Permanent magnet synchronous motor failure monitoring method, system and equipment for space environment

Abstract

The present invention discloses a method, system, and device for monitoring the failure of a permanent magnet synchronous motor in a space environment, and relates to the technical field of motor fault monitoring. The method comprises: constructing a simulated space environment experimental cabin, conducting accelerated aging experiments on the permanent magnet synchronous motor, and obtaining multi-dimensional degradation data; conducting material performance evaluation on the permanent magnet synchronous motor, determining the material performance degradation results, performing failure analysis, and constructing a space environment failure feature library; and monitoring the motor operating parameter set of the permanent magnet synchronous motor in real time, determining abnormal modes, and formulating failure maintenance recommendations. The present invention solves the technical problems in the prior art of being unable to accurately monitor the failure of permanent magnet synchronous motors in a space environment, as well as the poor reliability and insufficient operational stability of motors in a space environment. It achieves the technical effect of accurately monitoring the failure of permanent magnet synchronous motors and improving the reliability and operational stability of permanent magnet synchronous motors in a space environment.

Description

Technical Field

[0001] The present invention relates to the technical field of motor fault monitoring, and in particular to a permanent magnet synchronous motor failure monitoring method, system and equipment for use in a space environment. Background Art

[0002] In the aerospace sector, the space environment is complex and harsh, with factors such as high vacuum, strong radiation, and extreme temperature fluctuations. As the drive mechanism for key components of satellites and other spacecraft, the operational reliability of permanent magnet synchronous motors (PMSMs) is crucial. However, existing motor failure monitoring technologies struggle to adapt to the unique requirements of the space environment. They cannot fully capture motor degradation data in this environment, and their assessment of material properties under the influence of complex factors is subject to bias, making it difficult to accurately determine motor failures. Furthermore, due to the lack of accurate failure monitoring and effective risk prediction, sudden motor failures are common during operation, seriously impacting the normal operation of spacecraft.

[0003] The existing technology has technical problems such as the inability to accurately monitor the failure of permanent magnet synchronous motors in space environments, as well as poor reliability and insufficient operating stability of the motors in space environments. Summary of the Invention

[0004] The present application provides a permanent magnet synchronous motor failure monitoring method, system and equipment for use in a space environment, which is used to solve the technical problems in the existing technology that it is impossible to accurately monitor the failure of permanent magnet synchronous motors in a space environment, as well as the poor reliability and insufficient operating stability of the motors in a space environment.

[0005] In view of the above problems, the present application provides a permanent magnet synchronous motor failure monitoring method, system and equipment for use in a space environment.

[0006] In a first aspect of the present application, a permanent magnet synchronous motor failure monitoring method for a space environment is provided, the method comprising:

[0007] A simulated space environment experimental chamber is constructed, which includes extreme temperature cycling conditions and high vacuum conditions. Accelerated aging experiments are conducted on permanent magnet synchronous motors through the simulated space environment experimental chamber to obtain multi-dimensional degradation data. Material performance of the permanent magnet synchronous motor is evaluated based on the multi-dimensional degradation data to determine material performance degradation results. Failure analysis is performed based on the material performance degradation results to construct a space environment failure feature library. The motor operating parameter set of the permanent magnet synchronous motor is monitored in real time, the motor operating parameter set is matched with the space environment failure feature library to determine abnormal patterns, the failure risk level is predicted according to the abnormal patterns, and failure maintenance recommendations are formulated based on the failure risk level.

[0008] In a possible implementation method, a simulated space environment experimental chamber is constructed, which includes extreme temperature cycle conditions and high vacuum conditions. An accelerated aging experiment is performed on a permanent magnet synchronous motor through the simulated space environment experimental chamber to obtain multi-dimensional degradation data, and the following processing is performed: a ladder temperature cycle is performed according to the extreme temperature cycle conditions of the simulated space environment chamber, and a multi-type sensor array is arranged on the motor stator winding, permanent magnet surface, and bearing seat of the permanent magnet motor according to the high vacuum conditions of the simulated space environment chamber to synchronously collect temperature distribution signals, vibration signals, and current harmonic signals; the temperature distribution signal is filtered and denoised to obtain motor temperature distribution data, the vibration signal is subjected to empirical mode decomposition to obtain vibration spectrum data, and the current harmonic signal is transformed to obtain current harmonic data; the motor temperature distribution data, the vibration spectrum data, and the current harmonic data are fused in the time and frequency domain to generate the multi-dimensional degradation data.

[0009] In a possible implementation, the material performance of the permanent magnet synchronous motor is evaluated based on the multi-dimensional degradation data, the material performance degradation result is determined, and the following processing is performed: the demagnetization curve test of the permanent magnet synchronous motor is performed based on the number of temperature cycles determined by the motor temperature distribution data to obtain the demagnetization rate of the permanent magnet; the crystal structure evolution of the bearing lubrication film of the permanent magnet synchronous motor is performed based on the vibration spectrum data to generate a lubrication failure coefficient; the partial discharge starting voltage of the permanent magnet synchronous motor material is calculated based on the current harmonic data to draw an insulation performance degradation curve; the permanent magnet demagnetization rate, the lubrication failure coefficient, and the insulation performance degradation curve are coupled by multi-physics fields to construct the material performance degradation result.

[0010] In a possible implementation, failure analysis is performed based on the material performance degradation results, a space environment failure feature library is constructed, and the following processing is performed: simulation is performed based on the permanent magnet demagnetization rate, the lubrication failure coefficient, and the insulation performance degradation curve to determine the prior probabilities of multiple events; failure tree structures of multiple events are constructed based on the prior probabilities of multiple events, and weight analysis is performed on the failure tree structures of multiple events to determine multiple weight coefficients; a multidimensional failure feature space is constructed based on the failure tree structures of multiple events and the multiple weight coefficients; cluster analysis is performed according to the multidimensional failure feature space to determine multiple cluster centers, the multiple cluster centers contain multiple failure rules, and there is a correspondence between the multiple cluster centers and the multiple failure rules; high-density failure features are extracted based on the multiple failure rules to construct the space environment failure feature library.

[0011] In a possible implementation, the motor operating parameter set of the permanent magnet synchronous motor is monitored in real time, and the following processing is performed: the permanent magnet synchronous motor is sampled in real time by a high-frequency current probe to obtain the three-phase current harmonic component parameters; the permanent magnet synchronous motor is sampled in real time by a distributed optical fiber temperature sensor to obtain the winding temperature gradient parameters; the permanent magnet synchronous motor is sampled in real time by a vibration sensor to obtain the axial vibration acceleration parameters; wavelet packet transform is performed based on the three-phase current harmonic component parameters to extract the characteristic energy value of a fixed frequency band, and the characteristic energy value includes the current harmonic distortion rate; fluctuation calculation is performed based on the winding temperature gradient parameter to determine the temperature gradient standard deviation; feature separation is performed based on the axial vibration acceleration parameter to determine the micro-wear characteristic frequency, and the micro-wear characteristic frequency includes the vibration characteristic energy entropy; the current harmonic distortion rate, the temperature gradient standard deviation, and the vibration characteristic energy entropy are integrated to construct a composite operation monitoring vector, and the composite operation monitoring vector is added to the motor operating parameter set.

[0012] In a possible implementation, the motor operating parameter set is matched with the spatial environment failure feature library to determine the abnormal pattern, and the following processing is performed: feature dimensionality reduction is performed based on the composite operation monitoring vector to determine a composite dimensionality reduction vector; the composite dimensionality reduction vector is used as an index to traverse the spatial environment failure feature library for similarity matching to generate multiple matching degrees; when there is a matching degree that exceeds a preset warning value among the multiple matching degrees, an online reconfiguration instruction is triggered, and a fault analysis is performed through the online reconfiguration instruction to construct multiple abnormal labels; the motor operating parameter set is traced back according to the multiple abnormal labels for identification, and the abnormal pattern is determined based on the identification result.

[0013] In a possible implementation, the failure risk level is predicted according to the abnormal pattern, and the following processing is performed: the bearing wear value and the winding insulation degradation value of the permanent magnet synchronous motor are extracted according to the abnormal pattern; a multivariate degradation failure analysis is performed based on the bearing wear value and the winding insulation degradation value to determine the joint failure probability; a Markov chain is constructed according to the joint failure probability for prediction, a risk evolution trend is constructed, a failure impact analysis is performed based on the risk evolution trend, and a failure risk level is set.

