Operation and maintenance assessment method and device based on insulation status of power equipment

Abstract

This application relates to the field of power equipment monitoring technology, and in particular to a method and apparatus for operation and maintenance assessment based on the insulation status of power equipment. The method includes: acquiring multi-source data and fusing it to obtain fused feature data; determining tensor data to calculate the comprehensive deviation; determining the aging stage and calculating the insulation health comprehensive index to predict the remaining insulation life; identifying fault location and fault type based on the multi-source data, the insulation health comprehensive index, and the remaining insulation life; and determining the operation and maintenance plan for the target power equipment based on the insulation health comprehensive index, the remaining insulation life, the fault type, and the fault location. This solves the problems in related technologies, such as reliance on single-dimensional monitoring, lack of spatiotemporal alignment mechanisms, difficulty in associating heterogeneous data, resulting in assessment bias and neglect of microstructural evolution, and lack of differentiated guidance for operation and maintenance strategies, making it difficult to achieve full-scale, accurate assessment and operation and maintenance.

Description

Technical Field

[0001] This application relates to the field of power equipment monitoring technology, and in particular to a method and apparatus for operation and maintenance assessment based on the insulation status of power equipment. Background Technology

[0002] In related technologies, analysis is often conducted using single-dimensional monitoring data. For example, parameters such as voltage, current, and partial discharge are collected through electrical equipment, or temperature data of equipment is collected through temperature sensors. Alternatively, multi-dimensional data (electrical, temperature, mechanical, chemical, etc.) collected by different types of sensors can be integrated, and a more comprehensive insulation status assessment model can be constructed through spatiotemporal alignment and feature correlation.

[0003] However, most related technologies rely on single-dimensional monitoring data, which cannot comprehensively reflect the overall state of the insulation system. They are prone to evaluation bias due to missing local information. Furthermore, multi-data fusion lacks an effective spatiotemporal alignment mechanism, and data from different sources and sampling frequencies are not accurately correlated. The evaluation process focuses on macroscopic performance monitoring while ignoring changes in the microscopic insulation material structure. The operation and maintenance strategy adopts a uniform model without developing differentiated solutions based on the actual insulation state of the equipment. The overall approach is mainly based on periodic offline testing or single online monitoring, which makes it difficult to achieve full-scale, accurate evaluation and operation and maintenance guidance. Improvements are urgently needed. Summary of the Invention

[0004] This application provides an operation and maintenance assessment method and device based on the insulation status of power equipment, in order to solve the problems in related technologies, such as reliance on single-dimensional monitoring, lack of spatiotemporal alignment mechanism, difficulty in associating heterogeneous data, resulting in assessment bias and neglect of microstructure evolution, and lack of differentiated guidance for operation and maintenance strategies, making it difficult to achieve full-scale, accurate assessment and operation and maintenance.

[0005] The first aspect of this application provides a method for operation and maintenance assessment based on the insulation status of power equipment, comprising the following steps: acquiring multi-source data matching the insulation status of the target power equipment based on equipment data and operating data of the target power equipment, and fusing the multi-source data to obtain fused feature data; determining tensor data of the target power equipment based on the fused feature data, and calculating the comprehensive deviation between the current insulation status tensor and the health benchmark tensor based on the tensor data; determining the aging stage of the target power equipment based on the multi-source data, and calculating the insulation health comprehensive index of the insulation status based on the comprehensive deviation, and predicting the remaining insulation life of the target power equipment based on the insulation health comprehensive index and the aging stage; identifying the fault location and the fault type corresponding to the fault location of the target power equipment based on the multi-source data, the insulation health comprehensive index, and the remaining insulation life, and determining the operation and maintenance plan of the target power equipment based on the insulation health comprehensive index, the remaining insulation life, the fault type, and the fault location.

[0006] Through the above technical solution, multi-source data matching the insulation status of the target power equipment can be obtained based on the equipment data and operation data of the target power equipment. The multi-source data is then fused to obtain fused feature data. Tensor data is then determined based on the fused feature data to calculate the comprehensive deviation and determine the aging stage of the target power equipment, thereby obtaining the insulation health comprehensive index of the insulation status. This allows for the prediction of the remaining insulation life of the target power equipment. Combined with the identified fault location and fault type of the target power equipment, an operation and maintenance plan is determined. By constructing a tensor model through the fusion of multi-source heterogeneous data, the comprehensive deviation of the insulation status and the insulation health comprehensive index are accurately quantified. Combined with the aging stage, the remaining insulation life is predicted, and fault location and type are identified accordingly. This achieves full-scale accurate assessment and differentiated operation and maintenance decision-making from macro-operation to micro-structure, and formulates an integrated technical concept for differentiated operation and maintenance strategies.

[0007] Optionally, in one embodiment of this application, the step of acquiring multi-source data matching the insulation state of the target power equipment includes: detecting whether the multi-source data meets a preset condition; and if the multi-source data does not meet the preset condition, processing the multi-source data until multi-source data that meets the preset condition is obtained.

[0008] The above technical solution can process multi-source data until the preset conditions are met when the preset conditions are not met. By performing strict preset condition detection and preprocessing on multi-source data, abnormal data can be effectively eliminated or corrected, ensuring the quality and consistency of input data and providing a highly reliable data foundation for subsequent accurate evaluation.

[0009] Optionally, in one embodiment of this application, determining the aging stage of the target power equipment based on the multi-source data includes: obtaining the degree of polymerization of the insulating medium of the target power equipment; determining a first degree of damage to the target power equipment based on the degree of polymerization; obtaining the dielectric loss value, leakage current, and temperature value of the insulating medium; determining a second degree of damage to the target power equipment based on the dielectric loss value, the leakage current, and the temperature value; and determining the aging stage based on the first degree of damage and the second degree of damage.

[0010] The above technical solution can determine the first degree of damage based on the degree of polymerization of the insulating medium of the target power equipment, and the second degree of damage based on the dielectric loss value, leakage current and temperature value of the insulating medium, thereby determining the aging stage of the target power equipment. By integrating the degree of polymerization, which characterizes the nature of micromaterials, with dielectric and temperature parameters, which reflect macroscopic operating performance, complementary verification of microstructure and macroscopic performance is achieved, thus significantly improving the scientificity and accuracy of aging stage division.

[0011] Optionally, in one embodiment of this application, identifying the fault location and the corresponding fault type of the target power equipment based on the multi-source data, the insulation health comprehensive index, and the insulation remaining lifetime includes: obtaining a defect candidate region of the target power equipment based on the dielectric constant loss factor in the multi-source data; identifying the fault location based on the defect candidate region; and identifying the fault type based on the fault location, the insulation health comprehensive index, and the insulation remaining lifetime.

[0012] The above technical solution can identify the candidate defect area of ​​the target power equipment based on the dielectric constant and loss factor in multi-source data, thereby determining the corresponding fault location and identifying the corresponding fault type. By accurately locking the candidate defect area and location through dielectric parameters, and combining the insulation health index and remaining life to comprehensively judge the fault type, a deep coupling from physical location to property diagnosis is achieved, which significantly improves the accuracy and pertinence of fault diagnosis.

[0013] Optionally, in one embodiment of this application, the calculation formula for the fused feature data may be, but is not limited to, the following: , in, For device space coordinates ,time Fusion feature data at the location, These correspond to six-dimensional data sources: electrical, thermal, mechanical, chemical, environmental, and microwave photonics. For the first Dynamic weights of dimensional data sources For the first Data source of dimensional data The raw source data after standardization processing For the first Source credibility decay factor of dimensional data source For the first The spatiotemporal consistency coefficient of the data source.

[0014] The above technical solution can be used to calculate the fused feature data of the target power equipment by integrating multi-dimensional raw data, dynamic weights, source credibility decay factors and spatiotemporal consistency coefficients. By introducing dynamic weights and spatiotemporal consistency coefficients, the spatiotemporal alignment problem of multi-source heterogeneous data is effectively solved, and the anti-interference ability and representation accuracy of the fused data are improved by using source credibility decay factors.

