A method and system for detecting insulation detection function

Abstract

The present application provides a detection method and system for insulation detection function. Among them, when the electrical equipment to be tested is in operation, the temperature change on the surface of the electrical equipment to be tested is monitored in real time by a non-contact sensor to form a dynamic thermal image; according to the temperature fluctuation pattern of the preset area in the dynamic thermal image, combined with the ambient temperature compensation algorithm, the potential insulation defect area is identified and a preliminary insulation defect report is generated; for the insulation defect area marked in the preliminary insulation defect report, the electromagnetic field analysis technology is used to simulate the electromagnetic field distribution of the insulation defect area under different working conditions, evaluate the aging degree and damage risk of the insulation material, and obtain the evaluation result; based on the preliminary insulation defect report and the evaluation result, the probability of the insulation defect area developing into an actual fault is calculated through the fault prediction model, and the final insulation performance test report is output. The technical solution provided by the present application improves the operating efficiency and safety of the equipment.

Description

Technical Field

[0001] The present application relates to the technical field of electrical equipment maintenance and safe operation, and in particular to a detection method and system for insulation detection function. Background Art

[0002] With the continuous improvement of power systems and industrial automation levels, the stable operation of electrical equipment has a vital impact on production safety and economic benefits. During the operation of electrical equipment, due to long-term workloads, environmental factors, and material aging, the insulation performance will gradually decline, which may lead to serious safety hazards. Therefore, for electrical equipment, real-time monitoring of its insulation status and timely detection and treatment of potential insulation defects are the key to ensuring the safe operation of the equipment. This requires a technology that can monitor the surface temperature changes of the equipment in real time without stopping the equipment, and at the same time has the ability to identify and evaluate insulation defects to provide timely and effective maintenance suggestions.

[0003] At present, the insulation status monitoring of electrical equipment mainly relies on regular manual inspections and some traditional online monitoring technologies. Manual inspections usually involve the use of tools such as infrared thermal imagers, where technicians manually check the temperature distribution on the surface of the equipment. Although some obvious hot spots can be found, this method is inefficient and subject to human experience and judgment. In addition, although traditional online monitoring technologies can achieve a certain degree of continuous monitoring, most of them can only provide limited data, lack the ability to deeply analyze insulation defects, and it is difficult to accurately assess the aging degree and damage risk of insulation materials.

[0004] The existing solutions have the following defects: manual inspections rely on the experience of technicians and are prone to missed inspections or misjudgments. At the same time, the need to shut down the machine increases production costs and reduces production efficiency. Most existing online monitoring technologies can only provide basic temperature monitoring functions, and have weak recognition capabilities for complex temperature fluctuation patterns. They cannot accurately compensate for environmental factors, resulting in low recognition accuracy. In addition, these technologies often lack the ability to conduct in-depth analysis of insulation defect areas, such as the application of electromagnetic field distribution simulation and fault prediction models, which limits their role in fault warning and maintenance decision-making. Both manual inspections and traditional online monitoring technologies have failed to fully utilize the collected data for deep learning and intelligent analysis, and have been unable to form an effective fault prediction mechanism. It is difficult to predict the development trend of potential faults in advance, which affects the predictability and initiative of maintenance work.

[0005] In summary, the existing electrical equipment insulation status monitoring solutions have many shortcomings, and there is an urgent need for a new technology that can achieve real-time monitoring, accurate identification, in-depth analysis and intelligent prediction to meet the high standards of modern industry for the safe operation of electrical equipment. Summary of the invention

[0006] The embodiments of the present application provide a detection method and system for an insulation detection function, which are used to solve the problems of low operating efficiency and low safety of equipment in the prior art.

[0007] In a first aspect, an embodiment of the present application provides a method for detecting an insulation detection function, comprising:

[0008] When the electrical device to be tested is in operation, the temperature change on the surface of the electrical device to be tested is monitored in real time by a non-contact sensor to form a dynamic thermal image;

[0009] According to the temperature fluctuation pattern of the preset area in the dynamic thermal image, combined with the ambient temperature compensation algorithm, potential insulation defect areas are identified and a preliminary insulation defect report is generated;

[0010] For the insulation defect area marked in the preliminary insulation defect report, the electromagnetic field analysis technology is used to simulate the electromagnetic field distribution of the insulation defect area under different working conditions, evaluate the aging degree and damage risk of the insulation material, and obtain the evaluation result;

[0011] Based on the preliminary insulation defect report and the evaluation results, the probability of the insulation defect area developing into an actual fault is calculated through a fault prediction model, and a final insulation performance test report is output to guide equipment maintenance and safe operation.

[0012] Optionally, when the electrical device to be tested is in operation, the temperature change of the surface of the electrical device to be tested is monitored in real time by a non-contact sensor to form a dynamic thermal image, including:

[0013] The temperature data of the surface of the electrical equipment to be tested is collected in real time by means of a non-contact infrared sensor array installed around the electrical equipment to be tested;

[0014] Processing the temperature data using signal amplification and filtering techniques to reduce environmental interference and noise impact;

[0015] Convert the processed temperature data into a temperature distribution image to form a preliminary thermal image;

[0016] Image fusion technology is applied to fuse the preliminary thermal images corresponding to the non-contact infrared sensor array to generate a dynamic thermal image, which can show the temperature change trend of the surface of the electrical equipment to be tested.

[0017] Optionally, the step of identifying potential insulation defect areas based on the temperature fluctuation pattern of a preset area in the dynamic thermal image in combination with an ambient temperature compensation algorithm and generating a preliminary insulation defect report includes:

[0018] By real-time analysis of the temperature data in the dynamic thermal image, a preset area with abnormal temperature fluctuation is identified, wherein the abnormal temperature fluctuation refers to an area with a large temperature change amplitude or a high temperature change frequency compared with the surrounding area;

[0019] Applying an ambient temperature compensation algorithm, adjusting the temperature value of the preset area according to the collected ambient temperature data, and obtaining a temperature compensation result to ensure the accuracy of the temperature fluctuation pattern;

[0020] Using a machine learning algorithm, based on a historical insulation defect case library and the temperature fluctuation pattern of the preset area, intelligently identifying potential insulation defect areas, the machine learning algorithm being capable of identifying temperature fluctuation characteristics associated with the insulation defect area;

[0021] In combination with the temperature fluctuation pattern of the preset area and the temperature compensation result, a preliminary insulation defect report is generated, wherein the preliminary insulation defect report includes the location of the insulation defect area, the temperature fluctuation characteristics, and the adjusted temperature value of the preset area.

[0022] Optionally, for the insulation defect area marked in the preliminary insulation defect report, an electromagnetic field analysis technology is used to simulate the electromagnetic field distribution of the insulation defect area under different working conditions, to evaluate the aging degree and damage risk of the insulation material, and to obtain an evaluation result, including:

[0023] Determining a region of interest for electromagnetic field analysis based on the location and size of the insulation defect area identified in the preliminary insulation defect report;

[0024] Collecting relevant electrical parameters of the insulation defect area, including voltage level, current intensity, frequency and environmental parameters;

[0025] Constructing a three-dimensional geometric model of the insulation defect region, wherein the three-dimensional geometric model is used to reflect the actual geometric shape and material properties of the insulation defect region to ensure the accuracy of electromagnetic field analysis;

[0026] Using a finite element analysis method, simulating the electromagnetic field distribution under different working conditions on the three-dimensional geometric model to evaluate the electromagnetic response of the insulating material under various working conditions and obtain the electromagnetic field distribution results;

[0027] The electromagnetic field distribution result is analyzed to evaluate the aging degree and damage risk of the insulating material and obtain an evaluation result.