[0014] In a possible implementation, a failure maintenance recommendation is formulated based on the failure risk level, and the following processing is performed: a preset critical value is set based on the failure risk level, and the combined failure probability is compared with the preset critical value for determination; when the combined failure probability exceeds the preset critical value, a demagnetization compensation instruction is activated; multi-objective optimization is performed through the demagnetization compensation instruction, multi-level failure warning data is constructed, maintenance control is performed based on the multi-level failure warning data, and the failure maintenance recommendation is formulated.

[0015] A second aspect of the present application provides a permanent magnet synchronous motor failure monitoring system for a space environment, the system comprising:

[0016] A multi-dimensional degradation data acquisition module is used to construct a simulated space environment experimental chamber, which includes extreme temperature cycle conditions and high vacuum conditions. Accelerated aging experiments are performed on permanent magnet synchronous motors through the simulated space environment experimental chamber to obtain multi-dimensional degradation data; a feature library construction module is used to evaluate the material performance of permanent magnet synchronous motors based on the multi-dimensional degradation data, determine the material performance degradation results, perform failure analysis based on the material performance degradation results, and construct a space environment failure feature library; a failure maintenance recommendation formulation module is used to monitor the motor operating parameter set of the permanent magnet synchronous motor in real time, match the motor operating parameter set with the space environment failure feature library, determine the abnormal mode, predict the failure risk level according to the abnormal mode, and formulate failure maintenance recommendations based on the failure risk level.

[0017] The third aspect of the present application provides an electronic device, which includes: a processor; a memory for storing instructions executable by the processor; wherein the processor is used to execute the permanent magnet synchronous motor failure monitoring method for space environment provided in the present application.

[0018] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0019] A simulated space environment test chamber was constructed, in which accelerated aging experiments were conducted on permanent magnet synchronous motors to obtain multi-dimensional degradation data. Based on this multi-dimensional degradation data, material performance of the permanent magnet synchronous motors was evaluated, material performance degradation results were determined, and a space environment failure signature library was constructed. The motor operating parameter set of the permanent magnet synchronous motors was monitored in real time, matched with the space environment failure signature library, and abnormal patterns were determined. Failure risk levels were predicted based on these abnormal patterns, and failure maintenance recommendations were formulated based on these failure risk levels. This achieved the technical effect of accurately monitoring permanent magnet synchronous motor failures and improving the reliability and operational stability of permanent magnet synchronous motors in space environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0021] Figure 1A flow chart of a permanent magnet synchronous motor failure monitoring method for a space environment provided in an embodiment of the present application.

[0022] Figure 2 A schematic structural diagram of a permanent magnet synchronous motor failure monitoring system for a space environment provided in an embodiment of the present application.

[0023] Figure 3 This is a schematic diagram of the structure of an electronic device provided in this application.

[0024] Explanation of reference numerals: multi-dimensional degradation data acquisition module 10 , feature library construction module 20 , failure maintenance suggestion formulation module 30 , processor 21 , memory 22 , input device 23 , output device 24 . DETAILED DESCRIPTION

[0025] This application provides a permanent magnet synchronous motor failure monitoring method, system and equipment for use in a space environment, aiming to solve the technical problems in the existing technology that the failure of permanent magnet synchronous motors in a space environment cannot be accurately monitored, as well as the poor reliability and insufficient operating stability of the motors in a space environment.

[0026] The following will be combined with the accompanying drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making any creative work are within the scope of protection of this application.

[0027] Example 1, as Figure 1 As shown, the present application provides a permanent magnet synchronous motor failure monitoring method for a space environment, the method comprising:

[0028] Step S100: constructing a simulated space environment test chamber, wherein the simulated space environment test chamber includes extreme temperature cycle conditions and high vacuum conditions, and performing accelerated aging experiments on the permanent magnet synchronous motor through the simulated space environment test chamber to obtain multi-dimensional degradation data.

[0029] Specifically, a simulated space environment chamber with extreme temperature cycling and high vacuum conditions was constructed. To simulate the extreme temperature cycling conditions of the space environment, a stepped temperature cycling method was used to simulate the drastic temperature fluctuations experienced by the motor in space. The high vacuum conditions mimicked the vacuum environment of space, minimizing environmental interference with the experimental results. A permanent magnet synchronous motor was placed within this chamber for accelerated aging experiments. To comprehensively capture the various changes in the motor during aging, a multi-type sensor array was deployed at key locations, such as the motor's stator windings, permanent magnet surface, and bearing seat, to simultaneously collect temperature distribution signals, vibration signals, and current harmonic signals. After acquiring these raw signals, the temperature distribution signals were filtered and denoised to remove noise interference and obtain accurate motor temperature distribution data. Empirical mode decomposition (EMD) was applied to the vibration signals, decomposing the complex signals into multiple intrinsic mode functions (IMFs). This yielded vibration spectrum data, clearly displaying the vibration characteristics of different frequency components. Specific transformations were performed on the current harmonic signals to generate current harmonic data for analysis. Finally, the processed motor temperature distribution data, vibration spectrum data, and current harmonic data are fused in the time and frequency domain to integrate data of different types and dimensions to generate multi-dimensional degradation data that can comprehensively reflect the performance degradation of the motor in a simulated space environment.

[0030] Step S200: performing material performance evaluation on the permanent magnet synchronous motor based on the multi-dimensional degradation data, determining material performance degradation results, performing failure analysis according to the material performance degradation results, and constructing a space environment failure feature library.

[0031] Specifically, an in-depth analysis was conducted based on the acquired multi-dimensional degradation data. Using motor temperature distribution data, the demagnetization curve of the permanent magnets in the permanent magnet synchronous motor was tested after determining the number of temperature cycles. This yielded the permanent magnet demagnetization rate, which visually reflects the attenuation of the permanent magnet's magnetic properties in a simulated space environment. Vibration spectrum data was used to study the crystal structure evolution of the lubricating film in the permanent magnet synchronous motor bearings. Through quantitative analysis, a lubrication failure coefficient was generated to measure the degree of bearing lubrication degradation. Current harmonic data was used to calculate the partial discharge inception voltage of the permanent magnet synchronous motor material. Based on this, an insulation degradation curve was plotted, clearly demonstrating the performance trends of the insulation material. By integrating the permanent magnet demagnetization rate, lubrication failure coefficient, and insulation degradation curve through multi-physics coupling, a comprehensive analysis of various factors was conducted to construct a material degradation result, comprehensively revealing the performance changes of the motor material in a simulated space environment. Based on this material degradation result, failure analysis was initiated. Simulations were first performed based on the permanent magnet demagnetization rate, lubrication failure coefficient, and insulation degradation curve to determine the prior probabilities of multiple motor failure-related events. Next, these prior probabilities are used to construct a failure tree structure for multiple events. Weight analysis is performed to determine the importance of each event in the failure tree and determine multiple weight coefficients. Combining the failure tree structure and weight coefficients, a multidimensional failure feature space is constructed, providing a comprehensive mathematical model for analyzing motor failure characteristics. Cluster analysis is performed within the multidimensional failure feature space to identify multiple cluster centers. Each cluster center is associated with a specific failure rule that reflects the characteristic patterns of the motor under different failure conditions. Finally, high-density failure features are extracted based on the failure rules and integrated to construct a space environment failure feature library. This feature library covers characteristic information for various failure conditions of permanent magnet synchronous motors in simulated space environments, providing a key reference for subsequent real-time monitoring of motor operating status, identifying abnormal patterns, and predicting failure risk levels.

[0032] Step S300: monitor the motor operating parameter set of the permanent magnet synchronous motor in real time, match the motor operating parameter set with the space environment failure feature library, determine the abnormal mode, predict the failure risk level according to the abnormal mode, and formulate failure maintenance suggestions according to the failure risk level.

