Motor insulation monitoring method and device, electronic equipment and storage medium

Abstract

This application relates to the fields of insulation monitoring and artificial intelligence technology, and discloses a method, device, electronic device, and storage medium for monitoring motor insulation. The method includes: collecting insulation state parameters of a low-voltage motor; inputting the maximum partial discharge quantity and motor operating temperature into a main insulation degradation prediction model to obtain the pseudo-failure lifetime of the motor; wherein the main insulation degradation prediction model is pre-established based on the Wiener process, using the maximum partial discharge quantity as the degradation characteristic quantity of the motor's main insulation material, and combining the Arrhenius model to extrapolate the parameter estimates at high temperatures to room temperature, thereby establishing a calculation model for the quantitative relationship between the maximum partial discharge quantity, motor operating temperature, and the pseudo-failure lifetime of the main insulation; inputting the motor operating temperature and vibration signal into a stator remaining lifetime prediction model, and outputting the predicted value of the motor stator's remaining lifetime; wherein the stator remaining lifetime prediction model is a calculation model pre-fitted with Weibull distribution parameters based on a two-parameter Weibull distribution, and combined with an inverse power law formula to establish a quantitative relationship between the motor operating temperature, vibration signal, and stator insulation lifetime; and real-time monitoring of the pseudo-failure lifetime of the motor's main insulation material and the remaining predicted lifetime of the stator, generating monitoring results. This application improves prediction accuracy and achieves fault early warning.

Description

Technical Field

[0001] This application relates to the fields of insulation monitoring and artificial intelligence technology, and more specifically, to a method, device, electronic device, and storage medium for monitoring motor insulation. Background Technology

[0002] Low-voltage motors, as core drive components in modern industry and civil applications, are widely used in household appliances, information technology products, and automotive systems. Their operational reliability directly affects equipment safety and production efficiency. The motor insulation system, as a weak point in the motor structure, is subjected to the combined effects of electrical, thermal, mechanical, and environmental stresses over a long period, making it prone to aging, deterioration, and even breakdown failures, which can lead to equipment downtime or fires. Therefore, accurate monitoring and lifespan prediction of motor insulation has significant engineering value and safety implications.

[0003] However, traditional detection methods mostly rely on periodic offline measurements of insulation resistance or leakage current, which makes it difficult to capture the weak signal changes in the early stages of insulation aging and to provide early warning of faults. They are often only detected after the insulation performance has significantly deteriorated or even after signs of fault appear. Summary of the Invention

[0004] In view of the above situation, this application provides a method, device, electronic device and storage medium for monitoring motor insulation, which aims to solve the above problems or at least partially solve the above problems.

[0005] In a first aspect, embodiments of this application provide a method for monitoring motor insulation, the method comprising: The insulation status parameters of the low-voltage motor are collected, including at least the maximum partial discharge, insulation resistance, motor operating temperature, ambient humidity and vibration signal. The maximum partial discharge quantity and the motor operating temperature are input into the main insulation degradation prediction model to obtain the pseudo-failure lifetime of the motor. The main insulation degradation prediction model is pre-established based on the Wiener process, uses the maximum partial discharge quantity as the degradation characteristic quantity of the motor's main insulation material, and combines the Arrhenius model to extrapolate the parameter estimates at high temperature to room temperature, so as to establish a calculation model for the quantitative relationship between the maximum partial discharge quantity, the motor operating temperature and the pseudo-failure lifetime of the main insulation. The motor operating temperature and vibration signal are input into the stator remaining life prediction model, and the predicted value of the motor stator remaining life is output; wherein, the stator remaining life prediction model is a calculation model that is pre-fitted with Weibull distribution parameters based on a two-parameter Weibull distribution and combined with an inverse power law formula to establish a quantitative relationship between the motor operating temperature and vibration signal and the stator insulation life; The pseudo-failure lifetime of the main insulation material of the motor and the remaining predicted lifetime of the stator are monitored in real time, and monitoring results are generated.

[0006] Secondly, embodiments of this application also provide a motor insulation monitoring device, the device comprising: The acquisition module is used to acquire insulation status parameters of the low-voltage motor. The insulation status parameters include at least the maximum partial discharge, insulation resistance, motor operating temperature, ambient humidity, and vibration signal. The prediction module is used to input the maximum partial discharge quantity and the motor operating temperature into the main insulation degradation prediction model to obtain the pseudo-failure lifetime of the motor. The main insulation degradation prediction model is pre-established based on the Wiener process, using the maximum partial discharge quantity as the degradation characteristic quantity of the motor's main insulation material, and combining the Arrhenius model to extrapolate the parameter estimates at high temperature to room temperature, so as to establish a calculation model for the quantitative relationship between the maximum partial discharge quantity, the motor operating temperature and the pseudo-failure lifetime of the main insulation. The prediction module is also used to input the motor operating temperature and vibration signal into the stator remaining life prediction model and output the predicted value of the motor stator remaining life; wherein, the stator remaining life prediction model is a calculation model that is pre-fitted with Weibull distribution parameters based on a two-parameter Weibull distribution and combined with an inverse power law formula to establish a quantitative relationship between the motor operating temperature and vibration signal and the stator insulation life; The monitoring module is used to monitor the pseudo-failure lifetime of the main insulation material of the motor and the remaining predicted lifetime of the stator in real time, and generate monitoring results.

[0007] Thirdly, embodiments of this application also provide an electronic device, including: a processor; and a memory arranged to store computer-executable instructions, which, when executed, cause the processor to perform the steps described in the first aspect.

[0008] Fourthly, embodiments of this application also provide a computer-readable storage medium that stores one or more programs, which, when executed by an electronic device including multiple applications, cause the electronic device to perform the steps described in the first aspect.