[0028] Optionally, the synthesizing the preliminary insulation defect report and the evaluation result, calculating the probability of the insulation defect area developing into an actual fault through a fault prediction model, and outputting a final insulation performance test report to guide equipment maintenance and safe operation, including:

[0029] fusing the preliminary insulation defect report and the evaluation result to form a comprehensive evaluation data set, wherein the comprehensive evaluation data set includes the location of the insulation defect area, the temperature fluctuation characteristics, the adjusted temperature value of the preset area, the electromagnetic field distribution result, the aging degree and damage risk of the insulation material;

[0030] Applying a pre-trained fault prediction model, which is built based on a historical insulation defect case library and expert knowledge, to calculate the probability of an insulation defect area developing into an actual fault based on a comprehensive evaluation data set;

[0031] Performing a threshold judgment on the output result of the fault prediction model, and marking the insulation defect area as a high-risk area when the probability that the insulation defect area develops into an actual fault exceeds a preset threshold;

[0032] For the high-risk areas, potential failure modes and development trends are analyzed, and corresponding preventive measures and maintenance plans are formulated to generate a final insulation performance test report, wherein the final insulation performance test report contains detailed information on the insulation defect area, failure development probability, risk level, preventive measures and maintenance recommendations to guide the maintenance and safe operation of the equipment.

[0033] Optionally, the fault prediction model calculates the probability of the insulation defect area developing into an actual fault according to the comprehensive evaluation data set, and is calculated by the following calculation formula:

[0034] ;

[0035] in, Indicates the probability that a suspected defective area develops into an actual failure; Respectively represent The characteristic value corresponding to the temperature fluctuation characteristics of each insulation defect area, the characteristic value corresponding to the electromagnetic field distribution result and the environmental adaptability score; and They are The weight matrix and bias term of the layer are learned from the historical insulation defect case library through deep learning method; Indicates the number of insulation defect areas; is a multi-layer composite function used to integrate temperature fluctuation characteristics, electromagnetic field distribution results and environmental adaptability scores, defined as:

[0036] ;

[0037] in, It is A subfunction, defined as:

[0038] ;

[0039] in, It is the parameter learned from historical data; It is The weights of each sub-function are dynamically updated through an adaptive weight adjustment mechanism; is the activation function used to convert the weighted sum into a probability value, is the number of layers of the neural network, is the number of subfunctions in each layer.

[0040] Optionally, the environmental adaptability score The calculation formula is:

[0041] ;

[0042] in, Indicates The temperature value of each measuring point after ambient temperature compensation; Indicates The maximum temperature value of each measurement point is based on the maximum operating temperature setting of the equipment; Indicates The amount of noise reduced by each measurement point through signal amplification and filtering technology; Indicates The total noise originally collected at each measurement point; Indicates The stability score of the temperature measurement at each measurement point reflects the degree to which the temperature measurement is disturbed by the environment; Indicates The best stability score among the measurement points; is an exponential function, which is used here to increase the nonlinear relationship between the various parts of the formula to better reflect the actual physical process; It is The weights of each measurement point are dynamically updated through an adaptive weight adjustment mechanism; is the number of measurement points.

[0043] In a second aspect, an embodiment of the present application provides a detection system for an insulation detection function, comprising:

[0044] A forming module is used to monitor the temperature change of the surface of the electrical equipment to be tested in real time through a non-contact sensor when the electrical equipment to be tested is in operation, so as to form a dynamic thermal image;

[0045] An identification and generation module, for intelligently identifying potential insulation defect areas and generating a preliminary insulation defect report based on the temperature fluctuation pattern of a preset area in the dynamic thermal image in combination with an ambient temperature compensation algorithm;

[0046] An evaluation module, for simulating the electromagnetic field distribution of the suspected defective area marked in the preliminary insulation defect report by using electromagnetic field analysis technology under different working conditions, and evaluating the aging degree and damage risk of the insulation material;

[0047] The output module is used to integrate the analysis results of the temperature fluctuation pattern and the evaluation results of the electromagnetic field distribution, calculate the probability of the suspected defect area developing into an actual fault through a fault prediction model, and output a final insulation performance test report to guide equipment maintenance and safe operation.

[0048] In a third aspect, an embodiment of the present application provides a computing device, comprising a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement a detection method for an insulation detection function as described in any one of the first aspects.

[0049] In a fourth aspect, an embodiment of the present application provides a computer storage medium storing a computer program, wherein when the computer program is executed by a computer, a detection method for an insulation detection function as described in any one of the first aspects is implemented.

[0050] In the embodiment of the present application, when the electrical equipment to be tested is in operation, the temperature change on the surface of the electrical equipment to be tested is monitored in real time by a non-contact sensor to form a dynamic thermal image; according to the temperature fluctuation pattern of the preset area in the dynamic thermal image, combined with the ambient temperature compensation algorithm, the potential insulation defect area is identified and a preliminary insulation defect report is generated; for the insulation defect area marked in the preliminary insulation defect report, the electromagnetic field analysis technology is used to simulate the electromagnetic field distribution of the insulation defect area under different working conditions, evaluate the aging degree and damage risk of the insulation material, and obtain the evaluation result; based on the preliminary insulation defect report and the evaluation result, the probability of the insulation defect area developing into an actual fault is calculated by the fault prediction model, and the final insulation performance test report is output to guide equipment maintenance and safe operation. The technical solution provided by the present application improves the operating efficiency and safety of the equipment.

[0051] These and other aspects of the present application will become more clearly understood in the description of the following embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0053] Figure 1 A flow chart of a method for detecting an insulation detection function provided in an embodiment of the present application;

[0054] Figure 2 A schematic diagram of the structure of a detection system with an insulation detection function provided in an embodiment of the present application;

[0055] Figure 3 A schematic diagram of the structure of a computing device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0056] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.

[0057] In some of the processes described in the specification and claims of this application and the above-mentioned figures, multiple operations that appear in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this article or executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish between different operations, and the serial numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this article are used to distinguish different messages, devices, modules, etc., do not represent the order of precedence, and do not limit the "first" and "second" to be different types.

[0058] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0059] Figure 1 A flowchart of a method for detecting an insulation detection function is provided for an embodiment of the present application, such as Figure 1 As shown, the method includes:

[0060] 101. When the electrical device to be tested is in operation, the temperature change of the surface of the electrical device to be tested is monitored in real time by a non-contact sensor to form a dynamic thermal image;

[0061] In this step, a non-contact infrared camera or other type of temperature sensor is used to continuously monitor changes in the surface temperature of electrical equipment while it is in operation. This data is used to create a thermal image that changes over time, i.e. a dynamic thermogram. This method can help detect abnormal temperature rises caused by current, resistance or other factors.

[0062] In the embodiment of the present application, assuming that there is a high-voltage switch cabinet in operation, technicians can use drones or ground robots equipped with infrared cameras to regularly patrol and collect surface temperature data of the switch cabinet. These data are then transmitted to a computer system to generate a continuous thermal image video stream.

[0063] In the existing electrical equipment insulation performance testing methods, although the use of non-contact sensors for surface temperature monitoring is relatively common, there are still some challenges in practical application. For example, the data collected by a single sensor may be affected by environmental factors, resulting in inaccurate temperature measurement; in addition, due to the complex structure of electrical equipment, temperature data from a single perspective is difficult to fully reflect the overall temperature distribution of the equipment, thus affecting the accurate judgment of potential fault points.

[0064] Therefore, this application proposes an improved solution, which aims to improve the accuracy and reliability of temperature monitoring through a multi-sensor array and advanced data processing technology, and better serve the condition monitoring and fault warning of electrical equipment.

[0065] The options are as follows:

[0066] Optionally, in step 101, when the electrical equipment to be tested is in operation, the temperature changes on the surface of the electrical equipment to be tested are monitored in real time by a non-contact sensor to form a dynamic thermal image, including: collecting temperature data of the surface of the electrical equipment to be tested in real time by a non-contact infrared sensor array installed around the electrical equipment to be tested; processing the temperature data by signal amplification and filtering technology to reduce environmental interference and noise influence; converting the processed temperature data into a temperature distribution image to form a preliminary thermal image; applying image fusion technology to fuse the preliminary thermal images corresponding to the non-contact infrared sensor array respectively to generate a dynamic thermal image, and the dynamic thermal image can show the temperature change trend of the surface of the electrical equipment to be tested.

