Intelligent switch cabinet abnormal operation detection method and system

Abstract

The invention provides an intelligent switch cabinet abnormal operation detection method and system, and relates to the technical field of electrical equipment monitoring, and the method comprises the steps: S1, employing an electrical parameter sensor to collect the multi-dimensional operation data of the current, voltage, temperature, mechanical vibration and partial discharge of a switch cabinet, and carrying out the data preprocessing; s2, performing feature extraction on the multi-dimensional operation data after data preprocessing; s3, performing intelligent classification and anomaly detection on the multi-dimensional operation data after feature extraction by adopting a support vector machine algorithm of particle swarm optimization; s4, fault positioning is carried out on the switch cabinet according to the intelligent classification and anomaly detection results; according to the invention, real-time data processing can be realized, comprehensive monitoring, fault early warning and accurate positioning of the operation state of the switch cabinet are realized, and the operation safety and reliability of the switch cabinet are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of electrical equipment monitoring, in particular to an intelligent switch cabinet abnormal operation detection method and system. BACKGROUND

[0002] In modern power systems, switch cabinets, as the core equipment of power distribution and control, their running state is directly related to the stability and reliability of the power system. With the complexity of the running state of power equipment and the continuous growth of urban electricity demand, switch cabinets may have faults such as poor contact, partial discharge, abnormal temperature rise, etc. during long-term operation. If these faults are not detected and handled in time, it may lead to equipment damage, power outage accidents or even major safety hazards.

[0003] The current technical means for switch cabinet abnormal detection has obvious shortcomings: traditional relay protection devices can only act after a fault occurs, and cannot realize early warning; the detection precision of the temperature reaction film is low, and it cannot realize real-time dynamic monitoring of temperature changes; the ultrasonic detection method cannot effectively distinguish different types of faults such as discharge and temperature anomaly; the single sensor measurement mode cannot accurately determine the fault phase and position, and there is a detection blind area. In addition, the existing manual inspection method is not only low in efficiency, but also depends on the experience of the detection personnel, and it is difficult to meet the real-time monitoring needs of intelligent power grids. SUMMARY

[0004] The purpose of the present application is to provide an intelligent switch cabinet abnormal operation detection method and system which can solve the problems described in the background.

[0005] The technical scheme of the present application is: In a first aspect, the present application provides an intelligent switch cabinet abnormal operation detection method and system, which includes the following steps: S1, using an electrical parameter sensor to collect multi-dimensional running data of current, voltage, temperature, mechanical vibration and partial discharge of the switch cabinet, and performing data preprocessing; S2, performing feature extraction on the multi-dimensional running data after data preprocessing; S3, using a particle swarm optimization support vector machine algorithm to intelligently classify and detect abnormalities of the multi-dimensional running data after feature extraction; S4, locating the fault of the switch cabinet according to the results of intelligent classification and abnormal detection.

[0006] Further, in step S1, the data preprocessing includes denoising, data calibration, normalization and missing value processing.

[0007] Further, step S2 includes: The raw signal of the multi-dimensional running data after preprocessing is decomposed into 16 sub-bands; the energy value of each sub-band is calculated, and the calculation formula includes: In the formula, E 4,j For the first j The energy values ​​of each sub-band, where n is the number of discrete points. x j,k For the first j The amplitude of the kth discrete point in each sub-band; The feature vector is constructed using the energy values ​​of each sub-band as elements, and its calculation formula is as follows: In the formula, T is a feature vector constructed using sub-band energy values ​​as elements. E 4,0 This represents the initial sub-band energy value. E 4,15 This is the energy value of the 15th sub-band. The feature vector is normalized to obtain the feature extraction result, and the calculation formula is as follows: In the formula, T' Let E be the normalized eigenvector, and E be the sum of the energy values ​​of all sub-bands.

