A high voltage power equipment detection method and system

By obtaining the main current path and environmental data of high-voltage power equipment, waveform reconstruction and electromagnetic correlation analysis are carried out, and the current path skeleton is built, which solves the problems of detection errors and environmental neglect in the existing technology, and achieves efficient and accurate intelligent detection.

CN118795263BActive Publication Date: 2024-11-15HEYUAN TRANSMISSION & TRANSFORMATION ENG CO
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202411276892.8
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-09-12
Publication Date
2024-11-15
Estimated Expiration
2044-09-12

AI Technical Summary

Technical Problem

The existing high-voltage power equipment detection methods rely on manual inspection and basic electrical testing, and cannot fully reflect the complex electrical characteristics of the equipment. The data processing is complex, and errors are prone to occur, ignoring the impact of environmental factors on the equipment.

Method used

By obtaining the main current path of the power equipment, performing waveform time domain reconstruction and statistical feature extraction, analyzing the electromagnetic relationship, building a current path skeleton, performing circuit comparison simulation, combining the equipment usage environment data, building a state recognition model, and realizing intelligent detection.

Benefits of technology

It improves the accuracy and efficiency of detection, provides a more comprehensive understanding of the operating status of the equipment, enhances the analysis of electromagnetic coupling rules, improves the authenticity and adaptability of simulation results, and ensures the accuracy and reliability of the detection results.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118795263B_ABST
    Figure CN118795263B_ABST
Patent Text Reader

Abstract

The present invention relates to the technical field of power equipment detection, and in particular to a high-voltage power equipment detection method and system. The method comprises the following steps: starting from the current path of the power equipment, obtaining the statistical characteristics of the current waveform through waveform reconstruction and statistical feature extraction. Subsequently, the electromagnetic field variation of the equipment is generated through electromagnetic correlation analysis and conversion. Further, the circuit unit of the simulation equipment is obtained through skeleton structuring and simulation modeling, and the response analysis is performed in combination with environmental data. Finally, based on the simulation circuit response data, a state recognition model is constructed to realize the recognition and intelligent detection of the equipment state, providing key support and monitoring for the operation of high-voltage power equipment; the present invention can realize more accurate and reliable intelligent detection of high-voltage power equipment through current characteristic analysis, electromagnetic coupling modeling, circuit environment adaptation and intelligent diagnosis.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of power equipment detection, and in particular to a high-voltage power equipment detection method and system. Background Art

[0002] In the early stage of high-voltage power equipment inspection, it mainly relied on manual inspection and basic electrical testing methods. Technicians evaluate the operating status of equipment through regular visual inspection, insulation resistance test, and ground resistance measurement methods. These methods mainly focus on the physical state of the equipment and simple electrical parameters, and lack in-depth understanding of the complex electrical characteristics inside the equipment. Limited to basic physical inspection and a small number of electrical parameter measurements, it cannot fully reflect the actual operating status of the equipment. The test results depend on the experience and skills of the testers, are highly subjective, and prone to errors. After entering the computer-aided detection stage, data acquisition systems and computer analysis tools began to be applied. By installing sensors to collect equipment operation data, computers are used to process and analyze the data to generate detailed equipment operation reports. This stage introduced technologies such as vibration analysis, thermal imaging, and electrical parameter analysis to enhance the comprehensiveness and accuracy of equipment detection. Although computer analysis has been introduced, it still needs to rely on manual setting and adjustment of analysis parameters. The data processing and analysis process is complex and prone to errors. The data from different sensors need to be integrated and unified. The complexity of data integration increases the difficulty of analysis, and often ignores the impact of environmental factors on equipment. For example, the impact of ambient temperature and humidity on the electrical performance of equipment has not been effectively considered. There is insufficient consideration of adaptability to the actual working environment. For example, the impact of environmental interference on equipment status has not been fully evaluated. Summary of the invention

[0003] Based on this, it is necessary to provide a high-voltage power equipment detection method and system to solve at least one of the above technical problems.

[0004] To achieve the above object, a high voltage power equipment detection method comprises the following steps:

[0005] Step S1: obtaining the main current path of the power equipment; reconstructing the waveform of the main current path of the power equipment in the time domain to generate current waveform data; extracting statistical features of the current waveform data to obtain current waveform statistical features;

[0006] Step S2: Perform electromagnetic correlation analysis on the current waveform statistical features to obtain the electromagnetic correlation; perform proportional conversion on the current waveform statistical features based on the electromagnetic correlation to generate the device electromagnetic field variation;

[0007] Step S3: construct a skeleton structure of the main current path of the power equipment to obtain a current path skeleton; perform circuit proportional simulation on the current path skeleton and the electromagnetic field variation of the equipment to generate a simulated equipment circuit unit;

[0008] Step S4: Acquire device usage environment data; perform response analysis on the simulation device circuit unit based on the device usage environment data to obtain simulation circuit response data;

[0009] Step S5: Perform equipment environment adaptation analysis on the simulation circuit response data to obtain the interference environment adaptability; construct a state recognition model for the equipment electromagnetic field change and the interference environment adaptability to obtain the equipment state recognition model; use the equipment state recognition model to perform equipment state recognition on the high-voltage power equipment to perform the task of intelligently detecting the high-voltage power equipment.

[0010] The present invention can more accurately reflect the current characteristics of the equipment in actual operation by acquiring the main current path of the power equipment and reconstructing the waveform in the time domain, avoiding the measurement errors existing in the traditional method. Statistical feature extraction of current waveform data can obtain more dimensional information and provide a more comprehensive understanding of the equipment operation status. By analyzing the correlation between the statistical characteristics of the current waveform and the change of the electromagnetic field, the intrinsic connection between the current and the electromagnetic field during the operation of the equipment can be revealed, providing a scientific basis for subsequent analysis. By performing proportional conversion on the statistical characteristics of the current waveform to generate the change of the electromagnetic field of the equipment, this method can more intuitively reflect the impact of the current change on the electromagnetic field and improve the accuracy of the analysis. By constructing a skeleton structure for the main current path of the power equipment, the actual current path of the equipment can be better simulated, providing an accurate basic model for subsequent simulation. The circuit isometry simulation of the current path skeleton and the change of the electromagnetic field of the equipment is performed, and the generated simulation equipment circuit unit can more realistically reflect the current and electromagnetic field changes of the equipment in actual work, providing reliable data for further analysis. By acquiring the equipment use environment data and applying it to simulation analysis, the response of the equipment in the actual working environment can be better simulated, improving the authenticity and reliability of the simulation results. Based on the equipment usage environment data, the response analysis of the simulated equipment circuit unit is performed. The obtained simulated circuit response data can reflect the working status of the equipment in different environments, providing an important basis for subsequent adaptation analysis. The equipment environment adaptation analysis of the simulated circuit response data is performed to obtain the interference environment adaptability. This step can identify the adaptability of the equipment in different environments and provide data support for equipment maintenance and optimization. By constructing a state recognition model for the equipment electromagnetic field change and the interference environment adaptability, the health status of the equipment can be accurately classified to ensure the accuracy and reliability of the test results. Using the equipment state recognition model to identify the equipment state of high-voltage power equipment can achieve efficient intelligent detection, improve the efficiency and accuracy of detection, and promptly discover potential problems of the equipment.

[0011] This specification also provides a high-voltage electric equipment detection system for executing the high-voltage electric equipment detection method as described above, the high-voltage electric equipment detection system comprising:

[0012] The feature extraction module is used to obtain the main current path of the power equipment; reconstruct the waveform of the main current path of the power equipment in the time domain to generate current waveform data; extract statistical features from the current waveform data to obtain current waveform statistical features;

[0013] The electromagnetic conversion module is used to analyze the electromagnetic correlation relationship of the current waveform statistical characteristics to obtain the electromagnetic correlation relationship; based on the electromagnetic correlation relationship, the current waveform statistical characteristics are proportionally converted to generate the electromagnetic field variation of the equipment;

[0014] The circuit simulation module is used to construct the skeleton structure of the main current path of the power equipment to obtain the current path skeleton; perform circuit proportional simulation on the current path skeleton and the change of the electromagnetic field of the equipment to generate the circuit unit of the simulation equipment;

[0015] A response analysis module is used to obtain device usage environment data; based on the device usage environment data, a response analysis is performed on the simulation device circuit unit to obtain simulation circuit response data;

[0016] The state recognition module is used to perform equipment environment adaptation analysis on the simulation circuit response data to obtain the interference environment adaptability; to construct a state recognition model for the equipment electromagnetic field change and the interference environment adaptability to obtain the equipment state recognition model; and to use the equipment state recognition model to perform equipment state recognition on high-voltage power equipment to perform the task of intelligently detecting high-voltage power equipment.