[0009] The above-mentioned technical solutions adopted in this application embodiment can achieve the following beneficial effects: By collecting multi-dimensional insulation state parameters such as maximum partial discharge, insulation resistance, operating temperature, ambient humidity, and vibration signals, a comprehensive perception of the motor insulation health status is achieved, effectively overcoming the shortcomings of traditional single-parameter monitoring that is susceptible to interference and has a high misjudgment rate, and significantly improving the ability to capture early weak abnormal signals; on this basis, the method innovatively combines the degradation model based on the Wiener process with the Arrhenius model, using the maximum partial discharge as the key characteristic quantity of the main insulation material degradation, and extrapolating the high-temperature accelerated degradation test data to the normal temperature operating condition, thereby accurately calculating the pseudo-failure lifetime of the motor main insulation material without relying on long-term measured data, solving the technical problem that existing methods are difficult to quantitatively predict the long-term life of insulation materials at room temperature; at the same time, the method further adopts a two-parameter Wiener process... The method uses Boolean distribution to fit the stator insulation life distribution law and combines it with the inverse power law formula to establish a quantitative relationship model between operating temperature, vibration signal and stator insulation life. It can output the stator remaining life prediction value in real time, thus taking into account the comprehensive impact of thermal stress and mechanical stress on insulation aging. Compared with the traditional prediction method that only considers a single stress factor, its prediction results are closer to the actual operating conditions of the motor and have higher accuracy. In addition, by real-time monitoring and dynamic tracking of the pseudo-failure life of the main insulation and the remaining life of the stator, the method can generate monitoring results in a timely manner and provide clear quantitative basis for maintenance decisions. It realizes the transformation from passive post-event maintenance to proactive early warning maintenance, which significantly reduces the risk of unplanned downtime and maintenance costs. At the same time, all its steps can be performed online based on portable detection devices without stopping disassembly. It is simple to operate and safe and reliable, providing efficient, accurate and practical technical support for the full life cycle insulation management of low-voltage motors. Attached Figure Description

[0010] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments of this application and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings: Figure 1 A flowchart illustrating the motor insulation monitoring method provided in an embodiment of this application is shown; Figure 2 A structural diagram of the motor insulation monitoring device provided in an embodiment of this application is shown; Figure 3 A schematic diagram of the structure of an electronic device provided in an embodiment of this application is shown. Detailed Implementation

[0011] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0012] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such use can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the term "comprising" and its variations should be interpreted as open-ended terms meaning "including but not limited to."

[0013] Figure 1 This paper presents a schematic flowchart of the motor insulation monitoring method provided in an embodiment of this application. Figure 1 It can be seen that this application includes at least steps S101-S104: Step S101: Collect insulation status parameters of the low-voltage motor.

[0014] Among them, the insulation status parameters include at least the maximum partial discharge, insulation resistance, motor operating temperature, ambient humidity, and vibration signal.

[0015] Partial discharge is a non-penetrating discharge phenomenon that occurs under a high electric field when there are air gaps, impurities, or defects inside the main insulation material of the motor. The maximum partial discharge quantity refers to the maximum single discharge charge that occurs within the monitoring period. In this embodiment, a capacitive discharge sensor couples the partial discharge signal, processes the weak signal through a signal amplifier and filter, and then converts it into a digital quantity via an analog-to-digital converter before sending it to the processor. Insulation resistance represents the DC resistance value of the insulating medium between the motor windings and the casing. In this embodiment, the insulation resistance is inferred by measuring the leakage current, and a high-sensitivity sensor is used to capture weak leakage currents in the microampere or even nanoampere range. This embodiment uses a temperature sensor, a humidity sensor, and a vibration sensor to collect motor operating temperature, ambient humidity, and vibration signals, respectively.

[0016] The analog signals collected by the above sensors are processed by the signal conditioning circuit, then synchronously sampled and converted into digital quantities by the multi-channel analog-to-digital converter. The digital signals are then transmitted to the microprocessor through the digital interface. The microprocessor packages the data from each channel according to a unified timestamp to form a structured insulation state parameter dataset for subsequent steps.

[0017] In some embodiments, real-time data on the insulation status of the motor are clearly displayed in graphical or numerical form, which helps users understand the motor's operating status in real time.

[0018] In some embodiments, the collected motor insulation status data is uploaded to cloud storage via secure cloud transmission. This not only ensures the security and integrity of the data but also allows users to access historical data anytime, anywhere and perform remote analysis.

[0019] In some embodiments, the ability to generate periodic reports is provided, allowing users to export detailed data reports for internal audits, maintenance planning, and continuous improvement of potential issues.

[0020] The sensor array in this application does not rely on a single parameter but comprehensively considers changes in multiple insulation parameters during motor operation. The integrated sensing of parameters such as leakage current and insulation resistance allows the device to gain a more comprehensive understanding of the motor's insulation status, reducing the likelihood of misjudgment due to a single factor. The use of highly sensitive sensors enables the detection of even minute changes in leakage current and resistance. This is crucial for the early detection of insulation problems, as some issues may initially manifest as minor current leakage or resistance changes. Unlike traditional periodic inspections, real-time monitoring of the motor's insulation parameters allows for immediate response to changes in the motor's condition. This real-time monitoring helps to promptly identify potential problems, reducing maintenance and replacement costs. The sensors connect to other modules wirelessly or via wired connections, avoiding the safety hazards associated with traditional physical sensors, such as electrical short circuits or sensing problems, as no direct physical contact is involved.

[0021] Step S102: Input the maximum partial discharge and motor operating temperature into the main insulation degradation prediction model to obtain the pseudo failure life of the motor.

[0022] Among them, the main insulation degradation prediction model is pre-established based on the Wiener process, uses the maximum partial discharge as the degradation characteristic quantity of the motor's main insulation material, and combines the Arrhenius model to extrapolate the parameter estimates at high temperature to room temperature, so as to establish a calculation model for the quantitative relationship between the maximum partial discharge, the motor operating temperature and the pseudo-failure lifetime of the main insulation.

[0023] The model pre-determines the aging of the main insulation as a unidirectional degradation process with random fluctuations. Within this framework, the maximum partial discharge is defined as an index that accumulates over time, and its growth rate and fluctuation amplitude jointly determine the degradation trajectory of the main insulation. By setting a safety threshold, the moment when the discharge first crosses this threshold is defined as the end of the lifespan. Since insulation aging is extremely slow at room temperature, modeling based solely on room temperature measured data would take several years and is not engineering feasible. Therefore, the model undergoes accelerated degradation tests under high-temperature accelerated stress to obtain Wiener process parameters at high temperatures. Subsequently, using the Arrhenius model as a bridge, these high-temperature parameter estimates are extrapolated to room temperature conditions, thereby establishing a quantitative relationship between the discharge growth rate and temperature at room temperature. After the above pre-calibration, the model finally converges into a complete calculation formula integrating the maximum partial discharge and the motor operating temperature.