[0067] In this step, the non-contact infrared sensor array is a group of infrared sensors installed around the electrical equipment to be tested, which can capture the temperature information of the surface of the equipment from multiple angles at the same time. Signal amplification and filtering technology is a technology used to enhance useful signals and suppress noise, including amplifier circuits in hardware and digital filtering algorithms in software. The temperature distribution image is an image generated based on temperature data, in which different colors represent different temperature values. Image fusion technology is a technology that merges images from multiple sources into a higher quality or higher resolution image, which can be a weighted average based on pixel level, feature-based matching and other methods. Through the non-contact infrared sensor array installed around the electrical equipment to be tested, the temperature data of the surface of the electrical equipment to be tested is collected in real time: multiple non-contact infrared sensors are installed at different positions of the electrical equipment to be tested to ensure that the surface of the equipment can be fully covered from multiple angles.

[0068] First, the collected raw temperature data is preprocessed by using an appropriate amplifier to amplify the weak signal and using a digital filter to remove high-frequency noise and improve the signal-to-noise ratio.

[0069] Furthermore, the processed temperature data is mapped to a color space to generate an image representing the temperature distribution, and each image reflects the temperature condition at a certain moment.

[0070] Finally, the image fusion algorithm is used to combine the preliminary thermal images from different sensors into a more complete and clear thermal image, which can more accurately show the temperature change trend of the equipment surface.

[0071] In the embodiment of the present application, it is assumed that there is a large transformer. In order to monitor its insulation performance, 8 non-contact infrared sensors are evenly installed around it. These sensors send temperature data to the central processing unit once a second. The central processing unit first amplifies the received temperature data and uses an amplifier with a gain of 10 to ensure that even small temperature changes can be accurately captured. Then, a low-pass filter is used to remove high-frequency noise and retain signal components below 5Hz, which can effectively reduce the impact of ambient temperature changes and electromagnetic interference.

[0072] Next, the central processor converts the processed temperature data into a temperature distribution image, and each sensor generates a preliminary thermal image. In order to obtain a more comprehensive view of the temperature distribution, an image fusion technology based on pixel-level weighted average is used to combine these 8 preliminary thermal images into a high-resolution dynamic thermal image. In this thermal image, red represents high-temperature areas and blue represents low-temperature areas. It can intuitively see which parts of the transformer have higher temperatures and which parts have lower temperatures, as well as the temperature change trend over time.

[0073] The above solution not only improves the accuracy of temperature monitoring and reduces the interference of environmental factors, but also obtains more comprehensive and accurate equipment surface temperature distribution information through multi-angle monitoring and image fusion technology. This is of great significance for timely detection of potential insulation defects and prevention of electrical failures. In addition, the generation of dynamic thermal images also provides strong support for subsequent fault diagnosis and maintenance decisions.

[0074] 102. According to the temperature fluctuation pattern of the preset area in the dynamic thermal image, combined with the ambient temperature compensation algorithm, identify the potential insulation defect area and generate a preliminary insulation defect report;

[0075] In this step, based on the dynamic thermal image generated in step 101, a specialized algorithm is applied to analyze the temperature fluctuation pattern of the preset area, taking into account the influence of the ambient temperature, so as to accurately identify the parts where insulation problems may exist. The result of this step will be a preliminary insulation defect report indicating the areas that need further investigation.

[0076] In the embodiment of the present application, a deep learning model is used to train the algorithm, which has learned how to distinguish temperature changes under normal operating conditions from abnormal temperature increases caused by insulation defects. When the model detects that the temperature fluctuation in a certain area exceeds the expected range, it automatically marks the area and generates a preliminary report containing this information.

[0077] In traditional electrical equipment insulation performance testing, static thermal images or manual experience are mainly relied on to identify potential insulation defect areas. However, this method has several significant problems: first, static thermal images cannot capture the trend of temperature changes over time, which may lead to misjudgment; second, manual experience is difficult to quantify and is easily affected by subjective factors; finally, changes in ambient temperature will interfere with the measurement results, making the temperature data inaccurate.

[0078] Therefore, this application proposes an improved solution, which realizes intelligent identification of potential insulation defect areas by real-time analysis of temperature fluctuation patterns in dynamic thermal images and combines ambient temperature compensation algorithms and machine learning technology to solve the above technical problems and improve the accuracy and reliability of detection. The specific optional solution is as follows:

[0079] Optionally, the method described in step 102 identifies potential insulation defect areas and generates a preliminary insulation defect report based on the temperature fluctuation pattern of a preset area in the dynamic thermal image in combination with an ambient temperature compensation algorithm, including: identifying a preset area with abnormal temperature fluctuation by real-time analysis of the temperature data in the dynamic thermal image, wherein the abnormal temperature fluctuation refers to an area with a large temperature change amplitude or a high temperature change frequency compared with the surrounding area; applying an ambient temperature compensation algorithm to adjust the temperature value of the preset area according to the collected ambient temperature data to obtain a temperature compensation result to ensure the accuracy of the temperature fluctuation pattern; utilizing a machine learning algorithm to intelligently identify potential insulation defect areas based on a historical insulation defect case library and the temperature fluctuation pattern of the preset area, wherein the machine learning algorithm can identify temperature fluctuation characteristics related to the insulation defect area; and generating a preliminary insulation defect report in combination with the temperature fluctuation pattern of the preset area and the temperature compensation result, wherein the preliminary insulation defect report includes the location of the insulation defect area, the temperature fluctuation characteristics, and the adjusted temperature value of the preset area.

[0080] In this step, the dynamic thermal image is a series of continuously taken thermal images that can show the temperature change trend of the object surface over time. Abnormal temperature fluctuation is that in the dynamic thermal image, the temperature change amplitude of some areas is significantly greater than that of the surrounding areas, or the change frequency is significantly higher than that of other areas. The ambient temperature compensation algorithm is an algorithm that adjusts the temperature data to eliminate the impact of ambient temperature changes and ensure the accuracy of temperature measurement. The machine learning algorithm is an artificial intelligence technology that can identify specific patterns or features by learning historical data to make predictions or classifications.

[0081] First, computer vision technology is used to analyze the temperature data in the dynamic thermal image in real time to find areas with large temperature changes or high frequency changes. These areas may be potential insulation defect areas.

[0082] Secondly, collect ambient temperature data and use the ambient temperature compensation algorithm to correct the temperature value of the preset area to eliminate the interference of ambient temperature changes and ensure the accuracy of the temperature fluctuation pattern.

[0083] Furthermore, a machine learning model is trained based on a large library of historical insulation defect cases to identify temperature fluctuation characteristics associated with insulation defects. The temperature fluctuation pattern of a preset area is input into the model to predict whether there is an insulation defect in the area.

[0084] Finally, a preliminary insulation defect report is generated based on the prediction results of the machine learning model. The report should include detailed information such as the location of the insulation defect area, temperature fluctuation characteristics, and the adjusted temperature value of the preset area.

[0085] In the embodiment of the present application, it is assumed that the insulation performance of a high-voltage cable terminal is being monitored. A series of dynamic thermal images are obtained by installing a non-contact infrared sensor array around the cable terminal. These thermal images show the temperature change trend of the cable terminal surface over time.

[0086] Analyzing the temperature data in the dynamic thermal image, it is found that the temperature change amplitude of a preset area (marked as area A) at the cable terminal is significantly greater than that of the surrounding area, and the change frequency is higher. This indicates that there may be insulation defects in area A.

[0087] Assume that the ambient temperature is 25°C and the initial temperature reading of area A is 70°C. According to the ambient temperature compensation algorithm, the adjusted temperature value of area A is 68°C. This step ensures the accuracy of the temperature fluctuation pattern.