[0017] The benefit of the present invention lies in that by obtaining the main current path of the device, the actual current distribution of the device can be more comprehensively reflected, and the waveform reconstruction and statistical feature extraction of the current path can more accurately describe the actual current characteristics of the device. By adopting electromagnetic correlation analysis, the complex electromagnetic coupling law inside the device can be better captured. Based on the electromagnetic correlation, the statistical characteristics of the current waveform are converted, and the change of the electromagnetic field of the device can be more scientifically derived. Through the current path skeleton structured modeling, the electromagnetic field distribution inside the device can be more carefully reflected, and the circuit model can be combined with the equipment use environment data to enhance the adaptability and reliability of the circuit simulation. Using the equipment electromagnetic field change and environmental adaptability for state recognition modeling can achieve more intelligent equipment state judgment, make full use of the equipment use environment data, and improve the accuracy and robustness of the state recognition model. It has obvious advantages in current characteristic analysis, electromagnetic coupling modeling, circuit environment adaptation and intelligent diagnosis, which can better solve the limitations of power equipment detection technology and improve the intelligent detection level of high-voltage power equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 A schematic diagram of the steps of a high-voltage power equipment detection method;

[0019] Figure 2 for Figure 1 Detailed implementation steps of step S2 in the flowchart;

[0020] Figure 3 for Figure 1 Detailed implementation steps of step S3 in FIG.

[0021] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0022] The technical method of the present invention is described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.

[0023] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different network and / or processor methods and / or microcontroller methods.

[0024] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0025] To achieve this, please refer to Figures 1 to 3 , a high voltage power equipment detection method, comprising the following steps:

[0026] Step S1: obtaining the main current path of the power equipment; reconstructing the waveform of the main current path of the power equipment in the time domain to generate current waveform data; extracting statistical features of the current waveform data to obtain current waveform statistical features;

[0027] Step S2: Perform electromagnetic correlation analysis on the current waveform statistical features to obtain the electromagnetic correlation; perform proportional conversion on the current waveform statistical features based on the electromagnetic correlation to generate the device electromagnetic field variation;

[0028] Step S3: constructing a skeleton structure of the main current path of the power equipment to obtain a current path skeleton; performing circuit proportional simulation on the current path skeleton and the electromagnetic field variation of the equipment to generate a simulated equipment circuit unit;

[0029] Step S4: Acquire device usage environment data; perform response analysis on the simulation device circuit unit based on the device usage environment data to obtain simulation circuit response data;

[0030] Step S5: Perform equipment environment adaptation analysis on the simulation circuit response data to obtain the interference environment adaptability; construct a state recognition model for the equipment electromagnetic field change and the interference environment adaptability to obtain the equipment state recognition model; use the equipment state recognition model to perform equipment state recognition on the high-voltage power equipment to perform the task of intelligently detecting the high-voltage power equipment.

[0031] The present invention can more accurately reflect the current characteristics of the equipment in actual operation by acquiring the main current path of the power equipment and reconstructing the waveform in the time domain, avoiding the measurement errors existing in the traditional method. Statistical feature extraction of current waveform data can obtain more dimensional information and provide a more comprehensive understanding of the equipment operation status. By analyzing the correlation between the statistical characteristics of the current waveform and the change of the electromagnetic field, the intrinsic connection between the current and the electromagnetic field during the operation of the equipment can be revealed, providing a scientific basis for subsequent analysis. By performing proportional conversion on the statistical characteristics of the current waveform to generate the change of the electromagnetic field of the equipment, this method can more intuitively reflect the impact of the current change on the electromagnetic field and improve the accuracy of the analysis. By constructing a skeleton structure for the main current path of the power equipment, the actual current path of the equipment can be better simulated, providing an accurate basic model for subsequent simulation. The circuit isometry simulation of the current path skeleton and the change of the electromagnetic field of the equipment is performed, and the generated simulation equipment circuit unit can more realistically reflect the current and electromagnetic field changes of the equipment in actual work, providing reliable data for further analysis. By acquiring the equipment use environment data and applying it to simulation analysis, the response of the equipment in the actual working environment can be better simulated, improving the authenticity and reliability of the simulation results. Based on the equipment usage environment data, the response analysis of the simulated equipment circuit unit is performed. The obtained simulated circuit response data can reflect the working status of the equipment in different environments, providing an important basis for subsequent adaptation analysis. The equipment environment adaptation analysis of the simulated circuit response data is performed to obtain the interference environment adaptability. This step can identify the adaptability of the equipment in different environments and provide data support for equipment maintenance and optimization. By constructing a state recognition model for the equipment electromagnetic field change and the interference environment adaptability, the health status of the equipment can be accurately classified to ensure the accuracy and reliability of the test results. Using the equipment state recognition model to identify the equipment state of high-voltage power equipment can achieve efficient intelligent detection, improve the efficiency and accuracy of detection, and promptly discover potential problems of the equipment.

[0032] In the embodiment of the present invention, reference Figure 1 The above is a schematic diagram of the steps of a high-voltage power equipment detection method of the present invention. In this example, the high-voltage power equipment detection method includes the following steps:

[0033] Step S1: obtaining the main current path of the power equipment; reconstructing the waveform of the main current path of the power equipment in the time domain to generate current waveform data; extracting statistical features of the current waveform data to obtain current waveform statistical features;

[0034] In an embodiment of the present invention, the main current path of the power equipment is obtained, wherein the power equipment is a high-voltage power equipment including a high-voltage transformer, an air-insulated circuit breaker, a gas-insulated circuit breaker, an outdoor high-voltage disconnector and a high-voltage cable. Current signals are collected from the main current paths of the power equipment, and a high-precision current sensor installed in the current path of the equipment is measured to record the current signal. These signals are converted into a digital format by a data acquisition system, and then the current signal is processed using a time domain reconstruction algorithm, such as a fast Fourier transform (FFT) or a wavelet transform, to generate current waveform data. The statistical features of the current waveform data are extracted by a statistical analysis tool, including the mean, standard deviation, peak factor and transient response characteristics of the waveform. These statistical features describe the basic characteristics and change patterns of the current waveform, for example, for a high-voltage transformer, the fluctuation characteristics of the current are measured; for air-insulated circuit breakers and gas-insulated circuit breakers, the current waveform during the switch operation is analyzed; for outdoor high-voltage disconnectors and high-voltage cables, the current transient characteristics are focused on.

[0035] Step S2: Perform electromagnetic correlation analysis on the current waveform statistical features to obtain the electromagnetic correlation; perform proportional conversion on the current waveform statistical features based on the electromagnetic correlation to generate the device electromagnetic field variation;

[0036] In an embodiment of the present invention, an electromagnetic correlation analysis is performed on the statistical characteristics of the current waveform. Data mining and machine learning methods, such as correlation analysis, regression analysis, or cluster analysis, are used to identify the relationship between the statistical characteristics of the current waveform and the change in the electromagnetic field. The identified electromagnetic correlation is applied to the statistical characteristics of the current waveform, and the change in the electromagnetic field of the device is calculated by proportional conversion. This process uses an algorithm to quantify the relationship between the statistical characteristics of the current and the change in the electromagnetic field, and generates the data on the change in the electromagnetic field of the device.

[0037] Step S3: constructing a skeleton structure of the main current path of the power equipment to obtain a current path skeleton; performing circuit proportional simulation on the current path skeleton and the electromagnetic field variation of the equipment to generate a simulated equipment circuit unit;

[0038] In an embodiment of the present invention, a skeleton structure is constructed for the main current path of the power equipment. A skeleton model of the current path is established using CAD software or circuit design tools to ensure that the skeleton structure accurately reflects the flow path of the device current. Then, a circuit proportional simulation is performed based on the skeleton structure and the change in the electromagnetic field of the device, and the circuit is modeled and simulated using circuit simulation software (such as SPICE). By inputting the data of the change in the electromagnetic field of the device, simulated device circuit units are generated, which reflect the electromagnetic environment and its impact of the device in actual operation.