[0024] Step S103: Input the motor operating temperature and vibration signal into the stator remaining life prediction model, and output the predicted value of the motor stator remaining life.

[0025] Among them, the stator remaining life prediction model is a calculation model that pre-fits the Weibull distribution parameters based on the two-parameter Weibull distribution and combines the inverse power law formula to establish a quantitative relationship between the motor operating temperature and vibration signal and the stator insulation life.

[0026] Step S104: Monitor the pseudo-failure lifetime of the main insulation material of the motor and the remaining predicted lifetime of the stator in real time, and generate monitoring results.

[0027] from Figure 1As shown in the method, this application achieves comprehensive perception of the motor insulation health status by collecting multi-dimensional insulation state parameters such as maximum partial discharge, insulation resistance, operating temperature, ambient humidity, and vibration signals. This effectively overcomes the shortcomings of traditional single-parameter monitoring, which is susceptible to interference and has a high misjudgment rate, and significantly improves the ability to capture early weak abnormal signals. Furthermore, this method innovatively combines a degradation model based on the Wiener process with an Arrhenius model, using the maximum partial discharge as a key characteristic of the main insulation material degradation. It also extrapolates high-temperature accelerated degradation test data to room-temperature operating conditions, thus accurately calculating the pseudo-failure lifetime of the motor's main insulation material without relying on long-term measured data. This solves the technical problem of existing methods being unable to quantitatively predict the long-term room-temperature lifetime of insulation materials. Simultaneously, this method further employs a two-parameter Weibull distribution to fit the stator. By analyzing the distribution law of insulation life and establishing a quantitative relationship model between operating temperature, vibration signals, and stator insulation life using an inverse power law formula, this method can output the predicted value of the remaining stator life in real time. This takes into account the combined effects of thermal stress and mechanical stress on insulation aging. Compared with traditional prediction methods that only consider a single stress factor, its prediction results are closer to the actual operating conditions of the motor and have higher accuracy. In addition, by real-time monitoring and dynamic tracking of the pseudo-failure life of the main insulation and the remaining stator life, this method can generate monitoring results in a timely manner and provide clear quantitative basis for maintenance decisions. This realizes the transformation from passive post-event maintenance to proactive early warning maintenance, significantly reducing the risk of unplanned downtime and maintenance costs. At the same time, all steps can be performed online based on portable detection devices without stopping disassembly. The operation is simple, safe, and reliable, providing efficient, accurate, and practical technical support for the full life cycle insulation management of low-voltage motors.

[0028] In some embodiments of this application, the primary insulation degradation prediction model in the above method is constructed based on the following: A failure threshold for the maximum partial discharge is preset, and the failure threshold is used as the failure judgment boundary. The pseudo-failure lifetime is defined based on the first arrival time criterion. A univariate linear Wiener process degradation model with drift is established. Using the piecewise degradation increment dataset at each acceleration temperature, the drift parameters and diffusion parameters corresponding to each acceleration temperature are obtained. Using drift and diffusion parameters as inputs, and combining the first-time failure criterion, the cumulative failure distribution law, failure probability density law, and reliability function at each acceleration temperature are derived. The expectation of the failure probability density law is calculated to obtain the average pseudo-failure lifetime and lifetime variance at each acceleration temperature. Establish an exponential correspondence between drift parameters, diffusion parameters, and acceleration temperature; after logarithmically linearizing the exponential relationship, use multiple sets of drift parameters and diffusion parameters corresponding to acceleration temperatures to fit and obtain the undetermined coefficients of the temperature acceleration model, forming a quantitative mapping relationship between temperature and degradation parameters. By substituting the ambient temperature into the quantitative mapping relationship, the drift and diffusion parameters at ambient temperature are calculated. Then, by substituting these parameters into the reliability function, the pseudo-failure lifetime and reliability output results at ambient temperature are finally obtained.

[0029] Specifically, using the maximum partial discharge quantity as a degradation characteristic of the motor's main insulation material, a drift-dependent univariate linear Wiener process model is established: (1) Where μ, t, and σ are the drift parameter, degradation time, and diffusion parameter, respectively; X(t) is the cumulative degradation amount of the maximum partial discharge at time t, and X(t) ~ N( Let X(t) be a linear function of time, with expectation and variance of X(t); and B(t) be standard Brownian motion. Then, let... (i=1, 2, ..., n, j = 1, 2, ..., m) represents the segmentation degradation of the i-th sample in the j-th period, and ~ N( t), t is the periodic interval. The maximum likelihood function is as follows: (2) The log-likelihood function is (3) The parameter μ can be obtained from equation (3). The maximum likelihood estimate is: (4) Given a failure threshold L, the lifetime T = {t|X(t)≥L} is directly defined, and the corresponding lifetime distribution function is defined as follows: (5) The lifetime probability density function and lifetime distribution function are: (6) This leads to the reliability function. (7) Where Φ is the distribution function of the standard normal distribution.

[0030] To reduce the risk of failure, lifetime T is defined as the moment when X(t) first exceeds the failure threshold L, i.e., T = inf{t|X(t)≥L}. At this point, the lifetime probability density function and distribution function are as follows: (8) (9) Corresponding reliability function (10) This leads to the expected value and variance of the lifetime T. (11) An Arrhenius model of the unknown parameters of the Wiener process model and temperature stress is established. Then, the pseudo-failure lifetime of the motor's main insulation material is extrapolated at room temperature by utilizing the degradation characteristics of the motor's main insulation material and the maximum likelihood estimation method.