[0088] The temperature fluctuation pattern in area A is input into a pre-trained machine learning model. Based on a large library of historical insulation defect cases, the model can identify the temperature fluctuation characteristics associated with insulation defects. The model prediction results show that there is a 90% probability that there is an insulation defect in area A.

[0089] The resulting preliminary insulation defect report includes the following:

[0090] Location: Cable terminal area A

[0091] Temperature fluctuation characteristics: large temperature fluctuations and high frequency of changes

[0092] Adjusted temperature value: 68°C

[0093] Prediction result: The probability of insulation defect is 90%

[0094] Through the above scheme, not only can the temperature changes on the surface of electrical equipment be monitored in real time, but also potential insulation defect areas can be accurately identified through ambient temperature compensation algorithms and machine learning technology. This method not only improves the accuracy and reliability of detection, but also reduces human errors, providing a scientific basis for equipment maintenance and safe operation. In addition, the generated preliminary insulation defect report provides detailed data support for subsequent fault diagnosis and maintenance decisions, which helps to take timely measures to prevent the occurrence of faults.

[0095] 103. For the insulation defect area marked in the preliminary insulation defect report, use electromagnetic field analysis technology to simulate the electromagnetic field distribution of the insulation defect area under different working conditions, evaluate the aging degree and damage risk of the insulation material, and obtain an evaluation result;

[0096] In this step, electromagnetic field simulation software is used to simulate the electromagnetic field distribution in various working conditions in the suspected insulation defect areas pointed out in the preliminary report to evaluate the degree of insulation material aging and its potential damage risk. This step provides deeper insights and helps determine the severity of the problem.

[0097] In the embodiment of the present application, professional electromagnetic field simulation software such as ANSYS or COMSOL is used to input specific parameters of the suspected insulation defect area, set different working scenarios, and then run the simulation. By analyzing the simulation results, experts can determine whether the insulation material is in an early aging state and whether it will cause failure under extreme conditions.

[0098] In the existing electrical equipment insulation performance testing, although the potential insulation defect areas can be preliminarily identified through thermal imaging and machine learning technology, these methods mainly rely on the appearance of temperature changes and lack in-depth analysis of the internal electromagnetic field distribution and material properties. This limitation may lead to inaccurate assessment of the degree of insulation material aging and damage risk, which in turn affects the effectiveness of maintenance decisions.

[0099] Therefore, this application proposes an improved solution, which uses electromagnetic field analysis technology to simulate the electromagnetic field distribution in the insulation defect area under different working conditions, evaluate the aging degree and damage risk of the insulation material, so as to solve the problems existing in the prior art and improve the accuracy and reliability of the evaluation.

[0100] The options are as follows:

[0101] Optionally, in step 103, for the insulation defect area marked in the preliminary insulation defect report, the electromagnetic field analysis technology is used to simulate the electromagnetic field distribution of the insulation defect area under different working conditions, the aging degree and damage risk of the insulating material are evaluated, and the evaluation result is obtained, including: determining the area of ​​interest for electromagnetic field analysis according to the position and size of the insulation defect area marked in the preliminary insulation defect report; collecting relevant electrical parameters of the insulation defect area, including voltage level, current intensity, frequency and environmental parameters; constructing a three-dimensional geometric model of the insulation defect area, the three-dimensional geometric model is used to reflect the actual geometric shape and material properties of the insulation defect area, and ensure the accuracy of the electromagnetic field analysis; using the finite element analysis method, simulating the electromagnetic field distribution under different working conditions on the three-dimensional geometric model, so as to evaluate the electromagnetic response of the insulating material under various working conditions, and obtain the electromagnetic field distribution result; analyzing the electromagnetic field distribution result, evaluating the aging degree and damage risk of the insulating material, and obtaining the evaluation result.

[0102] In this step, electromagnetic field analysis technology is a technology that uses mathematical models and numerical methods to calculate and analyze the distribution of electromagnetic fields. The three-dimensional geometric model is a three-dimensional computer model that describes the geometric shape and material properties of an object. Finite element analysis method is a numerical analysis method that divides complex geometric structures into many small units to solve partial differential equations. It is suitable for the analysis of various physical fields such as electromagnetic fields, stress, and heat conduction. The electromagnetic field distribution is the distribution of the electromagnetic field in space, which is usually described by parameters such as electric field strength and magnetic field strength. The degree of aging is the degree of performance degradation of the insulating material during long-term use. Damage risk The possibility of failure or damage of the insulating material under specific conditions.

[0103] First, the location and size information of the insulation defect area is extracted from the preliminary insulation defect report to determine the specific area that needs electromagnetic field analysis.

[0104] Secondly, the working condition parameters of the insulation defect area, such as voltage level, current intensity, frequency, etc., as well as environmental parameters, are obtained. These parameters will be used as input for electromagnetic field analysis.

[0105] Next, computer-aided design (CAD) software is used to construct a detailed three-dimensional geometric model based on the actual geometry and material properties of the insulation defect area.

[0106] Furthermore, finite element analysis software is used to set different working conditions on the three-dimensional geometric model, simulate the electromagnetic field distribution, and calculate the electromagnetic field distribution results under various working conditions.

[0107] Finally, based on the electromagnetic field distribution results, the electromagnetic response of the insulating material under different working conditions is analyzed, its aging degree and damage risk are evaluated, and a detailed evaluation report is generated.

[0108] In the embodiment of the present application, it is assumed that an insulation defect area (marked as area B) of a high-voltage cable terminal is found in a preliminary insulation defect report, and its aging degree and damage risk need to be further evaluated.

[0109] From the preliminary insulation defect report, it is known that area B is located in the middle of the cable terminal and measures approximately 5cmx5cmx10cm.

[0110] The working voltage of the cable terminal is 110kV, the maximum current is 1000A, the frequency is 50Hz. The ambient temperature is 25°C and the relative humidity is 60%.

[0111] Use CAD software to build a detailed 3D geometric model based on the actual geometry and material properties of area B.

[0112] Using ANSYS software, different working conditions are set on the 3D geometric model to simulate the electromagnetic field distribution. For example, the voltage is set to 110kV, the current is 1000A, and the frequency is 50Hz to simulate the electromagnetic field distribution in area B under normal working conditions.

[0113] According to the simulation results, the electromagnetic response of area B under different working conditions was analyzed. For example, it was found that under the conditions of maximum voltage and current, the electric field strength in area B reached 100kV / m, which exceeded the tolerance limit of the insulation material and there was a high risk of damage. In addition, by comparing the electromagnetic field distribution under different working conditions and evaluating the aging degree of the insulation material, it was found that under long-term high voltage and high current conditions, the dielectric constant of the insulation material in area B gradually decreased, indicating that the material has begun to age.

[0114] Through the above scheme, not only can potential insulation defect areas be accurately identified, but also the electromagnetic response of these areas under different working conditions can be deeply evaluated through electromagnetic field analysis technology, so as to more accurately evaluate the aging degree and damage risk of insulation materials. This method improves the scientificity and reliability of the evaluation and provides strong data support for the maintenance and safe operation of equipment. Specifically: through three-dimensional geometric models and finite element analysis, the electromagnetic field distribution can be simulated more accurately, avoiding the errors caused by simplified assumptions in traditional methods. Not only the current working conditions are taken into account, but also the electromagnetic responses under various working conditions are simulated to comprehensively evaluate the damage risk of insulation materials. The generated evaluation report provides maintenance personnel with a detailed scientific basis, which helps to take maintenance measures in time, prevent the occurrence of faults, and ensure the safe operation of equipment.

[0115] 104. Combining the preliminary insulation defect report and the evaluation result, the probability of the insulation defect area developing into an actual fault is calculated through a fault prediction model, and a final insulation performance test report is output to guide equipment maintenance and safe operation.

