Step motor life prediction method and system based on multi-physical field coupling

Abstract

The application relates to the technical field of motor life prediction, and provides a stepping motor life prediction method and system based on multi-physical field coupling, electrical parameters of a stepping motor, multi-physical field data in a running state and a multi-dimensional feature vector corresponding to the multi-physical field data are acquired, a physical damage index corresponding to the stepping motor is determined according to the electrical parameters, the multi-physical field data and a preset physical damage index calculation formula, the multi-dimensional feature vector is input into a trained data-driven model, a data-driven damage index corresponding to the stepping motor is acquired, and a life prediction result of the stepping motor is acquired according to the physical damage index, the data-driven damage index and a preset life prediction formula. In this way, the influence of the multi-physical field data on the life of the stepping motor can be comprehensively considered, the limitation of a single mode in predicting the life of the stepping motor is overcome by fusing the physical damage index and the data-driven damage index, and the accuracy of the life prediction result of the stepping motor is improved.

Description

Technical Field

[0001] This invention relates to the field of motor life prediction technology, and in particular to a method and system for predicting the life of a stepper motor based on multi-physics coupling. Background Technology

[0002] As a core actuator for spacecraft attitude control, antenna drive, and precision pointing mechanisms, the reliability of aerospace stepper motors directly impacts the success of the entire mission. In the extreme environment of space, the combined effects of drastic temperature changes, high-energy particle radiation, microgravity, and high vacuum can cause irreversible performance degradation in critical stepper motor components, such as permanent magnets and bearings. In particular, mechanical deformation caused by uneven thermal expansion and demagnetization of permanent magnets severely affect the lifespan of stepper motors, thereby reducing their reliability.

[0003] Therefore, to address the aforementioned issues, existing technologies employ data-driven deep learning methods to predict the lifespan of stepper motors. Specifically, by learning from historical operating data using neural networks, accurate predictions of stepper motor performance degradation are achieved, thereby obtaining their remaining lifespan, which improves the reliability of stepper motors to some extent. However, existing technologies suffer from low prediction accuracy when forecasting stepper motor lifespan. Summary of the Invention

[0004] Therefore, it is necessary to provide a stepper motor life prediction method and system based on multi-physics coupling to address the above-mentioned technical problems. This method can comprehensively consider the impact of multi-physics data on the life of the stepper motor. Furthermore, by fusing the physical damage index and the data-driven damage index, it overcomes the limitations of a single mode in predicting the life of the stepper motor, thereby significantly improving the accuracy of the life prediction results.

[0005] In a first aspect, embodiments of the present invention provide a stepper motor life prediction method based on multi-physics coupling, the method comprising:

[0006] Obtain the electrical parameters of the stepper motor, the multi-physics field data during operation, and the multi-dimensional feature vector corresponding to the multi-physics field data;

[0007] The physical damage index corresponding to the stepper motor is determined based on the electrical parameters, the multi-physics field data, and the preset physical damage index calculation formula.

[0008] The multidimensional feature vector is input into the trained data-driven model to obtain the data-driven damage index corresponding to the stepper motor;

[0009] The life prediction result of the stepper motor is obtained based on the physical damage index, the data-driven damage index, and the preset life prediction formula.

[0010] In one embodiment, determining the physical damage index corresponding to the stepper motor based on the electrical parameters, the multiphysics data, and a preset physical damage index calculation formula includes:

[0011] Based on the electrical parameters and the multiphysics data, the demagnetization rate and thermally induced displacement of the permanent magnet are determined.

[0012] The physical damage index is calculated by substituting the permanent magnet demagnetization rate and the thermally induced displacement into the preset physical damage index calculation formula.

[0013] In one embodiment, the electrical parameters include: number of motor winding turns, constant magnetomotive force, number of motor pole pairs, and bearing length; the multiphysics data includes: two-phase current, bearing temperature, and rotor position mechanical angle; and determining the permanent magnet demagnetization rate and thermally induced displacement based on the electrical parameters and the multiphysics data includes:

[0014] The magnetic flux density is obtained based on the number of motor pole pairs, the rotor position mechanical angle, the constant magnetomotive force, the number of motor winding turns, and the two-phase current.

[0015] The demagnetization rate of the permanent magnet is obtained based on the bearing temperature and the magnetic flux density.