[0031] The formula for the Arrhenius model is as follows: (12) Where: y represents the parameters in the model; ρ is the absolute temperature; b is the Boltzmann constant; To obtain the activation energy, take the logarithm of both sides of equation (12) and linearize it to get... (13) in = lna, = - / b, Φ(t) = 1 / After the above simplification, the temperature The parameters of the Wiener process can be expressed as follows: (14) and / = / ,Right now = 2 Substituting into equation (14), we get: (15) Therefore, the relationship between the lifetime probability density function and the reliability function and temperature is as follows: (16) By studying the characteristics of the main insulation material of low-voltage motors, it can be concluded that... , , The initial values. Assuming the ambient temperature is 50 ~ 80℃ and the winding temperature rise is 125℃, the performance reference temperature of the motor's main insulation material is 175 ~ 205℃. The model parameter values ​​μ at ambient temperature can be obtained using equation (15). By combining equation (10), the lifetime probability density distribution of the main insulation material of the motor at room temperature is obtained, and then the maximum and minimum lifetimes of the main insulation material of the motor at room temperature are derived. Finally, μ, Substituting the value into equation (11) yields the pseudo-failure life of the motor's main insulation material at room temperature.

[0032] In this embodiment, an Arrhenius model was established using parameter estimates of the Wiener process at high temperature and accelerated degradation test data, enabling the prediction of the lifespan of the main insulation material of a motor at room temperature. This method provides motor manufacturers with a reliable means to predict the lifespan of the main insulation material of a motor under actual operating conditions, thereby facilitating reasonable maintenance and management.

[0033] In some embodiments of this application, the process of constructing the stator remaining lifetime prediction model in the above method is as follows: A two-parameter Weibull distribution statistical model for stator insulation lifetime is established, which includes shape parameters and scale parameters. The shape parameters reflect the insulation failure mechanism and the trend of failure rate, while the scale parameters characterize the overall magnitude of the insulation lifetime. By integrating the probability density function of the Weibull distribution over time, the cumulative failure distribution function and reliability function of the stator insulation lifetime are derived. The cumulative failure distribution function is transformed into a linear form by a logarithmic transformation. Combining the lifetime samples under each stress and the corresponding empirical failure probabilities, the shape parameters and scale parameters corresponding to each stress combination are obtained by least squares fitting. The single-stress inverse power law model is extended to a temperature and vibration dual-stress coupling form, and the correspondence between the scale parameters and the motor operating temperature and vibration aging rate is established. After the model is logarithmically linearized, the inverse power law constant, temperature stress endurance coefficient and vibration stress endurance coefficient are obtained by multivariate linear regression using the scale parameters corresponding to multiple stress combinations, forming a quantitative mapping relationship between stress level and stator insulation life. Based on the principle of conditional probability, the logic for calculating conditional reliability is derived. The stator insulation operating time and the preset target reliability level are substituted into the equation. Combined with the Weibull parameters obtained through the quantitative mapping relationship under actual operating conditions, the calculation rule for the predicted value of the remaining life of the stator is obtained by inverse solution.

[0034] Specifically, it is known that the stator insulation of a low-voltage motor experiences roughly the same stresses as the rolling bearings during operation. Therefore, it can be assumed that the stator insulation life also follows a two-parameter Weibull distribution, with its probability density function and cumulative density function being respectively... (17) (18) In the formula: m is the shape parameter, This is the scale parameter.

[0035] The relationship between the shape parameter m and the scale parameter can be proven from the cumulative density function of the Weibull distribution. There is a linear relationship between them, and the proof is as follows: (19) To improve the accuracy and precision of the prediction, least squares regression analysis is used. The least squares parameter estimation method is as follows: (20) (twenty one) (twenty two) (twenty three) Based on the known average lifespan data of the stator bars under different conditions, estimates of the parameters of a simple linear regression model can be obtained, namely, the two parameters in the Weibull distribution under different test conditions. Furthermore, the lifespan of the stator insulation conforms to an inverse power-law empirical formula; therefore, combined with the vibration aging rate... Using the inverse power-law empirical formula, we derive an empirical formula for predicting the lifespan of low-voltage motor stator insulation: (twenty four) In the formula: L is the life value under the corresponding test conditions, K is the inverse power law constant; T is the operating temperature of the motor; and n is the endurance coefficient.

[0036] This shows that the insulation life of the stator is related to the temperature and vibration frequency during motor operation. The stator insulation life under different conditions can be calculated using the two parameters obtained above, and the values ​​of the two parameters K and n can be obtained by fitting them again using the least squares method.

[0037] By substituting K, n, and the temperature and vibration parameters of the motor during normal operation into equation (24), the remaining life L of the motor stator can be predicted.

[0038] In this embodiment, the two parameters of the Weibull distribution are obtained by using the two-parameter Weibull distribution and the least squares method, and the predicted life curve is obtained by combining the inverse power law formula. The remaining life of the low-voltage motor stator is calculated based on the life curve, which provides an important reference for motor maintenance.

[0039] In some embodiments of this application, in the above method, step S104, which involves real-time monitoring of the pseudo-failure lifetime of the motor's main insulation material and the remaining predicted lifetime of the stator, includes: The pseudo-failure life of the motor's main insulation material is compared with the preset main insulation life grading threshold to determine the current aging level of the main insulation. The remaining predicted lifespan of the stator is compared with the preset stator lifespan classification threshold to determine the current stator's remaining lifespan level. Based on the combined assessment of the aging level of the main insulation and the remaining life level of the stator, a comprehensive evaluation result of the overall insulation health status of the motor is generated.

[0040] Specifically, multiple lifespan thresholds are pre-set based on the motor insulation design life and industry operation and maintenance standards. For example, they can be divided into four levels: healthy, warning, abnormal, and severe, each corresponding to a different remaining lifespan range. The real-time calculated pseudo-failure lifespan of the main insulation is compared with the preset grading thresholds one by one. Based on the threshold range in which the value falls, the aging level of the current main insulation is determined.

[0041] Independent multi-level remaining life classification thresholds are set in advance according to the design life and operation and maintenance requirements of the stator insulation; the real-time output of the stator's predicted remaining life is compared with the classification thresholds to determine the remaining life level corresponding to the current stator.

[0042] Since the motor insulation system consists of main insulation and stator insulation, the condition of a single component cannot fully represent the overall insulation level. Therefore, this application adopts a two-dimensional comprehensive judgment method to output the final conclusion. For example, when the two components have the same level, the corresponding comprehensive level is directly output; when the two components have different levels, the one with more severe deterioration and worse condition is taken as the dominant level, while the condition of the other component is marked as a supplementary explanation.