[0039] Step S4: Acquire device usage environment data; perform response analysis on the simulation device circuit unit based on the device usage environment data to obtain simulation circuit response data;

[0040] In the embodiment of the present invention, the use environment data of the device is obtained, and the data includes environmental parameters such as temperature, humidity, and electromagnetic interference. The data is collected using an environmental sensor or an environmental monitoring system. The environmental data is input into the circuit unit of the simulation device, and the circuit response analysis is performed using simulation software. This process generates simulation circuit response data by analyzing the response of the simulation circuit to environmental changes, reflecting the performance of the device under actual environmental conditions.

[0041] Step S5: Perform equipment environment adaptation analysis on the simulation circuit response data to obtain the interference environment adaptability; construct a state recognition model for the equipment electromagnetic field change and the interference environment adaptability to obtain the equipment state recognition model; use the equipment state recognition model to perform equipment state recognition on the high-voltage power equipment to perform the task of intelligently detecting the high-voltage power equipment.

[0042] In an embodiment of the present invention, the simulation circuit response data is subjected to equipment environment adaptation analysis. A statistical analysis method or a machine learning model (such as cluster analysis or principal component analysis) is used to evaluate the degree of adaptability between the circuit response data and the equipment environment. Based on the degree of adaptability, a device state recognition model is constructed, and the final device state recognition model is obtained through the model training and verification process by combining the change in the device electromagnetic field and the adaptability of the interference environment. The model is used to identify the state of high-voltage power equipment, complete intelligent detection tasks, and ensure the safe and reliable operation of high-voltage power equipment.

[0043] Preferably, step S1 comprises the following steps:

[0044] Step S11: Acquire the target of the electric power equipment to be tested; and identify the main current path of the target of the electric power equipment to be tested to obtain the main current path of the electric power equipment;

[0045] Step S12: performing real-time current measurement on the main current path of the power equipment to obtain equipment current data;

[0046] Step S13: reconstruct the waveform of the device current data in the time domain to generate current waveform data;

[0047] Step S14: performing fast Fourier transform on the current waveform data to generate a current spectrum diagram;

[0048] Step S15: extracting statistical features from the current spectrum to obtain statistical features of the current waveform.

[0049] The benefit of the present invention is that by identifying the main current path of the power equipment to be tested, the detection object can be accurately located, laying the foundation for subsequent analysis, helping to fully grasp the actual current flow and distribution of the equipment, and improving the pertinence and accuracy of the detection. Real-time measurement of the current data of the equipment can dynamically reflect the operating status of the equipment, which is conducive to timely detection of equipment abnormalities and provides reliable basic data for subsequent state analysis. By generating current waveform data through waveform time domain reconstruction, the time domain characteristics of the equipment current can be more comprehensively described, and fast Fourier transform can be performed to obtain the spectrum characteristics of the current, which is helpful to mine the frequency domain information of the equipment current, and the dynamic characteristics of the equipment current can be more deeply characterized, providing a basis for subsequent fault diagnosis. Extracting statistical feature indicators from the current waveform and spectrum diagram can efficiently summarize the key attributes of the equipment current, provide important feature vectors for subsequent state identification and fault diagnosis, and enhance the pertinence and reliability of the analysis. A comprehensive analysis from current path identification to feature extraction is achieved, laying a solid foundation for intelligent detection and fault diagnosis of high-voltage power equipment.

[0050] In an embodiment of the present invention, a target of a power equipment to be tested is determined, wherein the power equipment is a high-voltage power equipment including a high-voltage transformer, an air-insulated circuit breaker, a gas-insulated circuit breaker, an outdoor high-voltage disconnector and a high-voltage cable. The equipment is usually photographed by a high-resolution device image acquisition device such as a high-definition camera. During the photographing process, the key components of the power equipment are identified by an image processing algorithm, and the electrical connection diagram of the equipment is extracted. Next, the current path of the equipment is analyzed using electrical drawings or CAD drawings. The electrical drawings are converted into current path data using automated path recognition software to identify the main current path of the power equipment. At this time, a path recognition algorithm, such as a template recognition algorithm based on graphic matching, can be used to calibrate and verify the current path. Finally, the main current path of the equipment is obtained. When real-time current measurement is performed on the main current path of the power equipment, a current sensor (such as a Hall effect sensor or a current transformer) is first installed on the current path. These sensors monitor the current flowing through various parts of the equipment in real time in a contact or non-contact manner. The data acquisition system transmits the current data collected by the current sensor to the computer system through an interface (such as a data acquisition card or a wireless data transmission module). The computer system uses real-time data processing software to calibrate the collected data to ensure the accuracy and consistency of the data. The current data obtained by real-time measurement is input into the data processing system, which is equipped with high-performance signal processing algorithms. The signal processing software applies time domain reconstruction algorithms, such as wavelet transform or piecewise linear interpolation methods, to process the raw current data. This process involves dividing the data into multiple time periods and applying interpolation techniques to fill in the missing parts of the data to improve the continuity and resolution of the data. The reconstructed current waveform data is transformed using the fast Fourier transform (FFT) algorithm. The FFT algorithm converts the time domain signal into a frequency domain signal and displays the spectral characteristics of the signal. The data processing system performs FFT operations to calculate the amplitude and phase information of the current waveform data at different frequencies. The data in the spectrum graph is analyzed using statistical analysis software. The software calculates various statistical indicators of the spectrum graph, such as mean, variance, kurtosis, skewness, and power spectral density, which describe the energy distribution and changes of the current signal at different frequencies. The extracted statistical features are organized into structured data tables and stored in a database.

[0051] Preferably, step S2 comprises the following steps:

[0052] Step S21: Calculate the fluctuation intensity of the current waveform statistical characteristics to generate current fluctuation intensity data;

[0053] Step S22: performing electromagnetic correlation analysis on the current fluctuation intensity data to obtain an electromagnetic correlation;

[0054] Step S23: Calculate the conversion ratio of the electromagnetic correlation relationship to obtain electromagnetic conversion ratio data;

[0055] Step S24: Proportionally convert the current waveform statistical characteristics based on the electromagnetic conversion ratio data to generate the device electromagnetic field change.

[0056] The benefit of the present invention is that through the calculation of fluctuation intensity, the dynamic change trend of the equipment current waveform can be more objectively reflected, which is conducive to in-depth analysis of the fluctuation law of the equipment current in the time domain and frequency domain, and provides a basis for subsequent electromagnetic correlation analysis. Electromagnetic correlation analysis of current fluctuation intensity data can effectively reveal the complex electromagnetic coupling mechanism inside the equipment, which helps to more accurately understand the intrinsic connection between equipment current change and electromagnetic field change. By calculating the electromagnetic conversion ratio, the conversion relationship between the statistical characteristics of the current waveform and the change of the equipment electromagnetic field is quantitatively characterized, which provides an important reference basis for the subsequent estimation of the electromagnetic field change and enhances the reliability of the analysis results. Based on the electromagnetic conversion ratio, the current waveform statistical characteristics are proportionally converted to effectively generate the equipment electromagnetic field change, which provides key input information for subsequent equipment status identification and fault diagnosis, and lays the foundation for intelligent detection. Through fluctuation analysis, electromagnetic correlation mining, and conversion ratio quantification methods, the equipment electromagnetic field change is effectively derived, providing a reliable analysis basis for intelligent detection and fault diagnosis of high-voltage power equipment.

[0057] As an example of the present invention, refer to Figure 2 As shown, in this example, step S2 includes:

[0058] Step S21: Calculate the fluctuation intensity of the current waveform statistical characteristics to generate current fluctuation intensity data;

[0059] In an embodiment of the present invention, a high-performance computing tool, such as Python's NumPy library or MATLAB toolbox, is used to input the current waveform statistical characteristic data into the fluctuation intensity calculation program. The fluctuation intensity calculation involves the following steps: the standard deviation, root mean square value and other related fluctuation characteristics of the current waveform data are calculated. The standard deviation reflects the degree of distribution dispersion of the data, while the root mean square value characterizes the intensity fluctuation of the signal. Using these calculation results, current fluctuation intensity data can be generated.

