RPA-based high-voltage cable anomaly detection method and system

Abstract

The invention relates to an RPA-based high-voltage cable anomaly detection method and system, and the method comprises the following steps: judging whether a high-voltage cable is abnormal or not according to a collected grounding current abnormal state value of the high-voltage cable, carrying out the positioning of an abnormal region, and carrying out the RPA abnormal operation detection according to the abnormal region obtained through positioning; the RPA abnormal operation detection comprises the following steps: collecting index data of an abnormal area, and calculating a weight set of the index data based on a comprehensive weight model; performing state evaluation on the index data and the weight set thereof through a fuzzy comprehensive evaluation method to obtain a fuzzy comprehensive evaluation result; and determining a corresponding maintenance plan according to the obtained fuzzy comprehensive evaluation result. Compared with the prior art, the abnormal state can be rapidly detected, the detection efficiency of the high-voltage cable is improved, and the detection precision is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of high-voltage cable anomaly detection, and in particular to a high-voltage cable anomaly detection method and system based on RPA. Background Art

[0002] Traditional high-voltage cable online detection adopts segmented monitoring. For example, the invention with publication number CN115542084A discloses a precise positioning and analysis system and method for high-voltage cable faults, including: a fault monitoring device, which is arranged at both ends of the high-voltage cable to be monitored and is used to collect transient data in a non-contact manner; a fault positioning server, which is used to receive the transient data and analyze the fault distance measurement results; a high-precision timing module, which is used to achieve a timing accuracy of no higher than 20ns for the power system.

[0003] This solution performs fault detection based on the operating current and electric field of the high-voltage cable. However, due to its large coverage area, when the high-voltage cable is in an abnormal state, it cannot accurately detect the abnormal local area. Summary of the invention

[0004] The purpose of the present invention is to overcome the defects of the above-mentioned prior art and provide a high-voltage cable anomaly detection method and system based on RPA, so as to quickly detect abnormal conditions, improve the detection efficiency of high-voltage cables, and improve the detection accuracy.

[0005] The purpose of the present invention can be achieved by the following technical solutions: A high-voltage cable anomaly detection method based on RPA includes the following steps: According to the collected abnormal state value of the ground current of the high-voltage cable, determine whether the high-voltage cable is abnormal, locate the abnormal area, and perform RPA abnormal operation detection according to the abnormal area located; The RPA abnormal operation detection includes the following steps: Collecting indicator data of the abnormal area, and calculating a weight set of the indicator data based on a comprehensive weight model; Performing status evaluation on the indicator data and its weight set by using a fuzzy comprehensive evaluation method to obtain a fuzzy comprehensive evaluation result; According to the obtained fuzzy comprehensive evaluation results, the corresponding maintenance plan is determined.

[0006] Furthermore, the calculation expression of each element of the weight set of the indicator data is: In the formula, is the weight of the i-th indicator data, is the subjective weight of the i-th indicator data, is the objective weight of the i-th indicator data, and k is the variable weight coefficient; The subjective weight is obtained by improving the hierarchical analysis method, and the objective weight is obtained by entropy weight method.

[0007] Furthermore, the improved analytic hierarchy process comprises the following steps: S101: Decomposing the indicator data to construct a multi-level indicator model; S102: According to the multi-level indicator model, the importance of each indicator in the same level is determined by using the 1-9 scale method, and a judgment matrix is ​​constructed. The expression of the judgment matrix is: In the formula, is the judgment matrix, For the indicators and The importance ratio of the indicators, n is the total number of indicators; S103: Perform a consistency check on the judgment matrix; if the consistency check passes, obtain a weight matrix for n indicators; S104: Using different data sources or scaling methods, repeat steps S102-S103 to obtain s weight matrices for n indicators, and obtain the initial indicator weight matrix by arithmetic averaging. ; S105: Initial weight matrix for indicators Arrange the elements in from large to small to get a new weight set ; S106: New weight set The weighted vector E is obtained by weighting each element of . The calculation expression of each element in the weighted vector E is: In the formula, is the number of elements in the weight set, j is the position number of the element in the set, , is the value of the j+1th element in E, is the weight set The value of the jth element in ; S107: weighted vector E and weight set Perform weighted summation to obtain absolute weight , the absolute weight The calculation expressions of each element in are: In the formula, Absolute weight The jth element in ; S108: Calculate the relative weight of each element in the initial weight matrix according to the absolute weight, so as to obtain an improved subjective weight A. The calculation expression of each element in the subjective weight A is: In the formula, is the jth element in the subjective weight A.