[0015] Optionally, in one embodiment of this application, the formula for calculating the overall deviation can be, but is not limited to, the following: , in, This represents the combined deviation between the current insulation state tensor and the healthy baseline tensor. These correspond to the five core dimensions of the tensor model: time, space, frequency, device type, and dielectric properties. For the first Dimensional feature contribution For the current state, the first The eigenvalues ​​of the current insulation state tensor of dimension, For the first time in a healthy state dimensional health baseline tensor eigenvalues For the first Dynamic adjustment items for health benchmarks in the body. This refers to the equipment's service life.

[0016] The above technical solution can be used to quantitatively assess the insulation status of equipment by comparing the comprehensive deviation between the current insulation status tensor and the health baseline tensor, and combining the contribution of features in each dimension. By introducing a dynamic correction term based on the number of years of operation and a weighted mechanism for the contribution of multi-dimensional features, the influence of natural aging of equipment on the baseline status is effectively eliminated, and the dynamic adaptability and quantitative accuracy of insulation status assessment are significantly improved.

[0017] Optionally, in one embodiment of this application, the formula for calculating the insulation health comprehensive index may be, but is not limited to, the following: , in, For the comprehensive index of insulation health, This represents the combined deviation between the current insulation state tensor and the healthy baseline tensor. This is a correction factor for the aging stage. It is a defect risk amplification factor.

[0018] The above technical solution can quantify the comprehensive insulation health index of the target power equipment by combining deviation, aging stage correction coefficient and defect risk amplification factor. By introducing aging stage correction and defect risk amplification mechanism, the limitations of single deviation assessment are effectively made up for, and the full life cycle of equipment insulation status from normal aging to fault risk is accurately quantified.

[0019] A second aspect of this application provides an operation and maintenance assessment device based on the insulation status of power equipment, comprising: a fusion module, configured to acquire multi-source data matching the insulation status of the target power equipment based on equipment data and operating data of the target power equipment, and fuse the multi-source data to obtain fused feature data; a calculation module, configured to determine tensor data of the target power equipment based on the fused feature data, and calculate the comprehensive deviation between the current insulation status tensor and the health benchmark tensor based on the tensor data; a prediction module, configured to determine the aging stage of the target power equipment based on the multi-source data, and calculate the insulation health comprehensive index of the insulation status based on the comprehensive deviation, and predict the remaining insulation life of the target power equipment based on the insulation health comprehensive index and the aging stage; and a determination module, configured to identify the fault location and the fault type corresponding to the fault location of the target power equipment based on the multi-source data, the insulation health comprehensive index, and the remaining insulation life, and determine the operation and maintenance plan of the target power equipment based on the insulation health comprehensive index, the remaining insulation life, the fault type, and the fault location.

[0020] Through the above technical solution, multi-source data matching the insulation status of the target power equipment can be obtained based on the equipment data and operation data of the target power equipment. The multi-source data is then fused to obtain fused feature data. Tensor data is then determined based on the fused feature data to calculate the comprehensive deviation and determine the aging stage of the target power equipment, thereby obtaining the insulation health comprehensive index of the insulation status. This allows for the prediction of the remaining insulation life of the target power equipment. Combined with the identified fault location and fault type of the target power equipment, an operation and maintenance plan is determined. By constructing a tensor model through the fusion of multi-source heterogeneous data, the comprehensive deviation of the insulation status and the insulation health comprehensive index are accurately quantified. Combined with the aging stage, the remaining insulation life is predicted, and fault location and type are identified accordingly. This achieves full-scale accurate assessment and differentiated operation and maintenance decision-making from macro-operation to micro-structure, and formulates an integrated technical concept for differentiated operation and maintenance strategies.

[0021] Optionally, in one embodiment of this application, the fusion module includes: a detection unit for detecting whether the multi-source data meets a preset condition; and a processing unit for processing the multi-source data until multi-source data that meets the preset condition is obtained when the multi-source data is detected not to meet the preset condition.

[0022] The above technical solution can process multi-source data until the preset conditions are met when the preset conditions are not met. By performing strict preset condition detection and preprocessing on multi-source data, abnormal data can be effectively eliminated or corrected, ensuring the quality and consistency of input data and providing a highly reliable data foundation for subsequent accurate evaluation.

[0023] Optionally, in one embodiment of this application, the prediction module includes: a first acquisition unit, configured to acquire the degree of polymerization of the insulating medium of the target power equipment; a first determination unit, configured to determine a first degree of damage to the target power equipment based on the degree of polymerization; a second acquisition unit, configured to acquire the dielectric loss value, leakage current, and temperature value of the insulating medium; a second determination unit, configured to determine a second degree of damage to the target power equipment based on the dielectric loss value, the leakage current, and the temperature value; and a third determination unit, configured to determine the aging stage based on the first degree of damage and the second degree of damage.

[0024] The above technical solution can determine the first degree of damage based on the degree of polymerization of the insulating medium of the target power equipment, and the second degree of damage based on the dielectric loss value, leakage current and temperature value of the insulating medium, thereby determining the aging stage of the target power equipment. By integrating the degree of polymerization, which characterizes the nature of micromaterials, with dielectric and temperature parameters, which reflect macroscopic operating performance, complementary verification of microstructure and macroscopic performance is achieved, thus significantly improving the scientificity and accuracy of aging stage division.

[0025] Optionally, in one embodiment of this application, the determining module includes: a third acquisition unit, configured to acquire a defect candidate region of the target power equipment based on the dielectric constant loss factor in the multi-source data; a first identification unit, configured to identify the fault location based on the defect candidate region; and a second identification unit, configured to identify the fault type based on the fault location, the insulation health comprehensive index, and the insulation remaining life.

[0026] The above technical solution can identify the candidate defect area of ​​the target power equipment based on the dielectric constant and loss factor in multi-source data, thereby determining the corresponding fault location and identifying the corresponding fault type. By accurately locking the candidate defect area and location through dielectric parameters, and combining the insulation health index and remaining life to comprehensively judge the fault type, a deep coupling from physical location to property diagnosis is achieved, which significantly improves the accuracy and pertinence of fault diagnosis.

[0027] Optionally, in one embodiment of this application, the calculation formula for the fused feature data may be, but is not limited to, the following: , in, For device space coordinates ,time Fusion feature data at the location, These correspond to six-dimensional data sources: electrical, thermal, mechanical, chemical, environmental, and microwave photonics. For the first Dynamic weights of dimensional data sources For the first Data source of dimensional data The raw source data after standardization processing For the first Source credibility decay factor of dimensional data source For the first The spatiotemporal consistency coefficient of the data source.

[0028] The above technical solution can be used to calculate the fused feature data of the target power equipment by integrating multi-dimensional raw data, dynamic weights, source credibility decay factors and spatiotemporal consistency coefficients. By introducing dynamic weights and spatiotemporal consistency coefficients, the spatiotemporal alignment problem of multi-source heterogeneous data is effectively solved, and the anti-interference ability and representation accuracy of the fused data are improved by using source credibility decay factors.

[0029] Optionally, in one embodiment of this application, the formula for calculating the overall deviation can be, but is not limited to, the following: , in, This represents the combined deviation between the current insulation state tensor and the healthy baseline tensor. These correspond to the five core dimensions of the tensor model: time, space, frequency, device type, and dielectric properties. For the first Dimensional feature contribution For the current state, the first The eigenvalues ​​of the current insulation state tensor of dimension, For the first time in a healthy state dimensional health baseline tensor eigenvalues For the first Dynamic adjustment items for health benchmarks in the body. This refers to the equipment's service life.

[0030] The above technical solution can be used to quantitatively assess the insulation status of equipment by comparing the comprehensive deviation between the current insulation status tensor and the health baseline tensor, and combining the contribution of features in each dimension. By introducing a dynamic correction term based on the number of years of operation and a weighted mechanism for the contribution of multi-dimensional features, the influence of natural aging of equipment on the baseline status is effectively eliminated, and the dynamic adaptability and quantitative accuracy of insulation status assessment are significantly improved.

[0031] Optionally, in one embodiment of this application, the formula for calculating the insulation health comprehensive index may be, but is not limited to, the following: , in, For the comprehensive index of insulation health, This represents the combined deviation between the current insulation state tensor and the healthy baseline tensor. This is a correction factor for the aging stage. It is a defect risk amplification factor.