[0008] Further, step S3 includes: Data on switchgear under normal and abnormal conditions were collected from the multi-dimensional operational data after feature extraction, and training and testing sets were constructed based on the collected switchgear data. The support vector machine algorithm with particle swarm optimization and minimizing classification error is used as the optimization objective. The penalty factor and kernel function parameters of the SVN classifier are optimized, and their calculation formulas include: In the formula, For particles i exist k+ Speed ​​at moment 1 For particles i exist k The speed of time, For particles i exist k+ 1. Position at a given moment For particles i exist k Location at any given moment ω Inertia factor c1 ,c2 is an acceleration factor, r1 , r2 is a random number, is a particle i is the individual optimal position at k is the global optimal position at is the global optimal position at k is the global optimal position at the penalty factor and the kernel function parameter of the SVN classifier optimized by the particle swarm are used to train the SVM classifier with the training set to obtain a PSO-SVM classifier, the test set is input into the PSO-SVM classifier to perform intelligent classification and abnormality detection on the multi-dimensional operation data of the switch cabinet.

[0009] Further, in step S4, the process of fault positioning includes: according to the results of intelligent classification and abnormality detection, four or more ultrasonic sensors are arranged in the switch cabinet to form a positioning array; the time difference of the partial discharge signal reaching each ultrasonic sensor is measured; the discharge source coordinates are solved according to the time difference and the sound wave propagation speed, so as to output the fault positioning coordinates; wherein the calculation formula for solving the discharge source coordinates is: wherein, di is the distance from the discharge source to the first i ultrasonic sensor, x , y , z is the discharge source coordinates, x i , y i , z i is the coordinates of the first i ultrasonic sensor in space, v is the sound velocity, t i is the time when the ultrasonic wave reaches the first i ultrasonic sensor, t 0 is the discharge occurrence time.

[0010] In a second aspect, the application provides an intelligent switch cabinet abnormal operation detection system, comprising: a data acquisition module, configured to collect multi-dimensional operation data of current, voltage, temperature, mechanical vibration and partial discharge of the switch cabinet by using an electrical parameter sensor, and perform data preprocessing; The feature extraction module is used to extract features from the multi-dimensional running data after data preprocessing; the data classification and detection module is used to perform intelligent classification and anomaly detection on the multi-dimensional running data after feature extraction using a particle swarm optimization support vector machine algorithm. The fault location module is used to locate faults in the switchgear based on the results of intelligent classification and anomaly detection.

[0011] Furthermore, the above data preprocessing includes noise reduction, data calibration, normalization, and missing value handling.

[0012] Furthermore, the process of feature extraction from the preprocessed multi-dimensional operational data includes: The original signal of the multi-dimensional running data after data preprocessing is decomposed into 16 sub-frequency bands; The energy value of each sub-band is calculated using the following formulas: In the formula, E 4,j For the first j The energy values ​​of each sub-band, where n is the number of discrete points. x j,k For the first j The amplitude of the kth discrete point in each sub-band; The feature vector is constructed using the energy values ​​of each sub-band as elements, and its calculation formula is as follows: In the formula, T is a feature vector constructed using sub-band energy values ​​as elements. E 4,0 This represents the initial sub-band energy value. E 4,15 This is the energy value of the 15th sub-band. The feature vector is normalized to obtain the feature extraction result, and the calculation formula is as follows: In the formula, T' Let E be the normalized eigenvector, and E be the sum of the energy values ​​of all sub-bands.

[0013] Furthermore, the process of intelligent classification and anomaly detection of multi-dimensional running data after feature extraction using the support vector machine algorithm with particle swarm optimization includes: Data on switchgear under normal and abnormal conditions were collected from the multi-dimensional operational data after feature extraction, and training and testing sets were constructed based on the collected switchgear data. The support vector machine algorithm with particle swarm optimization and minimizing classification error is used as the optimization objective. The penalty factor and kernel function parameters of the SVN classifier are optimized, and their calculation formulas include: In the formula, For particles i exist k+ Speed ​​at moment 1 For particles i exist k The speed of time, For particles i exist k+ 1. Position at a given moment For particles i exist k Location at any given moment ω Inertia factor c1 , c2 As an acceleration factor, r1 , r2 It is a random number. For particles i exist k The optimal position of an individual at any given time. for k The globally optimal position at any given time; The PSO-SVM classifier is obtained by training the SVM classifier using the penalty factor and kernel function parameters of the SVN classifier optimized by particle swarm optimization on the training set. The test set is input into the PSO-SVM classifier for intelligent classification and anomaly detection of multi-dimensional operational data of the switchgear.