[0008] Furthermore, the fuzzy comprehensive evaluation method performs fuzzy operations on the weight set of the index data and the fuzzy relationship matrix through fuzzy operators to obtain fuzzy comprehensive evaluation results; The calculation expression of the fuzzy comprehensive evaluation result is: In the formula, B is the fuzzy comprehensive evaluation result, W is the weight set of indicator data, R is the fuzzy relationship matrix, is the nth element of the weight set W, element Indicates The evaluation index is relative to The membership degree of the level evaluation results, is the mth element of the fuzzy comprehensive evaluation result.

[0009] Furthermore, the method determines the corresponding evaluation level through the maximum membership principle based on the fuzzy comprehensive evaluation result and the membership intervals of the three abnormality levels of attention, abnormality and severe set in advance; According to the determined evaluation level, determine the corresponding maintenance plan.

[0010] Furthermore, the method searches the determined evaluation level against a pre-established standard library corresponding to the evaluation level to obtain the corresponding abnormality type, thereby determining the corresponding maintenance plan.

[0011] Furthermore, the process of determining whether the high-voltage cable is abnormal includes: The collected ground current abnormal state value is compared with the preset upper and lower limit thresholds of the current abnormal state value to determine whether there is any abnormality in the operation of the high-voltage cable.

[0012] Furthermore, the index data of the abnormal area includes sheath current and sheath induced voltage data.

[0013] Furthermore, a circulating current detection circuit is used to collect grounding current data of the high-voltage cable. The circulating current detection circuit includes a current transformer, an operational amplifier and an analog-to-digital converter connected in sequence. The circulating current detection circuit is installed in an outdoor field terminal or an intermediate joint cross-connection box. The outdoor field terminal is directly grounded, and both ends of the intermediate joint cross-connection box are grounded.

[0014] The present invention also provides a system using the above-mentioned high-voltage cable anomaly detection method based on RPA, comprising: The information collection module is used to collect the abnormal state values ​​of the grounding current of the high-voltage cable at different time periods, and to collect the sheath current and induced voltage index data under the RPA abnormal operation detection mode; A judgment module is used to judge whether the high-voltage cable is abnormal according to the abnormal state value of the ground current. If so, the abnormal area is located and the RPA abnormal operation detection module is executed for the abnormal current state area; The RPA abnormal operation detection module is used to calculate the weight set based on the comprehensive weight model according to the collected sheath current and induced voltage index data; to conduct status evaluation on the index data and its weight set through the fuzzy comprehensive evaluation method to obtain the fuzzy comprehensive evaluation results; and to determine the corresponding maintenance plan based on the obtained fuzzy comprehensive evaluation results.

[0015] Compared with the prior art, the present invention has the following advantages: (1) The present invention proposes that when a high-voltage cable is judged to be abnormal based on the grounding current of the high-voltage cable, based on the determined abnormal area, the sheath current and sheath induced voltage index data of the abnormal area are used, and the RPA abnormal operation detection mode is adopted to perform abnormal index weight analysis on the index data, and the state evaluation of the index data is realized through the fuzzy comprehensive evaluation method, so as to obtain the corresponding maintenance plan. The scheme can quickly detect abnormal states, improve the detection efficiency of high-voltage cables, and improve the detection accuracy.

[0016] (2) The weight set of indicator data calculated by the present invention includes subjective weight and objective weight. The subjective weight is obtained by using an improved hierarchical analysis method. After the judgment matrix constructed based on the indicator data is checked for consistency, the improved hierarchical analysis method uses different data sources or scaling methods to calculate the initial indicator weight matrix, and performs arithmetic averaging and sorting to obtain a weight set; each element of the weight set is weighted to obtain a weighted vector, which is combined with the weight set to obtain an absolute weight, and finally the calculated value of the subjective weight is obtained, thereby realizing a hierarchical decomposition of complex decision-making problems, making the problems clearer and more organized, and having a certain degree of flexibility, which can be adjusted and modified according to specific circumstances. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 The figure is a flow chart of a method for detecting abnormalities of high-voltage cables based on RPA provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0018] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings 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. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0019] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention claimed for protection, but merely represents selected embodiments of the present invention. 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.

[0020] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.