[0116] In this step, the information obtained in the first two steps - the preliminary insulation defect report and the electromagnetic field distribution assessment results - is combined, and the pre-established fault prediction model is used to calculate the possibility of the insulation defect area developing into an actual fault. Finally, all analysis results are integrated into a detailed insulation performance test report to provide a scientific basis for equipment maintenance and safe operation.

[0117] In the embodiment of the present application, a fault prediction model based on a Bayesian network is established, which takes into account multiple influencing factors, including but not limited to the degree of temperature anomaly, the abnormal pattern of electromagnetic field distribution, the type and age of insulating materials, etc. The output of the model is the probability value of each suspected defect area turning into a fault in the future. The final report not only contains these probability estimates, but also makes specific maintenance recommendations, such as recommending the immediate replacement of a certain component or planning a more detailed inspection at the next routine inspection.

[0118] In the existing insulation performance testing of electrical equipment, although the aging degree and damage risk of the insulation material can be evaluated through preliminary insulation defect reports and electromagnetic field analysis, this information is usually isolated and lacks systematic integration and comprehensive analysis. This leads to an inaccurate assessment of the probability of the insulation defect area developing into an actual fault, making it difficult to provide effective maintenance recommendations. Therefore, this application proposes an improved solution that comprehensively evaluates the development trend and failure probability of the insulation defect area through data fusion and fault prediction models, and generates a final insulation performance test report to guide the maintenance and safe operation of the equipment.

[0119] The options are as follows:

[0120] Optionally, the preliminary insulation defect report and the evaluation result are integrated in step 104, the probability of the insulation defect area developing into an actual fault is calculated through a fault prediction model, and a final insulation performance test report is output to guide equipment maintenance and safe operation, including: fusing the preliminary insulation defect report and the evaluation result to form a comprehensive evaluation data set, the comprehensive evaluation data set includes the location of the insulation defect area, temperature fluctuation characteristics, the adjusted temperature value of the preset area, the electromagnetic field distribution result, the aging degree and damage risk of the insulation material; applying a pre-trained fault prediction model, the fault prediction model is based on a historical insulation defect case library and expert knowledge are constructed to calculate the probability of the insulation defect area developing into an actual fault based on the comprehensive evaluation data set; a threshold judgment is performed on the output result of the fault prediction model, and when the probability of the insulation defect area developing into an actual fault exceeds a preset threshold, the insulation defect area is marked as a high-risk area; for the high-risk area, potential failure modes and development trends are analyzed, and corresponding preventive measures and maintenance plans are formulated to generate a final insulation performance test report, wherein the final insulation performance test report contains detailed information of the insulation defect area, the probability of fault development, the risk level, preventive measures and maintenance suggestions to guide the maintenance and safe operation of the equipment.

[0121] In this step, data fusion is the integration of data from different sources into a unified data set for more comprehensive analysis. The fault prediction model is a model based on historical data and expert knowledge that is used to predict the probability of equipment failure. The comprehensive evaluation data set contains data sets of information such as the location of the insulation defect area, temperature fluctuation characteristics, adjusted temperature values, electromagnetic field distribution results, aging degree of insulation materials, and damage risk. Threshold judgment is to classify the results of the model output according to preset standards to determine whether action is needed. Preventive measures and maintenance plans are to formulate specific maintenance measures and plans for high-risk areas to prevent the occurrence of failures.

[0122] First, the location, temperature fluctuation characteristics, and adjusted temperature values ​​in the preliminary insulation defect report are integrated with the electromagnetic field distribution, insulation material aging degree, and damage risk in the electromagnetic field analysis results to form a comprehensive evaluation data set.

[0123] Secondly, a fault prediction model pre-trained based on a historical insulation defect case library and expert knowledge is used as input to the comprehensive evaluation dataset to calculate the probability of each insulation defect area developing into an actual fault.

[0124] Furthermore, a preset threshold is set to judge the probability value output by the model. If the failure probability of a certain insulation defect area exceeds the threshold, it is marked as a high-risk area.

[0125] Finally, for areas marked as high risk, further analyze their potential failure modes and development trends, and formulate specific preventive measures and maintenance plans. The final insulation performance test report should contain detailed information on the insulation defect area, the probability of failure development, the risk level, preventive measures and maintenance recommendations.

[0126] In the embodiment of the present application, it is assumed that an insulation defect area (marked as area C) of a high-voltage cable terminal is found in the preliminary insulation defect report, and its aging degree and damage risk are evaluated through electromagnetic field analysis. Now it is necessary to further calculate the probability of area C developing into an actual fault and generate a final insulation performance test report.

[0127] The location of area C, temperature fluctuation characteristics, adjusted temperature values, etc. are extracted from the preliminary insulation defect report. The electromagnetic field distribution of area C, aging degree of insulation materials, and damage risk are extracted from the electromagnetic field analysis results.

[0128] This information is combined into a comprehensive evaluation dataset as follows:

[0129] Location: Middle of cable terminal

[0130] Temperature fluctuation characteristics: large temperature fluctuations and high frequency of changes

[0131] Adjusted temperature value: 68°C

[0132] Electromagnetic field distribution: electric field strength 100kV / m

[0133] Aging degree: Dielectric constant decreases by 10%

[0134] Risk of damage: High

[0135] A fault prediction model based on a historical insulation defect case library and expert knowledge pre-training is used to input the above comprehensive evaluation data set to calculate the probability of area C developing into an actual fault. Assume that the probability output by the model is 85%.

[0136] The preset failure probability threshold is 80%. Since the failure probability of area C is 85%, which exceeds the threshold, area C is marked as a high-risk area.

[0137] Potential failure modes: Excessive electric field strength leading to insulation breakdown, and decreased dielectric constant leading to decreased insulation performance.

[0138] Development trend: Under high voltage and high current conditions, the dielectric constant of insulating materials will further decrease and the risk of failure will increase.

[0139] Preventive measures: Regularly check the temperature and electromagnetic field distribution in area C, and perform local repairs or replace insulation materials when necessary.

[0140] Maintenance plan: It is recommended to conduct a detailed inspection of the C area at the next routine inspection and perform maintenance if necessary.

[0141] Finally, generate the final insulation performance test report:

[0142] Insulation defect area: middle of cable terminal (area C)

[0143] Failure development probability: 85%

[0144] Risk level: High

[0145] Preventive measures: Regularly check the temperature and electromagnetic field distribution in area C, and perform local repairs or replace insulation materials when necessary.

[0146] Maintenance suggestion: Perform a detailed inspection of area C during the next routine inspection. If abnormal temperature or electromagnetic field distribution is found, take maintenance measures immediately.

[0147] Through the above scheme, not only can the preliminary insulation defect report and electromagnetic field analysis results be integrated, but also the probability of the insulation defect area developing into an actual fault can be accurately calculated through the fault prediction model, and a detailed final insulation performance test report can be generated. This method has the following significant advantages: Through data fusion and fault prediction models, multiple factors are comprehensively considered to improve the accuracy and reliability of the evaluation. The generated final report provides maintenance personnel with a detailed scientific basis, which helps to take maintenance measures in time to prevent the occurrence of faults. Through preventive measures and maintenance plans for high-risk areas, the transition from passive maintenance to active prevention is achieved, ensuring the safe operation of equipment. Through accurate risk assessment, maintenance resources can be reasonably allocated, maintenance efficiency can be improved, and maintenance costs can be reduced.