[0032] The above technical solution can quantify the comprehensive insulation health index of the target power equipment by combining deviation, aging stage correction coefficient and defect risk amplification factor. By introducing aging stage correction and defect risk amplification mechanism, the limitations of single deviation assessment are effectively made up for, and the full life cycle of equipment insulation status from normal aging to fault risk is accurately quantified.

[0033] A third aspect of this application provides an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor. The processor executes the program to implement the operation and maintenance assessment method based on the insulation status of power equipment as described in the above embodiments.

[0034] A fourth aspect of this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described operation and maintenance assessment method based on the insulation status of power equipment.

[0035] A fifth aspect of this application provides a computer program product, including a computer program that, when executed, implements the above-described operation and maintenance assessment method based on the insulation status of power equipment.

[0036] This application embodiment can acquire multi-source data matching the insulation status of the target power equipment based on the equipment data and operational data of the target power equipment. The multi-source data is then fused to obtain fused feature data. Tensor data is then determined based on the fused feature data to calculate the comprehensive deviation and determine the aging stage of the target power equipment, thereby obtaining the insulation health comprehensive index of the insulation status. This predicts the remaining insulation life of the target power equipment. Combined with the identified fault location and fault type of the target power equipment, an operation and maintenance plan is determined. By fusing multi-source heterogeneous data to construct a tensor model, the comprehensive deviation of the insulation status and the insulation health comprehensive index are accurately quantified. Combined with the aging stage, the remaining insulation life is predicted, and fault location and type are identified accordingly. This achieves full-scale accurate assessment and differentiated operation and maintenance decisions from macro-operation to micro-structure, and establishes an integrated technical concept for differentiated operation and maintenance strategies. Therefore, it solves the problems in related technologies, such as reliance on single-dimensional monitoring, lack of spatiotemporal alignment mechanisms, difficulty in associating heterogeneous data, resulting in assessment bias and neglect of micro-structure evolution, and lack of differentiated guidance for operation and maintenance strategies, making it difficult to achieve full-scale, accurate assessment and operation and maintenance.

[0037] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0038] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein: Figure 1 This is a flowchart illustrating an operation and maintenance assessment method based on the insulation status of power equipment, according to an embodiment of this application. Figure 2 A flowchart illustrating the working principle of an operation and maintenance assessment method based on the insulation status of power equipment according to an embodiment of this application; Figure 3 This is a block diagram of an operation and maintenance assessment device based on the insulation status of power equipment provided in accordance with an embodiment of this application; Figure 4 This is a schematic diagram of the structure of an electronic device provided according to an embodiment of this application. Detailed Implementation

[0039] The embodiments of this application are described in detail below. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0040] The following describes, with reference to the accompanying drawings, an operation and maintenance assessment method and apparatus based on the insulation status of power equipment according to embodiments of this application. To address the issues mentioned in the background technology, such as reliance on single-dimensional monitoring, lack of spatiotemporal alignment mechanisms, difficulty in associating heterogeneous data, resulting in assessment bias and neglect of microstructural evolution, and lack of differentiated guidance for operation and maintenance strategies, making it difficult to achieve full-scale, accurate assessment and operation and maintenance, this application provides an operation and maintenance assessment method based on the insulation status of power equipment. In this method, multi-source data matching the insulation status of the target power equipment can be obtained based on the equipment data and operational data of the target power equipment. The multi-source data is then fused to obtain fused feature data. Tensor data is then determined based on the fused feature data to calculate the comprehensive deviation and determine the aging stage of the target power equipment, thereby obtaining the insulation health comprehensive index of the insulation status. This predicts the remaining insulation life of the target power equipment. Combined with the identified fault location and fault type of the target power equipment, an operation and maintenance plan is determined. By constructing a tensor model through the fusion of multi-source heterogeneous data, the comprehensive deviation of the insulation status and the insulation health comprehensive index are accurately quantified. Combined with the aging stage, the remaining insulation life is predicted, and the fault location and type are identified accordingly. This achieves full-scale accurate assessment and differentiated operation and maintenance decision-making from macro-operation to micro-structure, and formulates an integrated technical concept for differentiated operation and maintenance strategies. This solves the problems in related technologies, such as reliance on single-dimensional monitoring, lack of spatiotemporal alignment mechanisms, difficulty in associating heterogeneous data, resulting in evaluation bias and neglect of microstructure evolution, and lack of differentiated guidance for operation and maintenance strategies, making it difficult to achieve full-scale, accurate evaluation and operation and maintenance.

[0041] Specifically, Figure 1 This is a flowchart of an operation and maintenance assessment method based on the insulation status of power equipment, according to an embodiment of this application.

[0042] like Figure 1 As shown, this operation and maintenance assessment method based on the insulation status of power equipment includes the following steps: In step S101, based on the equipment data and operational data of the target power equipment, multi-source data matching the insulation state of the target power equipment is obtained, and the multi-source data is fused to obtain fused feature data. The calculation formula for the fused feature data may be, but is not limited to, the following: , in, For device space coordinates ,time Fusion feature data at the location, These correspond to six-dimensional data sources: electrical, thermal, mechanical, chemical, environmental, and microwave photonics. For the first Dynamic weights of dimensional data sources For the first Data source of dimensional data The raw source data after standardization processing For the first Source credibility decay factor of dimensional data source For the first The spatiotemporal consistency coefficient of the data source.

[0043] It is understood that, in the embodiments of this application, multi-source data may include, but is not limited to, six types of monitoring data: electrical data collected by electrical monitoring equipment, thermal data collected by thermal monitoring equipment, mechanical data collected by mechanical monitoring equipment, chemical data collected by chemical monitoring equipment, environmental data collected by environmental monitoring equipment, and microwave photon data collected by microwave photon monitoring equipment. The specific settings can be made by those skilled in the art according to the actual situation, and this application does not impose specific limitations.

[0044] The electrical monitoring equipment may include, but is not limited to, partial discharge sensors, voltage and current sensors, dielectric loss testers, etc., and this application does not impose specific limitations. Furthermore, embodiments of this application use electrical monitoring equipment to collect electrical data such as partial discharge signals, effective values ​​of three-phase voltage and current, dielectric loss values, and leakage current data during the operation of the target power equipment.

[0045] Thermal monitoring equipment may include, but is not limited to, infrared thermal imagers, fiber optic distributed temperature sensing cables, and radio frequency identification temperature sensors; this application does not impose specific limitations. Furthermore, embodiments of this application use thermal monitoring equipment to collect thermal data such as temperature values, temperature distribution, and top-layer oil temperature data of key components in the windings, core, and bushings of the target power equipment.

[0046] Mechanical monitoring equipment may include, but is not limited to, vibration sensors, strain gauges, distributed fiber optic vibration sensors, etc., and this application does not impose specific limitations. Furthermore, embodiments of this application use mechanical monitoring equipment to collect mechanical data such as vibration signals, mechanical strain data, and vibration frequency characteristics generated by the operation of the target power equipment.

[0047] Chemical monitoring equipment may include, but is not limited to, oil dissolved gas analyzers, moisture analyzers, and insulating oil dielectric loss testers; this application does not impose specific limitations. Furthermore, embodiments of this application use chemical monitoring equipment to collect chemical data such as the content of hydrogen and methane characteristic gases, the moisture content in the oil, and the dielectric loss factor.

[0048] Environmental monitoring equipment may include, but is not limited to, temperature and humidity sensors, pollution level monitors, and wind speed sensors; this application does not impose specific limitations. Furthermore, embodiments of this application collect environmental data such as temperature, humidity, pollution level, and wind speed data of the environment in which the target power equipment is located through environmental monitoring data collection.

[0049] Microwave photonic monitoring equipment can be a microwave photonic sensor array. Furthermore, in the embodiments of this application, the microwave photonic monitoring equipment can collect high-frequency electromagnetic wave signals reflected / scattered after penetrating the insulating medium, and simultaneously acquire microwave photonic data such as raw data related to the dielectric properties inside the insulation.

[0050] As one possible approach, embodiments of this application can obtain multi-source data matching the insulation status of the target power equipment based on the equipment data and operating data of the target power equipment.

