of each preprocessing value corresponding to each indicator data: represents the contribution value of the jth preprocessed value of the i-th indicator data, and They are The left and right values ​​of ; Calculate the entropy value E of each indicator data: and They are The left and right values ​​of ; Calculate the correlation weight a of each indicator data: 。 5. The intelligent status assessment system for smart grid secondary equipment according to claim 1, characterized in that: It also includes a state space construction module for setting the health state space of the secondary device, wherein the health state space is divided into T health state levels, wherein each health state level has a corresponding limit value interval. .

6. The intelligent status assessment system for smart grid secondary equipment according to claim 5, characterized in that: It also includes a membership value analysis module for calculating the membership value ds of each indicator data at each health status level; The calculation of the membership value ds of each indicator data at each state level is specifically as follows: Each health status level is represented as a status cloud diagram through a cloud model; Obtain the expected Ex, entropy En and super entropy He of each level of state cloud diagram; in, The expectation of the state cloud diagram representing the Tth level, represents the entropy of the state cloud diagram of level T, The hyperentropy of the state cloud diagram representing the Tth level, Indicates the minimum limit value of the state cloud diagram of level T, represents the maximum limit value of the state cloud diagram of level T, and cs represents a preset constant; Each indicator data has T levels of state cloud graphs, and several cloud drops of corresponding indicator data are randomly generated in each state cloud graph. , , ; in, Indicates For the expectation, A normal random value generated for the standard deviation, Indicates For the expectation, A normal random entropy generated by the standard deviation, represents the natural exponential function, The degree to which each value of the i-th indicator data on the inner contour curve of the T-th level state cloud diagram of the i-th indicator data belongs to the T-th health status level, The degree to which each value of the i-th indicator data on the outer contour curve of the T-th level state cloud diagram of the i-th indicator data belongs to the T-th health state level; Get the membership value ds of each indicator data at each health status level: in, and They are The left and right values ​​of Represents the current actual measurement value of the i-th indicator data.

7. The intelligent status assessment system for smart grid secondary equipment according to claim 1, characterized in that: It also includes a trust value calculation module, which calculates the trust value xrz of each health state level according to the membership value of each indicator data at each state level, and evaluates the health state level with the largest trust value as the health state of the current secondary device; wherein, the trust value of each state level is calculated according to the membership value of each indicator data at each state level, specifically: Calculate the comprehensive membership value of each indicator data at each health status level: in, It represents the comprehensive membership value of the i-th indicator data at the T-th health status level; In each health status level, first indicator data is screened out respectively, and the number of types yzs corresponding to the first indicator data is counted, and the comprehensive membership value of the first indicator data in each health status level is greater than or equal to a preset membership threshold; Calculate the trust value of each status level: in, represents the first preset weight, Indicates the second preset weight.

8. A method for intelligently evaluating the status of a smart grid secondary device, applied to the intelligent evaluation system for the status of a smart grid secondary device according to any one of claims 1 to 7, characterized in that: The following steps are involved: Obtain operating data of secondary equipment; Determining index data for evaluating the health status of secondary equipment from the operating data by using an interval principal component analysis method; Calculate the correlation weight a of each indicator data; Setting a health status space of a secondary device, wherein the health status space is divided into T health status levels; Calculate the membership value ds of each indicator data at each health status level; The trust value xrz of each health status level is calculated according to the membership value of each indicator data at each status level, and the health status level with the largest trust value is evaluated as the health status of the current secondary device.

9. The method for intelligent status assessment of smart grid secondary equipment according to claim 8, characterized in that: The step of determining the index data for evaluating the health status of the secondary equipment from the operation data by using interval principal component analysis specifically includes the following steps: Determine the actual measurement matrix based on the operating data ; For the actual measurement matrix Perform preprocessing to obtain a standardized matrix ; Get the normalized matrix The covariance matrix of and the correlation matrix ; Get the correlation matrix The m eigenvalues ​​λ and m eigenvectors of ; Obtain the first k principal components that satisfy the minimum cumulative contribution rate G greater than the first preset threshold for the first time as the preferred principal components; Analyze the load L of various operating data on each preferred principal component; If the absolute value of L is greater than the second preset threshold, the corresponding operating data is the important data of the corresponding preferred principal component. If the number of times the operating data is important data is greater than the third preset threshold, the corresponding operating data is indicator data, and the number of types of indicator data M is counted.

10. The method for intelligent status assessment of smart grid secondary equipment according to claim 8, characterized in that: The calculation of the membership value of each indicator data at each state level specifically includes the following steps: Each health status level is represented as a status cloud diagram through a cloud model; Get the expected Ex, entropy En and super entropy He of each level of state cloud diagram: in, The expectation of the state cloud diagram representing the Tth level, represents the entropy of the state cloud diagram of level T, The hyperentropy of the state cloud diagram representing the Tth level, Indicates the minimum limit value of the state cloud diagram of level T, represents the maximum limit value of the state cloud diagram of level T, and cs represents a preset constant; Each indicator data has T levels of state cloud graphs, and several cloud drops of corresponding indicator data are randomly generated in each state cloud graph. , , ; in, Indicates For the expectation, A normal random value generated for the standard deviation, Indicates For the expectation, A normal random entropy generated by the standard deviation, represents the natural exponential function, The degree to which each value of the i-th indicator data on the inner contour curve of the T-th level state cloud diagram of the i-th indicator data belongs to the T-th health status level, The degree to which each value of the i-th indicator data on the outer contour curve of the T-th level state cloud diagram of the i-th indicator data belongs to the T-th health state level; Get the membership value ds of each indicator data at each health status level: in, and They are The left and right values ​​of Represents the current actual measurement value of the i-th indicator data.

Images