[0043] In some embodiments, when the aging level of the main insulation and the remaining life level of the stator are both within their respective safety threshold ranges, a comprehensive assessment result of good overall insulation health status of the motor is generated, and normal operation recommendations are output. When either the aging level of the main insulation or the remaining life level of the stator exceeds the attention threshold but has not yet reached the abnormal threshold, a general comprehensive assessment result of the overall insulation health status of the motor is generated, and an enhanced monitoring prompt is output. When either the aging level of the main insulation or the remaining life level of the stator reaches the abnormal threshold but has not yet reached the danger threshold, a comprehensive assessment result indicating that the overall insulation health status of the motor is abnormal is generated, and a warning signal and maintenance suggestions are output. When either the aging level of the main insulation or the remaining life level of the stator reaches the danger threshold, a comprehensive assessment result indicating that the overall insulation health status of the motor is dangerous is generated, and an alarm signal and shutdown maintenance recommendations are output.

[0044] In this embodiment, the abstract lifespan value can be transformed into an intuitive state level by using a graded threshold, reducing the threshold for operation and maintenance interpretation; the main insulation and stator are graded separately, which can accurately distinguish the degree of degradation of different parts and different causes; the two-dimensional comprehensive judgment can avoid the one-sidedness of a single assessment and fully cover insulation risks; the grading results can be directly matched with graded early warning and differentiated operation and maintenance strategies, effectively supporting condition-based maintenance and improving operation and maintenance efficiency and operational safety.

[0045] In some embodiments of this application, after acquiring the insulation state parameters, the method further includes: The insulation condition parameters are matched and compared with a preset standard fault mode library to identify the motor's fault mode; the standard fault mode library stores at least the insulation condition parameter feature data corresponding to insulation aging fault mode, structural defect fault mode and temperature abnormality fault mode. Based on the matching comparison results, when the matching degree between the insulation status parameters and the feature data of the fault mode exceeds the preset threshold, it is determined that the motor is currently in the fault mode, and the corresponding fault type identification result is output.

[0046] Specifically, the insulation aging fault mode corresponds to a permanent fault caused by the long-term natural deterioration of insulation materials. Its characteristics include a continuous and slow increase in maximum partial discharge and a synchronous and slow decrease in insulation resistance. There are no sudden abnormalities in vibration and temperature; the parameter changes are gradual and irreversible, representing a typical manifestation of normal service aging. The structural defect fault mode corresponds to mechanical defects such as insulation loosening, wear, and interlayer cracking. Its characteristics include abnormal amplitude or sudden increase in vibration signals at specific frequencies, and intermittent fluctuations in maximum partial discharge. However, there is no overall decrease in insulation resistance or significant abnormality in operating temperature, indicating an insulation risk caused by mechanical structure. The temperature anomaly fault mode corresponds to insulation overheating caused by motor overload, poor heat dissipation, etc. Its characteristics include a significant increase in motor operating temperature, a synchronous increase in maximum partial discharge with temperature, and a synchronous decrease in insulation resistance with temperature. The parameters can partially recover when the temperature drops, indicating temporary deterioration caused by abnormal operating conditions, distinct from permanent aging.

[0047] When the similarity between the real-time parameter characteristics and the standard characteristics of a certain type of fault exceeds a preset threshold, it can be determined that the current motor has a corresponding type of fault; if multiple types of faults are matched at the same time, the primary and secondary fault conclusions can be output according to the matching degree. The output fault type identification results can be directly connected to the subsequent early warning and operation and maintenance suggestion generation process, and provide differentiated handling solutions for different fault types: for example, insulation aging prompts to arrange planned replacement, structural defects prompt to stop and check for tightening, and abnormal temperature prompts to check the load and heat dissipation system, so as to realize the practical application of diagnostic results.

[0048] In this embodiment, fault modes are identified by matching and comparing real-time collected multi-dimensional insulation state parameters with a preset standard fault mode library. This enables accurate differentiation of fault types based on the linkage and change characteristics of multiple parameters, overcoming the limitation that fluctuations of a single parameter can easily lead to misjudgment, and effectively improving the accuracy and anti-interference capability of insulation fault diagnosis.

[0049] In some embodiments of this application, the method further includes: Based on historical monitoring results and on-site operation and maintenance results, the actual failure time and fault verification results are used as correction samples to update the undetermined coefficients of the temperature acceleration model of the main insulation degradation prediction model, as well as the inverse power law constant and endurance coefficient of the stator remaining life prediction model.

[0050] Specifically, updating the undetermined coefficients of the temperature-accelerated model for the main insulation degradation prediction model involves merging the actual failure time, corresponding operating temperature, and maximum partial discharge degradation data from the corrected sample set with the original laboratory accelerated test dataset. Using incremental maximum likelihood estimation or weighted least squares, the exponential mapping relationship between temperature and drift and diffusion parameters is refitted, updating all undetermined coefficients in the Arrhenius temperature formula. During the fitting process, a higher weight is assigned to real-world maintenance samples from the field, while the weight of ideal laboratory test samples is reduced, making the corrected coefficients more closely reflect actual aging patterns in the field. After the parameters are updated, the ambient temperature is substituted into the corrected temperature mapping relationship, and the drift and diffusion parameters at ambient temperature are recalculated. These parameters are then substituted into the reliability function and lifetime distribution formula to obtain the updated pseudo-failure lifetime calculation logic, which is used for subsequent online monitoring lifetime prediction.

[0051] The update of the inverse power-law constant and endurance coefficient of the stator remaining life prediction model includes: merging the actual failure time, corresponding operating temperature, and vibration stress data from the corrected sample set with the original accelerated life test dataset; using a multivariate weighted least squares method to refit the correspondence between stress level and Weibull scale parameters; and updating the inverse power-law constant, temperature stress endurance coefficient, and vibration stress endurance coefficient in the inverse power-law model. During the fitting process, the weights are dynamically adjusted based on the fault verification results: if the field-verified fault is mainly thermal aging, the fitting weight of the temperature stress term is increased; if it is mainly mechanical wear and structural loosening, the fitting weight of the vibration stress term is increased, making the contribution ratio of the two stresses more consistent with the actual failure mechanism in the field. After the parameters are updated, the updated stator insulation life-stress mapping relationship is obtained by combining the shape parameters of the Weibull distribution. This relationship is then substituted into the conditional reliability calculation logic to form the updated remaining life prediction rule.