[0051] For example, in the embodiments of this application for a 220kV oil-immersed transformer, six types of monitoring equipment, namely electrical, thermal, mechanical, chemical, environmental and microwave photonic, can be deployed to carry out synchronous acquisition of six-dimensional data, namely electrical data, thermal data, mechanical data, chemical data, environmental data and microwave photonic data.

[0052] Among electrical monitoring equipment, partial discharge sensors are installed on the side wall of transformer tanks to collect partial discharge signals, which can promptly detect possible discharge anomalies inside the insulation; voltage and current sensors are connected to the transformer outgoing terminals to collect the effective values ​​of three-phase voltage and current, which can intuitively reflect the electrical load status of the equipment during operation; dielectric loss testers are connected to the bushing end screen to collect dielectric loss values ​​and leakage current data, which can preliminarily determine the degree of insulation medium loss.

[0053] In thermal monitoring equipment, infrared thermal imagers scan the entire transformer to obtain the temperature distribution of key parts such as windings, cores, and bushings, enabling rapid location of localized overheating areas; fiber optic distributed temperature sensing cables are laid along the windings to collect temperature values ​​of each layer of the windings, allowing for precise monitoring of temperature differences at different locations of the windings; and wireless radio frequency identification temperature sensors are installed on the top of the oil tank to collect top-layer oil temperature data, enabling real-time monitoring of the overall temperature changes of the insulating oil.

[0054] In mechanical monitoring equipment, vibration sensors are fixed to the base of the oil tank to collect vibration signals generated during equipment operation. Vibration characteristics can be used to determine whether there are any abnormalities in the internal structure. Strain gauges are attached to the iron core clamps to collect mechanical strain data, which can reflect whether the stress state of the iron core is stable. Distributed fiber optic vibration sensors are arranged on the body to collect vibration frequency characteristics, which can further refine the criteria for judging vibration anomalies.

[0055] In chemical monitoring equipment, the dissolved gas analyzer in oil collects insulating oil samples through the oil inlet to detect the content of characteristic gases such as hydrogen and methane, and can predict whether there is a decomposition fault in the insulation based on the changes in characteristic gases; the moisture analyzer measures the moisture content in the oil, which can avoid the effect of excessive moisture on the insulation performance; the insulating oil dielectric loss tester simultaneously acquires dielectric loss factor data, which can supplement the judgment of the insulation quality of the insulating oil.

[0056] Environmental monitoring equipment is installed on outdoor monitoring poles in substations. Temperature and humidity sensors collect ambient temperature and humidity, pollution level monitors detect the surrounding air pollution level, and wind speed sensors record ambient wind speed. This data can help analyze the impact of the external environment on the insulation status of the equipment.

[0057] Microwave photonic monitoring equipment uses a microwave photonic sensor array, which is arranged around the key areas of the transformer bushing and tank to collect high-frequency electromagnetic wave signals reflected / scattered after penetrating the insulating medium. Simultaneously, it acquires raw data related to the dielectric properties of the insulation, providing core basis for subsequent reconstruction of the internal state of the insulation.

[0058] Furthermore, embodiments of this application can fuse multi-source data to obtain fused feature data. The calculation formula for the fused feature data can be, but is not limited to, the following: , in, For device space coordinates ,time Fusion feature data at the location, These correspond to six-dimensional data sources: electrical, thermal, mechanical, chemical, environmental, and microwave photonics. For the first Dynamic weights of dimensional data sources For the first Data source of dimensional data The raw source data after standardization processing For the first Source credibility decay factor of dimensional data source For the first The spatiotemporal consistency coefficient of the data source improves the overall representativeness and accuracy of the data.

[0059] For example, embodiments of this application may employ a six-dimensional data fusion credibility algorithm, combining the dynamic weights of the source data in each dimension, the source credibility decay factor, and the spatiotemporal consistency coefficient to perform multi-source data fusion on the six-dimensional data, thereby obtaining fused feature data. The calculation formula for the fused feature data is shown above and will not be elaborated further here.

[0060] Optionally, in one embodiment of this application, acquiring multi-source data that matches the insulation state of the target power equipment includes: detecting whether the multi-source data meets preset conditions; and if the multi-source data does not meet the preset conditions, processing the multi-source data until multi-source data that meets the preset conditions is obtained.

[0061] In actual implementation, the embodiments of this application can first detect whether the multi-source data meets preset conditions, and if the preset conditions are not met, process the multi-source data until multi-source data that meets the preset conditions is obtained. The preset conditions can be set by those skilled in the art according to actual circumstances, and this application does not impose specific limitations.

[0062] For example, the embodiments of this application can perform spatiotemporal alignment processing on the collected six-dimensional data to ensure that the data format is uniform, laying the foundation for subsequent multi-source data fusion, and process the microwave photon data to generate a three-dimensional dielectric constant loss factor distribution map inside the insulation, thereby obtaining multi-source data that meets the preset conditions.

[0063] The spatiotemporal alignment process includes: time calibration using linear interpolation to supplement low-frequency data, using equal-interval sampling to downsample high-frequency data, and uniformly calibrating the sampling frequency of all data to a unified frequency; spatial alignment using equipment 3D modeling technology, pre-entering the installation coordinates of each sensor, and using coordinate mapping to associate the collected data of sensors at different locations with the corresponding areas of the equipment 3D model.

[0064] The processing of microwave photon data includes: first, denoising the received microwave photon reflection and scattering signals, extracting the effective signals reflecting the internal state of the insulation, then performing layered analysis of the effective signals according to different depths and regions of the insulation medium, gradually restoring the dielectric constant and loss factor information of each location inside the insulation, and finally generating a three-dimensional dielectric constant and loss factor distribution map inside the insulation.

[0065] For example, in this application embodiment, spatiotemporal alignment processing can be performed on the six-dimensional data. In the time calibration, linear interpolation is used to supplement low-frequency data such as environmental temperature and humidity, and equal-interval sampling is used to downsample high-frequency data such as partial discharge signals. The sampling frequency of all data is uniformly calibrated to the same frequency to eliminate the differences in the time dimension of different types of data and ensure the temporal consistency of subsequent data fusion. In the spatial alignment, a three-dimensional model of the oil-immersed transformer is constructed using equipment three-dimensional modeling technology. The specific installation coordinates of various sensors are pre-entered, and the data collected by sensors at different locations are accurately associated with the corresponding areas of the three-dimensional model through coordinate mapping, so that the data can match the actual structural position of the equipment and provide spatial positioning support for subsequent three-dimensional imaging.

[0066] Furthermore, in this embodiment, the microwave photonic data is processed by first removing the equipment casing, internal structure, and external electromagnetic interference signals to complete noise reduction and extract the effective signals reflecting the internal state of the insulation, thus avoiding interference signals from affecting the judgment of the internal condition of the insulation. Then, the effective signals are analyzed layer by layer according to different depths and regions of the insulation medium to gradually restore the dielectric constant and loss factor information of each location inside the insulation. Finally, a three-dimensional dielectric constant and loss factor distribution map of the insulation is generated, which intuitively presents the spatial distribution of the dielectric properties inside the insulation.

[0067] Furthermore, in this embodiment of the application, by first performing spatiotemporal alignment processing on the six-dimensional data and processing the microwave photon data, multi-source data that meets preset conditions is obtained.

[0068] In step S102, based on the fused feature data, tensor data of the target power equipment is determined, and the comprehensive deviation between the current insulation state tensor and the health baseline tensor is calculated based on the tensor data. The formula for calculating the comprehensive deviation may be, but is not limited to, the following: , in, This represents the combined deviation between the current insulation state tensor and the healthy baseline tensor. These correspond to the five core dimensions of the tensor model: time, space, frequency, device type, and dielectric properties. For the first Dimensional feature contribution For the current state, the first The eigenvalues ​​of the current insulation state tensor of dimension, For the first time in a healthy state dimensional health baseline tensor eigenvalues For the first Dynamic adjustment items for health benchmarks in the body. This refers to the equipment's service life.

[0069] In some embodiments, this application can mine tensor data of target power equipment based on fused feature data through tensor decomposition and attention mechanism, and quantify the degree of deviation between the current insulation state tensor and the health baseline tensor through tensor feature deviation algorithm to determine the corresponding comprehensive deviation.