[0021] Example 1 like Figure 1 As shown, this embodiment provides a high-voltage cable abnormality detection method based on RPA, including the following steps: According to the collected abnormal state value of the ground current of the high-voltage cable, determine whether the high-voltage cable is abnormal, locate the abnormal area, and perform RPA abnormal operation detection according to the abnormal area located; The RPA abnormal operation detection includes the following steps: S1: Collect indicator data of abnormal areas, and calculate a weight set of the indicator data based on a comprehensive weight model; S2: Performing status evaluation on the indicator data and its weight set by using a fuzzy comprehensive evaluation method to obtain a fuzzy comprehensive evaluation result; S3: Determine the corresponding maintenance plan based on the obtained fuzzy comprehensive evaluation results.

[0022] Specifically, in this embodiment, the grounding current is obtained by a circulating current detection circuit. The circulating current detection circuit is responsible for collecting the grounding current data of the high-voltage cable. The circulating current detection circuit of the monitoring terminal is composed of a current transformer, an operational amplifier, and an analog-to-digital converter. The current transformer passes through the secondary side of a winding of the open-type current transformer to remove current. The current transformer ratio is 5A / 2.5mA. The small current is converted into a voltage signal through a resistor, input into the operational amplifier and converted into a digital quantity through digital-to-analog conversion and sent to the central processing unit for calculation to measure the cable circulating current data. The installation location of the cable circulating current data acquisition mechanism is selected in the outdoor field terminal and the middle joint cross-connection box. The monitoring range is the entire section of the high-voltage cable line. The line terminal part adopts direct grounding, and the joint part adopts cross-connection grounding at both ends.

[0023] Judging whether there is an abnormality in the high-voltage cable includes making a threshold judgment on the abnormal grounding current state value. By comparing the collected abnormal current state value with the preset upper and lower thresholds of the abnormal current state value, it is judged whether there is an abnormality in the high-voltage cable. The grounding current method can reflect faults in the system's main insulation, accessories, interconnection boxes, etc.

[0024] In the above RPA abnormal operation detection, the processing process of step S1 is specifically as follows: The sheath current and sheath induced voltage index data in the current abnormal state area are collected, and the abnormal index weight analysis is performed on the index data; when a cable fails, the changes in the metal sheath induced voltage and induced current can be used as characteristic signals to judge the high-voltage cable fault. Therefore, the sheath current and sheath induced voltage data are used as indicator data.

[0025] Perform abnormal index weight analysis on the sheath current and sheath induced voltage index data; including calculating the weight set of index data based on the comprehensive weight model ; In the formula, is the weight of the i-th indicator data, is the subjective weight of the i-th indicator data, is the objective weight of the i-th indicator data, and k is the variable weight coefficient; The subjective weight is obtained by improving the hierarchical analysis method, and the objective weight is obtained by entropy weight method.

[0026] The improved AHP method includes the following steps: S101: Decompose the index data specified for the cable operation status and build a multi-level index model; S102: Construct a judgment matrix. The judgment matrix is ​​a matrix obtained by comparing the relative importance of each pair of indicators at the same level. That is, according to the multi-level indicator model, the importance of each indicator at the same level is determined using the 1-9 scale method, and each element of the judgment matrix is ​​assigned a value. The expression of the judgment matrix is: In the formula, is the judgment matrix, For the indicators and The importance ratio of the indicators, n is the total number of indicators; S103: Perform a consistency check on the judgment matrix; if the consistency check passes, obtain a weight matrix for n indicators; S104: Using different data sources or scaling methods, repeat steps S102-S103 to obtain s weight matrices for n indicators, and obtain the initial indicator weight matrix by arithmetic averaging. ; S105: Initial weight matrix for indicators Arrange the elements in from large to small to get a new weight set ; Initial weight matrix for indicators The purpose of sorting the elements in is as follows: 1) Highlight importance: By sorting, you can more intuitively see the elements with larger weights, thereby clarifying which factors or features have higher importance in the corresponding model or calculation.

[0027] 2) Simplified analysis: It makes the analysis of the weight matrix more concise and clear, which helps to quickly grasp the main influencing factors.

[0028] 3) Feature selection: helps to screen out important features or variables. In some cases, if the elements with smaller weights have little impact on the results, you can consider discarding them to simplify the model and algorithm and improve computational efficiency and accuracy.

[0029] 4) Compare and contrast: It is convenient to compare and contrast between different weight matrices to find the similarities and differences between them.

[0030] 5) Optimization and adjustment: To provide a basis for further optimization and adjustment, you can conduct more in-depth research and optimization on elements with larger weights, or adjust elements with unreasonable weights based on the sorting results.