[0060] Step S22: performing electromagnetic correlation analysis on the current fluctuation intensity data to obtain an electromagnetic correlation;

[0061] In an embodiment of the present invention, electromagnetic analysis software, such as COMSOL Multiphysics or Ansys Maxwell, is used to input current fluctuation intensity data. The software models the relationship between current fluctuation intensity and electromagnetic field through a built-in electromagnetic field analysis module. First, an electromagnetic field model is defined, including electrical parameters and material properties of the device, and then the current fluctuation intensity data is applied to the model. The software calculates the influence of current fluctuation on the electromagnetic field through numerical methods, such as finite element analysis (FEA), and obtains the electromagnetic correlation relationship.

[0062] Step S23: Calculate the conversion ratio of the electromagnetic correlation relationship to obtain electromagnetic conversion ratio data;

[0063] In the embodiment of the present invention, a mathematical calculation tool, such as MATLAB or a dedicated data analysis tool, is used to analyze the electromagnetic correlation relationship. The ratio of the electromagnetic field change is calculated by setting the reference value of the electromagnetic field and the actually measured electromagnetic field data. The specific operation steps include: inputting the electromagnetic field reference data and the actual data, and calculating using the ratio calculation formula. In the formula, the electromagnetic conversion ratio is the ratio of the actual electromagnetic field strength to the reference electromagnetic field strength.

[0064] Step S24: Proportionally convert the current waveform statistical characteristics based on the electromagnetic conversion ratio data to generate the device electromagnetic field change.

[0065] In an embodiment of the present invention, data processing software, such as Excel or Python data analysis library, is used to apply electromagnetic conversion ratio data to current waveform statistical features. The specific operation steps are: multiply each item of the current waveform statistical features by the corresponding electromagnetic conversion ratio, and the calculated result is the electromagnetic field change. For complex equipment, an automated processing program can be written in a scripting language to perform batch calculations and data aggregation. The final generated equipment electromagnetic field change is displayed in the form of charts and data tables and stored in a database.

[0066] Preferably, step S3 comprises the following steps:

[0067] Step S31: Identify the connectivity of the main current paths of the power equipment and generate current path connectivity data;

[0068] Step S32: constructing a skeleton structure of the main current path of the power equipment according to the current path connectivity data to obtain a current path skeleton;

[0069] Step S33: inferring the current direction of the current path skeleton based on the change in the electromagnetic field of the device to obtain a directional current path skeleton;

[0070] Step S34: Perform circuit proportional simulation on the device electromagnetic field variation and the directional current path skeleton to generate a simulated device circuit unit.

[0071] The benefit of the present invention is that through connectivity identification, the topological relationship of the main current path of the power equipment can be accurately analyzed, which helps to deeply understand the current flow direction and distribution status inside the equipment, and lays the foundation for the subsequent construction of the current path skeleton. Based on the current path connectivity data, the main current path is skeletonized and the current path skeleton is generated, which can more clearly describe the current flow structure inside the equipment and provide a basis for the subsequent current direction inference. Using the change in the electromagnetic field of the equipment, the current direction of the current path skeleton is inferred to obtain the directional current path skeleton, which can more accurately reflect the actual flow direction of the current inside the equipment and provide the necessary topological information for the subsequent circuit simulation. Based on the change in the electromagnetic field of the equipment and the directional current path skeleton, the circuit is simulated proportionally to generate the simulated equipment circuit unit, which can be closer to the actual equipment structure and operating state, and provide valuable simulation data for further equipment state identification and fault diagnosis. Through connectivity identification, skeleton structuring, current direction inference and circuit proportional simulation methods, a topological model of the current flow inside the equipment is effectively established, which provides an important analytical basis for the intelligent detection and fault diagnosis of high-voltage power equipment.

[0072] As an example of the present invention, refer to Figure 3 As shown, in this example, step S3 includes:

[0073] Step S31: Identify the connectivity of the main current paths of the power equipment and generate current path connectivity data;

[0074] In an embodiment of the present invention, the connection of the current path is analyzed by a connectivity identification algorithm based on the current path data. A graphics processing software, such as Graphviz or NetworkX, is used to perform connectivity analysis. The specific operation is as follows: the current path data is imported into the software, and a connectivity algorithm, such as a depth-first search (DFS) or a breadth-first search (BFS), is used to identify the connection relationship between nodes and edges in the current path. The connectivity matrix in the current path is calculated by the algorithm to generate current path connectivity data.

[0075] Step S32: constructing a skeleton structure of the main current path of the power equipment according to the current path connectivity data to obtain a current path skeleton;

[0076] In an embodiment of the present invention, a skeleton structure is constructed based on the connectivity data of the current path. The current path is structured using computer-aided design (CAD) software or a dedicated electrical simulation tool, such as AutoCAD Electrical or ETAP. First, the connectivity data is imported into the design software, and the current path is skeletonized and modeled using a skeleton modeling tool. The specific steps include: creating a current path skeleton model in the software, defining the main nodes and connecting lines of the current path, and constructing a structure using a skeleton modeling tool. During the skeleton structuring process, the software converts the connectivity information of the current path into a current path skeleton, and generates a current path skeleton diagram.

[0077] Step S33: inferring the current direction of the current path skeleton based on the change in the electromagnetic field of the device to obtain a directional current path skeleton;

[0078] In an embodiment of the present invention, electromagnetic field simulation software, such as COMSOL Multiphysics or ANSYSMaxwell, is used to analyze the current path skeleton. First, the electromagnetic field change data is imported into the simulation software. By setting the electromagnetic field model and the current path skeleton model, the current direction inference algorithm, such as the direction inference algorithm based on the field intensity gradient, is used to analyze the current flow direction in the skeleton. The algorithm calculates the impact of electromagnetic field changes on the current direction and marks the current flow direction in the skeleton model. Finally, a directional current path skeleton is generated and saved in a graphic format (such as PDF or SVG format) for circuit simulation.

[0079] Step S34: Perform circuit proportional simulation on the device electromagnetic field variation and the directional current path skeleton to generate a simulated device circuit unit.

[0080] In an embodiment of the present invention, circuit simulation software, such as SPICE (Simulation Program with Integrated Circuit Emphasis) or Proteus, is used to input the device electromagnetic field variation and directional current path skeleton data into the software. First, a simulation model is established, including components, connections, and electromagnetic field variation of the circuit. Then, simulation parameters, such as time step and simulation accuracy, are set, and the circuit simulation program is run. The simulation software adjusts the behavior of the circuit model according to the electromagnetic field variation and generates a simulated device circuit unit. The simulation results include the current, voltage, and power distribution in the circuit, which are saved in graphics and data files (such as NETLIST format) as a basis for further analysis and verification.

[0081] Preferably, step S33 includes the following steps:

[0082] Step S331: performing electromagnetic field mapping on the current path skeleton based on the electromagnetic field variation of the device to obtain electromagnetic field data corresponding to the skeleton;

[0083] Step S332: performing phase difference analysis on the electromagnetic field data corresponding to the skeleton to obtain electromagnetic field phase difference information;

[0084] Step S333: constructing a skeleton vector field of the current path skeleton according to the electromagnetic field phase difference information to generate a path point vector field;

[0085] Step S334: inferring the current direction of the path point vector field to obtain specific current direction data;

[0086] Step S335: marking the path direction of the current path skeleton according to the specific current direction data to generate a directional current path skeleton.

