Performance detection method for connecting element in electrical engineering
By obtaining the current and temperature data of terminal blocks under different temperature conditions, calculating the abnormality and comprehensive abnormality, and using the isolated forest model to adjust the detection sensitivity, the problem that traditional methods cannot adaptively adjust the performance detection of terminal blocks is solved, and accurate performance detection and dynamic adjustment of detection sensitivity under different temperature conditions is achieved.
Patent Information
- Application Number
- CN202510200223.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-02-24
- Publication Date
- 2025-03-25
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
Traditional methods cannot adaptively adjust the performance detection of terminal blocks, especially under different batches and temperature conditions, and cannot dynamically adjust the sensitivity of abnormal detection.
By obtaining the current data timing sequence and temperature data timing sequence of terminal blocks under different temperature conditions, the abnormality and comprehensive anomalies of each terminal block are calculated, and the detection sensitivity is adjusted according to the abnormality ratio using an isolated forest model.
It realizes accurate detection of the performance of the terminal block under different temperature conditions, dynamically adjusts the sensitivity of abnormal detection, and improves the accuracy and applicability of performance detection.
Smart Images
Figure CN119691659A_ABST
Abstract
Description
Technical Field
[0001] The invention relates to the technical field of data processing, and in particular to a performance detection method for connecting elements in electrical engineering. Background Art
[0002] With the popularization of electrical equipment and the improvement of safety requirements, the performance detection of terminal blocks, which are connection components, has become increasingly important. However, different batches of terminal blocks may have performance differences due to factors such as raw materials, manufacturing processes, and production environments. In traditional methods, the isolation forest algorithm is used to analyze the electrical variable data of terminal blocks, but the number of trees is usually fixed, and it is impossible to adaptively adjust the performance of terminal blocks in different batches and at different temperatures, and it is impossible to dynamically adjust the sensitivity of anomaly detection. Summary of the invention
[0003] The invention provides a performance detection method for a connection element in electrical engineering to solve the existing problems.
[0004] The performance detection method for connecting elements in electrical engineering of the present invention adopts the following technical scheme: An embodiment of the present invention provides a method for detecting performance of a connection element in electrical engineering, the method comprising the following steps: For a plurality of terminal blocks, a current data time series sequence and a temperature data time series sequence of each terminal block under a plurality of different temperature conditions within a period of time are obtained; Obtain the peak point in the current data time series of each terminal block; obtain the abnormality of each terminal block according to the peak point and current data in the current data time series of each terminal block under the same temperature condition; obtain the comprehensive abnormality of each terminal block according to the abnormality of each terminal block under different temperature conditions; Obtaining an abnormal value of each terminal row according to the current data difference between adjacent peak points in the current data time series sequence under the same temperature condition and the temperature data in the temperature data time series sequence of the terminal row; Obtaining comprehensive abnormal parameters of each terminal block according to the abnormal value and comprehensive abnormality of each terminal block under the same temperature condition; According to the comprehensive abnormal parameters of each terminal block, the abnormal ratio of the terminal block is obtained; the abnormal ratio of the terminal block is used as the adjustment coefficient of the isolation forest tree to construct an isolation forest model; and the performance of the terminal block is determined according to the isolation forest model.
[0005] Preferably, the step of obtaining the abnormality of each terminal block according to the peak point and current data in the current data time series of each terminal block under the same temperature condition comprises the following specific steps: The adjacent peak points are regarded as the starting point and the end point of the same cycle, the data between the adjacent peak points is regarded as a complete cycle, and the current data time series of the terminal block is divided into several cycles; The abnormality of each terminal row is obtained according to the number of cycles of the current data time series of each terminal row under the same temperature condition, the number of current data in the cycle and the difference.