[0070] It should be noted that, in the embodiments of this application, the tensor decomposition and attention mechanism includes, based on the high-order tensor model constructed from the fused feature data, first removing redundant information and handling outliers in the tensor data, and then using tensor decomposition technology to decompose the coupled features of each dimension in the tensor, thereby obtaining the corresponding tensor data.

[0071] Tensor decomposition techniques include parallel factor decomposition or Tucker decomposition, which use attention mechanisms to assign differentiated weights to features in each dimension, focusing on mining related features, change features, and abnormal features that are related to internal insulation defects and equipment operating status.

[0072] Furthermore, embodiments of this application can calculate the comprehensive deviation between the current insulation state tensor and the health baseline tensor using a comprehensive deviation calculation formula, the expression of which may be, but is not limited to: , in, This represents the combined deviation between the current insulation state tensor and the healthy baseline tensor. These correspond to the five core dimensions of the tensor model: time, space, frequency, device type, and dielectric properties. For the first Dimensional feature contribution For the current state, the first The eigenvalues ​​of the current insulation state tensor of dimension, For the first time in a healthy state dimensional health baseline tensor eigenvalues For the first Dynamic adjustment items for health benchmarks in the body. This refers to the equipment's service life.

[0073] For example, this application embodiment constructs a high-order tensor model based on fused feature data. First, redundant information is removed and outliers are processed from the tensor data to reduce interference from invalid data in subsequent analysis and ensure data quality. Then, parallel factorization or Tucker decomposition techniques are used to decompose the coupled features of each dimension in the tensor, breaking down the correlation barriers between data from different dimensions and clearly presenting the independent features of each dimension. Simultaneously, an attention mechanism is used to assign differentiated weights to the features of the five core dimensions: time, space, frequency, equipment type, and dielectric properties. This emphasizes the correlation, change, and abnormal features related to internal insulation defects and equipment operating status, making key information easier to identify. Then, through the calculation formula of the comprehensive deviation, combined with the feature contribution of each dimension, the tensor feature value in the current state, the benchmark tensor feature value in the healthy state, and the dynamic correction term of the healthy benchmark, the comprehensive deviation between the current insulation state and the healthy benchmark is quantified. This allows the differences in insulation quality to be reflected through specific quantitative results, providing a clear basis for subsequent health assessments.

[0074] In step S103, the aging stage of the target power equipment is determined based on multi-source data, and the insulation health comprehensive index of the insulation state is calculated based on the comprehensive deviation, so as to predict the remaining insulation life of the target power equipment according to the insulation health comprehensive index and the aging stage. The formula for calculating the insulation health comprehensive index may be, but is not limited to, the following: , in, For the comprehensive index of insulation health, This represents the combined deviation between the current insulation state tensor and the healthy baseline tensor. This is a correction factor for the aging stage. It is a defect risk amplification factor.

[0075] In some embodiments, the aging stage of the target power equipment can be determined first based on multi-source data, and the insulation health comprehensive index can be calculated using the calculation formula of the insulation health comprehensive index to predict the remaining insulation life of the target power equipment. The calculation formula of the insulation health comprehensive index can be, but is not limited to, the following: , in, For the comprehensive index of insulation health, This represents the combined deviation between the current insulation state tensor and the healthy baseline tensor. This is a correction factor for the aging stage, determined by the results of a full-scale aging assessment. It is a defect risk amplification factor.

[0076] For example, in the embodiments of this application, the insulation health comprehensive index can be calculated according to the calculation formula of the insulation health comprehensive index, combined with the comprehensive deviation, aging stage correction coefficient and defect risk amplification factor, and the remaining insulation life of the target power equipment can be predicted to form a complete evaluation result, providing a clear health status and life expectancy reference for operation and maintenance decisions.

[0077] Optionally, in one embodiment of this application, determining the aging stage of a target power device based on multi-source data includes: obtaining the degree of polymerization of the insulating medium of the target power device; determining a first degree of damage to the target power device based on the degree of polymerization; obtaining the dielectric loss value, leakage current, and temperature value of the insulating medium; determining a second degree of damage to the target power device based on the dielectric loss value, leakage current, and temperature value; and determining the aging stage based on the first degree of damage and the second degree of damage.

[0078] It is understood that, in the embodiments of this application, the first degree of damage can be understood as the damage data obtained by conducting a full-scale aging assessment in combination with changes in the microscopic insulating material structure, dividing the insulation aging stages; the second degree of damage can be understood as the damage data obtained by conducting a full-scale aging assessment in combination with macroscopic insulation performance data, dividing the insulation aging stages. The specific settings can be made by those skilled in the art according to the actual situation, and this application does not impose any specific limitations.

[0079] In some embodiments, the present application embodiments can determine the first degree of damage to the target power equipment by obtaining the degree of polymerization of the insulating medium of the target power equipment.

[0080] For example, in the embodiments of this application, changes in the molecular structure of the material can be determined at the micro level by measuring the degree of polymerization of the insulating paper. When the degree of polymerization is ≥1000, it is determined that the microstructure is intact; when 800≤degree of polymerization<1000, it is determined that the microstructure is slightly damaged; when the degree of polymerization<800, it is determined that the microstructure is severely damaged. This application does not impose specific limitations, thereby determining the first degree of damage to the target power equipment.

[0081] In some embodiments, the present application embodiments can determine the second degree of damage to the target power equipment by obtaining the dielectric loss value, leakage current and temperature value of the insulating medium.

[0082] For example, embodiments of this application can monitor the dielectric loss value of the insulating medium, the leakage current of the equipment insulation layer, and the local temperature value of the key parts of the equipment at the macroscopic level, and use the dielectric loss value >2%, leakage current >10μA, and local temperature rise >10℃ as the judgment thresholds for macroscopic performance degradation, thereby determining the second degree of damage to the target power equipment.

[0083] In some embodiments, the aging stage of the target electrical equipment can be determined based on a first degree of damage and a second degree of damage. In this embodiment, the aging stage can be divided into three insulation aging stages: normal stage, slight aging stage, and severe aging stage.

[0084] For example, in embodiments of this application, the aging stage can be determined as a normal stage when the microstructure is intact and all macroscopic performance data do not exceed the threshold; the aging stage can be determined as a slight aging stage when the microstructure is slightly damaged and one or two macroscopic performance data occasionally exceed the threshold; and the aging stage can be determined as a severe aging stage when the microstructure is severely damaged or two or more macroscopic performance data continuously exceed the threshold. The specific settings can be made by those skilled in the art according to the actual situation, and this application does not impose specific limitations.

[0085] For example, embodiments of this application can conduct a full-scale aging assessment of the target power equipment. At the microscopic level, the degree of polymerization of the transformer insulation paper is measured. When the degree of polymerization is ≥1000, it is determined that the microstructure is intact; when 800≤degree of polymerization<1000, it is determined that the microstructure is slightly damaged; when the degree of polymerization<800, it is determined that the microstructure is severely damaged. The first degree of damage to the target power equipment is determined from the molecular structure level. At the macroscopic level, the dielectric loss value of the insulating medium, the leakage current of the insulating layer, and the local temperature of key parts of the equipment are monitored. The threshold for judging macroscopic performance degradation is set as dielectric loss value >2%, leakage current >10μA, and local temperature rise >10℃. The second degree of damage to the target power equipment is determined from the perspective of the overall operating performance of the equipment.

[0086] Furthermore, this application establishes a correlation between microstructure changes and macroscopic performance data, dividing insulation aging stages: the normal stage is when the microstructure is intact and all macroscopic performance data do not exceed the threshold, indicating that the overall insulation condition is good; the slight aging stage is when the microstructure is slightly damaged and one or two macroscopic performance data occasionally exceed the threshold, indicating that the insulation has begun to show signs of deterioration but does not affect the overall operation for the time being; the severe aging stage is when the microstructure is severely damaged or two or more macroscopic performance data continuously exceed the threshold, indicating that the insulation deterioration has posed a threat to the safe operation of the equipment.