[0087] The benefit of the present invention lies in that the electromagnetic field mapping of the current path skeleton is performed using the change in the electromagnetic field of the device, and the electromagnetic field data corresponding to the skeleton is obtained, which provides the necessary input information for the subsequent phase difference analysis and vector field construction, and further explores the intrinsic connection between the current path and the electromagnetic field. The corresponding electromagnetic field data is subjected to phase difference analysis to obtain the electromagnetic field phase difference information, which reflects the electromagnetic coupling characteristics between different current path points and lays the foundation for the subsequent vector field construction. Based on the electromagnetic field phase difference information, the vector field of the current path skeleton is constructed to generate the path point vector field, which more clearly depicts the direction and intensity of the current flow inside the device, and provides a key basis for the subsequent current direction inference. For the path point vector field data, a specific current direction inference is performed to obtain the directional current data, which provides the necessary topological information for the final generation of the directional current path skeleton, and more accurately reflects the actual current flow direction inside the device. According to the inferred specific current direction data, the current path skeleton is annotated to generate a directional current path skeleton. This directional current path skeleton not only contains the connectivity of the current path, but also accurately depicts the actual current flow direction, providing more reliable basic data for subsequent equipment status analysis and fault diagnosis. Through electromagnetic field mapping, phase difference analysis, vector field construction and current direction inference methods, the intrinsic relationship between the current path and the electromagnetic field is effectively acquired and analyzed, and more accurate directional current path skeleton data is generated, providing important support for intelligent detection and fault diagnosis of high-voltage power equipment.

[0088] In an embodiment of the present invention, electromagnetic field simulation software, such as ANSYS Maxwell or COMSOL Multiphysics, is used to import electromagnetic field variation data into the electromagnetic field model of the software. First, a current path skeleton model is constructed in the simulation software, and the electromagnetic field variation is applied to the boundary conditions and source terms of the model. Next, an electromagnetic field mapping calculation is performed, and the software maps the electromagnetic field strength and distribution of each point in the current path skeleton to the skeleton. The generated electromagnetic field data includes electric field strength, magnetic field strength and their distribution, and is saved in a data file (such as a MAT file or CSV format), describing the electromagnetic field characteristics of each point on the skeleton, and providing a data basis for subsequent steps. Phase difference analysis is performed on the electromagnetic field data. The electromagnetic field data is processed using a signal processing tool, such as the SciPy library in MATLAB or Python. First, the time series or space series signal in the electromagnetic field data is input into the phase analysis module. By applying Fourier transform, the frequency domain representation of the electromagnetic field signal is obtained, and its phase information is calculated. A phase difference calculation algorithm, such as a phase difference measurement algorithm, is used to analyze the phase difference between different points in the electromagnetic field data. The generated electromagnetic field phase difference information includes the phase difference value and its distribution in space, and is saved in charts and data files (such as TXT or XLSX format) to provide a basis for the construction of the skeleton vector field. The current path skeleton is modeled by vector field using computational fluid dynamics (CFD) tools such as ANSYS Fluent or OpenFOAM. First, the electromagnetic field phase difference information is input into the vector field construction module. According to the phase difference information, a vector field construction algorithm, such as a gradient-based vector field calculation method, is used to generate a vector field on the current path skeleton. Each path point of the vector field will correspond to an electromagnetic field direction vector, describing the direction and intensity of the electromagnetic field. The generated path point vector field is saved in a three-dimensional model file (such as STL format) and a data file (such as CSV format), providing basic data for current direction inference. The path point vector field data is processed using vector analysis tools, such as the NumPy library in MATLAB or Python. First, the vector data of the path point vector field is input, and the current direction inference algorithm, such as a vector integral-based method, is applied to calculate the current flow direction of each path point. The algorithm infers the specific direction of the current at each path point by analyzing the direction and intensity of the vector field. The generated specific current direction data includes the current flow vector at each path point and is saved in a data table (such as XLSX format) and a graphic file (such as PNG format) for path direction annotation. Use graphic design software such as AutoCAD or Adobe Illustrator to edit the current path skeleton. First, import the specific current direction data into the design software. Use the path direction annotation tool to mark the current direction at each path point of the current path skeleton. The current flow direction can be displayed on the skeleton by arrows or vector symbols.After the annotation is completed, a directional current path skeleton diagram is generated and saved in a graphic file (such as DWG or SVG format). The directional current path skeleton diagram contains the current direction information of each path point, providing an accurate model for subsequent circuit simulation.

[0089] Preferably, step S34 includes the following steps:

[0090] Step S341: performing circuit geometric scaling on the directional current path skeleton to obtain a geometrically scaled circuit model;

[0091] Step S342: performing electromagnetic field distribution mapping on the directional current path skeleton based on the electromagnetic field variation of the device to generate an electromagnetic field distribution map;

[0092] Step S343: performing coupling analysis on the isotropic circuit model and the electromagnetic field distribution diagram to obtain electromagnetic-circuit coupling data;

[0093] Step S344: performing circuit proportional simulation on the proportional circuit model and the electromagnetic field distribution diagram based on the electromagnetic-circuit coupling data to generate a simulation device circuit unit.

[0094] The benefit of the present invention lies in that the directional current path skeleton is scaled geometrically to generate a geometric circuit model, which can better reflect the topological structure and parameter relationship of the internal circuit of the actual device, and provide a reliable basic model for subsequent coupling analysis and simulation. Based on the change in the electromagnetic field of the device, the electromagnetic field distribution of the directional current path skeleton is mapped to generate an electromagnetic field distribution diagram, which is well complementary to the geometric circuit model and provides more comprehensive input data for electromagnetic-circuit coupling analysis. The geometric circuit model and the electromagnetic field distribution diagram are coupled and analyzed to obtain electromagnetic-circuit coupling data, which reflects the interaction between the electromagnetic field and the circuit inside the device, and lays the foundation for subsequent simulation analysis. Based on the electromagnetic-circuit coupling data, the circuit geometric simulation of the geometric circuit model and the electromagnetic field distribution diagram is performed to generate a simulated device circuit unit, which can more accurately simulate the electromagnetic-circuit characteristics of the actual device, and provides strong support for device status analysis, fault diagnosis and performance optimization. Through proportional circuit model construction, electromagnetic field distribution mapping, electromagnetic-circuit coupling analysis and circuit proportional simulation methods, the circuit topology information, electromagnetic field distribution characteristics and actual equipment behavior are effectively integrated and fused to generate highly realistic simulation equipment circuit units, providing powerful simulation analysis support for intelligent detection and performance optimization of high-voltage power equipment.

[0095] In an embodiment of the present invention, data of a directional current path skeleton is obtained, and the data includes the geometric shape of the current path and its layout in the circuit. Computer-aided design (CAD) software is used to model the current path skeleton, and during the modeling process, it is necessary to ensure that the model accurately reflects the spatial structure of the actual current path. On this basis, a geometric scaling tool is used to geometrically scale the circuit model. The specific operation is to scale the size of the current path proportionally by adjusting the scaling factor to generate a new circuit model, the size of which has been scaled compared to the actual device circuit. Assume that when scaling the circuit model, the actual size of the original directional current path skeleton is the length =100mm, width =50mm. In order to perform geometric scaling, it is assumed that the size of the circuit model needs to be scaled to half of the original size to adapt to different test environments or simulation requirements. At this time, the scaling factor It can be calculated as follows: In this example, the target size is half the original size, so the scaling factor is for: . Use electromagnetic field simulation software (such as ANSYS HFSS or COMSOL Multiphysics) to input the geometric model of the current path skeleton. Apply current and voltage data under actual working conditions to the current path to simulate the changes in the electromagnetic field in the real working environment. The software will calculate the electromagnetic field distribution around the current path and generate an electromagnetic field distribution map. The figure shows the electromagnetic field strength and distribution characteristics at different positions of the current path. Use the electromagnetic-circuit coupling analysis tool (for example, the S-Parameter simulation module in ANSYS Electronics Desktop) to import the circuit model and electromagnetic field distribution map. This tool can couple the electromagnetic field distribution data with the circuit model to calculate the impact of the electromagnetic field on the circuit, including electromagnetic interference and signal integrity issues. During the coupling analysis process, the system integrates the change in the electromagnetic field with the response of the circuit and outputs the electromagnetic-circuit coupling data. These data include the impact of the electromagnetic field on the voltage, current and other circuit parameters of the current path, which helps to understand how the electromagnetic field affects the actual working conditions of the circuit. Select a simulation tool (such as Cadence PSpice or Keysight ADS) to import the previously generated electromagnetic-circuit coupling data into the simulation environment. Use this data to simulate the circuit model to simulate the behavior and performance of the circuit under the influence of electromagnetic fields. The simulation process includes changes in current paths, voltage distribution, and signal transmission. Based on the simulation results, a simulated device circuit unit is generated, which can be used to verify the correctness of the design and perform further optimization.