[0006] Preferably, the abnormality of each terminal block is obtained according to the number of cycles of the current data timing sequence of each terminal block under the same temperature condition, the number of current data in the cycle and the difference, including the specific calculation formula as follows: Where: Indicated in Under the temperature condition, The abnormality of each terminal block; Indicates the preset number of terminal blocks; Indicated in Under the temperature condition, The number of cycles of the current data timing sequence of each terminal row; Indicated in Under the temperature condition, The current data timing sequence of the terminal block The number of current data in a cycle; Indicated in Under the temperature condition, The average value of the number of current data in all cycles of the current data timing sequence of the terminal blocks; Indicated in Under the temperature condition, The first of the current data timing sequence of the terminal block The time corresponding to the first current data in a cycle; For the Under the temperature condition, The time corresponding to the last current data in the current data timing sequence of a terminal row; Indicated in Under the temperature condition, The first in the current data timing sequence of the terminal block The difference between the maximum current data and the minimum current data in a cycle; represents the linear normalization function; for Belong to the interval All internal time The standard deviation of .
[0007] Preferably, the step of obtaining the comprehensive abnormality of each terminal block according to the abnormality of each terminal block under different temperature conditions comprises the following specific steps: The first Under the temperature condition, The abnormality of the first terminal block accounts for all the abnormalities under different temperature conditions. The proportion of the sum of the abnormalities of the terminal rows is recorded as Under the temperature condition, The comprehensive abnormality of each terminal block.
[0008] Preferably, the method of obtaining the abnormal value of each terminal block according to the current data difference between adjacent peak points in the current data time series sequence under the same temperature condition and the temperature data in the temperature data time series sequence of the terminal block comprises the following specific steps: Calculate the absolute value of the difference between any two adjacent peak points in the current data time series of each terminal row, and record it as the current peak difference of the terminal row; The largest one of the current peak differences is recorded as the first current peak difference; According to the difference between each current peak difference of each terminal row and the first current peak difference, the similarity of the current peak difference of each terminal row is obtained; The abnormal value of each terminal row is obtained according to the number of current peak differences of the terminal row, the first current peak difference, the similarity of the current peak difference of each terminal row and the temperature data in the temperature data time series sequence under the same temperature condition.
[0009] Preferably, the obtaining of the similarity of the current peak difference of each terminal row according to the difference between each current peak difference of each terminal row and the first current peak difference comprises the following specific steps: The average of the absolute values of the differences between all the current peak differences of each terminal row and the first current peak difference is recorded as the similarity of the current peak difference of each terminal row.
[0010] Preferably, the abnormal value of each terminal row is obtained according to the number of current peak differences of the terminal row, the first current peak difference, the similarity of the current peak difference of each terminal row and the temperature data in the temperature data time series under the same temperature condition, and the specific calculation formula included is as follows: Where: Indicated in Under the temperature condition, Outliers for terminal blocks; Indicated in Under the temperature condition, The first current peak value difference of each terminal row; Indicated in Under the temperature condition, The number of current peak differences of the terminal blocks; Indicated in Under the temperature condition, The similarity of the current peak difference of the terminal blocks; Indicated in Under the temperature condition, Terminal block No. The current peak difference; Indicated in Under the temperature condition, The number of temperature data in the temperature data timing sequence of each terminal row; Indicated in Under the temperature condition, The temperature data timing sequence of the terminal block and The absolute value of the difference between the temperature data; for Belong to the interval All internal time The standard deviation of .
[0011] Preferably, the step of obtaining the comprehensive abnormality parameter of each terminal block according to the abnormal value and comprehensive abnormality degree of each terminal block under the same temperature condition comprises the following specific steps: Where: Indicates Comprehensive abnormal parameters of each terminal block; Indicates the number of presets for different temperature conditions; Indicated in Under the temperature condition, The comprehensive abnormality of each terminal block; Indicated in Under the temperature condition, Outliers for the terminal blocks.
[0012] Preferably, the step of obtaining the abnormal ratio of the terminal block according to the comprehensive abnormal parameters of each terminal block comprises the following specific steps: The comprehensive abnormal parameters of all terminal blocks are clustered by K-menas clustering to obtain several clusters; The cluster with the largest number of sample points is recorded as the largest cluster; The ratio of the mean number of sample points contained in clusters other than the largest cluster to the number of sample points contained in the largest cluster is recorded as the abnormal ratio of the terminal block.
