Insulating material service life prediction method and device, storage medium and computer equipment

Abstract

The invention discloses an insulating material service life prediction method and device, a storage medium and computer equipment. The method comprises the following steps: setting a preset environment condition required by a test for a thermal aging test space; controlling a pulse generating device to sequentially apply multi-stage pulse voltage to the to-be-predicted insulating material in the thermal aging test space so as to sequentially carry out multi-stage radiation on the to-be-predicted insulating material by using the pulse voltage, and collecting an electrical insulation process parameter and a thermal insulation process parameter of the to-be-predicted insulating material in each radiation stage process, acquiring an electrical insulation index parameter and a thermal insulation index parameter of the to-be-predicted insulating material after each radiation stage is ended; and determining the insulation life of the to-be-predicted insulation material based on the electrical insulation process parameter and the thermal insulation process parameter in each radiation stage process and the electrical insulation index parameter and the thermal insulation index parameter after each radiation stage is ended.

Description

Technical Field

[0001] The present invention relates to the technical field of high voltage testing, and in particular to a method, device, storage medium and computer equipment for predicting the life of an insulating material. Background Art

[0002] The high-voltage electrical penetrations in the hot chamber are part of the hot chamber wall. Relying on good shielding and sealing functions, they constitute a safety barrier to prevent the leakage of radioactive materials in the hot chamber and protect the personal health of operators. As the main functional component of the high-voltage electrical penetrations in the hot chamber, the polymer insulation material in the high-voltage conductor assembly has a high breakdown field strength and low dielectric loss. However, during the long-term operation of the equipment, the insulation material will inevitably age, resulting in increased transmission losses, reduced insulation performance, or even failure, causing equipment failures and accidents. Therefore, studying the life of the insulation material in the conductor assembly of the high-voltage electrical penetrations in the hot chamber has important engineering application value.

[0003] At present, the life of insulating materials is usually evaluated based on a single factor aging condition. However, in actual engineering conditions, there are many factors that affect the aging of insulating materials. Therefore, this method of evaluating the life of insulating materials based on a single factor aging condition is not accurate enough and is not applicable to actual engineering conditions, that is, it has no reference value. Summary of the invention

[0004] The present invention provides a method, device, storage medium and computer equipment for predicting the life of an insulating material, which are mainly capable of improving the prediction accuracy of the life of an insulating material, so that the predicted life of the insulating material has more reference value.

[0005] According to a first aspect of the present invention, there is provided a method, device, storage medium and computer equipment for predicting the life of an insulating material, comprising:

[0006] Applied to an aging test system, the aging test system includes a pulse generating device, a thermal aging test space, an insulation process parameter measuring device, and an insulation index parameter measuring device, including:

[0007] Setting the preset environmental conditions required for the test for the thermal aging test space containing the insulation material to be predicted, wherein the preset environmental conditions include temperature conditions and humidity conditions, wherein the preset environmental conditions are determined according to the actual working thermal chamber environment corresponding to the insulation material to be predicted, and the number of insulation materials to be predicted is multiple;

[0008] Control the pulse generating device to sequentially apply a pulse voltage of a preset frequency, preset amplitude, and preset duty cycle in multiple stages to the insulation material to be predicted in the thermal aging test space, so as to sequentially perform multi-stage radiation on the insulation material to be predicted by using the pulse voltage, control the insulation process parameter measuring device to collect the electrical insulation process parameters and thermal insulation process parameters of the insulation material to be predicted in real time during each radiation stage, and control the insulation index parameter measuring device to collect the electrical insulation index parameters and thermal insulation index parameters of the insulation material to be predicted after each radiation stage, wherein the pulse voltage in each radiation stage has the same preset frequency, the same preset amplitude, the same preset duty cycle, the same radiation duration, and the same voltage waveform;

[0009] Based on the electrical insulation process parameters and thermal insulation process parameters during each radiation stage, and the electrical insulation index parameters and thermal insulation index parameters after each radiation stage, the insulation life of the insulation material to be predicted is determined.

[0010] According to a second aspect of the present invention, there is provided an insulating material life prediction device, characterized in that it is applied to an aging test system, wherein the aging test system comprises a pulse generating device, a thermal aging test space, an insulation process parameter measuring device, and an insulation index parameter measuring device, including:

[0011] A setting unit, used for setting preset environmental conditions required for the test for the thermal aging test space containing the insulation material to be predicted, wherein the preset environmental conditions include temperature conditions and humidity conditions, wherein the preset environmental conditions are determined according to the actual working thermal chamber environment corresponding to the insulation material to be predicted, and the number of the insulation materials to be predicted is multiple;

[0012] An aging test unit, used to control the pulse generating device to sequentially apply a pulse voltage of a preset frequency, preset amplitude, and preset duty cycle to the insulating material to be predicted in the thermal aging test space, so as to sequentially perform multi-stage radiation on the insulating material to be predicted using the pulse voltage, control the insulation process parameter measuring device to collect in real time the electrical insulation process parameters and thermal insulation process parameters of the insulating material to be predicted during each radiation stage, and control the insulation index parameter measuring device to collect the electrical insulation index parameters and thermal insulation index parameters of the insulating material to be predicted after each radiation stage, wherein the pulse voltage in each radiation stage has the same preset frequency, the same preset amplitude, the same preset duty cycle, the same radiation duration, and the same voltage waveform;

[0013] The determination unit is used to determine the insulation life of the insulation material to be predicted based on the electrical insulation process parameters and thermal insulation process parameters during each radiation stage, and the electrical insulation index parameters and thermal insulation index parameters after each radiation stage.

[0014] According to a third aspect of the present invention, there is provided a computer-readable storage medium having a computer program stored thereon, which implements the above insulation material life prediction method when executed by a processor.

[0015] According to a fourth aspect of the present invention, there is provided a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above insulating material life prediction method when executing the program.

[0016] According to a method, device, storage medium and computer equipment for predicting the life of an insulating material provided by the present invention, compared with the current method of evaluating the life of an insulating material based on a single aging condition, the present invention constructs an aging test system, and sets the thermal stress environment conditions such as temperature and humidity required for the aging test for the thermal aging test space in the aging test system. On this basis, a multi-stage pulse voltage is applied to the insulating material to be predicted in the thermal aging test space for radiation, and the electrical insulation process parameters and thermal insulation process parameters in each radiation process, as well as the electrical insulation index parameters and thermal insulation index parameters after each radiation stage are collected. Finally, based on the electrical insulation process parameters, thermal insulation process parameters, electrical insulation index parameters and thermal insulation index parameters corresponding to each radiation stage, the insulation life of the insulating material to be predicted is determined, so that by constructing the aging test system, the aging test of the insulating material under temperature aging conditions, humidity aging conditions and voltage aging conditions is realized through the aging test system, that is, in the aging test process, a variety of influencing factors affecting the life of the insulating material and the coupling relationship between the various factors are comprehensively analyzed, which can improve the prediction accuracy of the life of the insulating material, thereby ensuring that the predicted life of the insulating material is more valuable for reference in engineering practice. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0018] Figure 1 A flowchart of an insulating material life prediction method, device, storage medium, and computer equipment provided by an embodiment of the present invention is shown;

[0019] Figure 2 A schematic diagram of the structure of an aging test system provided by an embodiment of the present invention is shown;

[0020] Figure 3 Another insulating material life prediction method, device, storage medium and computer equipment flow chart provided by an embodiment of the present invention is shown;

[0021] Figure 4 A schematic structural diagram of an insulating material life prediction device provided by an embodiment of the present invention is shown;

[0022] Figure 5 A schematic structural diagram of another insulating material life prediction device provided by an embodiment of the present invention is shown;

[0023] Figure 6 A schematic diagram of the physical structure of a computer device provided by an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0024] The present invention will be described in detail below with reference to the accompanying drawings and in combination with embodiments. It should be noted that the embodiments and features in the embodiments of the present application can be combined with each other without conflict.

[0025] At present, the life of insulating materials is evaluated based on a single aging condition. Other factors that affect the life of insulating materials are not considered, resulting in inaccurate prediction of the life of insulating materials.

[0026] In order to solve the above problems, the embodiments of the present invention provide a method, device, storage medium and computer equipment for predicting the life of an insulating material, such as Figure 1 As shown, the method includes:

[0027] 101. Construct an aging test system, which includes a pulse generating device, a thermal aging test space, an insulation process parameter measuring device, and an insulation index parameter measuring device.