[0033] Specifically, the system monitors the permanent magnet synchronous motor's operating parameters in real time. These parameters cover key indicators such as motor speed, current, voltage, and temperature. These parameters are then carefully matched against a pre-built space environment failure signature library. This failure signature library stores various abnormality patterns that occur in motors under different space environmental conditions. Through comparative analysis, the system accurately identifies the abnormality pattern exhibited by the current motor operation. Next, based on the identified abnormality pattern, the system predicts its failure risk level. This level is typically categorized as low, medium, or high to intuitively reflect the likelihood of a serious motor failure. Finally, based on the predicted failure risk level, targeted maintenance recommendations are formulated. For example, if the risk level is low, routine inspections may be increased; if the risk level is medium, spare parts may be prepared and technicians must closely monitor the situation; and if the risk level is high, the system requires immediate shutdown for comprehensive overhaul and maintenance. This ensures the safe, stable, and efficient operation of the permanent magnet synchronous motor in the complex space environment.

[0034] In one possible implementation, step S100 further includes:

[0035] Step S110: Perform a ladder temperature cycle according to the extreme temperature cycle conditions of the cabin in the simulated space environment, and arrange multiple types of sensor arrays on the stator windings, permanent magnet surface, and bearing seat of the permanent magnet motor to synchronously collect temperature distribution signals, vibration signals, and current harmonic signals according to the high vacuum conditions of the cabin in the simulated space environment.

[0036] Step S120: filtering and denoising the temperature distribution signal to obtain motor temperature distribution data, performing empirical mode decomposition on the vibration signal to obtain vibration spectrum data, and transforming the current harmonic signal to obtain current harmonic data.

[0037] Step S130: performing time-frequency domain fusion processing on the motor temperature distribution data, the vibration spectrum data, and the current harmonic data to generate the multi-dimensional degradation data.

[0038] Specifically, the simulated space environment chamber was designed with extreme temperature cycling and high vacuum conditions to closely replicate real-world space conditions. During the experiment, a stepped temperature cycle was implemented in strict accordance with the chamber's extreme temperature cycling conditions. This temperature variation pattern rapidly accelerates motor aging, simulating the complex temperature environment of space. By subjecting the motor to rapid temperature fluctuations similar to those experienced in space in a short period of time, the motor can more efficiently obtain data on performance changes under temperature stress. Furthermore, based on the high vacuum conditions of the simulated space environment chamber, a multi-type sensor array was deployed at key locations on the permanent magnet motor, including the stator windings, permanent magnet surfaces, and bearing seats. As a key component in the conversion of electrical and mechanical energy, the stator windings' temperature and current changes directly reflect the motor's operating status. Temperature changes on the permanent magnet surfaces are closely correlated with changes in the magnetic field, affecting the motor's magnetic properties and performance. The bearing seats are crucial to the motor's mechanical stability, and their vibration is a key indicator for evaluating its mechanical performance. By deploying multiple types of sensors in these key locations, temperature distribution signals, vibration signals, and current harmonic signals can be collected simultaneously, comprehensively capturing various aspects of real-time data on the motor as it operates in a simulated space environment. This provides rich and critical raw data support for subsequent in-depth analysis of motor performance degradation patterns and the construction of a failure monitoring system.

[0039] Temperature distribution signals collected from permanent magnet motors in simulated space environments are often contaminated with noise due to environmental interference and sensor characteristics. This noise can seriously interfere with accurately determining the motor's true temperature. Therefore, filtering and noise reduction techniques are employed. Using filtering algorithms, such as Kalman filtering or wavelet filtering, the temperature distribution signals are processed to effectively remove noise, resulting in motor temperature distribution data that accurately reflects the actual temperature conditions of each motor component. The collected vibration signals are processed using empirical mode decomposition (EMD). Vibration signals contain rich information about the motor's mechanical system, but they are often complex, nonlinear, and nonstationary. EMD decomposes the vibration signal into multiple intrinsic mode functions (IMFs) based on the signal's characteristic time scale. These IMFs represent the signal's fluctuation components at different time scales. Analysis of the decomposition results yields vibration spectrum data, which clearly demonstrates the distribution of vibration energy at different frequency components and helps determine whether the motor's mechanical structure is abnormal. Issues such as bearing wear and loose components may be reflected in the vibration spectrum data. As for current harmonic signals, since their raw form is not suitable for directly analyzing changes in the motor's electrical performance, they require transformation. Typically, methods such as Fourier transforms or wavelet transforms are used to convert current harmonic signals from the time domain to the frequency domain, thereby obtaining current harmonic data. In the frequency domain, information such as the frequency components, amplitudes, and phase relationships of current harmonics can be more intuitively observed. This current harmonic data is crucial for evaluating the motor's winding insulation performance and electromagnetic compatibility, helping monitoring personnel promptly identify potential faults in the motor's electrical system. The resulting motor temperature distribution data, vibration spectrum data, and current harmonic data from this series of processing lay the foundation for subsequent generation of multi-dimensional degradation data and the construction of a spatial environment failure signature library.

[0040] A wavelet transform algorithm is used to perform time-frequency fusion processing on the motor temperature distribution data, vibration spectrum data, and current harmonic data. The motor temperature distribution data is first subjected to wavelet decomposition to obtain low-frequency approximate coefficients and high-frequency detail coefficients at different scales. The low-frequency approximate coefficients reflect the trend of temperature changes, while the high-frequency detail coefficients contain information about temperature mutations. Similarly, the vibration spectrum data and current harmonic data are subjected to wavelet decomposition to obtain their characteristic coefficients at different scales. Then, based on the physical meaning and relevance of the data, the decomposed coefficients are weighted and fused. For example, the coefficients of characteristic frequency bands that reflect performance changes in key motor components are weighted more heavily. Finally, the fused coefficients are reconstructed using an inverse wavelet transform to generate multidimensional degradation data containing the time-frequency characteristics of the motor's temperature, vibration, and current harmonics, comprehensively presenting the motor's degradation status in a simulated space environment.

[0041] In one possible implementation, step S200 further includes:

[0042] Step S210: determining the number of temperature cycles based on the motor temperature distribution data, performing a demagnetization curve test on the permanent magnet synchronous motor, and obtaining a permanent magnet demagnetization rate.

[0043] Step S220: performing crystal structure evolution on the bearing lubricating film of the permanent magnet synchronous motor based on the vibration spectrum data to generate a lubrication failure coefficient.

[0044] Step S230: Calculate the partial discharge inception voltage of the permanent magnet synchronous motor material based on the current harmonic data, and draw an insulation performance degradation curve.

[0045] Step S240: performing multi-physics field coupling on the permanent magnet demagnetization rate, the lubrication failure coefficient, and the insulation performance degradation curve to construct the material performance degradation result.

[0046] Specifically, after obtaining the motor temperature distribution data, the demagnetization curve test is performed on the permanent magnet synchronous motor based on the number of temperature cycles determined based on this data to obtain the permanent magnet demagnetization rate. First, the characteristics of the temperature cycle, including the range, frequency, and amplitude of the temperature change, are identified from the motor temperature distribution data to determine the number of temperature cycles. Then, the demagnetization curve test is performed on the permanent magnet synchronous motor according to the determined number of temperature cycles. The magnetic properties of the permanent magnets, such as remanence and coercive force, are measured before and after each temperature cycle. By analyzing the changes in these magnetic properties during the temperature cycles, the demagnetization rate of the permanent magnets is calculated. This demagnetization rate reflects the degree of performance degradation of the permanent magnets under the influence of temperature cycles and provides an important basis for evaluating the reliability of permanent magnet synchronous motors in space environments.

[0047] Based on vibration spectrum data, the crystal structure evolution of the lubricating film in a permanent magnet synchronous motor bearing is analyzed and a lubrication failure coefficient is generated. This is achieved using the following machine learning algorithm: First, the vibration spectrum data is subjected to wavelet packet decomposition to extract energy features in different frequency bands as input feature vectors. Simultaneously, X-ray diffraction (XRD) analysis is used to obtain crystal structure parameters of the lubricating film (such as grain size and lattice distortion) as output labels. A hybrid model is constructed, integrating a bidirectional long short-term memory (Bi-LSTM) network with a convolutional neural network (CNN). The CNN extracts spatial features of the vibration spectrum to capture local frequency band anomalies, while the Bi-LSTM mines temporal features to analyze the historical dependencies of crystal structure evolution. A transfer learning strategy is employed to pre-train model parameters using laboratory accelerated aging data and then fine-tune them using real-world operating data. An attention mechanism is introduced during model training to automatically assign weights to features in different frequency bands, highlighting features strongly correlated with lubrication failure (such as energy changes at the bearing's pass frequency). Finally, the crystal structure parameters output by the model are input into a predefined physical degradation model. Fuzzy logic reasoning is used to generate a lubrication failure coefficient between 0 and 1, enabling a quantitative assessment of the bearing's lubrication condition.