[0013] Preferably, the determining the performance of the terminal block according to the isolation forest model comprises the following specific steps: The comprehensive anomaly parameters of each terminal block are evaluated using the isolation forest model to obtain the anomaly score of each terminal block; A terminal block with an abnormality score greater than or equal to a preset threshold is determined to be an abnormal terminal block.
[0014] The beneficial effect of the technical solution of the present invention is that by obtaining the comprehensive abnormality of the terminal block at different temperatures, the abnormal weight of the terminal block at each temperature can be determined, and the abnormal value of the terminal block at each temperature is comprehensively considered to determine its comprehensive abnormality parameter. This comprehensive performance takes into account the distinction between the performance of normal and abnormal terminal blocks at different temperatures, so that the difference between them is more obvious. In addition, this method can dynamically adjust the sensitivity of abnormality detection, thereby improving the accuracy and applicability of performance detection. BRIEF DESCRIPTION OF THE DRAWINGS
[0015] 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, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0016] Figure 1 The present invention is a flowchart of the steps of a method for detecting performance of connection elements in electrical engineering. DETAILED DESCRIPTION
[0017] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of the performance detection method for connecting elements in electrical engineering proposed by the present invention, its specific implementation, structure, features and effects, in conjunction with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.
[0018] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
[0019] A specific scheme of a performance detection method for connection elements in electrical engineering provided by the present invention is described in detail below with reference to the accompanying drawings.
[0020] See also Figure 1 , which shows a flow chart of a method for detecting performance of a connection element in electrical engineering provided by an embodiment of the present invention, the method comprising the following steps: Step S001: for a plurality of terminal blocks, obtaining a current data time series sequence and a temperature data time series sequence of each terminal block under a plurality of different temperature conditions within a period of time.
[0021] Within a period of time, current data timing sequences and temperature data timing sequences of a plurality of terminal blocks under a full-load working state under a plurality of temperature conditions are obtained.
[0022] In this embodiment, the preset number of terminal blocks is 6, the preset number of different temperature conditions is 5, the acquisition time of the current data timing sequence and the temperature data timing sequence is 2 hours, the acquisition frequency is once every 5 minutes, and the current data acquisition environment is a constant temperature room. Other values can be used in other cases, and this embodiment does not specifically limit it.
[0023] Step S002: Obtain the peak point in the current data timing sequence of each terminal block; obtain the abnormality of each terminal block based on the peak point and current data in the current data timing sequence of each terminal block under the same temperature condition; obtain the comprehensive abnormality of each terminal block based on the abnormality of each terminal block under different temperature conditions.
[0024] Under different temperature environments, the performance of normal terminal blocks is usually relatively consistent, while defective terminal blocks may show different degrees of performance differences. Considering the impact of different temperatures on the performance of terminal blocks, especially at lower temperatures, performance defects may not be easy to expose, making it difficult to distinguish between normal and defective terminal blocks. Therefore, when analyzing the relevant data of terminal blocks, it is necessary to consider the discrimination performance of normal and defective terminal blocks at different temperatures. When analyzing the discrimination performance of terminal blocks under different temperature environments, the more consistent the current data performance of the terminal blocks at the same temperature, the more stable the performance of the terminal blocks at the current temperature.
[0025] The peak point in the terminal block current data time series is obtained, and the adjacent peak points are regarded as the starting point and the end point in the same cycle. The data between the adjacent peak points is a complete cycle, and the terminal block current data time series is divided into several cycles. It should be noted that the peak point is obtained by a peak detection algorithm, which is a well-known technology and the specific method is not introduced here.
[0026] This embodiment provides a calculation method for evaluating the abnormality of the terminal block as follows: Where: Indicated in Under the temperature condition, The abnormality of each terminal block; Indicates the preset number of terminal blocks; Indicated in Under the temperature condition, The number of cycles of the current data timing sequence of each terminal row; Indicated in Under the temperature condition, The current data timing sequence of the terminal block The number of current data in a cycle; Indicated in Under the temperature condition, The average value of the number of current data in all cycles of the current data timing sequence of the terminal blocks; Indicated in Under the temperature condition, The first of the current data timing sequence of the terminal block The time corresponding to the first current data in a cycle; For the Under the temperature condition, The time corresponding to the last current data in the current data timing sequence of a terminal row; Indicated in Under the temperature condition, The first in the current data timing sequence of the terminal block The difference between the maximum current data and the minimum current data in a cycle; represents the linear normalization function; for Belong to the interval All internal time The standard deviation of .