[0014] Furthermore, the above-mentioned fault location process includes: Based on the results of intelligent classification and anomaly detection, more than four ultrasonic sensors are distributed and installed inside the switch cabinet. Wave sensors are used to form a positioning array; Measure the time difference between the arrival of the partial discharge signal at each ultrasonic sensor; The coordinates of the power supply are determined based on the time difference and the speed of sound wave propagation, so as to output the fault location coordinates; The formula for calculating the coordinates of the power source is as follows: In the formula, di To discharge the power to the first i The distance of an ultrasound wave, ( x , y , z ) represents the coordinates of the power source. x i , y i ,z i ) is the first i The coordinates of an ultrasonic sensor in space. v For the speed of sound, t i For ultrasound to reach the first i The time of each ultrasonic sensor t 0 This represents the time when the discharge occurs.

[0015] Thirdly, this application provides an electronic device, comprising: Memory, used to store one or more programs; processor; When one or more of the above programs are executed by the above processor, an intelligent switchgear abnormal operation detection method is implemented as described in any of the first aspects above.

[0016] Fourthly, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements an intelligent switchgear abnormal operation detection method as described in any of the first aspects above.

[0017] Compared with the prior art, the present invention has at least the following advantages or beneficial effects: (1) The present invention provides an intelligent switchgear abnormal operation detection method and system, which can process data in real time through multi-sensor data acquisition and information fusion, realize comprehensive monitoring of switchgear operation status, early warning of faults and accurate location, and improve the safety and reliability of switchgear operation; (2) The present invention uses the particle swarm optimization support vector machine algorithm to optimize parameters to construct the PSO-SVM classifier model, which significantly improves the anomaly identification accuracy, realizes the rapid location of fault sources and accurate identification of fault types, and provides decision support for operation and maintenance personnel; (3) This invention achieves three-dimensional precise location of the fault source by calculating the coordinates of the discharge source. Attached Figure Description

[0018] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is a flowchart illustrating the steps of an intelligent switchgear abnormal operation detection method according to the present invention. Figure 2This is a schematic structural block diagram of an electronic device according to an embodiment of the present invention.

[0020] Icons: 101, memory; 102, processor; 103, communication interface. Detailed Implementation

[0021] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are some embodiments of this application, but not all embodiments.

[0022] The components of the embodiments of this application described and illustrated in the accompanying drawings can typically be arranged and designed in a variety of different configurations.

[0023] Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely to illustrate selected embodiments of the application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0024] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

[0025] It should be noted that, in this document, the term "comprising" or any other variation thereof is intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0026] The following detailed description of some embodiments of this application is provided in conjunction with the accompanying drawings. Unless otherwise specified, the various embodiments and features described below can be combined with each other.

[0027] Example 1 Please see Figure 1 , Figure 1 The diagram shows the steps of an intelligent switchgear abnormal operation detection method and system provided in an embodiment of this application.

[0028] In a first aspect, this application provides an intelligent method and system for detecting abnormal operation of switchgear, which includes the following steps: S1. Use electrical parameter sensors to collect multi-dimensional operating data of the switchgear, including current, voltage, temperature, mechanical vibration, and partial discharge, and perform data preprocessing. S2. Extract features from the multi-dimensional running data after data preprocessing; S3. The particle swarm optimization support vector machine algorithm is used to perform intelligent classification and anomaly detection on the multi-dimensional running data after feature extraction; S4. Based on the results of intelligent classification and anomaly detection, locate the fault in the switchgear.

[0029] In step S3, if the detected anomaly type is an unknown anomaly, the Isolation Forest algorithm is used for detection. The detection process includes: The multi-dimensional running data after feature extraction is used as input, a feature and a split value of that feature are randomly selected, and the data is divided into two parts; The above process is repeated recursively for each subset until each subset contains only one sample or reaches a preset depth, at which point multiple isolated trees are constructed to form an isolated forest. Calculate the path length of each sample in the isolated tree; Anomaly scores are calculated based on path length, and samples exceeding a threshold are considered abnormal.