[0148] The options are as follows:

[0149] Optionally, the fault prediction model in step 104 calculates the probability of the insulation defect area developing into an actual fault according to the comprehensive evaluation data set, which is calculated by the following calculation formula:

[0150] ;

[0151] in, Indicates the probability that a suspected defective area develops into an actual failure; Respectively represent The characteristic value corresponding to the temperature fluctuation characteristics of each insulation defect area, the characteristic value corresponding to the electromagnetic field distribution result and the environmental adaptability score; and They are The weight matrix and bias term of the layer are learned from the historical insulation defect case library through deep learning method; Indicates the number of insulation defect areas; is a multi-layer composite function used to integrate temperature fluctuation characteristics, electromagnetic field distribution results and environmental adaptability scores, defined as:

[0152] ;

[0153] in, It is A subfunction, defined as:

[0154] ;

[0155] in, It is the parameter learned from historical data; It is The weights of each sub-function are dynamically updated through an adaptive weight adjustment mechanism; is the activation function used to convert the weighted sum into a probability value, is the number of layers of the neural network, is the number of subfunctions in each layer.

[0156] In this step, the fault prediction model is a model built based on historical data and deep learning methods to predict the probability of equipment failure. The comprehensive evaluation data set contains a data set of information such as the location of the insulation defect area, temperature fluctuation characteristics, electromagnetic field distribution results, aging degree of insulation materials, and damage risk. The weight matrix is ​​a weight parameter connecting different layers in the neural network, which is used to adjust the importance of input data. The bias term is a constant term in the neural network, which is used to adjust the output value. The multi-layer composite function is a complex function composed of multiple sub-functions, which is used to integrate multiple input features. The sub-function is a basic component in the multi-layer composite function, which is used to process specific input features. The activation function is a function used to convert the output of the neural network into a probability value. Common activation functions include sigmoid, ReLU, etc. The adaptive weight adjustment mechanism dynamically adjusts the weights of the sub-functions according to the performance of the model to optimize the prediction ability of the model.

[0157] First, the temperature fluctuation characteristics in the preliminary insulation defect report, the electromagnetic field distribution in the electromagnetic field analysis results, the aging degree and damage risk of the insulation material and other information are integrated to form a comprehensive evaluation data set.

[0158] Secondly, the weight matrix and bias term are learned from the historical insulation defect case library using deep learning methods. Define the multi-layer composite function , used to integrate temperature fluctuation characteristics, electromagnetic field distribution results and environmental adaptability scores. Define subfunction , used to process specific input features.

[0159] Next, the probability of an insulation defect area developing into an actual fault is calculated using the following formula:

[0160] ;

[0161] in, Indicates the probability that a suspected defective area develops into an actual failure; Respectively represent The characteristic value corresponding to the temperature fluctuation characteristics of each insulation defect area, the characteristic value corresponding to the electromagnetic field distribution result and the environmental adaptability score; and They are The weight matrix and bias term of the layer are learned from the historical insulation defect case library through deep learning method; Indicates the number of insulation defect areas; is a multi-layer composite function used to integrate temperature fluctuation characteristics, electromagnetic field distribution results and environmental adaptability scores, defined as:

[0162] ;

[0163] in, It is A subfunction, defined as:

[0164] ;

[0165] in, It is the parameter learned from historical data; It is The weights of each sub-function are dynamically updated through an adaptive weight adjustment mechanism; is the activation function used to convert the weighted sum into a probability value, is the number of layers of the neural network, is the number of subfunctions in each layer.

[0166] Furthermore, a preset fault probability threshold is set to judge the probability value output by the model. If the fault probability of a certain insulation defect area exceeds the threshold, it is marked as a high-risk area.

[0167] Finally, for areas marked as high risk, further analyze their potential failure modes and development trends, and formulate specific preventive measures and maintenance plans. The final insulation performance test report should contain detailed information on the insulation defect area, the probability of failure development, the risk level, preventive measures and maintenance recommendations.

[0168] In the embodiment of the present application, it is assumed that an insulation defect area (marked as area D) of a high-voltage cable terminal is found in the preliminary insulation defect report, and its aging degree and damage risk are evaluated through electromagnetic field analysis. Now it is necessary to further calculate the probability of area D developing into an actual fault and generate a final insulation performance test report.

[0169] Information such as the temperature fluctuation characteristics of the D area, the electromagnetic field distribution results, the aging degree of the insulation material and the damage risk are extracted from the preliminary insulation defect report.

[0170] The comprehensive evaluation dataset is as follows:

[0171] Temperature fluctuation characteristics: large temperature fluctuations, high frequency of changes, characteristic values ;

[0172] Electromagnetic field distribution: electric field strength , eigenvalue ;

[0173] Environmental adaptability score: score value ;

[0174] Assume the model parameters are as follows:

[0175] Weight Matrix and the bias term Learned from the historical insulation defect case library through deep learning methods; activation function (sigmoid function); sub-function parameters ; Sub-function weight Dynamically updated via an adaptive weight adjustment mechanism.

[0176] Assume the model structure is a single layer , each layer has two sub-functions .

[0177] Calculation subfunction :

[0178] ;

[0179] ;

[0180] Computing multi-layer composite functions :

[0181] ;

[0182] Assumptions :

[0183] ;

[0184] Calculating the probability of failure :

[0185] ;

[0186] Assumptions :

[0187] ;

[0188] The preset failure probability threshold is 80%. Since the failure probability of area D is 3.6%, which does not exceed the threshold, it is not marked as a high-risk area.

[0189] Generate the final insulation performance test report:

[0190] Insulation defect area: middle of cable terminal (area D)

[0191] Failure development probability: 3.6%

[0192] Risk level: Low

[0193] Preventive measures: Regularly check the temperature and electromagnetic field distribution in area D

[0194] If any abnormality is found, perform maintenance in time

[0195] Maintenance Recommendation: It is recommended to conduct a detailed inspection of area D during the next routine inspection.

[0196] Through the above scheme, not only can the preliminary insulation defect report and electromagnetic field analysis results be integrated, but also the probability of the insulation defect area developing into an actual fault can be accurately calculated through the fault prediction model, and a detailed final insulation performance test report can be generated. This method has the following significant advantages: The fault prediction model constructed by the deep learning method comprehensively considers the temperature fluctuation characteristics, electromagnetic field distribution results and environmental adaptability scores, which improves the accuracy and reliability of the evaluation. The generated final report provides maintenance personnel with a detailed scientific basis, which helps to take maintenance measures in time to prevent the occurrence of faults. Through preventive measures and maintenance plans for high-risk areas, the transition from passive maintenance to active prevention is achieved, ensuring the safe operation of equipment. Through accurate risk assessment, maintenance resources can be reasonably allocated, maintenance efficiency can be improved, and maintenance costs can be reduced.

[0197] In the existing electrical equipment insulation performance testing, although the aging degree and damage risk of insulation materials can be evaluated through preliminary insulation defect reports and electromagnetic field analysis, these methods usually lack a comprehensive assessment of environmental adaptability. The environmental adaptability score can reflect the impact of various interference factors on the equipment in the actual operating environment, such as temperature changes, noise interference, and the stability of temperature measurement. Existing methods often ignore these factors, resulting in inaccurate and incomplete evaluation results.

[0198] Therefore, this application proposes an improved solution by introducing an environmental fitness score and comprehensively considering temperature compensation, noise processing and temperature measurement stability of multiple measurement points to improve the accuracy and reliability of the evaluation.

[0199] The options are as follows:

[0200] Optionally, the environmental adaptability score in step 104 The calculation formula is:

[0201] ;

[0202] in, Indicates The temperature value of each measuring point after ambient temperature compensation; Indicates The maximum temperature value of each measurement point is based on the maximum operating temperature setting of the equipment; Indicates The amount of noise reduced by each measurement point through signal amplification and filtering technology; Indicates The total noise originally collected at each measurement point; Indicates The stability score of the temperature measurement at each measurement point reflects the degree to which the temperature measurement is disturbed by the environment; Indicates The best stability score among the measurement points; is an exponential function, which is used here to increase the nonlinear relationship between the various parts of the formula to better reflect the actual physical process; It is The weights of each measurement point are dynamically updated through an adaptive weight adjustment mechanism; is the number of measurement points.