[0052] In some embodiments, the model can be updated periodically or triggered. Periodic updates are performed at fixed intervals, completing batch iterations based on accumulated monitoring and maintenance data to achieve continuous model optimization; triggered updates are performed immediately after each motor overhaul and fault verification, using newly added ground truth samples to quickly correct model deviations.

[0053] After each parameter update, the accuracy of the updated model is verified using a reserved validation sample set. If the prediction accuracy meets the preset error requirements, the new parameters are officially used. If the accuracy decreases, the original parameters are retained to avoid abnormal samples from causing model distortion and to ensure the stability and reliability of the model operation.

[0054] In this embodiment, by iteratively updating the core parameters of the model based on historical monitoring results and on-site operation and maintenance results, the adaptation deviation between the theoretical model constructed under laboratory accelerated test conditions and the complex on-site operating conditions can be effectively corrected, significantly improving the accuracy of the prediction results of the main insulation pseudo-failure lifetime and the stator remaining lifetime, and avoiding prediction errors caused by the difference between the ideal test environment and the actual operating scenario.

[0055] In some embodiments of this application, a motor insulation monitoring device is provided, which corresponds one-to-one with the motor insulation monitoring method described in the above embodiments. For example... Figure 2 As shown, the motor insulation monitoring device includes a data acquisition module 101, a prediction module 102, and a monitoring module 103. The acquisition module 101 is used to acquire insulation status parameters of the low-voltage motor. The insulation status parameters include at least the maximum partial discharge, insulation resistance, motor operating temperature, ambient humidity and vibration signal. The prediction module 102 is used to input the maximum partial discharge quantity and the motor operating temperature into the main insulation degradation prediction model to obtain the pseudo-failure lifetime of the motor. The main insulation degradation prediction model is pre-established based on the Wiener process, using the maximum partial discharge quantity as the degradation characteristic quantity of the motor's main insulation material, and combining the Arrhenius model to extrapolate the parameter estimates at high temperature to room temperature, so as to establish a calculation model for the quantitative relationship between the maximum partial discharge quantity, the motor operating temperature and the pseudo-failure lifetime of the main insulation. The prediction module 102 is also used to input the motor operating temperature and vibration signal into the stator remaining life prediction model and output the predicted value of the motor stator remaining life; wherein, the stator remaining life prediction model is a calculation model that is pre-fitted with the Weibull distribution parameters based on a two-parameter Weibull distribution and combined with the inverse power law formula to establish a quantitative relationship between the motor operating temperature and vibration signal and the stator insulation life; The monitoring module 103 is used to monitor the pseudo-failure lifetime of the main insulation material of the motor and the remaining predicted lifetime of the stator in real time, and generate monitoring results.

[0056] In some embodiments of this application, in the above-described apparatus, the primary insulation degradation prediction model is constructed based on the following: A failure threshold with a preset maximum partial discharge is used as the failure determination boundary, and a pseudo-failure lifetime is defined based on the first arrival time criterion. A univariate linear Wiener process degradation model with drift is established. Using the piecewise degradation increment dataset at each acceleration temperature, the drift parameters and diffusion parameters corresponding to each acceleration temperature are obtained. Using the drift parameters and diffusion parameters as inputs, and combining the first-arrival failure criterion, the cumulative failure distribution law, failure probability density law, and reliability function at each acceleration temperature are derived. The expectation operation is performed on the failure probability density law to obtain the average pseudo-failure lifetime and lifetime variance at each acceleration temperature. Establish an exponential correspondence between drift parameters, diffusion parameters, and acceleration temperature; after logarithmically linearizing the exponential relationship, use multiple sets of drift parameters and diffusion parameters corresponding to acceleration temperatures to fit and obtain the undetermined coefficients of the temperature acceleration model, forming a quantitative mapping relationship between temperature and degradation parameters. Substituting the ambient temperature into the quantitative mapping relationship, the drift and diffusion parameters at ambient temperature are calculated. Then, substituting these parameters into the reliability function, the pseudo-failure lifetime and reliability output results at ambient temperature are finally obtained.

[0057] In some embodiments of this application, the process of constructing the stator remaining lifetime prediction model in the above-described apparatus is as follows: A two-parameter Weibull distribution statistical model for stator insulation lifetime is established, which includes shape parameters and scale parameters. The shape parameters reflect the insulation failure mechanism and the trend of failure rate, while the scale parameters characterize the overall magnitude of the insulation lifetime. By integrating the probability density function of the Weibull distribution over time, the cumulative failure distribution function and reliability function of the stator insulation lifetime are derived. The cumulative failure distribution function is transformed into a linear form by a logarithmic transformation. Combining the lifetime samples under each stress and the corresponding empirical failure probabilities, the shape parameters and scale parameters corresponding to each stress combination are obtained by least squares fitting. The single-stress inverse power law model is extended to a temperature and vibration dual-stress coupling form, and the correspondence between the scale parameters and the motor operating temperature and vibration aging rate is established. After the model is logarithmically linearized, the inverse power law constant, temperature stress endurance coefficient and vibration stress endurance coefficient are obtained by multivariate linear regression using the scale parameters corresponding to multiple stress combinations, forming a quantitative mapping relationship between stress level and stator insulation life. Based on the principle of conditional probability, the logic for calculating conditional reliability is derived. The stator insulation operating time and the preset target reliability level are substituted into the equation. Combined with the Weibull parameters obtained through the quantitative mapping relationship under actual operating conditions, the calculation rule for the predicted value of the remaining life of the stator is obtained by inverse solution.

[0058] In some embodiments of this application, in the above-described apparatus, the monitoring device 103 is specifically used to compare the pseudo-failure life of the motor main insulation material with a preset main insulation life grading threshold to determine the current aging level of the main insulation. The remaining predicted lifespan of the stator is compared with a preset stator lifespan classification threshold to determine the current stator's remaining lifespan level. Based on the combined assessment of the aging level of the main insulation and the remaining life level of the stator, a comprehensive evaluation result of the overall insulation health status of the motor is generated.