[0028] For the embodiments of the present invention, in order to improve the prediction accuracy of the life of the insulating material and make the predicted life more practical in engineering, it is necessary to simulate the aging test of the insulating material under the actual engineering environment and estimate the life of the insulating material according to the simulation results. Based on this, it is first necessary to build an aging test system, such as Figure 2 As shown, the aging test system includes: a pulse generator (high-frequency high-voltage pulse generator), a thermal aging test space (aging test chamber), an insulation process parameter measuring device (ultra-high frequency partial discharge sensor, thermocouple temperature sensor, leakage current sensor, color sensor, gravity sensor, visual sensor, etc.), and an insulation index parameter measuring device (insulation resistance tester, dielectric loss factor measuring instrument, temperature measuring instrument, tensile testing machine, density meter, hardness meter, etc.). For simplicity, Figure 2Only part of the measuring device is shown in the figure, and the aging test box contains a high-voltage conductor assembly with the insulating material to be predicted. Among them, the pulse generating device can output high-frequency and high-voltage pulses in a single stage. Specifically, the insulating material to be predicted is placed in a thermal aging test space, and then the environmental conditions for the thermal aging test space are set to be the same as the actual engineering environment to simulate the thermal aging test conditions such as temperature and humidity. Then, the pulse generating device radiates pulse voltage to the thermal aging test space to simulate the electrical aging test conditions of high frequency and high voltage. Then, under the coupling effect of the thermal aging test conditions and the electrical aging test conditions, the insulating material to be predicted is subjected to an aging test to predict the life of the insulating material, thereby setting the aging test conditions by comprehensively analyzing the various influencing factors (including temperature, humidity, high frequency and high voltage) that affect the life of the insulating material. In the process of predicting the life of the insulating material, not only the individual influences of the various influencing factors are considered, but also the coupling influences between the various influencing factors are considered, thereby improving the prediction accuracy of the life of the insulating material.

[0029] 102. Set the preset environmental conditions required for the test for the thermal aging test space containing the insulating materials to be predicted, wherein the preset environmental conditions include temperature conditions and humidity conditions. The preset environmental conditions are determined based on the actual working thermal chamber environment corresponding to the insulating materials to be predicted. There are multiple insulating materials to be predicted.

[0030] Among them, the high-voltage electrical penetration of the hot chamber is a part of the hot chamber wall. It relies on good shielding and sealing functions to form a safety barrier to prevent the leakage of radioactive materials in the hot chamber and protect the personal health of the operating personnel. The high-voltage conductor assembly is the main functional component of the high-voltage electrical penetration of the hot chamber. The polymer insulating material therein has a higher breakdown field strength and lower dielectric loss. Therefore, the insulating material to be predicted in the embodiment of the present invention can be a component of the high-voltage conductor assembly. Specifically, in order to simulate the actual working hot chamber environmental conditions, it is first necessary to set the preset temperature and preset humidity that are the same as the actual working hot chamber environmental conditions for the thermal aging test space containing the insulating material to be predicted, and then use a pulse generator to simulate the high-frequency voltage that is the same as the actual working hot chamber environmental conditions. In summary, it is possible to perform aging tests on the insulating material to be predicted based on various aging test conditions such as preset temperature, preset humidity, and preset voltage. The life of the insulating material to be predicted is determined by the aging test results, and the multi-factor coupling effect and the uncertainty factors in the long-term operation process are fully considered, and the life prediction results are more accurate.

[0031] 103. Control the pulse generating device to sequentially apply multi-stage pulse voltages of preset frequency, preset amplitude, and preset duty cycle to the insulation material to be predicted in the thermal aging test space, so as to perform multi-stage radiation on the insulation material to be predicted by using the pulse voltage, control the insulation process parameter measuring device to collect the electrical insulation process parameters and thermal insulation process parameters of the insulation material to be predicted in real time during each radiation stage, and control the insulation index parameter measuring device to collect the electrical insulation index parameters and thermal insulation index parameters of the insulation material to be predicted after each radiation stage, wherein the pulse voltage in each radiation stage has the same preset frequency, the same preset amplitude, the same preset duty cycle, the same radiation duration, and the same voltage waveform.

[0032] Among them, the electrical insulation process parameters include: leakage current amplitude, leakage current frequency, local discharge amplitude, local discharge phase, local discharge number, temperature value, etc. of the insulating material to be predicted during the aging test; the thermal insulation process parameters include: color, quality, appearance, and roughness of the insulating material to be predicted during the aging test; the electrical insulation index parameters include: insulation resistance value (insulation resistance value includes 15s insulation resistance R15s and 60s insulation resistance) and dielectric loss factor of the insulating material to be predicted after each aging test stage; the thermal insulation index parameters include: temperature index, relative temperature index, tensile strength, elongation at break, density, hardness, etc. of the insulating material; the preset frequency, preset amplitude, and preset duty cycle are determined according to the actual working conditions of the project in which the insulating material is applied.

[0033] Specifically, the aging test of the hot chamber high-voltage conductor assembly is divided into multiple test stages of equal duration and the same operation process (wherein the same operation process includes: the radiation time, voltage waveform, voltage frequency, voltage amplitude, and voltage duty cycle of each voltage radiation stage are the same). The thermal aging test space and high-frequency high-voltage pulse generator (pulse generator) are used to provide the insulation materials to be predicted in the hot chamber high-voltage conductor assembly with electrical and thermal stress conditions under the actual operation conditions of the project. During the power-on process, the leakage current signal, partial discharge signal, and temperature signal of the insulation materials to be predicted in the aging test process are collected, monitored, and displayed in real time. Electrical insulation process parameters such as color, quality, and roughness, thermal insulation process parameters such as insulation resistance value and dielectric loss factor value of the insulation materials during the aging test, and thermal insulation index parameters such as temperature index, relative temperature index, tensile strength, elongation at break, density, and hardness are measured after power is turned off in each test stage. By comparing and analyzing various electrical insulation process parameters, thermal insulation process parameters, electrical insulation index parameters, and thermal insulation index parameters, the aging condition of the insulation materials in the hot chamber high-voltage conductor assembly is evaluated and the insulation life is predicted. In the process of predicting the life of insulating materials, by using the actual working environment conditions of the project to perform aging tests on the insulating materials, the prediction accuracy of the life of the insulating materials can be improved, and the predicted life can be guaranteed to have more practical reference value for the project. At the same time, the test method provides a specific closed space and high frequency and high voltage for the test environment, and can flexibly and conveniently adjust and maintain the temperature and humidity conditions and the applied voltage waveform required by the test in real time. The aging test method can realize the automatic collection, monitoring, centralized display and data recording and storage functions of leakage current, partial discharge, temperature parameters and other parameters, as well as remote control of the entire test device, thereby ensuring the smooth and stable progress of the aging test.

[0034] 104. Determine the insulation life of the insulation material to be predicted based on the electrical insulation process parameters and the thermal insulation process parameters during each radiation stage, and the electrical insulation index parameters and the thermal insulation index parameters after each radiation stage.

[0035] Specifically, the electrical insulation process parameters, thermal insulation process parameters, electrical insulation index parameters, and thermal insulation index parameters collected at each radiation stage are used to analyze the aging trend of the insulation material to be predicted, and then the life of the insulation material is predicted based on the trend analysis results. Therefore, by simulating the thermal aging test of the insulation material to be predicted under the actual engineering environment conditions, the predicted life of the insulation material can be made more accurate and more valuable for actual engineering use.

[0036] According to a method for predicting the life of an insulating material provided by the present invention, compared with the current method of evaluating the life of an insulating material based on a single aging condition, the present invention constructs an aging test system, and sets the thermal stress environment conditions such as temperature and humidity required for the aging test for the thermal aging test space in the aging test system. On this basis, a multi-stage pulse voltage is applied to the insulating material to be predicted in the thermal aging test space for radiation, and the electrical insulation process parameters and thermal insulation process parameters in each radiation process, as well as the electrical insulation index parameters and thermal insulation index parameters after each radiation stage are collected. Finally, based on the electrical insulation process parameters, thermal insulation process parameters, electrical insulation index parameters, and thermal insulation index parameters corresponding to each radiation stage, the insulation life of the insulating material to be predicted is determined. Thus, by constructing the aging test system, the aging test of the insulating material under temperature aging conditions, humidity aging conditions, and voltage aging conditions is implemented through the aging test system. That is, in the aging test process, a comprehensive analysis is made of the various influencing factors affecting the life of the insulating material and the coupling relationship between the various factors, which can improve the prediction accuracy of the life of the insulating material, thereby ensuring that the predicted life of the insulating material is more valuable for reference in engineering practice.

[0037] Further, in order to better illustrate the above process of classifying data, as a refinement and extension of the above embodiment, the embodiment of the present invention provides another insulation material life prediction method, device, storage medium and computer equipment, such as Figure 3 As shown, the method includes:

[0038] 201. Construct an aging test system, which includes a pulse generating device, a thermal aging test space, an insulation process parameter measuring device, and an insulation index parameter measuring device.