[0031] S106: New weight set The weighted vector E is obtained by weighting each element of . The calculation expression of each element in the weighted vector E is: In the formula, is the number of elements in the weight set, j is the position number of the element in the set, , is the value of the j+1th element in E, is the weight set The value of the jth element in ; S107: weighted vector E and weight set Perform weighted summation to obtain absolute weight , the absolute weight The calculation expressions of each element in are: In the formula, Absolute weight The jth element in ; S108: Calculate the relative weight of each element in the initial weight matrix according to the absolute weight, so as to obtain an improved subjective weight A. The calculation expression of each element in the subjective weight A is: In the formula, is the jth element in the subjective weight A.

[0032] The entropy weight method includes: data standardization, i.e. normalizing each data item, calculating sample weights, calculating indicator entropy values, and calculating indicator weights. Since the entropy weight method is a standard algorithm, it will not be described in detail here.

[0033] Step S2 mainly uses the fuzzy comprehensive evaluation method to evaluate its status and collects statistics on the evaluation results; the specific process includes: The weight set of index data and fuzzy relationship matrix are fuzzy operated through fuzzy operators to obtain fuzzy comprehensive evaluation results; Fuzzy Relationship Matrix for: Among them, the element Indicates The evaluation index is relative to The membership degree of the level evaluation results; Fuzzy comprehensive evaluation results The requirements include: In the formula, B is the fuzzy comprehensive evaluation result, W is the weight set of indicator data, R is the fuzzy relationship matrix, is the nth element of the weight set W, element Indicates The evaluation index is relative to The membership degree of the level evaluation results, is the mth element of the fuzzy comprehensive evaluation result.

[0034] According to the fuzzy comprehensive evaluation result, based on the pre-set membership intervals of the three abnormality levels of attention, abnormality and severe, the corresponding evaluation level is determined by the maximum membership principle; According to the determined evaluation level, determine the corresponding maintenance plan.

[0035] Step S3 mainly specifies the maintenance plan according to the status of the status assessment, and the specific process is as follows: A standard library corresponding to the evaluation level is established for the database of abnormal conditions, and the type of abnormality is found in the standard library based on the obtained evaluation level for inspection and maintenance.

[0036] Example 2 This embodiment provides a system using the above-mentioned RPA-based high-voltage cable anomaly detection method, including: The information collection module is used to collect the abnormal state values ​​of the grounding current of the high-voltage cable at different time periods, and to collect the sheath current and induced voltage index data under the RPA abnormal operation detection mode; A judgment module is used to judge whether the high-voltage cable is abnormal according to the abnormal state value of the ground current. If so, the abnormal area is located and the RPA abnormal operation detection module is executed for the abnormal current state area; The RPA abnormal operation detection module is used to calculate the weight set based on the comprehensive weight model according to the collected sheath current and induced voltage index data; to conduct status evaluation on the index data and its weight set through the fuzzy comprehensive evaluation method to obtain the fuzzy comprehensive evaluation results; and to determine the corresponding maintenance plan based on the obtained fuzzy comprehensive evaluation results.

[0037] It should be noted that the specific content and beneficial effects of the device of the present application can be found in the above-mentioned method embodiment, which will not be repeated here.

[0038] The preferred specific embodiments of the present invention are described in detail above. It should be understood that a person skilled in the art can make many modifications and changes based on the concept of the present invention without creative work. Therefore, any technical solution that can be obtained by a person skilled in the art through logical analysis, reasoning or limited experiments based on the concept of the present invention on the basis of the prior art should be within the scope of protection determined by the claims.

Claims

1. A high-voltage cable anomaly detection method based on RPA, characterized in that: The following steps are involved: According to the collected abnormal state value of the ground current of the high-voltage cable, determine whether the high-voltage cable is abnormal, locate the abnormal area, and perform RPA abnormal operation detection according to the abnormal area located; The RPA abnormal operation detection includes the following steps: Collecting indicator data of the abnormal area, and calculating a weight set of the indicator data based on a comprehensive weight model; Conducting status evaluation on the indicator data and its weight set by using a fuzzy comprehensive evaluation method to obtain a fuzzy comprehensive evaluation result; According to the obtained fuzzy comprehensive evaluation results, the corresponding maintenance plan is determined.

2. According to claim 1, a high-voltage cable anomaly detection method based on RPA is characterized in that: The calculation expression of each element of the weight set of the indicator data is: In the formula, is the weight of the i-th indicator data, is the subjective weight of the i-th indicator data, is the objective weight of the i-th indicator data, and k is the variable weight coefficient; The subjective weight is obtained by improving the hierarchical analysis method, and the objective weight is obtained by entropy weight method.