[0048] After acquiring the current harmonic data of a permanent magnet synchronous motor, a fast Fourier transform (FFT) is first performed on the current harmonic data to convert the time-domain current harmonic signal into the frequency domain. This allows precise separation of the individual harmonic components and the acquisition of their amplitude and phase information. These harmonic characteristics, combined with parameters such as the dielectric constant and thickness of the motor insulation material, are used to solve the Poisson and Maxwell equations using finite element analysis, based on the electrical physics model of partial discharge. The electric field distribution within the motor is calculated. A criterion for partial discharge onset is set, such as when the electric field strength reaches a certain threshold, to determine the partial discharge onset voltage. As the motor operates, new current harmonic data is periodically collected, and the above analysis and calculation process is repeated, recording the partial discharge onset voltage values at different operating times. These discrete voltage values are processed using a polynomial fitting method to construct a functional relationship between the partial discharge onset voltage and time. This allows the generation of an insulation degradation curve, clearly demonstrating the degradation trend of the motor's insulation performance over time.

[0049] After obtaining the permanent magnet demagnetization rate, lubrication failure coefficient, and insulation performance degradation curves, a multi-physics field coupling method was used to construct material performance degradation results. First, a multi-field coupling model architecture was established, integrating the electromagnetic, thermal, structural, and fluid multi-physics fields through shared nodes and boundary conditions. For the permanent magnet demagnetization rate, the Jiles-Atherton model was used to describe the hysteresis loop variation, and a temperature correction factor was introduced to map the temperature distribution data in the thermal field to the electromagnetic field calculation. For the lubrication failure coefficient, computational fluid dynamics (CFD) was used to simulate the fluid dynamics properties of the bearing lubricant film. Molecular dynamics was used to simulate the effect of the lubricant film's crystal structure evolution on viscosity and friction coefficient, and mechanical vibration data was converted into fluid boundary conditions. In terms of insulation performance, the finite element method was used to solve the electric field distribution based on the partial discharge inception voltage data. The Weibull statistical model was then combined to describe the insulation aging process. The heat generated by the partial discharge was fed back into the thermal field calculation through the heat conduction equation. The coupled algorithm employs a sequential iterative solution strategy. First, the magnetic field changes caused by permanent magnet demagnetization are calculated in the electromagnetic field and transferred as loads to the structural field. The structural field then calculates the bearing vibration response and transfers the vibration parameters to the fluid field to correct the lubrication film properties. Data is exchanged between the fluid and thermal fields via convective heat transfer coefficients. Finally, the thermal field temperature distribution is fed back into the electromagnetic field and insulation aging models. By setting appropriate convergence criteria (e.g., energy error less than 5%), multiple iterations are performed until a stable solution is achieved. The final output is a comprehensive material degradation curve encompassing magnetic degradation, mechanical wear, and insulation aging, as well as life predictions for key components, providing a quantitative basis for reliability assessment of permanent magnet synchronous motors in space environments.

[0050] In one possible implementation, step S200 further includes:

[0051] Step S250: performing simulation based on the permanent magnet demagnetization rate, the lubrication failure coefficient, and the insulation performance degradation curve to determine the priori probabilities of multiple events.

[0052] Step S260: constructing a failure tree structure of multiple events based on the prior probabilities of multiple events, performing weight analysis on the failure tree structure of multiple events, and determining multiple weight coefficients.

[0053] Step S270: constructing a multi-dimensional failure feature space based on the failure tree structures of multiple events and the multiple weight coefficients.

[0054] Step S280: performing cluster analysis according to the multi-dimensional failure feature space to determine a plurality of cluster centers, wherein the plurality of cluster centers contain a plurality of failure rules, wherein the plurality of cluster centers correspond to the plurality of failure rules.

[0055] Step S290: extracting high-density failure features according to the multiple failure rules, and constructing the spatial environment failure feature library.

[0056] Specifically, to determine the prior probabilities of multiple events, data such as the permanent magnet demagnetization rate, lubrication failure coefficient, and insulation degradation curve were first organized and quantified. Finite element analysis software was used to construct a multi-physics coupled simulation model encompassing the motor's magnetic circuit, mechanical structure, and insulation system. Within the model, parameter variables related to permanent magnet demagnetization, bearing lubrication failure, and insulation degradation were defined. The permanent magnet demagnetization rate was converted into a change in magnetic permeability and input into the magnetic circuit module. The lubrication failure coefficient was reflected in changes in the bearing friction coefficient and lubricant film thickness. The insulation degradation curve was used to describe the time-dependent dielectric strength of the insulation material. Historical data from motor operation in space environments was combined to simulate the motor's operation under various operating conditions. During each simulation run, the number of key failure events, such as permanent magnet demagnetization reaching a certain level, complete bearing lubrication film failure, and insulation breakdown, was counted. After extensive simulation experiments, the number of occurrences of each failure event was divided by the total number of simulations to determine the frequency of each failure event under the current conditions. This frequency was then used as an approximation for the prior probabilities of the multiple events.

[0057] A failure tree is constructed by taking motor system failure as the top event and events related to permanent magnet demagnetization, lubrication failure, and insulation degradation as intermediate and bottom events, connected according to logical causal relationships. For example, if permanent magnet demagnetization causes a decrease in motor torque, thereby affecting system operation, the permanent magnet demagnetization event is considered the bottom event of the events leading to the decrease in motor torque. A weight analysis is performed using the Analytic Hierarchy Process (AHP) to construct a judgment matrix. First, factors influencing the importance of failure events are identified, such as the probability of occurrence, the degree of impact on motor performance, and the difficulty of repair. For each factor, the relative importance of different failure events is compared pairwise and assigned a value to construct a judgment matrix. Next, the maximum eigenvalue and eigenvector of the judgment matrix are calculated, and consistency checks are performed to ensure the rationality of the judgment. The elements in the eigenvector represent the relative weight of each failure event for that factor. By comprehensively considering the weights of all factors, a weighted average method is used to determine the final weight coefficient for each failure event.

[0058] A four-dimensional failure feature space is constructed based on the failure tree structure and weight coefficients. The specific implementation is as follows: the bottom events of the failure tree are mapped into the four dimensions of the feature space, where the permanent magnet demagnetization rate η is used as the magnetic performance dimension, the lubrication failure coefficient is converted to the mechanical degradation degree δ as the mechanical performance dimension, the bearing wear is converted to the wear degree ω as the structural performance dimension, and the natural logarithm of the vacuum degree P of the space environment is used as the environmental dimension. The prior probability of the bottom event is used as the coordinate origin of each dimension, and the weight coefficient is used as a scaling factor to weight the coordinates. For the logic gates in the failure tree, the probability propagation algorithm is used to calculate the position vectors of the intermediate and top events in the four-dimensional space. For example, if an intermediate event is connected by the demagnetization rate η and the degradation degree δ through an AND gate, its coordinate value is the product of the coordinate values of the two bottom events multiplied by the corresponding weight coefficient. A time dimension is introduced to form a dynamic coordinate system, and time-varying parameters such as the insulation degradation curve are used as dynamic coordinates on the time axis. Monte Carlo simulation is used to generate a large number of random sample points to verify the completeness of the feature space. Finally, a failure feature space consisting of four dimensions, namely, magnetic-mechanical-structural-environmental, was constructed. Each dimension carries physical meaning and weight information, providing a structured data basis for subsequent cluster analysis.

[0059] After constructing the multidimensional failure feature space, a cluster analysis algorithm is applied to the data points within this space. Cluster analysis divides data points into clusters based on their similarities, with each cluster having a corresponding cluster center. During the analysis process, clustering algorithms such as K-Means are used, and through continuous iteration, data points are gradually approximated to their most appropriate cluster centers. While determining the cluster centers, in-depth analysis is conducted on the characteristics of the data points encompassed by each cluster center. Based on the distribution patterns of dimensional data such as the permanent magnet demagnetization rate, lubrication failure coefficient, and insulation degradation curve, failure rules applicable to each cluster center are summarized. For example, if the majority of data points within a cluster center exhibit a permanent magnet demagnetization rate exceeding a certain threshold and a lubrication failure coefficient within a specific range, a failure rule can be defined as a permanent magnet demagnetization rate greater than X and a lubrication failure coefficient within the range YZ. Each cluster center is associated with a unique set of failure rules that accurately describe the motor failure mode represented by that cluster center, providing a key basis for the subsequent construction of a spatial environment failure feature library.