[0030] It should be noted that the electrical parameter sensors include high-precision current sensors, voltage sensors, temperature sensors, mechanical vibration sensors, and partial discharge sensors. The high-precision current sensor utilizes the Hall effect principle. The voltage sensor is installed at the busbar connection point to collect current and voltage signals from the main circuit and control circuit of the switchgear in real time. The temperature sensor combines a negative temperature coefficient thermistor array with an infrared temperature sensor to achieve comprehensive temperature field monitoring. It is installed at the circuit breaker contact point to monitor temperature anomalies caused by changes in contact resistance; it is also installed at the busbar connection point to monitor temperature anomalies at the connection point. The mechanical vibration sensor uses an accelerometer and is installed in the switchgear cabinet and operating mechanism to monitor mechanical vibration signals during the switch opening and closing process; abnormal signals can indicate mechanical faults. The partial discharge sensor integrates an ultra-high frequency sensor and an ultrasonic sensor, installed inside the switchgear to detect partial discharge phenomena inside the switchgear and whether insulation degradation has occurred.

[0031] In a preferred embodiment, step S1 includes data preprocessing, including noise reduction, data calibration, normalization, and missing value processing.

[0032] The noise reduction process includes using a combination of Gaussian filtering and median filtering to remove random noise and impulse interference from the signal; data calibration includes periodically calibrating sensor data based on a standard signal source; normalization process includes mapping sensor data of different types and ranges to the [0,1] interval to eliminate the influence of dimensions; and missing value processing includes using linear interpolation and prediction algorithms based on historical data to fill in occasionally missing data.

[0033] In a preferred embodiment, step S2 includes: The original signal of the multi-dimensional running data after data preprocessing is decomposed into 16 sub-frequency bands; The energy value of each sub-band is calculated using the following formulas: In the formula, E 4,j For the first j The energy values ​​of each sub-band, where n is the number of discrete points. x j,k For the first j The amplitude of the kth discrete point in each sub-band; The feature vector is constructed using the energy values ​​of each sub-band as elements, and its calculation formula is as follows: In the formula, T is a feature vector constructed using sub-band energy values ​​as elements. E 4,0 This represents the initial sub-band energy value. E 4,15 This is the energy value of the 15th sub-band. The feature vector is normalized to obtain the feature extraction result, and the calculation formula is as follows: In the formula, T' Let E be the normalized eigenvector, and E be the sum of the energy values ​​of all sub-bands.

[0034] In a preferred embodiment, step S3 includes: Data on switchgear under normal and abnormal conditions were collected from the multi-dimensional operational data after feature extraction, and training and testing sets were constructed based on the collected switchgear data. The support vector machine algorithm with particle swarm optimization and minimizing classification error is used as the optimization objective. The penalty factor and kernel function parameters of the SVN classifier are optimized, and their calculation formulas include: In the formula, For particles iexist k+ Speed ​​at moment 1 For particles i exist k The speed of time, For particles i exist k+ 1. Position at a given moment For particles i exist k Location at any given moment ω Inertia factor c1 , c2 As an acceleration factor, r1 , r2 It is a random number. For particles i exist k The optimal position of an individual at any given time. for k The globally optimal position at any given time; The PSO-SVM classifier is obtained by training the SVM classifier using the penalty factor and kernel function parameters of the SVN classifier optimized by particle swarm optimization on the training set. The test set is input into the PSO-SVM classifier for intelligent classification and anomaly detection of multi-dimensional operational data of the switchgear.

[0035] In a preferred embodiment, step S4, the fault location process includes: Based on the results of intelligent classification and anomaly detection, more than four ultrasonic sensors are distributed inside the switch cabinet to form a positioning array; Measure the time difference between the arrival of the partial discharge signal at each ultrasonic sensor; The coordinates of the power supply are determined based on the time difference and the speed of sound wave propagation to output the fault location coordinates; the formula for calculating the coordinates of the power supply is as follows: In the formula, di To discharge the power to the first i The distance of an ultrasound wave, ( x , y , z ) represents the coordinates of the power source. x i , y i , z i ) is the first i The coordinates of an ultrasonic sensor in space. v For the speed of sound, t i For ultrasound to reach the first iThe time of each ultrasonic sensor t 0 This represents the time when the discharge occurs.