[0087] In step S104, based on multi-source data, insulation health comprehensive index and insulation remaining life, the fault location and the fault type corresponding to the fault location of the target power equipment are identified, and the operation and maintenance plan of the target power equipment is determined according to the insulation health comprehensive index, insulation remaining life, fault type and fault location.

[0088] In some embodiments, the present application embodiments can identify the fault location and the fault type corresponding to the fault location of the target power equipment based on multi-source data, insulation health comprehensive index and insulation remaining life, and then determine the operation and maintenance plan of the target power equipment.

[0089] For example, in this application embodiment, by retrieving the fault case map, matching the current transformer's fault type, fault location, equipment model, and insulation health comprehensive index, highly matching historical cases can be selected from the fault case map, and corresponding operation and maintenance plans can be extracted to form an operation and maintenance plan adapted to the current state of the target power equipment, ensuring the pertinence and effectiveness of the maintenance measures.

[0090] The fault case map includes core data such as various fault types, fault locations, equipment models, comprehensive insulation health index, aging stages, and operation and maintenance plans. The operation and maintenance plans include... For equipment with a score of ≥80, remaining lifespan ≥10 years, and only minor defects, a daily online monitoring plus monthly data review operation and maintenance model is adopted to ensure equipment safety while reducing unnecessary operation and maintenance costs; for equipment with a score of ≤60, the operation and maintenance model is adopted to ensure equipment safety while reducing unnecessary operation and maintenance costs. For equipment scoring <80 points, with a remaining lifespan of 5 years ≤ 10 years, and in the slight aging stage, a special inspection every 3 months plus monthly online monitoring will be conducted. The special inspection includes moisture content testing and dielectric distribution scanning to enhance the tracking of changes in insulation condition. For equipment with a score of <60, remaining life of <5 years, or serious defects, an emergency maintenance procedure should be initiated within 48 hours. After maintenance, continuous monitoring should be conducted for 72 hours. The equipment can only be put into operation after the insulation condition is confirmed to have returned to normal, so as to minimize the risk of failure.

[0091] Optionally, in one embodiment of this application, identifying the fault location and the corresponding fault type of the target power equipment based on multi-source data, insulation health index, and insulation remaining life includes: obtaining a defect candidate region of the target power equipment based on the dielectric constant loss factor in the multi-source data; identifying the fault location based on the defect candidate region; and identifying the fault type based on the fault location, insulation health index, and insulation remaining life.

[0092] In some embodiments, the present application embodiments can obtain the defect candidate region of the target power equipment based on the dielectric constant loss factor in multi-source data, and then identify the fault location of the target power equipment. Furthermore, the present application embodiments can combine the insulation health comprehensive index and the insulation remaining life to identify the fault type of the target power equipment.

[0093] For example, embodiments of this application can determine candidate defect areas based on the comprehensive insulation health index, aging stage, remaining insulation life, and three-dimensional dielectric constant loss factor distribution map inside the insulation. This is achieved by comparing the deviation of the dielectric constant loss factor of each region in the three-dimensional dielectric constant loss factor distribution map inside the insulation from the health benchmark value. For instance, regions where the dielectric constant loss factor deviates from the health benchmark value by ≥15% are identified as candidate defect areas. Furthermore, embodiments of this application can identify regions with a dielectric constant loss factor >4.5 as micro-water accumulation regions, regions with a dielectric constant loss factor <2.5 as air gap regions, and air gaps with a diameter ≥2mm as air gap defects.

[0094] In addition, in the fault type identification of this application embodiment, when the insulation health comprehensive index is <60 points, the fault is in a severe aging stage, and the peak value of the partial discharge signal corresponding to the defect candidate area is >500mV, the fault type is determined to be a floating discharge fault; when the peak value of the partial discharge signal in the air gap defect area is between 200mV and 500mV, the fault type is determined to be an air gap discharge fault; when the dielectric constant gradient of the equipment surface area is >8% and the local temperature rise is >5°C, the fault type is determined to be a surface discharge fault.

[0095] This application embodiment uses the spatial coordinates of the candidate defect region to mark the three-dimensional dielectric constant and loss factor distribution map inside the insulation, accurately pinpointing the specific location of the micro-water accumulation region and the distribution range of air gap defects, providing precise location guidance for maintenance.

[0096] The working principle of the operation and maintenance assessment method based on the insulation status of power equipment proposed in this application will be introduced below with reference to a specific embodiment.

[0097] in, Figure 2 This is a flowchart illustrating the working principle of an operation and maintenance assessment method based on the insulation status of power equipment according to an embodiment of this application.

[0098] Step S201: Deploy six types of monitoring equipment to simultaneously collect and process six types of monitoring data.

[0099] In this application embodiment, which targets a 220kV oil-immersed transformer, six types of monitoring equipment can be deployed, including electrical, thermal, mechanical, chemical, environmental, and microwave photonic data, to simultaneously collect six-dimensional data: electrical data, thermal data, mechanical data, chemical data, environmental data, and microwave photonic data.

[0100] Furthermore, in this embodiment, when the multi-source data does not meet the preset conditions, the multi-source data can be processed, for example, by performing spatiotemporal alignment processing to ensure that the data format is uniform, laying the foundation for subsequent multi-source data fusion, and by processing the microwave photonic data to generate a three-dimensional dielectric constant loss factor distribution map inside the insulation, thereby obtaining multi-source data that meets the preset conditions.

[0101] Step S202: Fuse the multi-source data to obtain fused feature data.

[0102] In this embodiment, a six-dimensional data fusion credibility algorithm can be used. This algorithm combines the dynamic weights of the source data in each dimension, the source credibility decay factor, and the spatiotemporal consistency coefficient to perform multi-source data fusion on the six-dimensional data, obtaining fused feature data. The calculation formula for the fused feature data is shown above and will not be elaborated further here.

[0103] Step S203: Mine tensor data and calculate the overall deviation.

[0104] In this embodiment, a high-order tensor model is constructed based on fused feature data. First, redundant information and outliers are removed from the tensor data to reduce interference from invalid data in subsequent analysis and ensure data quality. Then, parallel factorization or Tucker decomposition techniques are used to decompose the coupled features of each dimension in the tensor, breaking down the correlation barriers between data from different dimensions and clearly presenting the independent features of each dimension. Simultaneously, an attention mechanism is used to assign differentiated weights to the features of the five core dimensions: time, space, frequency, equipment type, and dielectric properties. This emphasizes the correlation, change, and abnormal features related to internal insulation defects and equipment operating status, making key information easier to identify. Finally, through the calculation formula of the comprehensive deviation, combined with the feature contribution of each dimension, the tensor feature value in the current state, the benchmark tensor feature value in the healthy state, and the dynamic correction term of the healthy benchmark, the comprehensive deviation between the current insulation state and the healthy benchmark is quantified. This allows the differences in insulation quality to be reflected through specific quantitative results, providing a clear basis for subsequent health assessments.

[0105] Step S204: Assess insulation aging across all scales, calculate the comprehensive insulation health index, and predict the remaining insulation life.

[0106] In this application embodiment, changes in the molecular structure of the insulating paper can be determined at the microscopic level by measuring the degree of polymerization. When the degree of polymerization is ≥1000, the microstructure is considered intact; when 800≤degree of polymerization<1000, the microstructure is considered slightly damaged; and when the degree of polymerization<800, the microstructure is considered severely damaged. This application does not impose specific limitations, thereby determining the first degree of damage to the target power equipment. At the macroscopic level, the dielectric loss value of the insulating medium, the leakage current of the equipment insulation layer, and the local temperature value of the key parts of the equipment are monitored. The threshold for determining macroscopic performance degradation is set at a dielectric loss value >2%, a leakage current >10μA, and a local temperature increase >10℃, thereby determining the second degree of damage to the target power equipment.

[0107] Furthermore, this application establishes a correlation between microstructure changes and macroscopic performance data, dividing insulation aging stages: the normal stage is when the microstructure is intact and all macroscopic performance data do not exceed the threshold, indicating that the overall insulation condition is good; the slight aging stage is when the microstructure is slightly damaged and one or two macroscopic performance data occasionally exceed the threshold, indicating that the insulation has begun to show signs of deterioration but does not affect the overall operation for the time being; the severe aging stage is when the microstructure is severely damaged or two or more macroscopic performance data continuously exceed the threshold, indicating that the insulation deterioration has posed a threat to the safe operation of the equipment.