[0027] Similarly, obtain the abnormality of each terminal block under different temperature conditions. Under the temperature condition, The abnormality of the terminal block accounts for the following under different temperature conditions: The proportion of the sum of the abnormalities of the terminal rows is recorded as Under the temperature condition, The comprehensive abnormality of each terminal block.
[0028] Step S003: obtaining an abnormal value of each terminal block according to the current data difference between adjacent peak points in the current data time series sequence under the same temperature condition and the temperature data in the temperature data time series sequence of the terminal block.
[0029] When analyzing abnormal characteristics of terminal blocks, it is necessary to consider the performance of current at different temperatures. Abnormal characteristics of current may include whether the fluctuations at various temperatures are within the normal range, and whether there are obvious current fluctuations, current interruptions, or unstable balance caused by internal material device failures or poor wiring. Therefore, it is necessary to analyze the abnormal characteristics that may exist in the terminal block in depth based on the current performance at different temperatures to improve the accuracy and sensitivity of abnormal detection.
[0030] The absolute value of the difference between any two adjacent peak points in the current data timing sequence of each terminal row is calculated, and recorded as the current peak difference of the terminal row. The largest one of the current peak differences is recorded as the first current peak difference. In this embodiment, the peak point is obtained by a peak detection algorithm, which is a well-known technology, and the specific method is not repeated in this embodiment.
[0031] The average of the absolute values of the differences between all the current peak differences of each terminal row and the first current peak difference is recorded as the similarity of the current peak difference of each terminal row.
[0032] This embodiment provides a calculation method for evaluating the abnormal value of the terminal block as follows: Where: Indicated in Under the temperature condition, Outliers for terminal blocks; Indicated in Under the temperature condition, The first current peak value difference of each terminal row; Indicated in Under the temperature condition, The number of current peak differences of the terminal blocks; Indicated in Under the temperature condition, The similarity of the current peak difference of the terminal blocks; Indicated in Under the temperature condition, Terminal block No. The current peak difference; Indicated in Under the temperature condition, The number of temperature data in the temperature data timing sequence of each terminal row; Indicated in Under the temperature condition, The temperature data timing sequence of the terminal block and The absolute value of the difference between the temperature data; for Belong to the interval All internal time The standard deviation of .
[0033] Step S004: Obtain the comprehensive abnormality parameters of each terminal block according to the abnormal value and comprehensive abnormality degree of each terminal block under the same temperature condition.
[0034] The comprehensive abnormality of the terminal block at different temperatures, and the abnormal value of the terminal block at each temperature. The comprehensive abnormality is used as the feature weight, which is regarded as the key factor to guide the comprehensive evaluation, and the abnormal value of each terminal block at each temperature is used as the reference value. By combining the feature weight with the reference value, the comprehensive abnormal parameters of each terminal block are comprehensively determined.
[0035] This embodiment provides a calculation method for obtaining comprehensive abnormal parameters of the terminal block as follows: Where: Indicates Comprehensive abnormal parameters of each terminal block; Indicates the number of presets for different temperature conditions; Indicated in Under the temperature condition, The comprehensive abnormality of each terminal block; Indicated in Under the temperature condition, Outliers for the terminal blocks.
[0036] Step S005: according to the comprehensive abnormal parameters of each terminal block, obtain the abnormal ratio of the terminal block; use the abnormal ratio of the terminal block as the adjustment coefficient of the isolation forest tree to construct an isolation forest model; and determine the performance of the terminal block according to the isolation forest model.
[0037] The terminal strips are evaluated using Isolation Forest to identify samples that may have problems. For different clusters in the clustering results, the largest cluster is considered the best performing terminal strip, and samples in other clusters may have problems.