3. The method for detecting abnormality of a high-voltage cable based on RPA according to claim 2 is characterized in that: The improved analytic hierarchy process comprises the following steps: S101: Decomposing the indicator data to construct a multi-level indicator model; S102: According to the multi-level indicator model, the importance of each indicator in the same level is determined by using the 1-9 scale method, and a judgment matrix is ​​constructed. The expression of the judgment matrix is: In the formula, is the judgment matrix, For the indicators and The importance ratio of the indicators, n is the total number of indicators; S103: Performing consistency check on the judgment matrix; If the consistency check passes, obtain the weight matrix for n indicators; S104: Using different data sources or scaling methods, repeat steps S102-S103 to obtain s weight matrices for n indicators, and obtain the initial indicator weight matrix by arithmetic averaging. ; S105: Initial weight matrix for indicators Arrange the elements in from large to small to get a new weight set ; S106: New weight set The weighted vector E is obtained by weighting each element of . The calculation expression of each element in the weighted vector E is: In the formula, is the number of elements in the weight set, j is the position number of the element in the set, , is the value of the j+1th element in E, is the weight set The value of the jth element in ; S107: weighted vector E and weight set Perform weighted summation to obtain absolute weight , the absolute weight The calculation expressions of each element in are: In the formula, Absolute weight The jth element in ; S108: Calculate the relative weight of each element in the initial weight matrix according to the absolute weight, so as to obtain an improved subjective weight A. The calculation expression of each element in the subjective weight A is: In the formula, is the jth element in the subjective weight A.

4. The method for detecting abnormality of a high-voltage cable based on RPA according to claim 1, characterized in that: The fuzzy comprehensive evaluation method performs fuzzy operations on the weight set of index data and the fuzzy relationship matrix through fuzzy operators to obtain fuzzy comprehensive evaluation results; The calculation expression of the fuzzy comprehensive evaluation result is: In the formula, B is the fuzzy comprehensive evaluation result, W is the weight set of indicator data, R is the fuzzy relationship matrix, is the nth element of the weight set W, element Indicates The evaluation index is relative to The membership degree of the level evaluation results, is the mth element of the fuzzy comprehensive evaluation result.

5. The method for detecting abnormality of a high-voltage cable based on RPA according to claim 1, characterized in that: The method determines the corresponding evaluation level according to the fuzzy comprehensive evaluation result and the membership intervals of three abnormal levels of attention, abnormality and severe, by the maximum membership principle; According to the determined evaluation level, determine the corresponding maintenance plan.

6. The method for detecting abnormality of a high-voltage cable based on RPA according to claim 5, characterized in that: The method searches the determined evaluation level against a pre-established standard library corresponding to the evaluation level to obtain the corresponding abnormality type, thereby determining the corresponding maintenance plan.

7. The method for detecting abnormality of a high-voltage cable based on RPA according to claim 1, characterized in that: The process of determining whether the high-voltage cable is abnormal includes: The collected ground current abnormal state value is compared with the preset upper and lower limit thresholds of the current abnormal state value to determine whether there is any abnormality in the operation of the high-voltage cable.

8. The method for detecting abnormality of a high-voltage cable based on RPA according to claim 1, characterized in that: The index data of the abnormal area includes sheath current and sheath induced voltage data.

9. The method for detecting abnormality of a high-voltage cable based on RPA according to claim 1, characterized in that: A circulating current detection circuit is used to collect grounding current data of the high-voltage cable. The circulating current detection circuit includes a current transformer, an operational amplifier and an analog-to-digital converter connected in sequence. The circulating current detection circuit is installed in an outdoor field terminal or an intermediate joint cross-connection box. The outdoor field terminal is directly grounded, and both ends of the intermediate joint cross-connection box are grounded.

10. A system using a high-voltage cable anomaly detection method based on RPA as described in any one of claims 1 to 9, characterized in that: include: The information collection module is used to collect the abnormal state values ​​of the grounding current of the high-voltage cable at different time periods, and to collect the sheath current and induced voltage index data under the RPA abnormal operation detection mode; A judgment module is used to judge whether the high-voltage cable is abnormal according to the abnormal state value of the ground current. If so, the abnormal area is located and the RPA abnormal operation detection module is executed for the abnormal current state area; The RPA abnormal operation detection module is used to calculate the weight set based on the comprehensive weight model according to the collected sheath current and induced voltage index data; to conduct status evaluation on the index data and its weight set through the fuzzy comprehensive evaluation method to obtain the fuzzy comprehensive evaluation results; and to determine the corresponding maintenance plan based on the obtained fuzzy comprehensive evaluation results.

Images