[0039] Specifically, Figure 2As shown, the aging test system includes a host computer, a pulse generating device (high-frequency and high-voltage pulse generating power supply), a thermal aging test space (aging test box), an insulation process parameter measuring device, and an insulation index parameter measuring device; wherein, the host computer is electrically connected to the pulse generating device, and the pulse generating device is electrically connected to the thermal aging test space, the host computer is used to control the pulse generating device to transmit a pulse voltage to the thermal aging test space, the host computer is electrically connected to the insulation process parameter measuring device and the insulation index parameter measuring device respectively, the host computer controls the insulation process parameter measuring device to collect electrical insulation process parameters and thermal insulation process parameters, the host computer controls the insulation index parameter measuring device to collect electrical insulation index parameters and thermal insulation index parameters, and uploads the collected electrical insulation process parameters, thermal insulation process parameters, electrical insulation index parameters, and thermal insulation index parameters to the host computer, the host computer is used to perform trend analysis on the aging state of the insulation material to be predicted based on the electrical insulation process parameters, thermal insulation process parameters, electrical insulation index parameters, and thermal insulation index parameters, so as to predict the life of the insulation material according to the trend analysis results.

[0040] 202. Set preset environmental conditions required for the test for the thermal aging test space containing the insulating materials to be predicted, wherein the preset environmental conditions include temperature conditions and humidity conditions, and the preset environmental conditions are determined based on the actual working thermal chamber environment corresponding to the insulating materials to be predicted, and the number of insulating materials to be predicted is multiple.

[0041] Specifically, based on the actual engineering environment, a closed space (thermal aging test space) is provided for the insulating material to be predicted before the start of a single radiation stage, and the temperature and humidity of the thermal aging test space are adjusted to the conditions required for the test, so as to realize the aging test simulation of the insulating material to be predicted under the thermal aging test conditions.

[0042] 203. Control the pulse generating device to sequentially apply a pulse voltage of a multi-stage preset frequency, preset amplitude, and preset duty cycle to the insulating material to be predicted in the thermal aging test space, so as to perform multi-stage radiation on the insulating material to be predicted by using the pulse voltage, control the insulation process parameter measuring device to collect the electrical insulation process parameters and thermal insulation process parameters of the insulating material to be predicted in real time during each radiation stage, and control the insulation index parameter measuring device to collect the electrical insulation index parameters and thermal insulation index parameters of the insulating material to be predicted after each radiation stage, wherein the pulse voltage in each radiation stage has the same preset frequency, the same preset amplitude, the same preset duty cycle, the same radiation duration, and the same voltage waveform.

[0043] For the embodiment of the present invention, a pulse generating device is used to output high-frequency and high-voltage pulses in a single stage to the insulating material to be predicted in the thermal aging test space to simulate the actual engineering conditions, adjust the high-frequency and high-voltage pulse waveform, and apply a voltage with an amplitude of v, a frequency of f, and a duty cycle of k to the high-voltage conductor component under test, or a multi-stage voltage with an amplitude of v, a frequency of f, and a duty cycle of k, so as to simulate the electrical aging process in the actual engineering environmental conditions. During the power-on process of the aging test, the electrical insulation process parameters, thermal insulation process parameters, electrical insulation index parameters and thermal insulation index parameters of the tested insulating material are collected and monitored in real time, and then the life of the insulating material to be predicted is predicted based on the collected electrical insulation process parameters, thermal insulation process parameters, electrical insulation index parameters and thermal insulation index parameters, wherein the specific method for life prediction includes: judging whether the insulating material to be predicted meets the preset conditions for life prediction based on the electrical insulation process parameters and thermal insulation process parameters during each radiation stage; if the insulating material to be predicted meets the preset conditions, obtaining the control electrical insulation index parameters and control thermal insulation index parameters of the control insulating material in a normal state that has not been irradiated with pulse voltage and has not been thermally irradiated, wherein the material properties of the control insulating material are the same as those of the insulating material to be predicted before the aging test, and the material properties include material type, shape and size, hardness, density, elastic modulus, and mechanical strength; based on the control electrical insulation index parameters and the electrical insulation index parameters, as well as the control thermal insulation index parameters and the thermal insulation index parameters, determining the aging state data of the insulating material to be predicted.Among them, the method for judging whether the insulating material to be predicted meets the preset conditions for life prediction includes: judging whether the insulating material to be predicted has insulation defects based on the leakage current amplitude, leakage current frequency, partial discharge amplitude, partial discharge phase, partial discharge number, and temperature value. Among them, the specific judgment method includes: judging whether the leakage current amplitude is greater than a preset current amplitude threshold, judging whether the leakage current frequency is greater than a preset frequency threshold, judging whether the partial discharge amplitude is greater than a preset partial discharge amplitude threshold, judging whether the partial discharge phase is greater than a preset phase threshold, judging whether the partial discharge number is greater than a preset number threshold, and judging whether the temperature value is greater than a preset temperature threshold. If the leakage current amplitude is greater than the preset current amplitude threshold, the leakage current frequency is greater than the preset frequency threshold, the partial discharge amplitude is greater than the preset partial discharge amplitude threshold, the partial discharge phase is greater than the preset phase threshold, the partial discharge number is greater than the preset number threshold, and the temperature value is greater than the preset temperature threshold, then it is judged that the insulating material to be predicted has insulation defects. trap; based on the color, quality, shape, and roughness, determine whether the insulating material to be predicted has appearance defects, wherein the specific determination method includes: determining whether the color difference between the color of the insulating material to be predicted and the standard color is greater than a preset color difference threshold, determining whether the quality difference between the quality and the standard quality is greater than a preset quality threshold, determining whether the appearance difference between the appearance and the standard appearance is greater than a preset appearance threshold, determining whether the roughness difference between the roughness and the marked roughness is greater than a preset roughness threshold, if the color difference is greater than the preset color difference threshold, the quality difference is greater than the preset quality threshold, the appearance difference is greater than the preset appearance threshold, and the roughness difference is greater than the preset roughness threshold, then it is determined that the insulating material to be predicted has appearance defects; if the insulating material to be predicted has at least one of insulation defects and appearance defects, then it is determined that the insulating material to be predicted does not meet the preset conditions for life prediction; if the insulating material to be predicted does not have insulation defects and appearance defects, then it is determined that the insulating material to be predicted meets the preset conditions for life prediction.

[0044] Specifically, when the aging state of the insulating material is relatively light, the aging test can continue to be carried out to predict the life of the insulating material. At this time, the life prediction is meaningful, that is, the insulating material to be predicted meets the preset conditions for life prediction. If the aging state of the insulating material is relatively serious, it is meaningless to predict the life of the insulating material at this time, which wastes both computing resources and time, that is, the insulating material to be predicted does not meet the preset conditions for life prediction. Based on this, during the current radiation stage, it is necessary to determine whether the insulating material to be predicted meets the preset conditions for life prediction. If it meets the preset conditions, continue to the next radiation stage, otherwise, stop the aging test on the insulating material. Among them, the specific method for judging whether the insulating material to be predicted meets the preset conditions for life prediction is: if the leakage current amplitude of the insulating material to be predicted is greater than the preset current amplitude threshold, the leakage current frequency is greater than the preset frequency threshold, the partial discharge amplitude is greater than the preset partial discharge amplitude threshold, the partial discharge phase is greater than the preset phase threshold, the number of partial discharges is greater than the preset number threshold, and the temperature value is greater than the preset temperature threshold, then it is determined that the insulating material to be predicted has insulation defects; if the color difference of the insulating material to be predicted is greater than the preset color difference threshold, the quality difference is greater than the preset quality threshold, the shape difference is greater than the preset shape threshold, and the roughness difference is greater than the preset roughness threshold, It is determined that the insulating material to be predicted has appearance defects. When the insulating material to be predicted has insulation defects or appearance defects, it is determined that the insulating material to be predicted does not meet the preset conditions for life prediction, that is, the insulating material to be predicted has reached its life, and it is meaningless to continue the life prediction. At this time, stop the aging test on the insulating material, so as to save test resources. When the insulating material to be predicted has no insulation defects and no appearance defects, it is determined that the insulating material to be predicted meets the preset conditions for life prediction, that is, the insulating material to be predicted has not reached its life, and the next stage of radiation and other aging test process is continued on the insulating material.