[0036] Example 2 Secondly, this application provides an intelligent switchgear abnormal operation detection system, comprising: The data acquisition module is used to collect multi-dimensional operating data of the switchgear, including current, voltage, temperature, mechanical vibration, and partial discharge, using electrical parameter sensors, and to perform data preprocessing. The feature extraction module is used to extract features from the multi-dimensional operational data after data preprocessing; the data classification and detection module is used to perform intelligent classification and anomaly detection on the multi-dimensional operational data after feature extraction using a particle swarm optimization support vector machine algorithm; and the fault location module is used to locate faults in the switchgear based on the results of intelligent classification and anomaly detection.

[0037] In step S3, if the detected anomaly type is an unknown anomaly, the Isolation Forest algorithm is used for detection. The detection process includes: The multi-dimensional running data after feature extraction is used as input, a feature and a split value of that feature are randomly selected, and the data is divided into two parts; The above process is repeated recursively for each subset until each subset contains only one sample or reaches a preset depth, at which point multiple isolated trees are constructed to form an isolated forest. Calculate the path length of each sample in the isolated tree; Anomaly scores are calculated based on path length, and samples exceeding a threshold are considered abnormal.

[0038] It should be noted that the electrical parameter sensors include high-precision current sensors, voltage sensors, temperature sensors, mechanical vibration sensors, and partial discharge sensors. The high-precision current sensor utilizes the Hall effect principle. The voltage sensor is installed at the busbar connection point to collect current and voltage signals from the main circuit and control circuit of the switchgear in real time. The temperature sensor combines a negative temperature coefficient thermistor array with an infrared temperature sensor to achieve comprehensive temperature field monitoring. It is installed at the circuit breaker contact point to monitor temperature anomalies caused by changes in contact resistance; it is also installed at the busbar connection point to monitor temperature anomalies at the connection point. The mechanical vibration sensor uses an accelerometer and is installed in the switchgear cabinet and operating mechanism to monitor mechanical vibration signals during the switch opening and closing process; abnormal signals can indicate mechanical faults. The partial discharge sensor integrates an ultra-high frequency sensor and an ultrasonic sensor, installed inside the switchgear to detect partial discharge phenomena inside the switchgear and whether insulation degradation has occurred.

[0039] As a preferred implementation, data preprocessing includes noise reduction, data calibration, normalization, and missing value handling.

[0040] The noise reduction process includes using a combination of Gaussian filtering and median filtering to remove random noise and impulse interference from the signal; data calibration includes periodically calibrating sensor data based on a standard signal source; normalization process includes mapping sensor data of different types and ranges to the [0,1] interval to eliminate the influence of dimensions; and missing value processing includes using linear interpolation and prediction algorithms based on historical data to fill in occasionally missing data.

[0041] As a preferred implementation method, the process of feature extraction from multi-dimensional operational data after data preprocessing includes: The raw signal of the multi-dimensional running data after preprocessing is decomposed into 16 sub-bands; the energy value of each sub-band is calculated using the following formulas: In the formula, E 4,j For the first j The energy values ​​of each sub-band, where n is the number of discrete points. x j,k For the first j The amplitude of the kth discrete point in each sub-band; The feature vector is constructed using the energy values ​​of each sub-band as elements, and its calculation formula is as follows: In the formula, T is a feature vector constructed using sub-band energy values ​​as elements. E 4,0 This represents the initial sub-band energy value. E 4,15 This is the energy value of the 15th sub-band. The feature vector is normalized to obtain the feature extraction result, and the calculation formula is as follows: In the formula, T' Let E be the normalized eigenvector, and E be the sum of the energy values ​​of all sub-bands.