[0059] In some embodiments of this application, in the above-described apparatus, the monitoring device 103 is specifically used to generate a comprehensive assessment result that the overall insulation health status of the motor is good when the aging level of the main insulation and the remaining life level of the stator are both within their respective safety threshold ranges, and to output normal operation recommendations. When either the aging level of the main insulation or the remaining life level of the stator exceeds the attention threshold but has not yet reached the abnormal threshold, a general comprehensive assessment result of the overall insulation health status of the motor is generated, and an enhanced monitoring prompt is output. When either the aging level of the main insulation or the remaining life level of the stator reaches the abnormal threshold but has not yet reached the danger threshold, a comprehensive assessment result indicating that the overall insulation health status of the motor is abnormal is generated, and a warning signal and maintenance suggestions are output. When either the aging level of the main insulation or the remaining life level of the stator reaches a dangerous threshold, a comprehensive assessment result indicating that the overall insulation health status of the motor is dangerous is generated, and an alarm signal and shutdown maintenance recommendations are output.

[0060] In some embodiments of this application, the above-described device further includes a judgment module, which is used to match and compare the insulation state parameters with a preset standard fault mode library to identify the fault mode of the motor; the standard fault mode library stores at least the insulation state parameter feature data corresponding to the insulation aging fault mode, the structural defect fault mode, and the temperature abnormality fault mode. Based on the matching comparison results, when the degree of matching between the insulation state parameter and the feature data of the fault mode exceeds a preset threshold, it is determined that the motor is currently in the fault mode, and the corresponding fault type identification result is output.

[0061] In some embodiments of this application, the above-mentioned device further includes an update module, which is used to update the undetermined coefficients of the temperature acceleration model of the main insulation degradation prediction model and the inverse power law constant and endurance coefficient of the stator remaining life prediction model based on historical monitoring results and on-site operation and maintenance results, taking the actual failure time and fault verification results as correction samples.

[0062] It should be noted that any of the above-mentioned motor insulation monitoring devices can implement the aforementioned motor insulation monitoring methods one by one, which will not be elaborated here.

[0063] Figure 3 A schematic diagram of the structure of an electronic device provided in an embodiment of this application is shown. Figure 3 As shown, at the hardware level, this electronic device includes a processor, and optionally also includes an internal bus, a network interface, and memory. The memory may include main memory, such as high-speed random-access memory (RAM), or it may include non-volatile memory, such as at least one disk drive. Of course, this electronic device may also include other hardware required for other business operations.

[0064] The processor, network interface, and memory can be interconnected via an internal bus, which can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus, etc. The bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 3 The symbol is represented by a single double-headed arrow, but this does not mean that there is only one bus or one type of bus.

[0065] Memory is used to store programs. Specifically, programs may include program code, which includes computer operation instructions. Memory may include main memory and non-volatile memory, and provides instructions and data to the processor.

[0066] The processor reads the corresponding computer program from non-volatile memory into main memory and then runs it, forming a motor insulation monitoring device at the logical level. The processor executes the program stored in memory and specifically performs the aforementioned methods.

[0067] The processor may be an integrated circuit chip with signal processing capabilities. In implementation, each step of the above method can be completed by integrated logic circuits in the processor's hardware or by instructions in software form. The processor can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this application can be directly embodied in the execution of a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software modules can reside in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. The storage medium is located in the memory, and the processor reads the information in the memory and, in conjunction with its hardware, completes the steps of the above method.

[0068] This electronic device can execute the motor insulation monitoring method provided in several embodiments of this application, and is implemented as a motor insulation monitoring device. Figure 2 The functions of the embodiments shown are not described again in this application.

[0069] This application also proposes a computer-readable storage medium that stores one or more programs, the programs including instructions that, when executed by an electronic device including multiple applications, enable the electronic device to perform the motor insulation monitoring method provided in several embodiments of this application.

[0070] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0071] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0072] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0073] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0074] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0075] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0076] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0077] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0078] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0079] The above are merely embodiments of this application and are not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A method for monitoring the insulation of an electric motor, characterized in that, The method includes: The insulation status parameters of the low-voltage motor are collected, including at least the maximum partial discharge, insulation resistance, motor operating temperature, ambient humidity and vibration signal. The maximum partial discharge quantity and the motor operating temperature are input into the main insulation degradation prediction model to obtain the pseudo-failure lifetime of the motor. The main insulation degradation prediction model is pre-established based on the Wiener process, uses the maximum partial discharge quantity as the degradation characteristic quantity of the motor's main insulation material, and combines the Arrhenius model to extrapolate the parameter estimates at high temperature to room temperature, so as to establish a calculation model for the quantitative relationship between the maximum partial discharge quantity, the motor operating temperature and the pseudo-failure lifetime of the main insulation. The motor operating temperature and vibration signal are input into the stator remaining life prediction model, and the predicted value of the motor stator remaining life is output; wherein, the stator remaining life prediction model is a calculation model that is pre-fitted with Weibull distribution parameters based on a two-parameter Weibull distribution and combined with an inverse power law formula to establish a quantitative relationship between the motor operating temperature and vibration signal and the stator insulation life; The pseudo-failure lifetime of the main insulation material of the motor and the remaining predicted lifetime of the stator are monitored in real time, and monitoring results are generated.

2. The method according to claim 1, characterized in that, The main insulation degradation prediction model is constructed based on the following method: A failure threshold with a preset maximum partial discharge is used as the failure determination boundary, and a pseudo-failure lifetime is defined based on the first arrival time criterion. A univariate linear Wiener process degradation model with drift is established. Using the piecewise degradation increment dataset at each acceleration temperature, the drift parameters and diffusion parameters corresponding to each acceleration temperature are obtained. Using the drift parameters and diffusion parameters as inputs, and combining the first-arrival failure criterion, the cumulative failure distribution law, failure probability density law, and reliability function at each acceleration temperature are derived. The expectation operation is performed on the failure probability density law to obtain the average pseudo-failure lifetime and lifetime variance at each acceleration temperature. Establish an exponential relationship between drift parameters, diffusion parameters, and acceleration temperature; After logarithmically linearizing the exponential relationship, the undetermined coefficients of the temperature acceleration model are obtained by fitting multiple sets of drift and diffusion parameters corresponding to the acceleration temperature, thus forming a quantitative mapping relationship between temperature and degradation parameters. Substituting the ambient temperature into the quantitative mapping relationship, the drift and diffusion parameters at ambient temperature are calculated. Then, substituting these parameters into the reliability function, the pseudo-failure lifetime and reliability output results at ambient temperature are finally obtained.