[0045] Specifically, the total number of insulating materials to be predicted is M, and m insulating materials are taken as test pieces (m<M), and the remaining number of insulating materials (Mm) are taken as control pieces (control insulating materials). The aging test is evenly divided into multiple test stages of equal duration. The test piece is fixed inside the aging test box and connected to the loop. At the same time, the leakage current sensor, partial discharge acquisition sensor and thermocouple temperature sensor are arranged around the test piece. The aging test box is closed during the test. The various parameters of the voltage required for the aging test are set by a high-frequency high-voltage pulse power supply, and the temperature and humidity in the aging test box are set in the host computer. When the preset temperature ta and humidity ha are reached, a high-frequency voltage pulse is output to the test piece to start the first stage of the test. During the test, the leakage current, partial discharge, temperature signal, color, quality, appearance, roughness and other information of the test piece are collected and monitored in real time. After the test of this stage is completed, the power supply is automatically turned off. At this time, the circuit is disconnected and the test piece is taken out. The insulation resistance tester, dielectric loss meter and other measuring instruments are used to measure the electrical insulation index parameters such as insulation resistance and dielectric loss factor of each test piece, as well as the thermal insulation index parameters such as temperature index, relative temperature index, tensile strength, elongation at break, density, hardness, etc., and the test pieces are recorded as test group data. After completing a test stage, the test process of this stage is repeated, and the test piece is continued to be subjected to the next stage of aging test. After the last test stage is completed and the electrical insulation index parameters and thermal insulation index parameters are measured, the electrical insulation index parameters and thermal insulation index parameters of the control pieces (Mm) are measured in turn, and the control group data are recorded, and the aging process of the insulation material to be predicted is analyzed according to the control group data and the experimental group data, and finally the life of the insulation material is predicted according to the aging trend analysis results. In the embodiment of the present invention, the high-frequency high-voltage pulse generating power supply can be specifically a pulse power supply with an output voltage range of -15kV to +15kV, an output frequency range of 0 to 15kHz, and an adjustable duty cycle. In a single-stage aging test, the required voltage is set to a high-frequency voltage signal with an amplitude of v, a frequency of f, a duty cycle of k, and a duration of (T / N). The voltage waveform can be powered to the high-voltage conductor of the hot chamber if the relative error between the voltage waveform and the preset value is within 3%. The total duration of the electrical aging test is T and is evenly divided into N test stages of equal duration. The test duration of each stage is (T / N) and should not be less than 5h. The test steps of each stage are the same. After completing a test stage and measuring the insulation resistance and dielectric loss factor, continue to conduct the next aging test of (T / N) on the test piece. The measurement time between two single stages should not exceed 0.5h. After the last test stage of (T / N) is completed, the aging test time reaches the total duration T.During the single-stage aging test, the leakage current amplitude, partial discharge amplitude, phase, discharge number and temperature signal collected by each sensor in real time are transmitted to the host computer monitoring screen, and each data is stored in the host computer. The insulation resistance tester is specifically an electronic tester with an adjustable voltage range of 250V to 5kV. After each single stage of the aging test, the 15s insulation resistance R15s and 60s insulation resistance R60s of the hot chamber high-voltage conductor assembly are measured three times in sequence. The relative error between each measurement data should not exceed 5%. The dielectric loss measuring instrument is specifically an automatic anti-interference dielectric loss measuring instrument with a built-in variable frequency power supply, dielectric loss bridge and standard capacitor, and a maximum test voltage of 10kV. After each stage of the aging test, the dielectric loss factor tanδ (%) of the hot chamber high-voltage conductor assembly is measured three times in sequence. The relative error between each measurement data should not exceed 5%. The above description is only exemplary, and the embodiments of the present invention are not limited to the above description. In the embodiment of the present invention, multiple test samples are set up and aging tests are performed on them. Since multiple test samples can provide more data points, the reliability and statistical significance of the test results are enhanced. By comparing the aging performance of different samples under the same conditions, the life of the insulation material to be predicted can be more accurately evaluated.

[0046] Furthermore, after collecting the electrical insulation process parameters and thermal insulation process parameters during each radiation stage, as well as the electrical insulation index parameters and thermal insulation index parameters after each radiation stage, in order to ensure the accuracy of the collected parameters and thus ensure the accuracy of the insulation material life prediction, it is necessary to eliminate the abnormal parameters in each parameter. Based on this, the method includes: respectively taking the electrical insulation process parameters, thermal insulation process parameters, electrical insulation index parameters, and thermal insulation index parameters corresponding to each radiation stage as target parameters, and counting the data density in a preset neighborhood corresponding to any parameter in each of the target parameters; if the data density is greater than a preset density threshold, determining the arbitrary parameter as a clustering center; based on the clustering center, clustering each of the target parameters to obtain a clustering result; determining the target parameter that does not belong to any cluster in the clustering result as an abnormal parameter; eliminating the abnormal parameters in each of the target parameters to obtain the electrical insulation process parameters, thermal insulation process parameters, electrical insulation index parameters, and thermal insulation index parameters after cleaning.

[0047] Specifically, the electrical insulation process parameters corresponding to each radiation stage are determined as target parameters. First, several definitions are determined: core point: a target parameter with a number exceeding MinPts within a radius r; boundary point (boundary parameter): a point with a number of target parameters less than MinPts within a radius r, but falling within the neighborhood of the core point; noise point (abnormal parameter): a point that is neither a core point nor a boundary point. The specific clustering method is: for each target parameter, a set of data within its preset neighborhood is calculated. When the number of data in the set exceeds the preset density threshold, the target parameter is determined as a core point (clustering center), and then the remaining points are checked to see if they are within the neighborhood of the core point. The remaining points within the neighborhood of the core point are determined as boundary points, and the remaining points not within the neighborhood of the core point are determined as noise points. Then the parameters corresponding to the noise points are determined as abnormal parameters, and finally the abnormal parameters are eliminated from each target parameter. Thus, the abnormal parameters in the thermal insulation process parameters, electrical insulation index parameters, and thermal insulation index parameters can be eliminated in the above manner, thereby obtaining the electrical insulation process parameters, thermal insulation process parameters, electrical insulation index parameters, and thermal insulation index parameters after cleaning. The embodiments of the present invention can avoid the interference of abnormal parameters on the life prediction of insulating materials by eliminating abnormal parameters from the electrical insulation process parameters, thermal insulation process parameters, electrical insulation index parameters, and thermal insulation index parameters, and can also avoid wasting computing resources due to excessive analysis of abnormal parameters during the life prediction process, thereby improving the prediction accuracy of the life of insulating materials and saving computing resources.

[0048] 204. Based on the electrical insulation process parameters during each radiation stage and their corresponding parameter collection time, construct the electrical insulation process time series data; based on the thermal insulation process parameters during each radiation stage and their corresponding parameter collection time, construct the thermal insulation process time series data; based on the electrical insulation index parameters after each radiation stage and their corresponding parameter collection time, determine the electrical insulation index time series data; based on the thermal insulation index parameters after each radiation stage and their corresponding parameter collection time, determine the thermal insulation index time series data.

[0049] Specifically, the parameter collection time corresponding to the electrical insulation process parameters, thermal insulation process parameters, electrical insulation index parameters, and thermal insulation index parameters in each radiation stage is determined respectively, and then based on the parameter collection time, the electrical insulation process time series data, thermal insulation process time series data, electrical insulation index time series data, and thermal insulation index time series data are determined respectively. Thus, by constructing the electrical insulation process time series data, thermal insulation process time series data, electrical insulation index time series data, and thermal insulation index time series data, that is, arranging various data in time series, it is possible to reveal the changing trends of various parameters over time, which is convenient for analyzing the aging trend of insulating materials.

[0050] 205. Determine the electrical insulation process characteristic vector corresponding to the electrical insulation process time series data, the thermal insulation process characteristic vector corresponding to the thermal insulation process time series data, the electrical insulation index characteristic vector corresponding to the electrical insulation index time series data, and the thermal insulation index characteristic vector corresponding to the thermal insulation index time series data.

[0051] Specifically, word embedding and other methods are used to determine the electrical insulation process feature vector corresponding to the electrical insulation process time series data, the thermal insulation process feature vector corresponding to the thermal insulation process time series data, the electrical insulation index feature vector corresponding to the electrical insulation index time series data, and the thermal insulation index feature vector corresponding to the thermal insulation index time series data.

[0052] 206. Perform cross processing on the electrical insulation process characteristic vector, the thermal insulation process characteristic vector, the electrical insulation index characteristic vector, and the thermal insulation index characteristic vector to obtain a cross aging characteristic vector.