[0016] The thermally induced displacement is obtained based on the bearing length, the bearing temperature, and the ambient temperature.

[0017] In one embodiment, the formula for calculating the preset physical damage index can be defined by the following expression:

[0018]

[0019] in, Indicates the first k Physical damage index at the sampling time, Indicates the first k The demagnetization rate of the permanent magnet at the sampling time. This indicates the maximum permissible demagnetization rate of the stepper motor. Indicates the first k The thermally induced displacement at the sampling time, This represents the maximum permissible safe deformation of the stepper motor. Indicates the first k The weighting coefficient corresponding to the ratio of the absolute value of the permanent magnet demagnetization rate at the sampling time to the maximum allowable demagnetization rate. Indicates the firstk The weighting coefficient corresponding to the ratio of the absolute value of the thermally induced displacement at the sampling time to the maximum allowable safe deformation.

[0020] In one embodiment, before inputting the multidimensional feature vector into the trained data-driven model to obtain the data-driven damage index corresponding to the stepper motor, the method further includes:

[0021] Obtain a sample training set, wherein the sample training set includes: multiple training multidimensional feature vectors, and label data-driven damage indexes corresponding to the training multidimensional feature vectors;

[0022] The sample training set is input into the initial data-driven model for training. The weight parameters of the model are adjusted according to the preset loss function until the model converges, and the trained data-driven model is obtained.

[0023] In one embodiment, obtaining the multidimensional feature vector corresponding to the multiphysics data includes:

[0024] Obtain the time-domain and frequency-domain characteristics of the multiphysics data, permanent magnet demagnetization rate, thermally induced displacement, and magnetic flux density, respectively.

[0025] A multidimensional feature vector is determined based on multiple time-domain features and multiple frequency-domain features.

[0026] In one embodiment, acquiring the time-domain and frequency-domain characteristics corresponding to the multiphysics data, permanent magnet demagnetization rate, thermally induced displacement, and magnetic flux density, respectively, includes:

[0027] The mean and variance of the multiphysics field data, permanent magnet demagnetization rate, thermally induced displacement and magnetic flux density are calculated to obtain multiple time-domain features.

[0028] Fast Fourier transform operations are performed on the multiphysics field data, permanent magnet demagnetization rate, thermally induced displacement, and magnetic flux density to obtain multiple frequency domain features.

[0029] In one embodiment, obtaining the life prediction result of the stepper motor based on the physical damage index, the data-driven damage index, and a preset life prediction formula includes:

[0030] The physical damage index and the data-driven damage index are weighted and summed to determine the comprehensive damage index;

[0031] The comprehensive damage index is substituted into the preset life prediction formula to calculate and determine the life prediction result of the stepper motor.

[0032] In one embodiment, the preset lifetime prediction formula may be defined by the following expression:

[0033]

[0034] in, This indicates the preset total lifespan of the stepper motor. Indicates the first k The comprehensive damage index corresponding to the sampling time. Indicates the first k The life prediction result of the stepper motor corresponding to the sampling time.

[0035] Secondly, embodiments of the present invention provide a stepper motor life prediction system based on multi-physics coupling. The system includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the steps of the stepper motor life prediction method based on multi-physics coupling described in the first aspect.

[0036] The technical solution provided by the embodiments of the present invention has the following advantages compared with the prior art:

[0037] This invention provides a stepper motor life prediction method based on multi-physics coupling. It acquires the stepper motor's electrical parameters, multi-physics data during operation, and corresponding multi-dimensional feature vectors. Based on the electrical parameters, multi-physics data, and a preset physical damage index calculation formula, a physical damage index for the stepper motor is determined. The multi-dimensional feature vector is then input into a trained data-driven model to obtain the data-driven damage index for the stepper motor. Finally, based on the physical damage index, the data-driven damage index, and the preset life prediction formula, the stepper motor's life prediction result is obtained. This approach comprehensively considers the impact of multi-physics data on the stepper motor's lifespan and overcomes the limitations of a single model in predicting stepper motor lifespan by fusing the physical damage index and the data-driven damage index, thus significantly improving the accuracy of the stepper motor's lifespan prediction results. Attached Figure Description

[0038] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0039] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0040] Figure 1This is a flowchart illustrating a stepper motor life prediction method based on multi-physics coupling, provided in an embodiment of the present invention. Detailed Implementation

[0041] To better understand the above-mentioned objectives, features, and advantages of the present invention, the solutions of the present invention will be further described below. It should be noted that, unless otherwise specified, the embodiments of the present invention and the features thereof can be combined with each other.