[0108] Step S205: Identify the fault location and fault type, and determine the operation and maintenance plan.

[0109] In this embodiment, the fault case map can be retrieved to match the fault type, fault location, equipment model and insulation health index of the current transformer. Highly matching historical cases can be selected from the fault case map, and corresponding operation and maintenance plans can be extracted to form an operation and maintenance plan that is adapted to the current state of the target power equipment, so as to ensure the pertinence and effectiveness of the maintenance measures.

[0110] For example, regions where the dielectric constant loss factor deviates from the healthy baseline value by ≥15% are identified as candidate defect regions. Furthermore, in this embodiment, regions with a dielectric constant loss factor >4.5 are identified as micro-water accumulation regions, regions with a dielectric constant loss factor <2.5 are identified as air gap regions, and air gaps with a diameter ≥2mm are identified as air gap defects.

[0111] In addition, in the fault type identification of this application embodiment, when the insulation health comprehensive index is <60 points, the fault is in a severe aging stage, and the peak value of the partial discharge signal corresponding to the defect candidate area is >500mV, the fault type is determined to be a floating discharge fault; when the peak value of the partial discharge signal in the air gap defect area is between 200mV and 500mV, the fault type is determined to be an air gap discharge fault; when the dielectric constant gradient of the equipment surface area is >8% and the local temperature rise is >5°C, the fault type is determined to be a surface discharge fault.

[0112] The operation and maintenance solution includes... For equipment with a score of ≥80, remaining lifespan ≥10 years, and only minor defects, a daily online monitoring plus monthly data review operation and maintenance model is adopted to ensure equipment safety while reducing unnecessary operation and maintenance costs; for equipment with a score of ≤60, the operation and maintenance model is adopted to ensure equipment safety while reducing unnecessary operation and maintenance costs. For equipment scoring <80 points, with a remaining lifespan of 5 years ≤ 10 years, and in the slight aging stage, a special inspection every 3 months plus monthly online monitoring will be conducted. The special inspection includes moisture content testing and dielectric distribution scanning to enhance the tracking of changes in insulation condition. For equipment with a score of <60, remaining life of <5 years, or serious defects, an emergency maintenance procedure should be initiated within 48 hours. After maintenance, continuous monitoring should be conducted for 72 hours. The equipment can only be put into operation after the insulation condition is confirmed to have returned to normal, so as to minimize the risk of failure.

[0113] The operation and maintenance assessment method based on the insulation status of power equipment proposed in this application can acquire multi-source data matching the insulation status of the target power equipment based on the equipment data and operation data of the target power equipment. This multi-source data is then fused to obtain fused feature data. Tensor data is determined based on the fused feature data, the comprehensive deviation is calculated, and the aging stage of the target power equipment is determined, thereby obtaining the comprehensive insulation health index of the insulation status. This predicts the remaining insulation life of the target power equipment. Combined with the identified fault location and fault type of the target power equipment, an operation and maintenance plan is determined. By fusing multi-source heterogeneous data to construct a tensor model, the comprehensive deviation of the insulation status and the comprehensive insulation health index are accurately quantified. Combined with the aging stage, the remaining insulation life is predicted, and fault location and type are identified accordingly. This achieves full-scale accurate assessment and differentiated operation and maintenance decision-making from macro-operation to micro-structure, and establishes an integrated technical concept for differentiated operation and maintenance strategies. Therefore, it solves the problems in related technologies, such as reliance on single-dimensional monitoring, lack of spatiotemporal alignment mechanisms, difficulty in associating heterogeneous data, resulting in assessment bias and neglect of micro-structure evolution, and lack of differentiated guidance for operation and maintenance strategies, making it difficult to achieve full-scale, accurate assessment and operation and maintenance.

[0114] Next, referring to the accompanying drawings, we describe the operation and maintenance assessment device based on the insulation status of power equipment according to an embodiment of this application.

[0115] Figure 3 This is a block diagram of an operation and maintenance assessment device based on the insulation status of power equipment provided according to an embodiment of this application.

[0116] like Figure 3 As shown, the operation and maintenance assessment device 10 based on the insulation status of power equipment includes: a fusion module 100, a calculation module 200, a prediction module 300, and a determination module 400.

[0117] The fusion module 100 is used to acquire multi-source data matching the insulation status of the target power equipment based on the equipment data and operation data of the target power equipment, and to fuse the multi-source data to obtain fused feature data.

[0118] The calculation module 200 is used to determine the tensor data of the target power equipment based on the fused feature data, so as to calculate the comprehensive deviation between the current insulation state tensor and the health baseline tensor based on the tensor data.

[0119] The prediction module 300 is used to determine the aging stage of the target power equipment based on multi-source data, and to calculate the insulation health comprehensive index of the insulation status based on the comprehensive deviation, so as to predict the remaining insulation life of the target power equipment according to the insulation health comprehensive index and the aging stage.

[0120] The determination module 400 is used to identify the fault location and the corresponding fault type of the target power equipment based on multi-source data, insulation health comprehensive index and insulation remaining life, and to determine the operation and maintenance plan of the target power equipment according to the insulation health comprehensive index, insulation remaining life, fault type and fault location.

[0121] Optionally, in one embodiment of this application, the fusion module 100 includes a detection unit and a processing unit.

[0122] The detection unit is used to detect whether the multi-source data meets the preset conditions.

[0123] The processing unit is used to process the multi-source data when it is detected that the multi-source data does not meet the preset conditions, until the multi-source data that meets the preset conditions is obtained.

[0124] Optionally, in one embodiment of this application, the prediction module 300 includes: a first acquisition unit, a first determination unit, a second acquisition unit, a second determination unit, and a third determination unit.

[0125] The first acquisition unit is used to acquire the degree of polymerization of the insulating medium of the target power equipment.

[0126] The first determining unit is used to determine the first degree of damage to the target power equipment based on the degree of aggregation.

[0127] The second acquisition unit is used to acquire the dielectric loss value, leakage current, and temperature value of the insulating medium.

[0128] The second determining unit is used to determine the second degree of damage to the target power equipment based on the dielectric loss value, leakage current, and temperature value.

[0129] The third determining unit is used to determine the aging stage based on the first damage level and the second damage level.

[0130] Optionally, in one embodiment of this application, the determining module 400 includes: a third acquisition unit, a first identification unit, and a second identification unit.

[0131] The third acquisition unit is used to acquire candidate defect regions of the target power equipment based on the dielectric constant and loss factor in the multi-source data.

[0132] The first identification unit is used to identify the fault location based on the defect candidate region.

[0133] The second identification unit is used to identify the fault type based on the fault location, the comprehensive insulation health index, and the remaining insulation life.

[0134] Optionally, in one embodiment of this application, the calculation formula for the fused feature data may be, but is not limited to, the following: , in, For device space coordinates ,time Fusion feature data at the location, These correspond to six-dimensional data sources: electrical, thermal, mechanical, chemical, environmental, and microwave photonics. For the first Dynamic weights of dimensional data sources For the first Data source of dimensional data The raw source data after standardization processing For the first Source credibility decay factor of dimensional data source For the first The spatiotemporal consistency coefficient of the data source.

[0135] Optionally, in one embodiment of this application, the formula for calculating the overall deviation can be, but is not limited to, the following: , in, This represents the combined deviation between the current insulation state tensor and the healthy baseline tensor. These correspond to the five core dimensions of the tensor model: time, space, frequency, device type, and dielectric properties. For the first Dimensional feature contribution For the current state, the first The eigenvalues ​​of the current insulation state tensor of dimension, For the first time in a healthy state dimensional health baseline tensor eigenvalues For the first Dynamic adjustment items for health benchmarks in the body. This refers to the equipment's service life.

[0136] Optionally, in one embodiment of this application, the formula for calculating the insulation health comprehensive index may be, but is not limited to, the following: , in, For the comprehensive index of insulation health, This represents the combined deviation between the current insulation state tensor and the healthy baseline tensor. This is a correction factor for the aging stage. It is a defect risk amplification factor.