[0053] In practical applications, the electrical insulation process time series data, the thermal insulation process time series data, the electrical insulation index time series data, and the thermal insulation index time series data belong to data of different dimensions, and need to be processed into data of the same latitude, that is, they are processed into electrical insulation process feature vectors, thermal insulation process feature vectors, and electrical insulation index feature vectors. Then, in order to extract more implicit features, it is necessary to cross-process the above-mentioned vectors. Based on this, step 206 specifically includes: multiplying each element in the electrical insulation process feature vector with the corresponding position element in the thermal insulation process feature vector to obtain an initial insulation process cross vector, and determining a process convolution transformation function and a process vector weight corresponding to the initial insulation process cross vector; based on the process vector weight, convolution the initial insulation process cross vector using the process convolution transformation function Product transformation to obtain an insulation process cross vector; multiply each element in the electrical insulation index feature vector with the corresponding position element in the thermal insulation index feature vector to obtain an initial insulation index cross vector, and determine the index convolution transformation function and index vector weight corresponding to the initial insulation index cross vector, based on the index vector weight, use the index convolution transformation function to perform convolution transformation on the initial insulation process cross vector to obtain an insulation index cross vector; perform element-level cross processing on the insulation process cross vector and the insulation index cross vector to obtain an element cross vector; perform low-order cross processing on the insulation process cross vector and the insulation index cross vector to obtain a low-order cross vector; use a preset transformation function to transform the element cross vector and the low-order cross vector to obtain a cross-aging feature vector.

[0054] The transformation function and vector weight are set according to actual needs. Specifically, for example, if the electrical insulation process characteristic vector is (a 1 ,a2 ,a 3 ), the characteristic vector of thermal insulation process is (b 1 ,b 2 ,b 3 ), the electrical insulation index characteristic vector is (c 1 ,c 2 ,c 3 ), the thermal insulation index characteristic vector is (d 1 ,d 2 ,d 3 ), firstly, the electrical insulation process feature vector and the thermal insulation process feature vector are crossed at the feature level, that is, all elements between the vectors are Hadamard products, and then convolution transformation is performed under certain weights. The insulation process cross vector obtained is f(w 1 *(a 1 *b 1 ,a 2 *b 2 ,a 3 *b 3 )), Similarly, the electrical insulation index feature vector and the thermal insulation index feature vector are crossed at the feature level, that is, all elements between the vectors are Hadamard products, and then convolution transformation is performed under certain weights. The insulation index cross vector obtained is f(w 2 *(c 1 *d 1 ,c 2 *d 2 ,c 3 *d 3 )), then the insulation process cross vector and the insulation index cross vector are subjected to element-level cross processing, that is, after each element between the vectors is subjected to Hadamard product, different weight values ​​are assigned to the result after each product, and then a linear transformation is performed, and the obtained element cross vector is f(w 3 (w 1 *a 1 *b 1 *w 2 *c 1 *d 1 ),w 4 (w 1 *a 2 *b 2 *w 2 *c 2 *d 2 ),w 5 (w 1 *a 3 *b 3 *w 2 *c 3 *d 3)), and perform low-order cross processing on the insulation process cross vector and the insulation index cross vector, that is, horizontally splice the insulation process cross vector and the insulation index cross vector to obtain a low-order cross vector f(w 1 *(a 1 *b 1 ,a 2 *b 2 ,a 3 *b 3 ), w 2 *(c 1 *d 1 ,c 2 *d 2 ,c 3 *d 3 )), and finally utilize the preset transformation function to transform the element cross vector and the low-order cross vector together to obtain the cross-aging feature vector, wherein the preset transformation function can be set according to the actual situation, and this embodiment does not limit this. Thus, by cross-processing the electrical insulation process feature vector, the thermal insulation process feature vector, the electrical insulation index feature vector, and the thermal insulation index feature vector, different features can be automatically or explicitly combined to generate new feature combinations. These combined features may contain complex nonlinear relationships between the original features, so that the model can capture more detailed and rich information in the data, that is, it can make full use of the relationship between various data, extract more implicit features, and take into account both high-order and low-order processing, so that data utilization is more sufficient, and the life prediction results obtained later are more accurate, meeting the needs of actual application scenarios.

[0055] 207. Input the cross-aging feature vector into a preset life prediction model to perform life prediction, and obtain the insulation life of the insulation material to be predicted.

[0056] For the embodiment of the present invention, in order to improve the prediction accuracy of the preset life prediction model, it is first necessary to train and construct the preset life prediction model. Based on this, the method includes: constructing multiple preset initial life prediction models; obtaining a sample data set corresponding to the sample insulation material, wherein the sample data set includes sample electrical insulation process parameters and sample thermal insulation process parameters of the sample insulation material in each working time period under the actual hot chamber high-voltage working condition, as well as sample electrical insulation index parameters and sample thermal insulation index parameters after each working time period, and the actual life of the sample insulation material; based on the number of models of the preset initial life prediction model, dividing the sample data set into multiple groups of training data and multiple groups of test data; using each group of training data to predict the corresponding preset initial life The model is trained to obtain a trained preset initial life prediction model, wherein during the training process, the sample electrical insulation process parameters of each working time period, the sample thermal insulation process parameters, the sample electrical insulation index parameters after each working time period, and the sample thermal insulation index parameters in the training data are used as input data, and the actual life is used as output data; each group of test data is used to test the corresponding trained preset initial life prediction model to obtain the test result, and based on the test result, the prediction accuracy corresponding to each of the trained preset initial life prediction models is determined; a target preset initial life prediction model with the maximum prediction accuracy is determined among each of the trained preset initial life prediction models, and the target preset initial life prediction model is determined as the preset life prediction model.

[0057] Among them, the sample electrical insulation process parameters in the sample data set include: leakage current amplitude, leakage current frequency, local discharge amplitude, local discharge phase, local discharge number, temperature value, etc. of the sample insulation material in the actual hot chamber working environment; the sample thermal insulation process parameters include: color, quality, shape, and roughness of the sample insulation material in the actual hot chamber working environment; the sample electrical insulation index parameters include: insulation resistance value and dielectric loss factor of the sample insulation material in the actual hot chamber working environment; the sample thermal insulation index parameters include: temperature index, relative temperature index, tensile strength, elongation at break, density, hardness, etc. of the sample insulation material in the actual hot chamber working environment.

[0058] Specifically, multiple preset initial life prediction models can be constructed based on a very deep factorization machine model, which includes a linear module and a deep neural network module. The model structures of the multiple preset initial life prediction models can be the same or different. When training and constructing a life prediction model, first obtain a sample data set, and divide the sample data set into multiple groups of training data and multiple groups of test data according to the number of preset initial life prediction models. For example, the preset initial life prediction model includes: model 1, model 2, and model 3; the divided training data includes: training data 1, training data 2, and training data 3; the divided test data includes: test data 1, test data 2, and test data 3; use training data 1 to train model 1, use training data 2 to train model 2, and use training data 3 to train model 3, then use test data 1 to test the trained model 1, use test data 2 to test the trained model 2, and use test data 3 to test the trained model 3. Finally, according to the test results, select the model with the highest test prediction accuracy as the preset life prediction model, and then input the cross-aging feature vector into the preset life prediction model for life prediction, and obtain the insulation life of the insulating material to be predicted, thereby improving the prediction accuracy of the insulation material life.

[0059] According to another insulation material life prediction method provided by the present invention, compared with the current method of evaluating the life of insulation materials based on a single factor aging condition, the present invention constructs an aging test system, and sets the thermal stress environment conditions such as temperature and humidity required for the aging test for the thermal aging test space in the aging test system. On this basis, a multi-stage pulse voltage is applied to the insulation material to be predicted in the thermal aging test space for radiation, and the electrical insulation process parameters and thermal insulation process parameters in each radiation process, as well as the electrical insulation index parameters and thermal insulation index parameters after each radiation stage are collected. Finally, based on the electrical insulation process parameters, thermal insulation process parameters, electrical insulation index parameters, and thermal insulation index parameters corresponding to each radiation stage, the insulation life of the insulation material to be predicted is determined, thereby constructing an aging test system, and implementing aging tests on the insulation material under temperature aging conditions, humidity aging conditions, and voltage aging conditions through the aging test system, that is, in the aging test process, a comprehensive analysis of the various influencing factors affecting the life of the insulation material and the coupling relationship between the various factors is performed, which can improve the prediction accuracy of the insulation material life, thereby ensuring that the predicted insulation material life is more valuable for reference in engineering practice.

[0060] Further, as Figure 1 In a specific implementation, an embodiment of the present invention provides an insulating material life prediction device, which is applied to an aging test system. The aging test system includes a pulse generating device, a thermal aging test space, an insulation process parameter measuring device, and an insulation index parameter measuring device. Figure 4 As shown, the device includes: a setting unit 31, an aging test unit 32, and a determination unit 33.

[0061] The setting unit 31 can be used to set the preset environmental conditions required for the test for the thermal aging test space containing the insulating material to be predicted, wherein the preset environmental conditions include temperature conditions and humidity conditions, wherein the preset environmental conditions are determined based on the actual working hot chamber environment corresponding to the insulating material to be predicted, and the number of insulating materials to be predicted is multiple.