[0060] After obtaining multiple failure rules, the data related to these rules is comprehensively sorted and analyzed. For each failure rule, data samples that meet the rule are screened from a large amount of motor operating data. The various failure features contained in these samples, such as the permanent magnet demagnetization rate, lubrication failure coefficient, and insulation degradation parameters, are of particular interest. Statistical analysis methods are used to calculate the frequency and distribution of each feature in the data samples that meet the corresponding failure rule. Features with high frequency and critical indicative significance for failure determination are identified as high-density failure features. For example, if, under a certain failure rule, the probability of motor failure is extremely high when the permanent magnet demagnetization rate reaches a certain value range, then this demagnetization rate value range is considered a high-density failure feature. All high-density failure features extracted from different failure rules are integrated, classified, and organized according to a specific storage structure and indexing method to construct a spatial environment failure feature library. This feature library quickly and accurately provides a reference for abnormal pattern identification during real-time monitoring of permanent magnet synchronous motor operating parameters, significantly improving the efficiency and accuracy of motor failure detection.

[0061] In one possible implementation, step S300 further includes:

[0062] Step S310: collecting data from the permanent magnet synchronous motor in real time using a high-frequency current probe to obtain parameters of three-phase current harmonic components.

[0063] Step S320: Real-time data acquisition is performed on the permanent magnet synchronous motor through a distributed optical fiber temperature sensor to obtain winding temperature gradient parameters.

[0064] Step S330: collecting data of the permanent magnet synchronous motor in real time through a vibration sensor to obtain axial vibration acceleration parameters.

[0065] Step S340: performing wavelet packet transformation based on the three-phase current harmonic component parameters to extract characteristic energy values of a fixed frequency band, wherein the characteristic energy values include the current harmonic distortion rate.

[0066] Step S350: performing fluctuation calculation based on the winding temperature gradient parameter to determine the temperature gradient standard deviation.

[0067] Step S360: performing feature separation based on the axial vibration acceleration parameter to determine the fretting wear characteristic frequency, where the fretting wear characteristic frequency includes vibration characteristic energy entropy.

[0068] Step S370: Integrate the current harmonic distortion rate, the temperature gradient standard deviation, and the vibration characteristic energy entropy to construct a composite operation monitoring vector, and add the composite operation monitoring vector to the motor operation parameter set.

[0069] Specifically, parameter acquisition is first performed. A high-frequency current probe is used to collect the motor's three-phase current in real time. Fast Fourier Transform (FFT) is then used to convert the time-domain current signal into the frequency domain, thereby obtaining the parameters of the three-phase current harmonic components. These parameters reflect changes in the motor's electrical performance.

[0070] At the same time, the motor winding temperature is monitored in real time with the help of distributed optical fiber temperature sensors. The sensor can accurately measure the temperature at different positions of the winding, and then obtain the winding temperature gradient parameter, which can effectively reflect the heat distribution inside the winding.

[0071] In addition, a vibration sensor is used to collect the axial vibration of the motor in real time to obtain the axial vibration acceleration parameter, which is closely related to the mechanical structure state of the motor.

[0072] Then feature extraction and calculation are carried out. The collected three-phase current harmonic component parameters are processed using wavelet packet transform. Wavelet packet transform can decompose the signal into different frequency bands. By extracting the characteristic energy value of a fixed frequency band, the current harmonic distortion rate can be calculated. This indicator is an important parameter for measuring the quality of motor current.

[0073] After obtaining the winding temperature gradient parameters, a fluctuation calculation is performed to determine the temperature gradient standard deviation. The collected winding temperature gradient data is first arranged in chronological order, and the temperature gradient differences between adjacent time points are calculated to obtain a series of gradient change values. Next, a statistical method is used to calculate the mean of these gradient change values. The standard deviation of the temperature gradient is calculated by taking the sum of the squares of the differences between each gradient change value and the mean, dividing the sum by the number of data points minus 1, and taking the square root. This effectively reflects the degree of fluctuation in the winding temperature gradient.

[0074] For axial vibration acceleration parameters, methods such as wavelet transforms or time-frequency analysis are used to perform feature separation. These methods filter frequency components related to fretting wear from the complex vibration signal and determine the characteristic frequency of fretting wear. During this process, the energy distribution of the vibration signal at different frequency bands is calculated to derive the vibration characteristic energy entropy, which measures the complexity and disorder of the vibration signal.

[0075] Finally, the three key parameters obtained previously—current harmonic distortion, temperature gradient standard deviation, and vibration characteristic energy entropy—are integrated. These parameters are combined in a specific order to construct a composite operation monitoring vector. For example, a three-dimensional vector is formed with current harmonic distortion as the first element, temperature gradient standard deviation as the second element, and vibration characteristic energy entropy as the third element. Once constructed, this composite operation monitoring vector is added to the motor operating parameter set, providing an important basis for subsequent comprehensive evaluation of the permanent magnet synchronous motor's operating status and facilitating the timely detection of potential motor failure hazards.

[0076] In one possible implementation, step S300 further includes:

[0077] Step S380: Perform feature dimensionality reduction based on the composite operation monitoring vector to determine a composite dimensionality reduction vector; use the composite dimensionality reduction vector as an index to traverse the spatial environment failure feature library for similarity matching to generate multiple matching degrees; when there is a matching degree exceeding a preset warning value among the multiple matching degrees, trigger an online reconfiguration instruction, perform fault analysis through the online reconfiguration instruction, and construct multiple abnormal labels; trace back to the motor operation parameter set according to the multiple abnormal labels for identification, and determine the abnormal mode according to the identification result.

[0078] Specifically, after obtaining the composite operation monitoring vector, a combination of principal component analysis (PCA) and kernel principal component analysis (KPCA) is used to perform feature dimensionality reduction. First, the original vector is standardized and preprocessed to eliminate the impact of dimensional differences in different parameters. By calculating the eigenvalues and eigenvectors of the feature covariance matrix, principal components whose cumulative contribution rates exceed a preset threshold are extracted to achieve linear dimensionality reduction. KPCA with a Gaussian kernel function is also applied to process nonlinear features. Using kernel techniques, the data is mapped to a high-dimensional space before principal component extraction. Hypothesis testing methods are used to analyze the differences between the two dimensionality reduction results, and dimensionality reduction schemes are dynamically selected or combined based on the test results. Finally, through feature importance assessment, the core dimensions with the highest fault sensitivity are retained to construct a composite dimensionality reduction vector.

[0079] When using the composite reduced dimensionality vector as an index for similarity matching, a hash algorithm is first used to preprocess the data in the spatial environment failure signature database. A unique hash value is generated for each failure signature vector, and the vector is stored in the corresponding hash bucket based on the hash value to construct a hash table. This allows subsequent searches to quickly locate the region containing potentially matching vectors, significantly reducing the number of searches. When calculating similarity, the cosine similarity formula is used to measure the degree of similarity between the composite reduced dimensionality vector and vectors in the failure signature database. For each candidate vector retrieved from the hash bucket, its cosine similarity with the composite reduced dimensionality vector is calculated. After traversing all relevant candidate vectors, a matching score is generated for each candidate vector. These matching scores reflect the degree of similarity between the composite reduced dimensionality vector and each candidate vector. Values closer to 1 indicate a higher similarity between the two vectors, while values closer to 0 indicate a lower similarity. Finally, the generated matching scores are organized into a list for easy screening and analysis, providing a basis for determining the match between the motor's current operating state and known failure modes.