[0096] Preferably, step S4 comprises the following steps:

[0097] Step S41: collecting multi-source data of the equipment use environment through the environmental sensor network; integrating the multi-source data of the equipment use environment to obtain the equipment use environment data;

[0098] Step S42: constructing a change environment field for the equipment usage environment data to generate a simulated environment field;

[0099] Step S43: simulating the circuit operation of the circuit unit of the simulation device according to the simulated environment field to obtain simulated circuit operation data;

[0100] Step S44: injecting a pseudo-random signal into the analog circuit working data to generate interference injection circuit working data;

[0101] Step S45: performing interference spectrum analysis on the interference injection circuit working data to obtain simulation circuit response data.

[0102] The invention is beneficial in that it collects multi-source data of the equipment use environment through the environmental sensor network and integrates the data, so as to fully grasp the environmental conditions of the equipment during actual operation, such as temperature, humidity, vibration, and electromagnetic interference factors. These environmental data are the basis for subsequent simulation of environmental fields and circuit operation simulation, and can ensure that the simulation results are closer to reality. The simulated environmental field is constructed based on the collected environmental data, so as to better reproduce the dynamic characteristics of the actual use environment of the equipment. Such changing environmental fields, such as temperature fields and electromagnetic fields, can more comprehensively reflect the operating state of the equipment in a complex environment, rather than simple static environmental conditions. According to the simulated environmental field, the circuit operation simulation of the simulated equipment circuit unit can more accurately predict the circuit performance and working state of the equipment in the actual use environment. By coupling environmental factors with circuit characteristics, some hidden working anomalies and potential faults can be found. Pseudo-random signals are injected into the simulated circuit working data to simulate various interferences suffered by power equipment in the actual environment. Such interference injection can test the anti-interference ability of the equipment circuit and find out the abnormal behavior of the equipment in a complex electromagnetic environment. Interference spectrum analysis is performed on the interference injection circuit working data to accurately identify abnormal characteristics in the equipment circuit response. This provides a basis for subsequent fault diagnosis, helps to quickly locate the root cause of equipment failure, and take targeted maintenance measures. Making full use of actual environmental data, building simulation models, injecting interference signals, and performing waveform analysis can fully simulate the working state of high-voltage power equipment in the actual use environment, providing a reliable basis for equipment performance evaluation and fault diagnosis.

[0103] In an embodiment of the present invention, multi-source data of the device use environment are collected through an environmental sensor network. These sensors include temperature sensors, humidity sensors, pressure sensors, and light sensors, which are distributed at key locations around the device. These sensors continuously monitor environmental variables and transmit data to a central data processing system in real time. Next, a data integration tool is used to fuse the raw data from different sensors. For example, a data fusion algorithm (such as a Kalman filter or a weighted average method) is used to integrate the sensor data into a comprehensive environmental data set. The environmental data set includes time series data and spatial data, reflecting the overall situation of the device use environment. Finally, the device use environment data is generated. The device use environment data is input using environmental modeling software (such as COMSOL Multiphysics or Ansys Fluent). The software can build an environmental model around the device based on sensor data, for example, to establish a three-dimensional environmental field model including temperature, humidity, and airflow factors. The environmental field simulation function of the software is used to process the environmental data and generate a simulated environmental field. This simulated environmental field can reflect changes under different environmental conditions, including temperature gradients, humidity distribution, and airflow patterns. The simulated environmental field is imported into a circuit simulation software (such as a SPICE simulation tool). The software can accept the influencing parameters of the environmental field and apply them to the circuit model. Perform circuit operation simulation to simulate the circuit operation of the device under different environmental conditions. The simulation software calculates the current, voltage and power consumption parameters of the circuit and generates simulated circuit operation data. These data reflect the operating status of the device under actual environmental conditions, such as changes in circuit performance or potential failure risks. Perform pseudo-random signal injection on the simulated circuit operation data. First, select a pseudo-random signal generator (such as a random noise source or a pseudo-random number generator) to generate a pseudo-random signal. Inject the pseudo-random signal into the circuit simulation model, which can be achieved by setting up a signal injection module or adding a noise source in the simulation software. The role of the pseudo-random signal is to simulate the interference situation in actual use and evaluate the circuit's response to various interference signals. The generated interference injection circuit operation data includes the impact of the pseudo-random signal on the circuit performance, such as signal distortion and voltage fluctuations. Perform interference spectrum analysis on the interference injection circuit operation data. Use a spectrum analyzer (such as Agilent E5071C) to perform frequency domain analysis on the interference injection circuit operation data. Input the circuit operation data into the spectrum analyzer and calculate the signal's spectrum information through Fourier transform. Analyze the interference peaks and noise frequencies that appear in the spectrum graph to identify the interference pattern in the signal. Finally, the simulated circuit response data is obtained to describe the response characteristics of the circuit under interference conditions. These data help evaluate the circuit's anti-interference ability and provide a basis for optimizing circuit design.

[0104] Preferably, step S5 comprises the following steps:

[0105] Step S51: Calculate the signal power spectrum density of the simulation circuit response data to obtain the response power spectrum density;

[0106] Step S52: evaluating the response intensity of the response power spectrum density to generate the circuit response intensity;

[0107] Step S53: mapping the circuit response intensity to the environmental adaptability to obtain the interference environment adaptability;

[0108] Step S54: constructing a state recognition model for the device electromagnetic field variation and the interference environment adaptability to obtain a device state recognition model;

[0109] Step S55: using the device status recognition model to identify the device status of the high-voltage power equipment, so as to perform the task of intelligently detecting the high-voltage power equipment.

[0110] The benefit of the present invention lies in that the signal power spectrum density is calculated for the simulation circuit response data, and the characteristics of the circuit response can be analyzed from the frequency domain perspective. The power spectrum density can reflect the energy distribution of the circuit in different frequency bands, which helps to identify abnormal frequency bands and provide a basis for subsequent fault analysis. The response intensity of the response power spectrum density is evaluated to quantitatively describe the severity of the circuit response. This indicator can reflect the sensitivity of the circuit to external interference and provide an important reference for evaluating the anti-interference performance of the equipment. By mapping the circuit response intensity with the actual environmental characteristics, the interference environment adaptability of the equipment in the environment can be obtained. This provides a basis for subsequent equipment status judgment and can determine whether the equipment can adapt to a complex electromagnetic environment. The equipment status recognition model is constructed based on the electromagnetic field change and the interference environment adaptability, which can more comprehensively evaluate the working status of the equipment. This state recognition model based on multi-dimensional indicators can more accurately diagnose the fault type and severity of the equipment. Using the constructed equipment status recognition model, intelligent status monitoring and fault diagnosis of high-voltage power equipment can be realized. This method based on simulation analysis and intelligent recognition can timely discover hidden fault hazards of equipment and provide a reliable basis for intelligent maintenance of power equipment. By making full use of the spectral characteristics of circuit response and interference environment adaptability factors, an intelligent equipment status recognition model is constructed to provide strong support for status monitoring and fault diagnosis of high-voltage power equipment, greatly improving the accuracy and intelligence level of detection.