[0062] The aging test unit 32 can be used to control the pulse generating device to sequentially apply a pulse voltage of a multi-stage preset frequency, preset amplitude, and preset duty cycle to the insulating material to be predicted in the thermal aging test space, so as to utilize the pulse voltage to sequentially perform multi-stage radiation on the insulating material to be predicted, control the insulation process parameter measuring device to collect the electrical insulation process parameters and thermal insulation process parameters of the insulating material to be predicted in real time during each radiation stage, and control the insulation index parameter measuring device to collect the electrical insulation index parameters and thermal insulation index parameters of the insulating material to be predicted after each radiation stage, wherein the pulse voltage in each radiation stage has the same preset frequency, the same preset amplitude, the same preset duty cycle, the same radiation duration, and the same voltage waveform.

[0063] The determination unit 33 may be used to determine the insulation life of the insulation material to be predicted based on the electrical insulation process parameters and the thermal insulation process parameters during each radiation stage, and the electrical insulation index parameters and the thermal insulation index parameters after each radiation stage.

[0064] In a specific application scenario, in order to determine the insulation life of the insulation material to be predicted, such as Figure 5 As shown, the determination unit 33 includes a judgment module 331 , an acquisition module 332 , and a determination module 333 .

[0065] The judgment module 331 can be used to judge whether the insulation material to be predicted meets the preset conditions for life prediction based on the electrical insulation process parameters and the thermal insulation process parameters during each radiation stage.

[0066] The acquisition module 332 can be used to obtain control electrical insulation index parameters and control thermal insulation index parameters of a control insulation material in a normal state that has not been irradiated with pulse voltage and heat, if the insulation material to be predicted meets the preset conditions, wherein the material properties of the control insulation material are the same as the material properties of the insulation material to be predicted before the aging test, and the material properties include material type, shape and size, hardness, density, elastic modulus, and mechanical strength.

[0067] The determination module 333 may be used to determine the aging status data of the insulation material to be predicted based on the reference electrical insulation index parameter and the electrical insulation index parameter, and the reference thermal insulation index parameter and the thermal insulation index parameter.

[0068] In a specific application scenario, the electrical insulation process parameters include: leakage current amplitude, leakage current frequency, partial discharge amplitude, partial discharge phase, number of partial discharges, and temperature value; the thermal insulation process parameters include: color, quality, shape, and roughness; in order to determine whether the insulation material to be predicted meets the preset conditions for life prediction, the judgment module 331 can be specifically used to determine whether the insulation material to be predicted has insulation defects based on the leakage current amplitude, leakage current frequency, partial discharge amplitude, partial discharge phase, number of partial discharges, and temperature value, wherein the specific judgment method includes: determining whether the leakage current amplitude is greater than a preset current amplitude threshold, determining whether the leakage current frequency is greater than a preset frequency threshold, determining whether the partial discharge amplitude is greater than a preset partial discharge amplitude threshold, determining whether the partial discharge phase is greater than a preset phase threshold, determining whether the number of partial discharges is greater than a preset number threshold, and determining whether the temperature value is greater than a preset temperature threshold. If the leakage current amplitude is greater than the preset current amplitude threshold, the leakage current frequency is greater than the preset frequency threshold, the partial discharge amplitude is greater than the preset partial discharge amplitude threshold, and the partial discharge phase is greater than the preset phase threshold, the partial discharge amplitude is greater than the preset partial discharge amplitude threshold, and the partial discharge phase is greater than the preset phase threshold, the partial discharge amplitude is greater than the preset partial discharge amplitude threshold, and the partial discharge phase is greater than the preset phase threshold. value, the number of partial discharges is greater than the preset number threshold, and the temperature value is greater than the preset temperature threshold, then it is determined that the insulating material to be predicted has insulation defects; based on the color, quality, shape, and roughness, it is determined whether the insulating material to be predicted has appearance defects, wherein the specific judgment method includes: determining whether the color difference between the color of the insulating material to be predicted and the standard color is greater than the preset color difference threshold, determining whether the quality difference between the quality and the standard quality is greater than the preset quality threshold, determining whether the appearance difference between the appearance and the standard appearance is greater than the preset appearance threshold, and determining whether the roughness difference between the roughness and the marked roughness is greater than the preset roughness threshold; if the color difference is greater than the preset color difference threshold, the quality difference is greater than the preset quality threshold, the appearance difference is greater than the preset appearance threshold, and the roughness difference is greater than the preset roughness threshold, then it is determined that the insulating material to be predicted has appearance defects; if the insulating material to be predicted has at least one of insulation defects and appearance defects, then it is determined that the insulating material to be predicted does not meet the preset conditions for life prediction; if the insulating material to be predicted does not have insulation defects and appearance defects, then it is determined that the insulating material to be predicted meets the preset conditions for life prediction.

[0069] In a specific application scenario, in order to determine the insulation life of the insulating material to be predicted, the determination unit 33 further includes a construction module 334 , a cross processing module 335 , and a prediction module 336 .

[0070] The construction module 334 can be used to construct electrical insulation process time series data based on the electrical insulation process parameters and their corresponding parameter collection time during each radiation stage, to construct thermal insulation process time series data based on the thermal insulation process parameters and their corresponding parameter collection time during each radiation stage, to determine electrical insulation index time series data based on the electrical insulation index parameters and their corresponding parameter collection time after the end of each radiation stage, and to determine thermal insulation index time series data based on the thermal insulation index parameters and their corresponding parameter collection time after the end of each radiation stage.

[0071] The determination module 333 can also be used to determine the electrical insulation process characteristic vector corresponding to the electrical insulation process time series data, the thermal insulation process characteristic vector corresponding to the thermal insulation process time series data, the electrical insulation index characteristic vector corresponding to the electrical insulation index time series data, and the thermal insulation index characteristic vector corresponding to the thermal insulation index time series data.

[0072] The cross-processing module 335 may be used to perform cross-processing on the electrical insulation process feature vector, the thermal insulation process feature vector, the electrical insulation index feature vector, and the thermal insulation index feature vector to obtain a cross-aging feature vector.

[0073] The prediction module 336 may be used to input the cross-aging feature vector into a preset life prediction model to perform life prediction, and obtain the insulation life of the insulation material to be predicted.

[0074] In a specific application scenario, in order to perform cross-processing on the electrical insulation process characteristic vector, the thermal insulation process characteristic vector, the electrical insulation index characteristic vector, and the thermal insulation index characteristic vector, the cross-processing module 335 can be specifically used to multiply each element in the electrical insulation process characteristic vector with the corresponding position element in the thermal insulation process characteristic vector to obtain an initial insulation process cross vector, and determine the process convolution transformation function and process vector weight corresponding to the initial insulation process cross vector; based on the process vector weight, the initial insulation process cross vector is convoluted using the process convolution transformation function to obtain an insulation process cross vector; each element in the electrical insulation index characteristic vector is multiplied with the thermal insulation process characteristic vector; The elements at corresponding positions in the indicator feature vector are multiplied to obtain an initial insulation indicator cross vector, and the indicator convolution transformation function and the indicator vector weight corresponding to the initial insulation indicator cross vector are determined. Based on the indicator vector weight, the initial insulation process cross vector is convoluted using the indicator convolution transformation function to obtain an insulation indicator cross vector; element-level cross processing is performed on the insulation process cross vector and the insulation indicator cross vector to obtain an element cross vector; low-order cross processing is performed on the insulation process cross vector and the insulation indicator cross vector to obtain a low-order cross vector; the element cross vector and the low-order cross vector are transformed using a preset transformation function to obtain a cross-aging feature vector.

[0075] In a specific application scenario, in order to preset an initial life prediction model, the construction module 334 can also be used to construct multiple preset initial life prediction models; obtain a sample data set corresponding to the sample insulation material, wherein the sample data set includes sample electrical insulation process parameters and sample thermal insulation process parameters of the sample insulation material in each working time period under the actual hot chamber high-voltage working condition, as well as sample electrical insulation index parameters and sample thermal insulation index parameters after each working time period, and the actual life of the sample insulation material; based on the number of models of the preset initial life prediction model, divide the sample data set into multiple groups of training data and multiple groups of test data; use each group of training data to train the corresponding preset initial life prediction model to obtain A trained preset initial life prediction model, wherein during the training process, sample electrical insulation process parameters of each working time period, sample thermal insulation process parameters, sample electrical insulation index parameters after each working time period, and sample thermal insulation index parameters in the training data are used as input data, and the actual life is used as output data; each group of test data is used to test the corresponding trained preset initial life prediction model to obtain the test result, and based on the test result, the prediction accuracy corresponding to each of the trained preset initial life prediction models is determined; a target preset initial life prediction model with the maximum prediction accuracy is determined among each of the trained preset initial life prediction models, and the target preset initial life prediction model is determined as the preset life prediction model.