[0042] Many specific details are set forth in the following description in order to provide a full understanding of the invention, but the invention may also be practiced in other ways different from those described herein; obviously, the embodiments in the specification are only some embodiments of the invention, and not all embodiments.

[0043] In one embodiment, such as Figure 1 As shown, Figure 1 A flowchart illustrating a stepper motor life prediction method based on multi-physics coupling, provided in this embodiment of the invention, specifically includes the following steps:

[0044] S10: Obtain the electrical parameters of the stepper motor, the multi-physics field data during operation, and the multi-dimensional feature vectors corresponding to the multi-physics field data.

[0045] The electrical parameters of the stepper motor include: the number of motor winding turns, constant magnetomotive force, number of motor pole pairs, and bearing length. For example, the number of motor pole pairs can be 4, the number of motor winding turns can be 100, and the bearing length can be 0.015m, but it is not limited to these. The present invention does not impose specific limitations, and those skilled in the art can set them according to the actual situation.

[0046] Multiphysics data during operation refers to the data corresponding to the stepper motor's physical fields such as electric and magnetic fields. Multiphysics data includes: two-phase current, bearing temperature, rotor position, and mechanical angle. For example, in the first... k At the sampling time, the two phase currents The phase current could be, for example, 2.8A. b The phase current can be, for example, 2.5A, the bearing temperature can be, for example, 78.3°C, and the rotor position mechanical angle can be, for example, 127°, but is not limited thereto. The present invention is not specifically limited, and those skilled in the art can set it according to the actual situation.

[0047] Multidimensional feature vectors are feature vectors constructed based on multiphysics field data.

[0048] Specifically, for stepper motors, we acquire the electrical parameters of the stepper motor, the multi-physics data of its operating state under multi-physics conditions, and the multi-dimensional feature vectors corresponding to the multi-physics data.

[0049] S11: Determine the physical damage index corresponding to the stepper motor based on electrical parameters, multi-physics field data, and the preset physical damage index calculation formula.

[0050] The preset physical damage index calculation formula is used to calculate the physical damage index, which refers to the damage that exists in the stepper motor during operation.

[0051] Specifically, after obtaining the electrical parameters of the stepper motor and the multi-physics field data under operating conditions, the physical damage index corresponding to the stepper motor is calculated and determined based on the electrical parameters of the stepper motor, the multi-physics field data under operating conditions, and the preset physical damage index calculation formula.

[0052] Optionally, based on the above embodiments, in some embodiments of the present invention, one implementation of S11 may be:

[0053] S111: Determine the demagnetization rate and thermally induced displacement of the permanent magnet based on electrical parameters and multiphysics data.

[0054] Specifically, after obtaining the electrical parameters of the stepper motor and the multi-physics field data under operating conditions, the demagnetization rate of the permanent magnet and the thermally induced displacement of the stepper motor are obtained based on the electrical parameters of the stepper motor and the multi-physics field data under operating conditions.

[0055] Optionally, based on the above embodiments, in some embodiments of the present invention, one implementation of S111 may be:

[0056] S1111: Obtain the magnetic flux density based on the number of motor pole pairs, rotor position mechanical angle, constant magnetomotive force, number of motor winding turns, and two-phase current.

[0057] Optionally, based on the above embodiments, in some embodiments of the present invention, one implementation of S1111 may be:

[0058] Substitute the two-phase current, the number of motor winding turns, the number of motor pole pairs, the constant magnetomotive force, and the rotor position mechanical angle into the total magnetomotive force calculation formula to calculate and determine the total magnetomotive force.

[0059] Optionally, based on the above embodiments, in some embodiments of the present invention, the formula for calculating the total magnetomotive force may be limited by the following expression:

[0060]

[0061] in, Indicates the first k Total magnetomotive force at the sampling time. It represents a constant magnetomotive force. This indicates the number of turns in the motor windings of a stepper motor. Indicates the first k The two-phase current at the sampling time Phase current, Indicates the first k The two-phase current at the sampling time Phase current, Indicates the first k The rotor position mechanical angle at the sampling time, This indicates the number of pole pairs of the motor.