[0137] It should be noted that the foregoing explanation of the embodiment of the operation and maintenance assessment method based on the insulation status of power equipment also applies to the operation and maintenance assessment device based on the insulation status of power equipment in this embodiment, and will not be repeated here.

[0138] The operation and maintenance assessment device based on the insulation status of power equipment proposed in this application can acquire multi-source data matching the insulation status of the target power equipment based on the equipment data and operation data of the target power equipment. This multi-source data is then fused to obtain fused feature data. Tensor data is determined based on the fused feature data, the comprehensive deviation is calculated, and the aging stage of the target power equipment is determined, thereby obtaining the insulation health comprehensive index of the insulation status. This predicts the remaining insulation life of the target power equipment. Combined with the identified fault location and fault type of the target power equipment, an operation and maintenance plan is determined. By fusing multi-source heterogeneous data to construct a tensor model, the comprehensive deviation of the insulation status and the insulation health comprehensive index are accurately quantified. Combined with the aging stage, the remaining insulation life is predicted, and fault location and type are identified accordingly. This achieves full-scale accurate assessment and differentiated operation and maintenance decision-making from macro-operation to micro-structure, and establishes an integrated technical concept for differentiated operation and maintenance strategies. Therefore, it solves the problems in related technologies, such as reliance on single-dimensional monitoring, lack of spatiotemporal alignment mechanisms, difficulty in associating heterogeneous data, resulting in assessment bias and neglect of micro-structure evolution, and lack of differentiated guidance in operation and maintenance strategies, making it difficult to achieve full-scale, accurate assessment and operation and maintenance.

[0139] Figure 4 This is a schematic diagram of the structure of an electronic device provided according to an embodiment of this application. The electronic device may include: The memory 401, the processor 402, and the computer program stored on the memory 401 and capable of running on the processor 402.

[0140] When the processor 402 executes the program, it implements the operation and maintenance assessment method based on the insulation status of power equipment provided in the above embodiments.

[0141] Furthermore, electronic devices also include: Communication interface 403 is used for communication between memory 401 and processor 402.

[0142] The memory 401 is used to store computer programs that can run on the processor 402.

[0143] Memory 401 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0144] If the memory 401, processor 402, and communication interface 403 are implemented independently, then the communication interface 403, memory 401, and processor 402 can be interconnected via a bus to complete communication between them. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized into address buses, data buses, control buses, etc. For ease of representation, Figure 4 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0145] Optionally, in a specific implementation, if the memory 401, processor 402, and communication interface 403 are integrated on a single chip, then the memory 401, processor 402, and communication interface 403 can communicate with each other through an internal interface.

[0146] Processor 402 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application.

[0147] This application also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the above-described operation and maintenance assessment method based on the insulation status of power equipment.

[0148] This application also provides a computer program product, including a computer program that, when executed, implements the above-described operation and maintenance assessment method based on the insulation status of power equipment.

[0149] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0150] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0151] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or N executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0152] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). In addition, computer-readable media can even be paper or other suitable media on which programs can be printed, because programs can be obtained electronically by optically scanning paper or other media, then editing, interpreting or otherwise processing them as necessary, and then storing them in computer memory.

[0153] It should be understood that the various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. If implemented in hardware, as in another embodiment, it can be implemented using any one or more of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0154] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0155] Furthermore, the functional units in the various embodiments of this application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0156] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of this application.

Claims

1. A method for operation and maintenance assessment based on the insulation status of power equipment, characterized in that, Includes the following steps: Based on the equipment data and operation data of the target power equipment, multi-source data matching the insulation status of the target power equipment is obtained, and the multi-source data is fused to obtain fused feature data. Based on the fused feature data, tensor data of the target power equipment is determined, and the comprehensive deviation between the current insulation state tensor and the health baseline tensor is calculated based on the tensor data. The aging stage of the target power equipment is determined based on the multi-source data, and the insulation health index of the insulation state is calculated based on the comprehensive deviation, so as to predict the remaining insulation life of the target power equipment according to the insulation health index and the aging stage. Based on the multi-source data, the insulation health comprehensive index, and the remaining insulation life, the fault location and the corresponding fault type of the target power equipment are identified, and the operation and maintenance plan of the target power equipment is determined according to the insulation health comprehensive index, the remaining insulation life, the fault type, and the fault location.

2. The method according to claim 1, characterized in that, The acquisition of multi-source data matching the insulation state of the target power equipment includes: Detect whether the multi-source data meets preset conditions; If the multi-source data is found to not meet the preset conditions, the multi-source data is processed until multi-source data that meets the preset conditions is obtained.

3. The method according to claim 1, characterized in that, Determining the aging stage of the target power equipment based on the multi-source data includes: Obtain the degree of polymerization of the insulating medium of the target power equipment; Based on the degree of aggregation, the first degree of damage to the target power equipment is determined; Obtain the dielectric loss value, leakage current, and temperature value of the insulating medium; Based on the dielectric loss value, the leakage current, and the temperature value, the second degree of damage to the target power equipment is determined; The aging stage is determined based on the first degree of damage and the second degree of damage.

4. The method according to claim 1, characterized in that, The process of identifying the fault location and corresponding fault type of the target power equipment based on the multi-source data, the comprehensive insulation health index, and the remaining insulation life includes: Based on the dielectric constant and loss factor in the multi-source data, the defect candidate region of the target power equipment is obtained. Based on the defect candidate region, the fault location is identified; The fault type is identified based on the fault location, the comprehensive insulation health index, and the remaining insulation life.

5. The method according to claim 1, characterized in that, The calculation formula for the fused feature data is as follows: ， in, For device space coordinates ,time Fusion feature data at the location, These correspond to six-dimensional data sources: electrical, thermal, mechanical, chemical, environmental, and microwave photonics. For the first Dynamic weights of dimensional data sources For the first Data source of dimensional data The raw source data after standardization processing For the first Source credibility decay factor of dimensional data source For the first The spatiotemporal consistency coefficient of the data source.

6. The method according to claim 1, characterized in that, The formula for calculating the overall deviation is: ， in, This represents the combined deviation between the current insulation state tensor and the healthy baseline tensor. These correspond to the five core dimensions of the tensor model: time, space, frequency, device type, and dielectric properties. For the first Dimensional feature contribution For the current state, the first The eigenvalues ​​of the current insulation state tensor of dimension, For the first time in a healthy state dimensional health baseline tensor eigenvalues For the first Dynamic adjustment items for health benchmarks in the body. This refers to the equipment's service life.

7. The method according to claim 1, characterized in that, The formula for calculating the comprehensive insulation health index is as follows: ， in, For the comprehensive index of insulation health, This represents the combined deviation between the current insulation state tensor and the healthy baseline tensor. This is a correction factor for the aging stage. It is a defect risk amplification factor.

8. A maintenance assessment device based on the insulation status of power equipment, characterized in that, include: The fusion module is used to acquire multi-source data matching the insulation status of the target power equipment based on the equipment data and operation data of the target power equipment, and to fuse the multi-source data to obtain fused feature data. The calculation module is used to determine the tensor data of the target power equipment based on the fused feature data, so as to calculate the comprehensive deviation between the current insulation state tensor and the health reference tensor according to the tensor data; The prediction module is used to determine the aging stage of the target power equipment based on the multi-source data, and to calculate the insulation health comprehensive index of the insulation state based on the comprehensive deviation, so as to predict the remaining insulation life of the target power equipment according to the insulation health comprehensive index and the aging stage. The determination module is used to identify the fault location and the fault type corresponding to the fault location of the target power equipment based on the multi-source data, the insulation health comprehensive index, and the insulation remaining life, and to determine the operation and maintenance plan of the target power equipment according to the insulation health comprehensive index, the insulation remaining life, the fault type, and the fault location.

9. An electronic device, characterized in that, include: A memory, a processor, and a computer program stored in the memory and executable on the processor, the processor executing the program to implement the operation and maintenance assessment method based on the insulation status of power equipment as described in any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, The program is executed by the processor to implement the operation and maintenance assessment method based on the insulation status of power equipment as described in any one of claims 1-7.

Images