[0042] As a preferred implementation, the process of intelligently classifying and detecting anomalies in multi-dimensional runtime data after feature extraction using a particle swarm optimization support vector machine algorithm includes: Data on switchgear under normal and abnormal conditions were collected from the multi-dimensional operational data after feature extraction, and training and testing sets were constructed based on the collected switchgear data. The support vector machine algorithm with particle swarm optimization and minimizing classification error is used as the optimization objective. The penalty factor and kernel function parameters of the SVN classifier are optimized, and their calculation formulas include: In the formula, For particles i exist k+ Speed ​​at moment 1 For particles i exist k The speed of time, For particles i exist k+ 1. Position at a given moment For particles i exist k Location at any given moment ω Inertia factor c1 , c2 As an acceleration factor, r1 , r2 It is a random number. For particles i exist k The optimal position of an individual at any given time. for k The globally optimal position at any given time; The PSO-SVM classifier is obtained by training the SVM classifier using the penalty factor and kernel function parameters of the SVN classifier optimized by particle swarm optimization on the training set. The test set is input into the PSO-SVM classifier for intelligent classification and anomaly detection of multi-dimensional operational data of the switchgear.

[0043] As a preferred implementation method, the fault location process includes: Based on the results of intelligent classification and anomaly detection, more than four ultrasonic sensors are distributed inside the switch cabinet to form a positioning array; Measure the time difference between the arrival of the partial discharge signal at each ultrasonic sensor; calculate the power supply coordinates based on the time difference and the speed of sound wave propagation, and output the fault location coordinates. The formula for calculating the coordinates of the power source is as follows: In the formula, di To discharge the power to the first i The distance of an ultrasound wave, ( x , y , z ) represents the coordinates of the power source. x i , y i , zi ) is the first i The coordinates of an ultrasonic sensor in space. v For the speed of sound, t i For ultrasound to reach the first i The time of each ultrasonic sensor t 0 This represents the time when the discharge occurs.

[0044] Example 3 Please see Figure 2 , Figure 2 This is a schematic structural block diagram of an electronic device provided in an embodiment of this application.

[0045] An electronic device includes a memory 101, a processor 102, and a communication interface 103. The memory 101, processor 102, and communication interface 103 are electrically connected directly or indirectly to enable data transmission or interaction. For example, these components can be electrically connected to each other via one or more communication buses or signal lines. The memory 101 can be used to store software programs and modules. The processor 102 executes various functional applications and data processing by executing the software programs and modules stored in the memory 101. The communication interface 103 can be used for signaling or data communication with other node devices.

[0046] The memory 101 may be, but is not limited to, random access memory (RAM), read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), etc.

[0047] Processor 102 can be an integrated circuit chip with signal processing capabilities. Processor 102 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0048] It is understood that the structure shown in the figure is for illustrative purposes only. An intelligent switchgear abnormal operation detection method and system may include more or fewer components than those shown in the figure, or have a different configuration. The components shown in the figure can be implemented using hardware, software, or a combination thereof.

[0049] In the embodiments provided in this application, it should be understood that the disclosed methods can also be implemented in other ways. The embodiments described above are merely illustrative; for example, the flowcharts or block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of methods and computer program products according to various embodiments of this application. In this regard, each block in the flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved.

[0050] It should also be noted that each box in a block diagram and / or flowchart, as well as combinations of boxes in a block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0051] In addition, the functional modules in the various embodiments of this application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0052] If the aforementioned function is implemented as a software module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or the technical solution itself... Part of this can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0053] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

[0054] It will be apparent to those skilled in the art that this application is not limited to the details of the exemplary embodiments described above, and that this application can be implemented in other specific forms without departing from the spirit or essential characteristics of this application. Therefore, the embodiments should be considered illustrative and non-limiting in all respects, and the scope of this application is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be included within this application. No reference numerals in the claims should be construed as limiting the scope of the claims.

Claims

1. An intelligent method for detecting abnormal operation of switchgear, characterized in that, Includes the following steps: S1. Electrical parameter sensors are used to collect data on the switchgear's current, voltage, temperature, and mechanical vibration. Multi-dimensional operational data of partial discharge were collected and preprocessed. S2. Extract features from the multi-dimensional running data after data preprocessing; S3. A support vector machine algorithm with particle swarm optimization is used to perform multi-dimensional computation after feature extraction. According to the data, intelligent classification and anomaly detection are performed; S4. Based on the results of intelligent classification and anomaly detection, locate the fault in the switchgear.