[0038] The comprehensive abnormal parameters of all terminal blocks are clustered by K-menas clustering to obtain several clusters, among which the cluster with the largest number of sample points is recorded as the largest cluster.
[0039] The ratio of the mean number of sample points in clusters other than the largest cluster to the number of sample points in the largest cluster is recorded as the abnormal ratio of the terminal row, and the abnormal ratio of the terminal row is used as the adjustment coefficient of the isolated forest tree.
[0040] The isolation forest model is constructed according to the preset reference value, the preset fluctuation range, the adjustment coefficient and the comprehensive abnormal parameters of each terminal block. The construction of the isolation forest model is a well-known technology, and the specific method is not introduced here.
[0041] The isolation forest model is used to evaluate the comprehensive abnormal parameters of each terminal block to obtain the abnormal score of each terminal block. The terminal blocks with abnormal scores greater than or equal to a preset threshold are determined to be abnormal terminal blocks.
[0042] In this embodiment, the preset threshold value is 0.92, the preset reference value is 50, and the preset fluctuation range is 100. Other numerical values may be used in other implementations, and this implementation does not specifically limit them.
[0043] So far, the present invention is completed.
[0044] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the principles of the present invention should be included in the protection scope of the present invention.
Claims
1. A performance detection method for connecting elements in electrical engineering, characterized in that: The method comprises the following steps: For a plurality of terminal blocks, a current data time series sequence and a temperature data time series sequence of each terminal block under a plurality of different temperature conditions within a period of time are obtained; Obtain the peak point in the current data time series of each terminal block; obtain the abnormality of each terminal block according to the peak point and current data in the current data time series of each terminal block under the same temperature condition; obtain the comprehensive abnormality of each terminal block according to the abnormality of each terminal block under different temperature conditions; Obtaining an abnormal value of each terminal row according to the current data difference between adjacent peak points in the current data time series sequence under the same temperature condition and the temperature data in the temperature data time series sequence of the terminal row; Obtaining comprehensive abnormal parameters of each terminal block according to the abnormal value and comprehensive abnormality of each terminal block under the same temperature condition; According to the comprehensive abnormal parameters of each terminal block, the abnormal ratio of the terminal block is obtained; the abnormal ratio of the terminal block is used as the adjustment coefficient of the isolation forest tree to construct an isolation forest model; and the performance of the terminal block is determined according to the isolation forest model.
2. A performance detection method for connection elements in electrical engineering according to claim 1, characterized in that: The specific steps of obtaining the abnormality of each terminal block according to the peak point and current data in the current data time series of each terminal block under the same temperature condition include the following: The adjacent peak points are regarded as the starting point and the end point of the same cycle, the data between the adjacent peak points is regarded as a complete cycle, and the current data time series of the terminal block is divided into several cycles; The abnormality of each terminal row is obtained according to the number of cycles of the current data time series of each terminal row under the same temperature condition, the number of current data in the cycle and the difference.
3. A performance detection method for connection elements in electrical engineering according to claim 2, characterized in that: The abnormality of each terminal row is obtained according to the number of cycles of the current data time series of each terminal row under the same temperature condition, the number of current data in the cycle and the difference, including the specific calculation formula as follows: Where: Indicated in Under the temperature condition, The abnormality of each terminal block; Indicates the preset number of terminal blocks; Indicated in Under the temperature condition, The number of cycles of the current data timing sequence of each terminal row; Indicated in Under the temperature condition, The current data timing sequence of the terminal block The number of current data in a cycle; Indicated in Under the temperature condition, The average value of the number of current data in all cycles of the current data timing sequence of the terminal blocks; Indicated in Under the temperature condition, The first of the current data timing sequence of the terminal block The time corresponding to the first current data in a cycle; For the Under the temperature condition, The time corresponding to the last current data in the current data timing sequence of a terminal row; Indicated in Under the temperature condition, The first in the current data timing sequence of the terminal block The difference between the maximum current data and the minimum current data in a cycle; represents the linear normalization function; for Belong to the interval All internal time The standard deviation of .