[0076] In a specific application scenario, in order to determine abnormal parameters, the device further includes: a parameter cleaning unit 34.

[0077] The parameter cleaning unit 34 can be specifically used to respectively use the electrical insulation process parameters, thermal insulation process parameters, electrical insulation index parameters, and thermal insulation index parameters corresponding to each radiation stage as target parameters, and to count the data density within a preset neighborhood corresponding to any parameter in each of the target parameters; if the data density is greater than a preset density threshold, the arbitrary parameter is determined as a clustering center; based on the clustering center, each of the target parameters is clustered to obtain a clustering result; the target parameter that does not belong to any cluster in the clustering result is determined as an abnormal parameter; the abnormal parameter is eliminated from each of the target parameters to obtain the cleaned electrical insulation process parameters, thermal insulation process parameters, electrical insulation index parameters, and thermal insulation index parameters.

[0078] It should be noted that for other corresponding descriptions of the functional modules involved in the insulating material life prediction device provided in the embodiment of the present invention, reference can be made to Figure 1 The corresponding description of the method shown will not be repeated here.

[0079] Based on the above Figure 1The method shown, accordingly, an embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the following steps are implemented: applied to an aging test system, the aging test system includes a pulse generating device, a thermal aging test space, an insulation process parameter measuring device, and an insulation index parameter measuring device, including:

[0080] The preset environmental conditions required for the test are set for the thermal aging test space containing the insulating material to be predicted, wherein the preset environmental conditions include temperature conditions and humidity conditions, and the preset environmental conditions are determined according to the actual working thermal chamber environment corresponding to the insulating material to be predicted, and the number of the insulating materials to be predicted is multiple; the pulse generating device is controlled to sequentially apply pulse voltages of multiple stages of preset frequency, preset amplitude, and preset duty cycle to the insulating material to be predicted in the thermal aging test space, so as to sequentially perform multiple stages of radiation on the insulating material to be predicted by using the pulse voltage; the insulation process parameter measuring device is controlled to collect the electrical insulation process parameters and thermal insulation process parameters of the insulating material to be predicted in real time during each radiation stage, and the insulation index parameter measuring device is controlled to collect the electrical insulation index parameters and thermal insulation index parameters of the insulating material to be predicted after each radiation stage, wherein the pulse voltage in each radiation stage has the same preset frequency, the same preset amplitude, the same preset duty cycle, the same radiation duration, and the same voltage waveform; based on the electrical insulation process parameters and thermal insulation process parameters during each radiation stage, and the electrical insulation index parameters and thermal insulation index parameters after each radiation stage, the insulation life of the insulating material to be predicted is determined.

[0081] Based on the above Figure 1 The method shown and Figure 4 The embodiment of the device shown in the figure, the embodiment of the present invention also provides a physical structure diagram of a computer device, such as Figure 6 As shown, the computer device includes: a processor 41, a memory 42, and a computer program stored in the memory 42 and executable on the processor, wherein the memory 42 and the processor 41 are both arranged on a bus 43, and the processor 41 implements the following steps when executing the program: applied to an aging test system, the aging test system includes a pulse generating device, a thermal aging test space, an insulation process parameter measuring device, and an insulation index parameter measuring device, including:

[0082] The preset environmental conditions required for the test are set for the thermal aging test space containing the insulating material to be predicted, wherein the preset environmental conditions include temperature conditions and humidity conditions, and the preset environmental conditions are determined according to the actual working thermal chamber environment corresponding to the insulating material to be predicted, and the number of the insulating materials to be predicted is multiple; the pulse generating device is controlled to sequentially apply pulse voltages of multiple stages of preset frequency, preset amplitude, and preset duty cycle to the insulating material to be predicted in the thermal aging test space, so as to sequentially perform multiple stages of radiation on the insulating material to be predicted by using the pulse voltage; the insulation process parameter measuring device is controlled to collect the electrical insulation process parameters and thermal insulation process parameters of the insulating material to be predicted in real time during each radiation stage, and the insulation index parameter measuring device is controlled to collect the electrical insulation index parameters and thermal insulation index parameters of the insulating material to be predicted after each radiation stage, wherein the pulse voltage in each radiation stage has the same preset frequency, the same preset amplitude, the same preset duty cycle, the same radiation duration, and the same voltage waveform; based on the electrical insulation process parameters and thermal insulation process parameters during each radiation stage, and the electrical insulation index parameters and thermal insulation index parameters after each radiation stage, the insulation life of the insulating material to be predicted is determined.

[0083] Through the technical scheme of the present invention, the present invention constructs an aging test system, and sets the thermal stress environmental conditions such as temperature and humidity required for the aging test for the thermal aging test space in the aging test system. On this basis, a multi-stage pulse voltage is applied to the insulation material to be predicted in the thermal aging test space for radiation, and the electrical insulation process parameters and thermal insulation process parameters in each radiation process, as well as the electrical insulation index parameters and thermal insulation index parameters after each radiation stage are collected. Finally, based on the electrical insulation process parameters, thermal insulation process parameters, electrical insulation index parameters, and thermal insulation index parameters corresponding to each radiation stage, the insulation life of the insulation material to be predicted is determined, thereby constructing an aging test system, and implementing aging tests on the insulation material under temperature aging conditions, humidity aging conditions, and voltage aging conditions through the aging test system, that is, in the aging test process, a comprehensive analysis of the various influencing factors affecting the life of the insulation material and the coupling relationship between the various factors is performed, which can improve the prediction accuracy of the life of the insulation material, thereby ensuring that the predicted life of the insulation material is more valuable for reference in engineering practice.

[0084] Obviously, those skilled in the art should understand that the above modules or steps of the present invention can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, and optionally, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order than here, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0085] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for predicting the life of an insulating material, characterized in that: Applied to an aging test system, the aging test system includes a pulse generating device, a thermal aging test space, an insulation process parameter measuring device, and an insulation index parameter measuring device, including: Setting the preset environmental conditions required for the test for the thermal aging test space containing the insulation material to be predicted, wherein the preset environmental conditions include temperature conditions and humidity conditions, and the preset environmental conditions are determined according to the actual working thermal chamber environment corresponding to the insulation material to be predicted, and the number of insulation materials to be predicted is multiple; Control the pulse generating device to sequentially apply a pulse voltage of a preset frequency, preset amplitude, and preset duty cycle in multiple stages to the insulation material to be predicted in the thermal aging test space, so as to sequentially perform multi-stage radiation on the insulation material to be predicted by using the pulse voltage, control the insulation process parameter measuring device to collect the electrical insulation process parameters and thermal insulation process parameters of the insulation material to be predicted in real time during each radiation stage, and control the insulation index parameter measuring device to collect the electrical insulation index parameters and thermal insulation index parameters of the insulation material to be predicted after each radiation stage, wherein the pulse voltage in each radiation stage has the same preset frequency, the same preset amplitude, the same preset duty cycle, the same radiation duration, and the same voltage waveform; Based on the electrical insulation process parameters and thermal insulation process parameters during each radiation stage, and the electrical insulation index parameters and thermal insulation index parameters after each radiation stage, the insulation life of the insulation material to be predicted is determined.

2. The method according to claim 1, characterized in that Determining the insulation life of the insulation material to be predicted based on the electrical insulation process parameters and the thermal insulation process parameters during each radiation stage, and the electrical insulation index parameters and the thermal insulation index parameters after each radiation stage, comprises: Based on the electrical insulation process parameters and the thermal insulation process parameters in each radiation stage, determining whether the insulation material to be predicted meets the preset conditions for life prediction; If the insulation material to be predicted meets the preset conditions, then obtain the control electrical insulation index parameters and control thermal insulation index parameters of the control insulation material in a normal state that has not been irradiated with pulse voltage and heat, wherein the material properties of the control insulation material are the same as the material properties of the insulation material to be predicted before the aging test, and the material properties include material type, shape and size, hardness, density, elastic modulus, and mechanical strength; Based on the reference electrical insulation index parameter and the electrical insulation index parameter, as well as the reference thermal insulation index parameter and the thermal insulation index parameter, the aging state data of the insulation material to be predicted is determined.