[0062] Substitute the total magnetomotive force and the rotor position mechanical angle into the magnetic flux density calculation formula to calculate and determine the magnetic flux density.

[0063] Optionally, based on the above embodiments, in some embodiments of the present invention, the magnetic flux density calculation formula may be defined by the following expression:

[0064]

[0065] in, Indicates the first k Magnetic flux density at the sampling time, Indicates the first k Total magnetomotive force at the sampling time. Indicates the first k The rotor position mechanical angle at the sampling time, Indicates the first k Air gap permeability at the sampling time, The effective cross-sectional area of ​​the air gap magnetic field is represented. For example, the effective cross-sectional area can be 0.01m², but it is not limited thereto. This invention does not impose specific limitations, and those skilled in the art can set it according to the actual situation.

[0066] S1112: Obtain the demagnetization rate of the permanent magnet based on the bearing temperature and magnetic flux density.

[0067] Specifically, after obtaining the magnetic flux density, the bearing temperature and magnetic flux density are substituted into the formula for calculating the demagnetization rate of the permanent magnet to determine the demagnetization rate of the permanent magnet.

[0068] Optionally, based on the above embodiments, in some embodiments of the present invention, the formula for calculating the demagnetization rate of the permanent magnet can be limited by the following expression:

[0069]

[0070] in, Indicates the first k Demagnetization rate of permanent magnet at the sampling time. This represents the demagnetization rate coefficient, which can be, for example, […]. , This represents the magnetic field strength coefficient, which can be, for example, 0.1 / T. This indicates the sampling time interval, which can be, for example, 0.1 seconds. Indicates the first k Magnetic flux density at the sampling time, Indicates the first i The bearing temperature at the sampling time is used, but it is not limited to this. This invention does not impose specific limitations, and those skilled in the art can set it according to the actual situation.

[0071] S1113: Obtain thermally induced displacement based on bearing length, bearing temperature, and ambient temperature.

[0072] Specifically, the bearing length, bearing temperature, and ambient temperature are substituted into the thermally induced displacement calculation formula to determine the thermally induced displacement.

[0073] Optionally, based on the above embodiments, in some embodiments of the present invention, the formula for calculating thermally induced displacement may be limited by the following expression:

[0074]

[0075] in, Indicates the first k Thermally induced displacement at the sampling time α This represents the coefficient of thermal expansion of the bearing material. For example, the coefficient of thermal expansion of the bearing material can be... , L Indicates the bearing length. Indicates ambient temperature. Indicates the first k The bearing temperature at the time of sampling.

[0076] S112: Substitute the demagnetization rate of the permanent magnet and the thermally induced displacement into the preset physical damage index calculation formula to calculate and determine the physical damage index.

[0077] Specifically, after obtaining the demagnetization rate and thermally induced displacement of the permanent magnet, the demagnetization rate and thermally induced displacement of the permanent magnet are substituted into the preset physical damage index calculation formula for calculation, and the physical damage index is calculated and determined.

[0078] Optionally, based on the above embodiments, in some embodiments of the present invention, the formula for calculating the preset physical damage index may be limited by the following expression:

[0079]

[0080] in, Indicates the first k Physical damage index at the sampling time, Indicates the first kDemagnetization rate of permanent magnet at the sampling time. This indicates the maximum permissible demagnetization rate of the stepper motor. For example, the maximum permissible demagnetization rate could be 0.2. Indicates the first k Thermally induced displacement at the sampling time This indicates the maximum permissible safe deformation of the stepper motor. For example, the maximum permissible safe deformation could be 15 μm. Indicates the first k The weighting coefficient corresponding to the ratio of the absolute value of the permanent magnet demagnetization rate at the sampling time to the maximum allowable demagnetization rate, for example, could be 0.4. Indicates the first k The weighting coefficient corresponding to the ratio of the absolute value of the thermally induced displacement at the sampling time to the maximum allowable safe deformation can be, for example, 0.6, but is not limited thereto. This invention does not impose specific limitations, and those skilled in the art can set it according to the actual situation.