[0080] When the monitoring system detects a match exceeding a preset warning value among multiple matching degrees, it immediately triggers an online reconfiguration instruction. A deep learning-based fault analysis process is initiated, utilizing a convolutional neural network (CNN) to deeply mine fault features. First, the CNN automatically extracts high-level fault features hidden within the data using a composite dimensionality reduction vector as input through multiple convolutional and pooling layers. These features are correlated with data patterns in a spatial environmental failure signature library. A comparative learning algorithm further enhances the understanding and differentiation of fault features. Simultaneously, a decision tree-based classification algorithm is used to classify the extracted features. Based on pre-set decision rules, the decision tree gradually determines the fault type based on key parameters such as current harmonic distortion, temperature gradient standard deviation, and vibration signature energy entropy. During the analysis process, a support vector machine (SVM) is used to delineate fault data boundaries, improving classification accuracy and stability. Finally, the results of these algorithms are combined to construct multiple anomaly labels. These labels cover various fault conditions that may occur in permanent magnet synchronous motors in space environments, such as permanent magnet demagnetization, bearing wear, winding insulation aging, etc., providing a detailed and accurate basis for subsequent determination of the motor's abnormal mode.

[0081] After constructing multiple anomaly labels, the system uses spatiotemporal indexing to quickly locate the raw measurement data segment corresponding to the motor's operating parameter set based on the fault feature keywords in the labels. Parameter sequences, such as current harmonic distortion, temperature gradient standard deviation, and vibration characteristic energy entropy, are extracted before and after the label generation moment. Granger causality testing is then applied to identify strongly correlated parameter subsets. A Bayesian network is used to construct a fault propagation probability model, analyzing the temporal dependence of parameter changes and the strength of causal relationships. A dynamic time warping (DTW) algorithm is used to match parameter sequences with standard fault patterns in the feature library. When parameter subsets corresponding to multiple labels form a closed-loop causal chain and the similarity exceeds a preset threshold, a specific anomaly pattern is identified. Finally, the anomaly pattern is mapped to a fault ontology library, generating a multidimensional diagnostic report that includes the fault type, development stage, and impact range, providing a decision-making basis for fault isolation and repair.

[0082] In one possible implementation, step S300 further includes:

[0083] Step S390: extract the bearing wear value and the winding insulation degradation value of the permanent magnet synchronous motor according to the abnormal mode; perform a multivariate degradation failure analysis based on the bearing wear value and the winding insulation degradation value to determine the joint failure probability; construct a Markov chain for prediction based on the joint failure probability, construct a risk evolution trend, perform a failure impact analysis based on the risk evolution trend, and set a failure risk level.

[0084] Specifically, after identifying the abnormal patterns of the permanent magnet synchronous motor, the team began extracting relevant key data. For bearing wear values, the team used the axial vibration acceleration parameters continuously collected by the vibration sensor to convert the time-domain vibration signal into a frequency-domain signal through a fast Fourier transform to obtain the vibration spectrum. The team then analyzed the amplitude changes in specific frequency bands within the spectrum (such as characteristic frequencies associated with bearing failures) and combined them with a pre-built mapping model between vibration amplitude and bearing wear, which was derived from fitting a large amount of experimental data. For example, when the vibration amplitude reaches a certain threshold within the 100Hz-200Hz frequency band, the corresponding bearing wear value can be calculated based on the model. Regarding the winding insulation degradation value, a comprehensive analysis is performed using the winding temperature gradient parameters obtained by the distributed fiber optic temperature sensor, combined with the three-phase current harmonic component parameters collected by the high-frequency current probe. First, the partial discharge inception voltage is calculated based on the current harmonic data, because partial discharge is an important indicator of winding insulation degradation. Then, based on the relationship between the temperature gradient and the insulation aging rate, combined with the pre-drawn insulation performance degradation curve (this curve is obtained from aging experiments under different temperature and voltage conditions), the degree of winding insulation degradation over time at the current temperature and partial discharge inception voltage is determined, and the winding insulation degradation value is then obtained.

[0085] After obtaining bearing wear and winding insulation degradation values, the joint failure probability is determined by combining a long short-term memory (LSTM) network with an extreme learning machine (ELM). The bearing wear and winding insulation degradation values, as well as relevant data such as the ambient temperature and load change rate during motor operation, are normalized and then fed into the LSTM network in a time series format. The LSTM network effectively captures long-term dependencies in the data. Through its internal forget gate, input gate, and output gate mechanisms, it filters out historical data features that are significantly impactful on motor failure. Next, the feature vector output by the LSTM network is fed into the extreme learning machine (ELM). The ELM randomly generates connection weights between the input and hidden layers and thresholds for the hidden layer neurons. Training is fast, requiring only a specific number of hidden layer neurons. It further performs classification and regression on the features extracted by the LSTM, establishing a complex nonlinear relationship between the input features and motor failure. Finally, the ELM outputs the motor's joint failure probability.

[0086] Based on the determined joint failure probability, a Markov chain is constructed to predict motor state changes, establish risk evolution trends, and assign failure risk levels. First, the operating states of the permanent magnet synchronous motor are divided into discrete states: normal, mild abnormality, moderate abnormality, and severe fault. Based on the joint failure probability and the motor's historical operating data, the transition probabilities between different states are determined, and a state transition probability matrix is constructed. For example, data analysis reveals that if the motor is currently in the normal state, the probability of transitioning to the mild abnormality state at the next moment is 0.1. The probabilities of transitioning to other states are determined accordingly and entered into the matrix. Next, the constructed Markov chain is used to simulate the motor's future operating state changes through multiple iterations. In each iteration, the next state is randomly determined based on the current state and the state transition probability matrix. After multiple iterations, a series of state change sequences is generated, and a risk evolution trend is constructed, visually displaying the changing probabilities of the motor being in different states at different time points. Based on the risk evolution trends, a failure impact analysis is performed to assess the impact of the motor on the entire system (such as a satellite system) under different risk states. For mild motor anomalies, the impact on satellite attitude control accuracy and energy consumption is analyzed. For moderate and severe fault conditions, the impact on satellite mission execution and component damage is assessed and quantified. For example, a mild anomaly can cause a 2% decrease in attitude control accuracy, while a moderate anomaly can increase energy consumption by 10%. Finally, a failure risk level is assigned based on the severity of the failure. The risk levels are categorized as low, medium, and high. If the motor is likely to remain normal for a period of time, and even a mild anomaly has minimal impact on the system, the risk level is low. If there is a certain probability of a moderate anomaly with a significant impact on system performance, the risk level is medium. If there is a high probability of a severe fault, which could severely impact the system or even cause mission failure, the risk level is high. This approach provides a clear basis for subsequent targeted maintenance measures.

[0087] In one possible implementation, step S390 further includes:

[0088] Step S391: setting a preset critical value based on the failure risk level, and comparing the combined failure probability with the preset critical value.

[0089] Step S392: When the combined failure probability exceeds the preset critical value, activating the demagnetization compensation instruction.

[0090] Step S393: performing multi-objective optimization through the demagnetization compensation instruction, constructing multi-level failure warning data, performing maintenance control based on the multi-level failure warning data, and formulating the failure maintenance suggestion.

[0091] Specifically, based on the established failure risk levels, corresponding thresholds are set for low, medium, and high levels. For example, the threshold for low risk is 0.3, for medium risk is 0.6, and for high risk is 0.8. The calculated joint failure probability is compared with these thresholds to determine the current risk status of the motor.

[0092] During the motor failure monitoring process, once the combined failure probability is calculated, it is compared in real time with a preset critical value. Once the system determines that the combined failure probability exceeds the preset critical value, it immediately triggers the demagnetization compensation mechanism and activates the demagnetization compensation command. At this point, the monitoring system quickly sends a signal to the motor's control system. Upon receiving the command, the control system immediately initiates a pre-set demagnetization compensation program. This program accurately analyzes the motor's demagnetization condition based on the motor's current operating parameters, such as the three-phase current harmonic components, winding temperature gradients, and axial vibration acceleration, combined with previously accumulated failure signature data. The control system then adjusts the motor's control strategy based on the analysis results, such as by varying the current magnitude, phase, and frequency. Through precise current regulation, a compensating magnetic field in the opposite direction of the demagnetization field is generated, offsetting the weakening of the magnetic field caused by demagnetization. This maintains the motor's normal performance and ensures continued stable operation despite the risk of demagnetization.