3. The method according to claim 2, characterized in that The electrical insulation process parameters include: leakage current amplitude, leakage current frequency, partial discharge amplitude, partial discharge phase, partial discharge number, temperature value; the thermal insulation process parameters include: color, quality, shape, roughness; The step of judging whether the insulation material to be predicted meets the preset conditions for life prediction based on the electrical insulation process parameters and the thermal insulation process parameters in each radiation stage includes: Based on the leakage current amplitude, leakage current frequency, partial discharge amplitude, partial discharge phase, number of partial discharges, and temperature value, it is judged whether the insulation material to be predicted has insulation defects, wherein the specific judgment method includes: judging whether the leakage current amplitude is greater than a preset current amplitude threshold, judging whether the leakage current frequency is greater than a preset frequency threshold, judging whether the partial discharge amplitude is greater than a preset partial discharge amplitude threshold, judging whether the partial discharge phase is greater than a preset phase threshold, judging whether the number of partial discharges is greater than a preset number threshold, and judging whether the temperature value is greater than a preset temperature threshold. If the leakage current amplitude is greater than the preset current amplitude threshold, the leakage current frequency is greater than the preset frequency threshold, the partial discharge amplitude is greater than the preset partial discharge amplitude threshold, the partial discharge phase is greater than the preset phase threshold, the number of partial discharges is greater than the preset number threshold, and the temperature value is greater than the preset temperature threshold, it is judged that the insulation material to be predicted has insulation defects; Based on the color, quality, shape, and roughness, determine whether the insulating material to be predicted has appearance defects, wherein the specific determination method includes: determining whether the color difference between the color of the insulating material to be predicted and the standard color is greater than a preset color difference threshold, determining whether the quality difference between the quality and the standard quality is greater than a preset quality threshold, determining whether the appearance difference between the appearance and the standard appearance is greater than a preset appearance threshold, determining whether the roughness difference between the roughness and the marked roughness is greater than a preset roughness threshold, if the color difference is greater than the preset color difference threshold, the quality difference is greater than the preset quality threshold, the appearance difference is greater than the preset appearance threshold, and the roughness difference is greater than the preset roughness threshold, then it is determined that the insulating material to be predicted has appearance defects; If the insulation material to be predicted has at least one of an insulation defect and an appearance defect, it is determined that the insulation material to be predicted does not meet the preset conditions for life prediction; If the insulating material to be predicted does not have insulation defects and appearance defects, it is determined that the insulating material to be predicted meets the preset conditions for life prediction.

4. The method according to claim 1, characterized in that: Determining the insulation life of the insulation material to be predicted based on the electrical insulation process parameters and the thermal insulation process parameters during each radiation stage, and the electrical insulation index parameters and the thermal insulation index parameters after each radiation stage, comprises: Based on the electrical insulation process parameters during each radiation stage and their corresponding parameter collection time, the electrical insulation process time series data is constructed; based on the thermal insulation process parameters during each radiation stage and their corresponding parameter collection time, the thermal insulation process time series data is constructed; based on the electrical insulation index parameters after each radiation stage and their corresponding parameter collection time, the electrical insulation index time series data is determined; based on the thermal insulation index parameters after each radiation stage and their corresponding parameter collection time, the thermal insulation index time series data is determined; Determine an electrical insulation process characteristic vector corresponding to the electrical insulation process time series data, a thermal insulation process characteristic vector corresponding to the thermal insulation process time series data, an electrical insulation index characteristic vector corresponding to the electrical insulation index time series data, and a thermal insulation index characteristic vector corresponding to the thermal insulation index time series data; Cross-processing the electrical insulation process characteristic vector, the thermal insulation process characteristic vector, the electrical insulation index characteristic vector, and the thermal insulation index characteristic vector to obtain a cross-aging characteristic vector; The cross-aging feature vector is input into a preset life prediction model to perform life prediction, so as to obtain the insulation life of the insulation material to be predicted.

5. The method according to claim 4, characterized in that The cross-processing of the electrical insulation process characteristic vector, the thermal insulation process characteristic vector, the electrical insulation index characteristic vector, and the thermal insulation index characteristic vector to obtain the cross-aging characteristic vector includes: Multiply each element in the electrical insulation process characteristic vector with the element at the corresponding position in the thermal insulation process characteristic vector to obtain an initial insulation process cross vector, determine a process convolution transformation function and a process vector weight corresponding to the initial insulation process cross vector, and based on the process vector weight, perform a convolution transformation on the initial insulation process cross vector using the process convolution transformation function to obtain an insulation process cross vector; Multiply each element in the electrical insulation index characteristic vector with the element at the corresponding position in the thermal insulation index characteristic vector to obtain an initial insulation index cross vector, and determine the index convolution transformation function and the index vector weight corresponding to the initial insulation index cross vector, and based on the index vector weight, use the index convolution transformation function to perform a convolution transformation on the initial insulation process cross vector to obtain an insulation index cross vector; Performing element-level cross processing on the insulation process cross vector and the insulation index cross vector to obtain an element cross vector; Performing low-order cross processing on the insulation process cross vector and the insulation index cross vector to obtain a low-order cross vector; The element cross vector and the low-order cross vector are transformed by using a preset transformation function to obtain a cross aging feature vector.

6. The method according to claim 4, characterized in that Before inputting the cross-aging feature vector into a preset life prediction model to perform life prediction and obtain the insulation life of the insulation material to be predicted, the method further includes: Construct multiple preset initial life prediction models; Acquire a sample data set corresponding to the sample insulation material, wherein the sample data set includes sample electrical insulation process parameters and sample thermal insulation process parameters of the sample insulation material in each working time period under the actual hot chamber high pressure working condition, as well as sample electrical insulation index parameters and sample thermal insulation index parameters after each working time period, and the actual life of the sample insulation material; Based on the number of models of the preset initial life prediction model, dividing the sample data set into multiple groups of training data and multiple groups of test data; Using each group of training data to train the corresponding preset initial life prediction model, a trained preset initial life prediction model is obtained, wherein during the training process, sample electrical insulation process parameters of each working time period, sample thermal insulation process parameters, sample electrical insulation index parameters after each working time period in the training data, and sample thermal insulation index parameters are used as input data, and the actual life is used as output data; Using each group of test data to test the corresponding trained preset initial life prediction model to obtain test results, and based on the test results, determine the prediction accuracy corresponding to each of the trained preset initial life prediction models; A target preset initial life prediction model with the maximum prediction accuracy is determined among the trained preset initial life prediction models, and the target preset initial life prediction model is determined as the preset life prediction model.

7. The method according to claim 1, characterized in that Before determining the insulation life of the insulation material to be predicted based on the electrical insulation process parameters and the thermal insulation process parameters during each radiation stage, and the electrical insulation index parameters and the thermal insulation index parameters after each radiation stage, the method further includes: The electrical insulation process parameters, thermal insulation process parameters, electrical insulation index parameters, and thermal insulation index parameters corresponding to each radiation stage are respectively used as target parameters, and the data density within a preset neighborhood corresponding to any parameter of each of the target parameters is counted; If the data density is greater than a preset density threshold, determining the arbitrary parameter as a cluster center; Based on the cluster centers, clustering the target parameters to obtain clustering results; Determine the target parameter that does not belong to any cluster in the clustering result as an abnormal parameter; The abnormal parameters are eliminated from each of the target parameters to obtain the electrical insulation process parameters, thermal insulation process parameters, electrical insulation index parameters, and thermal insulation index parameters after cleaning.

8. An insulating material life prediction device, characterized in that: Applied to an aging test system, the aging test system includes a pulse generating device, a thermal aging test space, an insulation process parameter measuring device, and an insulation index parameter measuring device, including: A setting unit, used for setting preset environmental conditions required for the test for the thermal aging test space containing the insulation material to be predicted, wherein the preset environmental conditions include temperature conditions and humidity conditions, wherein the preset environmental conditions are determined according to the actual working thermal chamber environment corresponding to the insulation material to be predicted, and the number of the insulation materials to be predicted is multiple; An aging test unit, used to control the pulse generating device to sequentially apply a pulse voltage of a preset frequency, preset amplitude, and preset duty cycle to the insulating material to be predicted in the thermal aging test space, so as to sequentially perform multi-stage radiation on the insulating material to be predicted using the pulse voltage, control the insulation process parameter measuring device to collect in real time the electrical insulation process parameters and thermal insulation process parameters of the insulating material to be predicted during each radiation stage, and control the insulation index parameter measuring device to collect the electrical insulation index parameters and thermal insulation index parameters of the insulating material to be predicted after each radiation stage, wherein the pulse voltage in each radiation stage has the same preset frequency, the same preset amplitude, the same preset duty cycle, the same radiation duration, and the same voltage waveform; The determination unit is used to determine the insulation life of the insulation material to be predicted based on the electrical insulation process parameters and thermal insulation process parameters during each radiation stage, and the electrical insulation index parameters and thermal insulation index parameters after each radiation stage.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images