[0111] In an embodiment of the present invention, time series data obtained from the working data of the interference injection circuit are collected. A signal processing tool (such as MATLAB or Python's NumPy library) is used to perform power spectral density analysis on these data. The time domain signal is converted to the frequency domain by Fourier transform, and the power of each frequency component is calculated. The specific operation is to input the time series data into the power spectral density calculation function to obtain a power spectral density diagram, which shows the power distribution of the signal at different frequencies. This diagram is used to analyze the frequency characteristics of the signal and its intensity in the interference environment, thereby generating a response power spectral density. Determine an evaluation index, such as the peak power, root mean square power or total power of the signal. Use a statistical analysis tool (such as MATLAB's Signal Processing Toolbox or Python's SciPy library) to analyze the response power spectral density diagram. The specific steps of calculating the response intensity include: extracting the main frequency components in the power spectral density diagram, evaluating the corresponding power values, and combining these values ​​to evaluate the intensity of the signal at each frequency. The generated circuit response intensity data is used to measure the response intensity of the circuit under interference conditions. Define a fitness index, such as environmental interference tolerance or environmental adaptability coefficient. Use a fitness mapping tool (such as the mapping function in MATLAB or the Pandas library in Python) to compare the circuit response intensity with the predefined environmental interference standard. Input the circuit response intensity data into the fitness mapping algorithm to calculate the interference environment fitness. The mapping process generates an interference environment fitness graph that shows the adaptability of the circuit in various interference environments to evaluate its performance stability under different interference conditions. Collect electromagnetic field change data and interference environment fitness data as input variables. Use machine learning modeling tools (such as MATLAB's Machine Learning Toolbox or Python's scikit-learn library) to build the model. Select an appropriate algorithm (such as support vector machine, decision tree, or neural network) to train the electromagnetic field change and interference environment fitness data into a state recognition model. During the model training process, use historical data to adjust and optimize the model parameters to improve the recognition accuracy. Finally, a device state recognition model is obtained, which can classify and predict the device state based on the input data. Use the device state recognition model to perform state recognition on high-voltage power equipment. First, the real-time collected electromagnetic field variation and interference environment adaptability data are input into the constructed state recognition model. The model is used to analyze these data and generate equipment state prediction results. The prediction results of the equipment state recognition model are used to determine the operating state of high-voltage power equipment, such as normal, abnormal, or faulty. Based on the state information output by the model, intelligent detection tasks are performed, such as issuing alarms, triggering maintenance operations, or adjusting equipment operating parameters to ensure the safe and stable operation of high-voltage power equipment.

[0112] Preferably, constructing a state recognition model for the electromagnetic field variation of the equipment and the interference environment adaptability includes:

[0113] Design the identification logic for the equipment electromagnetic field variation and interference environment adaptability to obtain the model identification logic;

[0114] The model recognition logic is as follows:

[0115] When the change in the electromagnetic field of the equipment is greater than the electromagnetic field change threshold, the result that immediate maintenance is required is output;

[0116] When the change in the device's electromagnetic field is less than the electromagnetic field change threshold, the adaptability of the interference environment is judged:

[0117] When the interference environment adaptability is less than the environment adaptability threshold, the output needs to maintain the result;

[0118] When the interference environment adaptability is greater than the environment adaptability threshold, a good working state result is output;

[0119] Based on the model recognition logic, an automatic recognition model is constructed for the equipment electromagnetic field change and interference environment adaptability to generate an equipment status recognition model.

[0120] The benefit of the present invention is that by setting the electromagnetic field change threshold and the environmental adaptability threshold, a clear logical judgment rule is established. This clear recognition logic helps to improve the interpretability and repeatability of diagnostic decisions and provide a reliable basis for subsequent maintenance and repair. Combining the two indicators of the equipment electromagnetic field change and the interference environment adaptability for state identification can more comprehensively evaluate the working state of the equipment. This can not only reflect the fault condition inside the equipment, but also take into account the impact of the external environment on the equipment, which is conducive to discovering hidden fault hazards. The automated recognition model constructed based on the model recognition logic can realize rapid diagnosis and judgment of the equipment state. This greatly improves the detection efficiency, reduces the workload of manual inspections, and provides support for the intelligent management of power equipment. According to different diagnostic results, corresponding maintenance and repair strategies can be formulated. When the equipment needs immediate maintenance, it can be handled as a priority; when the equipment needs maintenance, it can be prevented in advance to avoid the occurrence of failures; when the equipment is in good working condition, it can continue to operate to reduce unnecessary maintenance expenses. This helps to improve the reliability of power equipment and reduce maintenance costs. By setting reasonable thresholds, potential fault hazards of equipment can be discovered in time. When the fault threshold is approached, it can warn of problems with the equipment, provide support for proactive maintenance and preventive repairs, and improve the safety of the power system. A comprehensive and automated equipment status recognition model has been built to effectively monitor the working status of high-voltage power equipment, providing important support for accurate diagnosis and intelligent maintenance, which is of great significance to improving the reliability and operating efficiency of power equipment.

[0121] In the embodiment of the present invention, the electromagnetic field change threshold and the environmental adaptability threshold are determined. These thresholds can be set through historical data analysis and expert experience. For example, the electromagnetic field change threshold is set to =0.5mT, and the environmental adaptation threshold is set to =0.7mT. The threshold value is determined by the working standard and environmental conditions of the equipment. Greater than , the system will directly output the result of "immediate maintenance required". This judgment is made by comparing the change in the electromagnetic field with the preset threshold, ensuring that maintenance measures are taken immediately when a large change in the electromagnetic field occurs to prevent damage to the equipment or aggravation of the fault. Less than , then it is necessary to further check the adaptability of the interference environment. For comparison. Less than , the output is "maintenance required". This indicates that although the electromagnetic field change is normal, the environmental interference is large, which will affect the normal operation of the equipment and maintenance inspection is required; if Greater than , then the result of "working in good condition" is output. This means that when the environmental interference adaptability is normal, the electromagnetic field change is within the safe range, the equipment is in good condition and does not require maintenance. is the electromagnetic field change threshold, is the environmental adaptation threshold, is the change in the electromagnetic field of the equipment, The data is collected by using sensor networks and environmental monitoring systems to collect data and organize them into structured data sets. The data sets include electromagnetic field changes, , Interference environment adaptability and equipment status labels (such as "maintenance required" and "in good working condition"). Use modeling tools (such as MATLAB's Machine Learning Toolbox or Python's scikit-learn library) to build the model. First, select an appropriate classification algorithm, such as decision tree, support vector machine (SVM), or logistic regression, to classify the data according to the equipment's status label and divide the data set into a training set and a test set. Use the training set to train the selected classification algorithm to learn the relationship between the electromagnetic field change and the interference environment adaptability and the equipment status. Through model training, adjust the algorithm parameters to optimize the classification performance, and use cross-validation technology to evaluate the accuracy of the model. Validate the trained model on the test set to evaluate its prediction accuracy and generalization ability. Adjust the model parameters to ensure the accuracy of the model in practical applications. For the classification model, calculate the confusion matrix, precision, and recall indicators to evaluate the model performance. After training, save the trained model and generate the equipment status recognition model.

[0122] This specification also provides a high-voltage electric equipment detection system for executing the high-voltage electric equipment detection method as described above, the high-voltage electric equipment detection system comprising:

[0123] The feature extraction module is used to obtain the main current path of the power equipment; reconstruct the waveform of the main current path of the power equipment in the time domain to generate current waveform data; extract statistical features from the current waveform data to obtain current waveform statistical features;

[0124] The electromagnetic conversion module is used to analyze the electromagnetic correlation relationship of the current waveform statistical characteristics to obtain the electromagnetic correlation relationship; based on the electromagnetic correlation relationship, the current waveform statistical characteristics are proportionally converted to generate the electromagnetic field variation of the equipment;

[0125] The circuit simulation module is used to construct the skeleton structure of the main current path of the power equipment to obtain the current path skeleton; perform circuit proportional simulation on the current path skeleton and the change of the electromagnetic field of the equipment to generate the circuit unit of the simulation equipment;

[0126] A response analysis module is used to obtain device usage environment data; based on the device usage environment data, a response analysis is performed on the simulation device circuit unit to obtain simulation circuit response data;

[0127] The state recognition module is used to perform equipment environment adaptation analysis on the simulation circuit response data to obtain the interference environment adaptability; to construct a state recognition model for the equipment electromagnetic field change and the interference environment adaptability to obtain the equipment state recognition model; and to use the equipment state recognition model to perform equipment state recognition on high-voltage power equipment to perform the task of intelligently detecting high-voltage power equipment.