[0203] In this step, the temperature data of each measurement point is firstly compensated for the ambient temperature to obtain ; Secondly, the temperature data of each measuring point is amplified and filtered to calculate the amount of noise reduction ; Further, the temperature measurement stability of each measurement point is evaluated and obtained ; Finally, the environmental fitness score is calculated using the above formula.

[0204] In the present application example, it is assumed that an insulation defect area (marked as area E) of a high-voltage cable terminal is found in the preliminary insulation defect report, and its aging degree and damage risk are evaluated through electromagnetic field analysis. Now it is necessary to further calculate the environmental adaptability score of area E and generate a final insulation performance test report.

[0205] Calculate the temperature value after temperature compensation :

[0206] Assume that there are three measurement points in area E, namely E1, E2 and E3.

[0207] The temperature values ​​after ambient temperature compensation are:

[0208] ;

[0209] Calculate the amount of noise reduction :

[0210] Assume that the total noise amount at each measurement point is:

[0211] ;

[0212] After signal amplification and filtering, the noise reduction is:

[0213] ;

[0214] Calculating the stability score :

[0215] Assume that the stability score for each measurement point is:

[0216] ;

[0217] Assume that the best stability score for each measurement point is:

[0218] ;

[0219] Calculating environmental fitness scores :

[0220] Assume that the weights of each measurement point are:

[0221] ;

[0222] Assume that the maximum temperature value at each measurement point is:

[0223] ;

[0224] Calculate the exponential function part for each measurement point:

[0225] ;

[0226] Calculate the noise portion for each measurement point:

[0227] ;

[0228] Calculate the stability part for each measurement point:

[0229] ;

[0230] Calculating environmental fitness scores :

[0231] ;

[0232] Through the above scheme, not only can the preliminary insulation defect report and electromagnetic field analysis results be integrated, but also the performance of the equipment in the actual operating environment can be comprehensively evaluated through the environmental adaptability score. This method has the following significant advantages: By introducing the environmental adaptability score, multiple factors such as temperature compensation, noise processing and temperature measurement stability are comprehensively considered, which improves the accuracy and reliability of the evaluation. The environmental adaptability score not only reflects the impact of temperature changes, but also takes into account noise interference and measurement stability, providing a more comprehensive evaluation result. The generated final report provides maintenance personnel with a detailed scientific basis, which helps to take maintenance measures in time to prevent the occurrence of failures. Through preventive measures and maintenance plans for high-risk areas, the transition from passive maintenance to active prevention is achieved, ensuring the safe operation of equipment. Through accurate risk assessment, maintenance resources can be reasonably allocated, maintenance efficiency can be improved, and maintenance costs can be reduced.

[0233] Figure 2 A schematic diagram of a detection system for insulation detection function is provided in an embodiment of the present application. Figure 2 As shown, the system includes:

[0234] Forming module 21, used for monitoring the temperature change of the surface of the electrical equipment under test in real time through a non-contact sensor when the electrical equipment under test is in operation, and forming a dynamic thermal image;

[0235] An identification and generation module 22, for intelligently identifying potential insulation defect areas and generating a preliminary insulation defect report based on the temperature fluctuation pattern of a preset area in the dynamic thermal image in combination with an ambient temperature compensation algorithm;

[0236] An evaluation module 23 is used to use electromagnetic field analysis technology to simulate the electromagnetic field distribution of the suspected defect area marked in the preliminary insulation defect report under different working conditions, and evaluate the aging degree and damage risk of the insulation material;

[0237] The output module 24 is used to integrate the analysis results of the temperature fluctuation pattern and the evaluation results of the electromagnetic field distribution, calculate the probability of the suspected defect area developing into an actual fault through a fault prediction model, and output a final insulation performance test report to guide equipment maintenance and safe operation.

[0238] Figure 2 The insulation detection function detection system can perform Figure 1 The implementation principle and technical effect of the detection method of the insulation detection function described in the embodiment are not described in detail. The specific way in which each module and unit performs operations in the detection system of the insulation detection function in the above embodiment has been described in detail in the embodiment of the method, and will not be described in detail here.

[0239] In one possible design, Figure 2 The detection system of the insulation detection function of the embodiment shown can be implemented as a computing device, such as Figure 3 As shown, the computing device may include a storage component 31 and a processing component 32;

[0240] The storage component 31 stores one or more computer instructions, wherein the one or more computer instructions are called and executed by the processing component 32 .

[0241] The processing component 32 is used to: when the electrical equipment to be tested is in operation, monitor the temperature change of the surface of the electrical equipment to be tested in real time through a non-contact sensor to form a dynamic thermal image; identify potential insulation defect areas according to the temperature fluctuation pattern of the preset area in the dynamic thermal image in combination with the ambient temperature compensation algorithm, and generate a preliminary insulation defect report; for the insulation defect area marked in the preliminary insulation defect report, use electromagnetic field analysis technology to simulate the electromagnetic field distribution of the insulation defect area under different working conditions, evaluate the aging degree and damage risk of the insulation material, and obtain an evaluation result; combine the preliminary insulation defect report and the evaluation result, calculate the probability of the insulation defect area developing into an actual fault through a fault prediction model, and output a final insulation performance test report to guide equipment maintenance and safe operation.

[0242] The processing component 32 may include one or more processors to execute computer instructions to complete all or part of the steps in the above method. Of course, the processing component may also be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components to perform the above method.

[0243] The storage component 31 is configured to store various types of data to support operations at the terminal. The storage component can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0244] Of course, the computing device may also include other components, such as input / output interfaces, display components, communication components, etc.

[0245] The input / output interface provides an interface between the processing component and the peripheral interface module, which may be an output device, an input device, etc.

[0246] The communication component is configured to facilitate, among other things, wired or wireless communications between the computing device and other devices.

[0247] Among them, the computing device can be a physical device or an elastic computing host provided by a cloud computing platform, etc. In this case, the computing device can refer to a cloud server, and the above-mentioned processing components, storage components, etc. can be basic server resources rented or purchased from the cloud computing platform.

[0248] The present application also provides a computer storage medium storing a computer program, wherein the computer program can achieve the above-mentioned Figure 1 The detection method of the insulation detection function of the embodiment shown.

[0249] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0250] The system embodiment described above is merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art may understand and implement it without creative work.

[0251] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0252] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for detecting insulation detection function, characterized in that: include: When the electrical device to be tested is in operation, the temperature change on the surface of the electrical device to be tested is monitored in real time by a non-contact sensor to form a dynamic thermal image; According to the temperature fluctuation pattern of the preset area in the dynamic thermal image, combined with the ambient temperature compensation algorithm, potential insulation defect areas are identified and a preliminary insulation defect report is generated; For the insulation defect area marked in the preliminary insulation defect report, the electromagnetic field analysis technology is used to simulate the electromagnetic field distribution of the insulation defect area under different working conditions, evaluate the aging degree and damage risk of the insulation material, and obtain the evaluation result; Combining the preliminary insulation defect report and the evaluation results, calculating the probability of the insulation defect area developing into an actual fault through a fault prediction model, and outputting a final insulation performance test report to guide equipment maintenance and safe operation; The process of calculating the probability of an insulation defect area developing into an actual fault is calculated using the following formula: ； in, Indicates the probability that a suspected defective area develops into an actual failure; Respectively represent The characteristic value corresponding to the temperature fluctuation characteristics of each insulation defect area, the characteristic value corresponding to the electromagnetic field distribution result and the environmental adaptability score; and They are The weight matrix and bias term of the layer are learned from the historical insulation defect case library through deep learning method; Indicates the number of insulation defect areas; is a multi-layer composite function used to integrate temperature fluctuation characteristics, electromagnetic field distribution results and environmental adaptability scores, defined as: ； in, It is A subfunction, defined as: ； in, It is the parameter learned from historical data; It is The weights of each sub-function are dynamically updated through an adaptive weight adjustment mechanism; is the activation function used to convert the weighted sum into a probability value, is the number of layers of the neural network, is the number of subfunctions in each layer; The environmental fitness score The calculation formula is: ； in, Indicates The temperature value of each measuring point after ambient temperature compensation; Indicates The maximum temperature value of each measurement point is based on the maximum operating temperature setting of the equipment; Indicates The amount of noise reduced by each measurement point through signal amplification and filtering technology; Indicates The total noise originally collected at each measurement point; Indicates The stability score of the temperature measurement at each measurement point reflects the degree to which the temperature measurement is disturbed by the environment; Indicates The best stability score among the measurement points; is an exponential function, which is used here to increase the nonlinear relationship between the various parts of the formula to better reflect the actual physical process; It is The weights of each measurement point are dynamically updated through an adaptive weight adjustment mechanism; is the number of measurement points.