[0093] A particle swarm optimization (PSO) algorithm is used for multi-objective optimization, with the optimization objectives being improving motor efficiency, minimizing torque ripple, and controlling temperature rise within a reasonable range. A swarm of particles is initialized, each representing a set of motor control parameters (such as current amplitude and phase angle). The particle's position and velocity are randomly distributed in the solution space. In each iteration, the particle updates its velocity and position based on its own historical optimal position and the swarm's historical optimal position, continuously approaching the optimal solution. Through multiple iterations of optimization, a series of compensation parameter combinations that meet the multi-objective requirements are obtained. Based on these optimized parameters, multi-level failure warning data is constructed in conjunction with real-time motor operating data. Clustering algorithms (such as DBSCAN) are used to analyze the motor operating parameters and classify the motor operating status into four levels: normal, slightly abnormal, moderately abnormal, and severely abnormal. A corresponding threshold is set for each level. For example, under normal conditions, the current harmonic distortion rate is within 5%, slightly abnormal is 5% to 10%, moderately abnormal is 10% to 20%, and severely abnormal is greater than 20%. Maintenance control and failure maintenance recommendations are formulated based on this multi-level failure warning data. If the motor is in normal condition, arrange regular periodic maintenance inspections; if there is a slight abnormality, increase the monitoring frequency and pay close attention to changes in the motor operating parameters; if there is a moderate abnormality, remind you to prepare to replace wearing parts (such as bearings) and arrange technicians to be on standby; if there is a serious abnormality, immediately issue an emergency alarm, stop the motor operation, and guide technicians to perform a comprehensive overhaul of the motor, such as replacing permanent magnets, repairing winding insulation, etc., to ensure safe and stable operation of the motor.

[0094] Embodiment 2 is based on the same inventive concept as the permanent magnet synchronous motor failure monitoring method for space environment in the above embodiment. Figure 2 As shown, the present application provides a permanent magnet synchronous motor failure monitoring system for a space environment. The system and method embodiments in the present application are based on the same inventive concept. The system includes:

[0095] The multi-dimensional degradation data acquisition module 10 is used to construct a simulated space environment experimental chamber, which includes extreme temperature cycle conditions and high vacuum conditions. The accelerated aging experiment of the permanent magnet synchronous motor is carried out through the simulated space environment experimental chamber to obtain multi-dimensional degradation data.

[0096] The feature library construction module 20 is used to evaluate the material performance of the permanent magnet synchronous motor based on the multi-dimensional degradation data, determine the material performance degradation results, perform failure analysis according to the material performance degradation results, and construct a space environment failure feature library.

[0097] The failure maintenance suggestion formulation module 30 is used to monitor the motor operating parameter set of the permanent magnet synchronous motor in real time, match the motor operating parameter set with the space environment failure feature library, determine the abnormal mode, predict the failure risk level according to the abnormal mode, and formulate failure maintenance suggestions according to the failure risk level.

[0098] Furthermore, the system is also used to implement the following functions:

[0099] A ladder temperature cycle is performed according to the extreme temperature cycle conditions of the cabin in the simulated space environment. A multi-type sensor array is arranged on the motor stator winding, permanent magnet surface, and bearing seat of the permanent magnet motor according to the high vacuum conditions of the cabin in the simulated space environment to synchronously collect temperature distribution signals, vibration signals, and current harmonic signals; the temperature distribution signal is filtered and denoised to obtain motor temperature distribution data, the vibration signal is subjected to empirical mode decomposition to obtain vibration spectrum data, and the current harmonic signal is transformed to obtain current harmonic data; the motor temperature distribution data, the vibration spectrum data, and the current harmonic data are fused in the time and frequency domain to generate the multi-dimensional degradation data.

[0100] Furthermore, the system is also used to implement the following functions:

[0101] Based on the motor temperature distribution data, the number of temperature cycles is determined to perform a demagnetization curve test on the permanent magnet synchronous motor to obtain the demagnetization rate of the permanent magnet; based on the vibration spectrum data, the crystal structure evolution of the bearing lubrication film of the permanent magnet synchronous motor is performed to generate a lubrication failure coefficient; based on the current harmonic data, the partial discharge starting voltage of the permanent magnet synchronous motor material is calculated to draw an insulation performance degradation curve; the permanent magnet demagnetization rate, the lubrication failure coefficient, and the insulation performance degradation curve are coupled by multi-physics fields to construct the material performance degradation result.

[0102] Furthermore, the system is also used to implement the following functions:

[0103] Based on the demagnetization rate of the permanent magnet, the lubrication failure coefficient, and the insulation performance degradation curve, simulation is performed to determine the prior probabilities of multiple events; based on the prior probabilities of multiple events, a failure tree structure of multiple events is constructed, and a weight analysis is performed on the failure tree structure of multiple events to determine multiple weight coefficients; based on the failure tree structure of multiple events and the multiple weight coefficients, a multidimensional failure feature space is constructed; cluster analysis is performed according to the multidimensional failure feature space to determine multiple cluster centers, wherein the multiple cluster centers contain multiple failure rules, wherein there is a corresponding relationship between the multiple cluster centers and the multiple failure rules; high-density failure features are extracted according to the multiple failure rules to construct the spatial environment failure feature library.

[0104] Furthermore, the system is also used to implement the following functions:

[0105] Real-time data acquisition of the permanent magnet synchronous motor is performed through a high-frequency current probe to obtain the three-phase current harmonic component parameters; real-time data acquisition of the permanent magnet synchronous motor is performed through a distributed optical fiber temperature sensor to obtain the winding temperature gradient parameters; real-time data acquisition of the permanent magnet synchronous motor is performed through a vibration sensor to obtain the axial vibration acceleration parameters; wavelet packet transform is performed based on the three-phase current harmonic component parameters to extract the characteristic energy value of a fixed frequency band, and the characteristic energy value includes the current harmonic distortion rate; fluctuation calculation is performed based on the winding temperature gradient parameters to determine the temperature gradient standard deviation; feature separation is performed based on the axial vibration acceleration parameters to determine the micro-wear characteristic frequency, and the micro-wear characteristic frequency includes the vibration characteristic energy entropy; the current harmonic distortion rate, the temperature gradient standard deviation, and the vibration characteristic energy entropy are integrated to construct a composite operation monitoring vector, and the composite operation monitoring vector is added to the motor operation parameter set.

[0106] Furthermore, the system is also used to implement the following functions:

[0107] Based on the composite operation monitoring vector, feature dimensionality reduction is performed to determine a composite dimensionality reduction vector; using the composite dimensionality reduction vector as an index, the spatial environment failure feature library is traversed to perform similarity matching to generate multiple matching degrees; when a matching degree among the multiple matching degrees exceeds a preset warning value, an online reconfiguration instruction is triggered, fault analysis is performed through the online reconfiguration instruction, and multiple abnormality labels are constructed; according to the multiple abnormality labels, the motor operation parameter set is traced back for identification, and the abnormal mode is determined according to the identification result.

[0108] Furthermore, the system is also used to implement the following functions:

[0109] According to the abnormal pattern, the bearing wear value and the winding insulation degradation value of the permanent magnet synchronous motor are extracted; based on the bearing wear value and the winding insulation degradation value, a multivariate degradation failure analysis is performed to determine the joint failure probability; based on the joint failure probability, a Markov chain is constructed for prediction, a risk evolution trend is constructed, and a failure impact analysis is performed based on the risk evolution trend to set a failure risk level.

[0110] Furthermore, the system is also used to implement the following functions:

[0111] A preset critical value is set based on the failure risk level, and the combined failure probability is compared with the preset critical value for determination; when the combined failure probability exceeds the preset critical value, a demagnetization compensation instruction is activated; multi-objective optimization is performed using the demagnetization compensation instruction, multi-level failure warning data is constructed, maintenance control is performed based on the multi-level failure warning data, and the failure maintenance recommendation is formulated.

[0112] Example 3, Figure 3 A structural schematic diagram of an electronic device provided for the permanent magnet synchronous motor failure monitoring method for a space environment of the present invention shows a block diagram of an exemplary electronic device suitable for implementing an embodiment of the present invention. Figure 3 The electronic device shown is only an example and should not limit the functions and scope of use of the embodiments of the present invention. Figure 3 As shown, the electronic device includes a processor 21, a memory 22, an input device 23 and an output device 24; the number of processors 21 in the electronic device can be one or more. Figure 3 Taking a processor 21 as an example, the processor 21, memory 22, input device 23 and output device 24 in the electronic device can be connected through a bus or other means. Figure 3 The bus connection is taken as an example.