3. The method according to claim 1, characterized in that, The construction process of the stator remaining life prediction model is as follows: A two-parameter Weibull distribution statistical model for stator insulation lifetime is established, which includes shape parameters and scale parameters. The shape parameters reflect the insulation failure mechanism and the trend of failure rate, while the scale parameters characterize the overall magnitude of the insulation lifetime. By integrating the probability density function of the Weibull distribution over time, the cumulative failure distribution function and reliability function of the stator insulation lifetime are derived. The cumulative failure distribution function is transformed into a linear form by a logarithmic transformation. Combining the lifetime samples under each stress and the corresponding empirical failure probabilities, the shape parameters and scale parameters corresponding to each stress combination are obtained by least squares fitting. The single-stress inverse power law model is extended to a temperature and vibration dual-stress coupling form, and the correspondence between the scale parameters and the motor operating temperature and vibration aging rate is established. After the model is logarithmically linearized, the inverse power law constant, temperature stress endurance coefficient and vibration stress endurance coefficient are obtained by multivariate linear regression using the scale parameters corresponding to multiple stress combinations, forming a quantitative mapping relationship between stress level and stator insulation life. Based on the principle of conditional probability, the logic for calculating conditional reliability is derived. The stator insulation operating time and the preset target reliability level are substituted into the equation. Combined with the Weibull parameters obtained through the quantitative mapping relationship under actual operating conditions, the calculation rule for the predicted value of the remaining life of the stator is obtained by inverse solution.

4. The method according to claim 1, characterized in that, The real-time monitoring of the pseudo-failure lifetime of the motor's main insulation material and the remaining predicted lifetime of the stator generates monitoring results including: The pseudo-failure life of the motor's main insulation material is compared with a preset main insulation life grading threshold to determine the current aging level of the main insulation. The remaining predicted lifespan of the stator is compared with a preset stator lifespan classification threshold to determine the current stator's remaining lifespan level. Based on the combined assessment of the aging level of the main insulation and the remaining life level of the stator, a comprehensive evaluation result of the overall insulation health status of the motor is generated.

5. The method according to claim 4, characterized in that, The comprehensive assessment result of the overall insulation health status of the motor is generated based on the combined judgment result of the aging level of the main insulation and the remaining life level of the stator, including: When the aging level of the main insulation and the remaining life level of the stator are both within their respective safety threshold ranges, a comprehensive assessment result of good overall insulation health status of the motor is generated, and normal operation recommendations are output. When either the aging level of the main insulation or the remaining life level of the stator exceeds the attention threshold but has not yet reached the abnormal threshold, a general comprehensive assessment result of the overall insulation health status of the motor is generated, and an enhanced monitoring prompt is output. When either the aging level of the main insulation or the remaining life level of the stator reaches the abnormal threshold but has not yet reached the danger threshold, a comprehensive assessment result indicating that the overall insulation health status of the motor is abnormal is generated, and a warning signal and maintenance suggestions are output. When either the aging level of the main insulation or the remaining life level of the stator reaches a dangerous threshold, a comprehensive assessment result indicating that the overall insulation health status of the motor is dangerous is generated, and an alarm signal and shutdown maintenance recommendations are output.

6. The method according to claim 1, characterized in that, After acquiring insulation state parameters, the method further includes: The insulation status parameters are matched and compared with a preset standard fault mode library to identify the fault mode of the motor; the standard fault mode library stores at least the insulation status parameter feature data corresponding to the insulation aging fault mode, the structural defect fault mode, and the temperature abnormality fault mode. Based on the matching comparison results, when the degree of matching between the insulation state parameter and the feature data of the fault mode exceeds a preset threshold, it is determined that the motor is currently in the fault mode, and the corresponding fault type identification result is output.

7. The method according to any one of claims 1 to 5, characterized in that, The method further includes: Based on historical monitoring results and on-site operation and maintenance results, the actual failure time and fault verification results are used as correction samples to update the undetermined coefficients of the temperature acceleration model of the main insulation degradation prediction model, as well as the inverse power law constant and endurance coefficient of the stator remaining life prediction model.

8. A motor insulation monitoring device, characterized in that, The device includes: The acquisition module is used to acquire insulation status parameters of the low-voltage motor. The insulation status parameters include at least the maximum partial discharge, insulation resistance, motor operating temperature, ambient humidity, and vibration signal. The prediction module is used to input the maximum partial discharge quantity and the motor operating temperature into the main insulation degradation prediction model to obtain the pseudo-failure lifetime of the motor. The main insulation degradation prediction model is pre-established based on the Wiener process, using the maximum partial discharge quantity as the degradation characteristic quantity of the motor's main insulation material, and combining the Arrhenius model to extrapolate the parameter estimates at high temperature to room temperature, so as to establish a calculation model for the quantitative relationship between the maximum partial discharge quantity, the motor operating temperature and the pseudo-failure lifetime of the main insulation. The prediction module is also used to input the motor operating temperature and vibration signal into the stator remaining life prediction model and output the predicted value of the motor stator remaining life; wherein, the stator remaining life prediction model is a calculation model that is pre-fitted with Weibull distribution parameters based on a two-parameter Weibull distribution and combined with an inverse power law formula to establish a quantitative relationship between the motor operating temperature and vibration signal and the stator insulation life; The monitoring module is used to monitor the pseudo-failure lifetime of the main insulation material of the motor and the remaining predicted lifetime of the stator in real time, and generate monitoring results.

9. An electronic device, comprising: processor; as well as A memory configured to store computer-executable instructions, which, when executed, cause the processor to perform the steps of the motor insulation monitoring method as described in any one of claims 1-7.

10. A computer-readable storage medium storing one or more programs, which, when executed by an electronic device including a plurality of applications, cause the electronic device to perform the steps of the motor insulation monitoring method as claimed in any one of claims 1-7.

Images