[0128] The benefit of the present invention lies in that by obtaining the main current path of the device, the actual current distribution of the device can be more comprehensively reflected, and the waveform reconstruction and statistical feature extraction of the current path can more accurately describe the actual current characteristics of the device. By adopting electromagnetic correlation analysis, the complex electromagnetic coupling law inside the device can be better captured. Based on the electromagnetic correlation, the statistical characteristics of the current waveform are converted, and the change of the electromagnetic field of the device can be more scientifically derived. Through the current path skeleton structured modeling, the electromagnetic field distribution inside the device can be more carefully reflected, and the circuit model can be combined with the equipment use environment data to enhance the adaptability and reliability of the circuit simulation. Using the equipment electromagnetic field change and environmental adaptability for state recognition modeling can achieve more intelligent equipment state judgment, make full use of the equipment use environment data, and improve the accuracy and robustness of the state recognition model. Optimization is carried out in current characteristic analysis, electromagnetic coupling modeling, circuit environment adaptation and intelligent diagnosis, which can better solve the limitations of power equipment detection technology and improve the intelligent detection level of high-voltage power equipment.

[0129] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0130] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A method for detecting high voltage power equipment, It is characterized in that The following steps are involved: Step S1: obtaining the main current path of the power equipment; reconstructing the waveform of the main current path of the power equipment in the time domain to generate current waveform data; Statistical features are extracted from the current waveform data to obtain current waveform statistical features, wherein step S1 includes the following steps: Step S11: Acquire the target of the electric power equipment to be tested; and identify the main current path of the target of the electric power equipment to be tested to obtain the main current path of the electric power equipment; Step S12: performing real-time current measurement on the main current path of the power equipment to obtain equipment current data; Step S13: reconstruct the waveform of the device current data in the time domain to generate current waveform data; Step S14: performing fast Fourier transform on the current waveform data to generate a current spectrum diagram; Step S15: extracting statistical features from the current spectrum to obtain statistical features of the current waveform; Step S2: Perform electromagnetic correlation analysis on the current waveform statistical features to obtain the electromagnetic correlation; perform proportional conversion on the current waveform statistical features based on the electromagnetic correlation to generate the device electromagnetic field variation, wherein step S2 includes the following steps: Step S21: Calculate the fluctuation intensity of the current waveform statistical characteristics to generate current fluctuation intensity data; Step S22: performing electromagnetic correlation analysis on the current fluctuation intensity data to obtain an electromagnetic correlation; Step S23: Calculate the conversion ratio of the electromagnetic correlation relationship to obtain electromagnetic conversion ratio data; Step S24: performing proportional conversion on the current waveform statistical characteristics based on the electromagnetic conversion ratio data to generate the device electromagnetic field variation; Step S3: construct a skeleton structure for the main current path of the power equipment to obtain a current path skeleton; perform circuit proportional simulation on the current path skeleton and the electromagnetic field variation of the equipment to generate a simulated equipment circuit unit, wherein step S3 includes the following steps: Step S31: Identify the connectivity of the main current paths of the power equipment and generate current path connectivity data; Step S32: constructing a skeleton structure of the main current path of the power equipment according to the current path connectivity data to obtain a current path skeleton; Step S33: inferring the current direction of the current path skeleton based on the change in the electromagnetic field of the device to obtain a directional current path skeleton, wherein step S33 includes the following steps: Step S331: performing electromagnetic field mapping on the current path skeleton based on the electromagnetic field variation of the device to obtain electromagnetic field data corresponding to the skeleton; Step S332: performing phase difference analysis on the electromagnetic field data corresponding to the skeleton to obtain electromagnetic field phase difference information; Step S333: constructing a skeleton vector field of the current path skeleton according to the electromagnetic field phase difference information to generate a path point vector field; Step S334: inferring the current direction of the path point vector field to obtain specific current direction data; Step S335: marking the path direction of the current path skeleton according to the specific current direction data to generate a directional current path skeleton; Step S34: performing circuit proportional simulation on the device electromagnetic field variation and the directional current path skeleton to generate a simulated device circuit unit, wherein step S34 includes the following steps: Step S341: performing circuit geometric scaling on the directional current path skeleton to obtain a geometrically scaled circuit model; Step S342: performing electromagnetic field distribution mapping on the directional current path skeleton based on the electromagnetic field variation of the device to generate an electromagnetic field distribution map; Step S343: performing coupling analysis on the isotropic circuit model and the electromagnetic field distribution diagram to obtain electromagnetic-circuit coupling data; Step S344: performing circuit proportional simulation on the proportional circuit model and the electromagnetic field distribution diagram based on the electromagnetic-circuit coupling data to generate a simulation device circuit unit; Step S4: acquiring device usage environment data; performing response analysis on the simulated device circuit unit based on the device usage environment data to obtain simulated circuit response data, wherein step S4 includes the following steps: Step S41: collecting multi-source data of the equipment use environment through the environmental sensor network; integrating the multi-source data of the equipment use environment to obtain the equipment use environment data; Step S42: constructing a change environment field for the equipment usage environment data to generate a simulated environment field; Step S43: simulating the circuit operation of the circuit unit of the simulation device according to the simulated environment field to obtain simulated circuit operation data; Step S44: injecting a pseudo-random signal into the analog circuit working data to generate interference injection circuit working data; Step S45: performing interference spectrum analysis on the interference injection circuit working data to obtain simulation circuit response data; Step S5: Performing equipment environment adaptation analysis on the simulation circuit response data to obtain the interference environment adaptability; constructing a state recognition model for the equipment electromagnetic field variation and the interference environment adaptability to obtain an equipment state recognition model; using the equipment state recognition model to perform equipment state recognition on the high-voltage power equipment to perform the intelligent detection of the high-voltage power equipment task, wherein step S5 includes the following steps: Step S51: Calculate the signal power spectrum density of the simulation circuit response data to obtain the response power spectrum density; Step S52: evaluating the response intensity of the response power spectrum density to generate the circuit response intensity; Step S53: mapping the circuit response intensity to the environmental adaptability to obtain the interference environment adaptability; Step S54: constructing a state recognition model for the device electromagnetic field variation and the interference environment adaptability to obtain a device state recognition model; Step S55: using the device status recognition model to identify the device status of the high-voltage power equipment, so as to perform the task of intelligently detecting the high-voltage power equipment.

2. The high voltage power equipment detection method according to claim 1, It is characterized in that The state recognition model construction of the equipment electromagnetic field change and interference environment adaptability includes: Design the identification logic for the equipment electromagnetic field variation and interference environment adaptability to obtain the model identification logic; The model recognition logic is as follows: When the change in the electromagnetic field of the equipment is greater than the electromagnetic field change threshold, the result that immediate maintenance is required is output; When the change in the device's electromagnetic field is less than the electromagnetic field change threshold, the adaptability of the interference environment is judged: When the interference environment adaptability is less than the environment adaptability threshold, the output needs to maintain the result; When the interference environment adaptability is greater than the environment adaptability threshold, a good working state result is output; Based on the model recognition logic, an automatic recognition model is constructed for the equipment electromagnetic field change and interference environment adaptability to generate an equipment status recognition model.

3. A high voltage power equipment detection system, It is characterized in that Used to perform the high-voltage power equipment detection method as claimed in claim 1, the high-voltage power equipment detection system comprises: The feature extraction module is used to obtain the main current path of the power equipment; reconstruct the waveform of the main current path of the power equipment in the time domain to generate current waveform data; extract statistical features from the current waveform data to obtain current waveform statistical features; The electromagnetic conversion module is used to analyze the electromagnetic correlation relationship of the current waveform statistical characteristics to obtain the electromagnetic correlation relationship; based on the electromagnetic correlation relationship, the current waveform statistical characteristics are proportionally converted to generate the electromagnetic field variation of the equipment; The circuit simulation module is used to construct the skeleton structure of the main current path of the power equipment to obtain the current path skeleton; perform circuit proportional simulation on the current path skeleton and the change of the electromagnetic field of the equipment to generate the circuit unit of the simulation equipment; A response analysis module is used to obtain device usage environment data; based on the device usage environment data, a response analysis is performed on the simulation device circuit unit to obtain simulation circuit response data; The state recognition module is used to perform equipment environment adaptation analysis on the simulation circuit response data to obtain the interference environment adaptability; to construct a state recognition model for the equipment electromagnetic field change and the interference environment adaptability to obtain the equipment state recognition model; and to use the equipment state recognition model to perform equipment state recognition on high-voltage power equipment to perform the task of intelligently detecting high-voltage power equipment.

Citation Information

Cited By

  • Electric-thermal two-parameter two-dimensional explosion-proof cable joint monitoring method and system

    CN119666067A