2. The intelligent switchgear abnormal operation detection method as described in claim 1, characterized in that, In step S1, the data preprocessing includes denoising, data calibration, normalization, and missing value processing.

3. The intelligent switchgear abnormal operation detection method as described in claim 1, characterized in that, Step S2 includes: The original signal of the multi-dimensional running data after data preprocessing is decomposed into 16 sub-frequency bands; The energy value of each sub-band is calculated using the following formulas: In the formula, E4,j For the first j The energy values ​​of each sub-band, where n is the number of discrete points. xj,k For the first j The amplitude of the kth discrete point in each sub-band; The feature vector is constructed using the energy values ​​of each sub-band as elements, and its calculation formula is as follows: In the formula, T is a feature vector constructed using sub-band energy values ​​as elements. E 4,0 This represents the initial sub-band energy value. E 4,15 This is the energy value of the 15th sub-band. The feature vector is normalized to obtain the feature extraction result, and the calculation formula is as follows: In the formula, T' Let E be the normalized eigenvector, and E be the sum of the energy values ​​of all sub-bands.

4. The intelligent switchgear abnormal operation detection method as described in claim 1, characterized in that, Step S3 includes: Data on switchgear under normal and abnormal conditions were collected from the multi-dimensional operational data after feature extraction, and training and testing sets were constructed based on the collected switchgear data. The support vector machine algorithm with particle swarm optimization and minimizing classification error is used as the optimization objective. The penalty factor and kernel function parameters of the SVN classifier are optimized, and their calculation formulas include: In the formula, For particles i exist k+ Speed ​​at moment 1 For particles i exist k The speed of time, For particles i exist k+ 1. Position at a given moment For particles i exist k Location at any given moment ω Inertia factor c1 , c2 As an acceleration factor, r1 , r2 It is a random number. For particles i exist k The optimal position of an individual at any given time. for k The globally optimal position at any given time; The PSO-SVM classifier is obtained by training the SVM classifier using the penalty factor and kernel function parameters of the SVN classifier optimized by particle swarm optimization on the training set. The test set is input into the PSO-SVM classifier for intelligent classification and anomaly detection of multi-dimensional operational data of the switchgear.

5. The intelligent switchgear abnormal operation detection method as described in claim 1, characterized in that, In step S4, the fault location process includes: Based on the results of intelligent classification and anomaly detection, more than four ultrasonic sensors are distributed inside the switch cabinet to form a positioning array; Measure the time difference between the arrival of the partial discharge signal at each ultrasonic sensor; The coordinates of the power supply are determined based on the time difference and the speed of sound wave propagation to output the fault location coordinates; the formula for calculating the coordinates of the power supply is as follows: In the formula, d i To discharge the power to the first i The distance of an ultrasound wave, ( x , y , z ) represents the coordinates of the power source. xi , yi , zi ) is the first i The coordinates of an ultrasonic sensor in space. v For the speed of sound, t i For ultrasound to reach the first i The time of each ultrasonic sensor t 0 This represents the time when the discharge occurs.

6. An intelligent switchgear abnormal operation detection system, characterized in that, include: The data acquisition module is used to collect multi-dimensional operating data of the switchgear, including current, voltage, temperature, mechanical vibration, and partial discharge, using electrical parameter sensors, and to perform data preprocessing. The feature extraction module is used to extract features from multi-dimensional running data after data preprocessing; The data classification and detection module is used to perform intelligent classification and anomaly detection on multi-dimensional running data after feature extraction using a particle swarm optimization support vector machine algorithm. The fault location module is used to locate faults in the switchgear based on the results of intelligent classification and anomaly detection.

7. An electronic device, characterized in that, include: Memory, used to store one or more programs; processor; When the processor executes the one or more programs, it implements an intelligent switchgear abnormal operation detection method as described in any one of claims 1-5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements an intelligent switchgear abnormal operation detection method as described in any one of claims 1-5.

Images