[0081] S12: Input the multidimensional feature vector into the trained data-driven model to obtain the data-driven damage index corresponding to the stepper motor.

[0082] The data-driven model refers to a neural network model with time-series modeling capabilities obtained by training on big data. This data-driven model can be, for example, a long short-term memory network, a convolutional neural network, etc., but is not limited to these. This invention does not impose specific limitations, and those skilled in the art can set it according to the actual situation.

[0083] Optionally, based on the above embodiments, in some embodiments of the present invention, one method for obtaining the above-mentioned multidimensional feature vector may be:

[0084] S20: Obtain the time-domain and frequency-domain characteristics of multiphysics field data, permanent magnet demagnetization rate, thermally induced displacement, and magnetic flux density, respectively.

[0085] Optionally, based on the above embodiments, in some embodiments of the present invention, one implementation of S20 may be:

[0086] S201: The mean and variance of multiphysics field data, permanent magnet demagnetization rate, thermally induced displacement and magnetic flux density are calculated to obtain multiple time-domain features.

[0087] Specifically, the mean and variance of multi-physics field data such as two-phase current, bearing temperature, rotor position mechanical angle, permanent magnet demagnetization rate, thermally induced displacement, and magnetic flux density are calculated respectively. The mean and variance corresponding to each data are determined, and the mean and variance are determined as the time-domain characteristics corresponding to two-phase current, bearing temperature, rotor position mechanical angle, permanent magnet demagnetization rate, thermally induced displacement, and magnetic flux density respectively.

[0088] S202: Perform Fast Fourier Transform operations on multiphysics field data, permanent magnet demagnetization rate, thermally induced displacement, and magnetic flux density to obtain multiple frequency domain features.

[0089] Specifically, fast Fourier transform operations are performed on multi-physics field data such as two-phase current, bearing temperature, rotor position mechanical angle, permanent magnet demagnetization rate, thermally induced displacement, and magnetic flux density to obtain the main frequency amplitude corresponding to each data. The main frequency amplitude is determined to be the frequency domain characteristic corresponding to two-phase current, bearing temperature, rotor position mechanical angle, permanent magnet demagnetization rate, thermally induced displacement, and magnetic flux density, respectively.

[0090] S21: Determine the multidimensional feature vector based on multiple time-domain features and multiple frequency-domain features.

[0091] Specifically, after obtaining the time-domain and frequency-domain characteristics of the two-phase current, bearing temperature, rotor position mechanical angle, permanent magnet demagnetization rate, thermally induced displacement, and magnetic flux density, a multidimensional feature vector is determined based on multiple time-domain and frequency-domain characteristics.

[0092] Optionally, based on the above embodiments, in some embodiments of the present invention, before performing S12, the following steps are further included:

[0093] S30: Obtain the sample training set.

[0094] The sample training set includes: multiple training multidimensional feature vectors, and label data-driven damage indices corresponding to the training multidimensional feature vectors.

[0095] S31: Input the sample training set into the initial data-driven model for training, adjust the model's weight parameters according to the preset loss function until the model converges, and obtain the trained data-driven model.

[0096] Specifically, a sample training set is obtained, which includes multiple training multidimensional feature vectors and the corresponding label data-driven damage index of the training multidimensional feature vectors. The sample training set is input into the initial data-driven model to train the initial data-driven model. During the training process, the model's weight parameters are adjusted according to the preset loss function until the model converges, and the trained data-driven model is obtained.

[0097] S13: Obtain the life prediction result of the stepper motor based on the physical damage index, the data-driven damage index, and the preset life prediction formula.

[0098] Optionally, based on the above embodiments, in some embodiments of the present invention, one implementation of S13 may be:

[0099] S131: The physical damage index and the data-driven damage index are weighted and summed to determine the comprehensive damage index.

[0100] Specifically, the physical damage index and the data-driven damage index are weighted and summed to determine the comprehensive damage index.