2. The method according to claim 1, characterized in that: The method of monitoring the temperature change of the surface of the electrical equipment under test in real time by a non-contact sensor when the electrical equipment under test is in operation to form a dynamic thermal image includes: The temperature data of the surface of the electrical equipment to be tested is collected in real time by means of a non-contact infrared sensor array installed around the electrical equipment to be tested; Processing the temperature data using signal amplification and filtering techniques to reduce environmental interference and noise impact; Convert the processed temperature data into a temperature distribution image to form a preliminary thermal image; Image fusion technology is applied to fuse the preliminary thermal images corresponding to the non-contact infrared sensor array to generate a dynamic thermal image, which can show the temperature change trend of the surface of the electrical equipment to be tested.

3. The method according to claim 1, characterized in that The method of identifying potential insulation defect areas based on the temperature fluctuation pattern of the preset area in the dynamic thermal image in combination with the ambient temperature compensation algorithm and generating a preliminary insulation defect report includes: By real-time analysis of the temperature data in the dynamic thermal image, a preset area with abnormal temperature fluctuation is identified, wherein the abnormal temperature fluctuation refers to an area with a large temperature change amplitude or a high temperature change frequency compared with the surrounding area; Applying an ambient temperature compensation algorithm, adjusting the temperature value of the preset area according to the collected ambient temperature data, and obtaining a temperature compensation result to ensure the accuracy of the temperature fluctuation pattern; Using a machine learning algorithm, based on a historical insulation defect case library and the temperature fluctuation pattern of the preset area, intelligently identifying potential insulation defect areas, the machine learning algorithm being capable of identifying temperature fluctuation characteristics associated with the insulation defect area; In combination with the temperature fluctuation pattern of the preset area and the temperature compensation result, a preliminary insulation defect report is generated, wherein the preliminary insulation defect report includes the location of the insulation defect area, the temperature fluctuation characteristics, and the adjusted temperature value of the preset area.

4. The method according to claim 1, characterized in that: For the insulation defect area marked in the preliminary insulation defect report, the electromagnetic field analysis technology is used to simulate the electromagnetic field distribution of the insulation defect area under different working conditions, evaluate the aging degree and damage risk of the insulation material, and obtain the evaluation results, including: Determining a region of interest for electromagnetic field analysis based on the location and size of the insulation defect area identified in the preliminary insulation defect report; Collecting relevant electrical parameters of the insulation defect area, including voltage level, current intensity, frequency and environmental parameters; Constructing a three-dimensional geometric model of the insulation defect region, wherein the three-dimensional geometric model is used to reflect the actual geometric shape and material properties of the insulation defect region to ensure the accuracy of electromagnetic field analysis; Using a finite element analysis method, simulating the electromagnetic field distribution under different working conditions on the three-dimensional geometric model to evaluate the electromagnetic response of the insulating material under various working conditions and obtain the electromagnetic field distribution results; The electromagnetic field distribution result is analyzed to evaluate the aging degree and damage risk of the insulating material and obtain an evaluation result.

5. The method according to claim 1, characterized in that The method integrates the preliminary insulation defect report and the evaluation results, calculates the probability of the insulation defect area developing into an actual fault through a fault prediction model, and outputs a final insulation performance test report to guide equipment maintenance and safe operation, including: fusing the preliminary insulation defect report and the evaluation result to form a comprehensive evaluation data set, wherein the comprehensive evaluation data set includes the location of the insulation defect area, the temperature fluctuation characteristics, the adjusted temperature value of the preset area, the electromagnetic field distribution result, the aging degree and damage risk of the insulation material; Applying a pre-trained fault prediction model, which is built based on a historical insulation defect case library and expert knowledge, to calculate the probability of an insulation defect area developing into an actual fault based on a comprehensive evaluation data set; Performing a threshold judgment on the output result of the fault prediction model, and marking the insulation defect area as a high-risk area when the probability that the insulation defect area develops into an actual fault exceeds a preset threshold; For the high-risk areas, potential failure modes and development trends are analyzed, and corresponding preventive measures and maintenance plans are formulated to generate a final insulation performance test report, wherein the final insulation performance test report contains detailed information on the insulation defect area, failure development probability, risk level, preventive measures and maintenance recommendations to guide the maintenance and safe operation of the equipment.

6. A detection system for insulation detection function, characterized in that: include: A forming module is used to monitor the temperature change of the surface of the electrical equipment to be tested in real time through a non-contact sensor when the electrical equipment to be tested is in operation, so as to form a dynamic thermal image; An identification and generation module, for intelligently identifying potential insulation defect areas and generating a preliminary insulation defect report based on the temperature fluctuation pattern of a preset area in the dynamic thermal image in combination with an ambient temperature compensation algorithm; An evaluation module, for simulating the electromagnetic field distribution of the suspected defective area marked in the preliminary insulation defect report by using electromagnetic field analysis technology under different working conditions, and evaluating the aging degree and damage risk of the insulation material; An output module is used to integrate the analysis results of the temperature fluctuation mode and the evaluation results of the electromagnetic field distribution, calculate the probability of the suspected defect area developing into an actual fault through a fault prediction model, and output a final insulation performance test report to guide equipment maintenance and safe operation; The process of calculating the probability of an insulation defect area developing into an actual fault is calculated using the following formula: ； in, Indicates the probability that a suspected defective area develops into an actual failure; Respectively represent The characteristic value corresponding to the temperature fluctuation characteristics of each insulation defect area, the characteristic value corresponding to the electromagnetic field distribution result and the environmental adaptability score; and They are The weight matrix and bias term of the layer are learned from the historical insulation defect case library through deep learning method; Indicates the number of insulation defect areas; is a multi-layer composite function used to integrate temperature fluctuation characteristics, electromagnetic field distribution results and environmental adaptability scores, defined as: ； in, It is A subfunction, defined as: ； in, It is the parameter learned from historical data; It is The weights of each sub-function are dynamically updated through an adaptive weight adjustment mechanism; is the activation function used to convert the weighted sum into a probability value, is the number of layers of the neural network, is the number of subfunctions in each layer; The environmental fitness score The calculation formula is: ； in, Indicates The temperature value of each measuring point after ambient temperature compensation; Indicates The maximum temperature value of each measurement point is based on the maximum operating temperature setting of the equipment; Indicates The amount of noise reduced by each measurement point through signal amplification and filtering technology; Indicates The total noise originally collected at each measurement point; Indicates The stability score of the temperature measurement at each measuring point reflects the degree of environmental interference in the temperature measurement; Indicates The best stability score among the measurement points; is an exponential function, which is used here to increase the nonlinear relationship between the various parts of the formula to better reflect the actual physical process; It is The weights of each measurement point are dynamically updated through an adaptive weight adjustment mechanism; is the number of measurement points.

7. A computing device, characterized in that It comprises a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement a detection method for an insulation detection function as described in any one of claims 1 to 5.

8. A computer storage medium, characterized in that: A computer program is stored, and when the computer program is executed by a computer, a detection method for an insulation detection function as described in any one of claims 1 to 5 is implemented.

Images