4. A performance detection method for connection elements in electrical engineering according to claim 1, characterized in that: The method of obtaining the comprehensive abnormality degree of each terminal block according to the abnormality degree of each terminal block under different temperature conditions includes the following specific steps: The first Under the temperature condition, The abnormality of the first terminal block accounts for all the abnormalities under different temperature conditions. The proportion of the sum of the abnormalities of the terminal rows is recorded as Under the temperature condition, The comprehensive abnormality of each terminal block.
5. A performance detection method for connection elements in electrical engineering according to claim 1, characterized in that: The method of obtaining the abnormal value of each terminal row according to the current data difference between adjacent peak points in the current data time series under the same temperature condition and the temperature data in the temperature data time series of the terminal row includes the following specific steps: Calculate the absolute value of the difference between any two adjacent peak points in the current data time series of each terminal row, and record it as the current peak difference of the terminal row; The largest one of the current peak differences is recorded as the first current peak difference; According to the difference between each current peak difference of each terminal row and the first current peak difference, the similarity of the current peak difference of each terminal row is obtained; The abnormal value of each terminal row is obtained according to the number of current peak differences of the terminal row, the first current peak difference, the similarity of the current peak difference of each terminal row and the temperature data in the temperature data time series sequence under the same temperature condition.
6. A performance detection method for connection elements in electrical engineering according to claim 5, characterized in that: The method of obtaining the similarity of the current peak difference of each terminal row according to the difference between each current peak difference of each terminal row and the first current peak difference comprises the following specific steps: The average of the absolute values of the differences between all the current peak differences of each terminal row and the first current peak difference is recorded as the similarity of the current peak difference of each terminal row.
7. A performance detection method for connection elements in electrical engineering according to claim 5, characterized in that: The specific calculation formula for obtaining the abnormal value of each terminal row according to the number of current peak differences of the terminal row, the first current peak difference, the similarity of the current peak difference of each terminal row and the temperature data in the temperature data time series sequence under the same temperature condition is as follows: Where: Indicated in Under the temperature condition, Outliers for terminal blocks; Indicated in Under the temperature condition, The first current peak value difference of each terminal row; Indicated in Under the temperature condition, The number of current peak differences of the terminal blocks; Indicated in Under the temperature condition, The similarity of the current peak difference of the terminal blocks; Indicated in Under the temperature condition, Terminal block No. The current peak difference; Indicated in Under the temperature condition, The number of temperature data in the temperature data timing sequence of each terminal row; Indicated in Under the temperature condition, The temperature data timing sequence of the terminal block and The absolute value of the difference between the temperature data; for Belong to the interval All internal time The standard deviation of .
8. A performance detection method for connection elements in electrical engineering according to claim 1, characterized in that: The method of obtaining the comprehensive abnormality parameter of each terminal block according to the abnormal value and comprehensive abnormality degree of each terminal block under the same temperature condition includes the following specific steps: Where: Indicates Comprehensive abnormal parameters of each terminal block; Indicates the number of presets for different temperature conditions; Indicated in Under the temperature condition, The comprehensive abnormality of each terminal block; Indicated in Under the temperature condition, Outliers for the terminal blocks.
9. A performance detection method for connection elements in electrical engineering according to claim 1, characterized in that: The method of obtaining the abnormal ratio of the terminal block according to the comprehensive abnormal parameters of each terminal block includes the following specific steps: The comprehensive abnormal parameters of all terminal blocks are clustered by K-menas clustering to obtain several clusters; The cluster with the largest number of sample points is recorded as the largest cluster; The ratio of the mean number of sample points contained in clusters other than the largest cluster to the number of sample points contained in the largest cluster is recorded as the abnormal ratio of the terminal block.
10. A performance detection method for connection elements in electrical engineering according to claim 1, characterized in that: The specific steps of determining the performance of the terminal block according to the isolation forest model are as follows: The comprehensive anomaly parameters of each terminal block are evaluated using the isolation forest model to obtain the anomaly score of each terminal block; A terminal block with an abnormality score greater than or equal to a preset threshold is determined to be an abnormal terminal block.