[0113] It should be noted that the order in which the embodiments of the present application are presented is for illustrative purposes only and does not necessarily represent the superiority or inferiority of the embodiments. Furthermore, the foregoing descriptions of specific embodiments of this specification are provided. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order or sequential sequence shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0114] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should be included in the scope of protection of the present application.

[0115] This specification and drawings are merely illustrative of the present application and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Obviously, those skilled in the art may make various modifications and variations to this application without departing from the scope of this application. Thus, this application is intended to include such modifications and variations as fall within the scope of this application and its equivalents.

Claims

1. A permanent magnet synchronous motor failure monitoring method for a space environment, characterized in that: The method comprises: Constructing a simulated space environment test chamber, which includes extreme temperature cycling conditions and high vacuum conditions, to conduct accelerated aging experiments on permanent magnet synchronous motors in the simulated space environment test chamber to obtain multi-dimensional degradation data; Performing material performance evaluation on the permanent magnet synchronous motor based on the multi-dimensional degradation data, determining material performance degradation results, performing failure analysis based on the material performance degradation results, and constructing a space environment failure feature library; real-time monitoring of a motor operating parameter set of a permanent magnet synchronous motor, matching the motor operating parameter set with the space environment failure feature library, determining an abnormality pattern, predicting a failure risk level according to the abnormality pattern, and formulating a failure maintenance recommendation based on the failure risk level; Constructing a simulated space environment test chamber, wherein the simulated space environment test chamber includes extreme temperature cycle conditions and high vacuum conditions, and conducting accelerated aging experiments on a permanent magnet synchronous motor in the simulated space environment test chamber to obtain multi-dimensional degradation data, the method comprising: Performing a ladder temperature cycle according to the extreme temperature cycle conditions of the cabin in the simulated space environment, and deploying a multi-type sensor array on the stator winding, permanent magnet surface, and bearing seat of the permanent magnet motor to synchronously collect temperature distribution signals, vibration signals, and current harmonic signals according to the high vacuum conditions of the cabin in the simulated space environment; Filtering and denoising the temperature distribution signal to obtain motor temperature distribution data, performing empirical mode decomposition on the vibration signal to obtain vibration spectrum data, and transforming the current harmonic signal to obtain current harmonic data; Performing time-frequency domain fusion processing on the motor temperature distribution data, the vibration spectrum data, and the current harmonic data to generate the multi-dimensional degradation data; Performing material performance evaluation on the permanent magnet synchronous motor based on the multi-dimensional degradation data to determine a material performance degradation result, the method comprising: Based on the motor temperature distribution data, after determining the number of temperature cycles, a demagnetization curve test is performed on the permanent magnet synchronous motor to obtain a permanent magnet demagnetization rate; performing a crystal structure evolution analysis on a bearing lubricating film of a permanent magnet synchronous motor based on the vibration spectrum data to generate a lubrication failure coefficient; Calculating the partial discharge inception voltage of the permanent magnet synchronous motor material based on the current harmonic data and drawing an insulation performance degradation curve; The demagnetization rate of the permanent magnet, the lubrication failure coefficient, and the insulation performance degradation curve are coupled by multi-physics fields to construct the material performance degradation result.

2. The permanent magnet synchronous motor failure monitoring method for space environment according to claim 1, characterized in that: Performing failure analysis based on the material performance degradation results and building a space environment failure feature library, the method includes: Performing simulation based on the permanent magnet demagnetization rate, the lubrication failure coefficient, and the insulation performance degradation curve to determine a priori probabilities of multiple events; constructing a failure tree structure of multiple events based on the prior probabilities of the multiple events, performing weight analysis on the failure tree structure of the multiple events, and determining multiple weight coefficients; Constructing a multidimensional failure feature space based on the failure tree structure of multiple events and the multiple weight coefficients; Performing cluster analysis according to the multidimensional failure feature space to determine a plurality of cluster centers, wherein the plurality of cluster centers contain a plurality of failure rules, wherein the plurality of cluster centers correspond to the plurality of failure rules; High-density failure features are extracted according to the multiple failure rules to construct the spatial environment failure feature library.

3. The permanent magnet synchronous motor failure monitoring method for space environment according to claim 1, characterized in that: Real-time monitoring of a motor operating parameter set of a permanent magnet synchronous motor, including: The high-frequency current probe is used to collect the current of the permanent magnet synchronous motor in real time to obtain the three-phase current harmonic component parameters; The distributed optical fiber temperature sensor is used to collect data on the permanent magnet synchronous motor in real time to obtain the winding temperature gradient parameters. The vibration sensor is used to collect data from the permanent magnet synchronous motor in real time to obtain the axial vibration acceleration parameters; Performing wavelet packet transformation based on the three-phase current harmonic component parameters to extract characteristic energy values of a fixed frequency band, wherein the characteristic energy values include the current harmonic distortion rate; Performing fluctuation calculation based on the winding temperature gradient parameter to determine the temperature gradient standard deviation; Performing feature separation based on the axial vibration acceleration parameter to determine a fretting wear characteristic frequency, wherein the fretting wear characteristic frequency includes vibration characteristic energy entropy; The current harmonic distortion rate, the temperature gradient standard deviation, and the vibration characteristic energy entropy are integrated to construct a composite operation monitoring vector, and the composite operation monitoring vector is added to the motor operation parameter set.

4. The permanent magnet synchronous motor failure monitoring method for space environment according to claim 3, characterized in that: Matching the motor operating parameter set with the space environment failure feature library to determine an abnormal mode, the method comprising: Performing feature dimensionality reduction based on the composite operation monitoring vector to determine a composite dimensionality reduction vector; Using the composite dimensionality reduction vector as an index, traversing the spatial environment failure feature library to perform similarity matching, and generating multiple matching degrees; When a matching degree among the multiple matching degrees exceeds a preset warning value, an online reconfiguration instruction is triggered, and a fault analysis is performed through the online reconfiguration instruction to construct multiple abnormal labels; The motor operation parameter set is traced back according to the multiple abnormal tags for identification, and the abnormal mode is determined according to the identification result.

5. The permanent magnet synchronous motor failure monitoring method for space environment according to claim 1, characterized in that: The method for predicting the failure risk level according to the abnormal mode includes: Extracting bearing wear values and winding insulation degradation values of the permanent magnet synchronous motor according to the abnormal pattern; Performing a multivariate degradation failure analysis based on the bearing wear value and the winding insulation degradation value to determine a combined failure probability; A Markov chain is constructed based on the joint failure probability for prediction, a risk evolution trend is constructed, a failure impact analysis is performed based on the risk evolution trend, and a failure risk level is set.

6. The permanent magnet synchronous motor failure monitoring method for space environment according to claim 5, characterized in that: Formulate failure maintenance recommendations based on the failure risk level, including: Setting a preset critical value based on the failure risk level, and comparing the combined failure probability with the preset critical value; When the combined failure probability exceeds the preset critical value, activating a demagnetization compensation instruction; Multi-objective optimization is performed through the demagnetization compensation instruction to construct multi-level failure warning data, maintenance control is performed based on the multi-level failure warning data, and the failure maintenance suggestion is formulated.

7. A permanent magnet synchronous motor failure monitoring system for space environment, characterized in that: The system is used to implement the permanent magnet synchronous motor failure monitoring method for a space environment according to any one of claims 1 to 6, and the system includes: A multi-dimensional degradation data acquisition module is used to construct a simulated space environment test chamber, which includes extreme temperature cycling conditions and high vacuum conditions. The simulated space environment test chamber is used to conduct accelerated aging experiments on permanent magnet synchronous motors to obtain multi-dimensional degradation data. A feature library construction module is used to perform material performance evaluation on the permanent magnet synchronous motor based on the multi-dimensional degradation data, determine the material performance degradation results, perform failure analysis based on the material performance degradation results, and construct a space environment failure feature library; A failure maintenance suggestion formulation module is used to monitor the motor operating parameter set of the permanent magnet synchronous motor in real time, match the motor operating parameter set with the space environment failure feature library, determine the abnormal pattern, predict the failure risk level according to the abnormal pattern, and formulate failure maintenance suggestions according to the failure risk level.

8. An electronic device, characterized in that: The electronic device comprises: processor; a memory for storing instructions executable by the processor; Wherein, the processor is used to execute the permanent magnet synchronous motor failure monitoring method for space environment as described in any one of claims 1 to 6.

Images