[0101] Optionally, based on the above embodiments, in some embodiments of the present invention, the weighted summation formula for the comprehensive damage index can be defined by the following expression:

[0102]

[0103] in, Indicates the first k The comprehensive damage index at the sampling time. Indicates the first k Physical damage index at the sampling time, Indicates the first k The weighting coefficient of the physical damage index at the sampling time can be, for example, 0.4. Indicates the first k Data at the sampling time drives the damage index. Indicates the first k The weighting coefficient of the damage index driven by the data at the sampling time can be, for example, 0.6, but is not limited thereto. This invention does not impose specific limitations, and those skilled in the art can set it according to the actual situation.

[0104] S132: Substitute the comprehensive damage index into the preset life prediction formula to calculate and determine the life prediction result of the stepper motor.

[0105] Specifically, the obtained comprehensive damage index is substituted into the preset life prediction formula for calculation to determine the comprehensive damage index.

[0106] Optionally, based on the above embodiments, in some embodiments of the present invention, the preset lifetime prediction formula may be limited by the following expression:

[0107]

[0108] in, This indicates the preset total lifespan of the stepper motor. For example, the preset total lifespan of a stepper motor could be 4000 hours. Indicates the first k The comprehensive damage index corresponding to the sampling time. Indicates the first k The life prediction results of the stepper motor at the sampling time.

[0109] Thus, this embodiment provides a stepper motor life prediction method based on multi-physics coupling. It acquires the stepper motor's electrical parameters, multi-physics data during operation, and the corresponding multi-dimensional feature vectors. Based on the electrical parameters, multi-physics data, and a preset physical damage index calculation formula, it determines the physical damage index corresponding to the stepper motor. The multi-dimensional feature vectors are then input into a trained data-driven model to obtain the data-driven damage index for the stepper motor. Finally, based on the physical damage index, the data-driven damage index, and the preset life prediction formula, the stepper motor's life prediction result is obtained. This approach comprehensively considers the impact of multi-physics data on the stepper motor's lifespan and overcomes the limitations of a single model in predicting stepper motor lifespan by fusing the physical damage index and the data-driven damage index, thereby significantly improving the accuracy of the stepper motor's lifespan prediction results.

[0110] It should be understood that, although Figure 1 The steps in the flowchart are shown sequentially as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order in which these steps are executed, and they can be performed in other orders. Figure 1 At least some of the steps in the process may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but may be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but may be executed in turn or alternately with other steps or at least some of the sub-steps or stages of other steps.

[0111] This invention provides a stepper motor life prediction system based on multi-physics coupling, comprising: a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, it can implement the stepper motor life prediction method based on multi-physics coupling provided in this invention. For example, when the processor executes the computer program, it can implement... Figure 1 The technical solutions of the method embodiments shown are similar in principle and in effect, and will not be described again here.

[0112] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the methods described above. Any references to memory, databases, or other media used in the embodiments provided by this invention can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, or optical storage, etc. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static random access memory (SRAM) and dynamic random access memory (DRAM), etc.

[0113] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0114] The embodiments described above are merely illustrative of several implementations of the present invention, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these all fall within the protection scope of the present invention. Therefore, the protection scope of this invention patent should be determined by the appended claims.

Claims

1. A method for predicting the lifespan of a stepper motor based on multi-physics coupling, characterized in that, include: Obtain the electrical parameters of the stepper motor, the multi-physics field data during operation, and the multi-dimensional feature vector corresponding to the multi-physics field data; Based on the electrical parameters and the multiphysics data, the demagnetization rate and thermally induced displacement of the permanent magnet are determined. Substitute the permanent magnet demagnetization rate and the thermally induced displacement into the preset physical damage index calculation formula to calculate and determine the physical damage index. The formula for calculating the preset physical damage index can be defined by the following expression: in, Indicates the first Physical damage index at the sampling time, Indicates the first The demagnetization rate of the permanent magnet at the sampling time. This indicates the maximum permissible demagnetization rate of the stepper motor. Indicates the first The thermally induced displacement at the sampling time, This represents the maximum permissible safe deformation of the stepper motor. Indicates the first The weighting coefficient corresponding to the ratio of the absolute value of the permanent magnet demagnetization rate at the sampling time to the maximum allowable demagnetization rate. Indicates the first The weighting coefficient corresponding to the ratio of the absolute value of the thermally induced displacement at the sampling time to the maximum allowable safe deformation; The multidimensional feature vector is input into the trained data-driven model to obtain the data-driven damage index corresponding to the stepper motor; The physical damage index and the data-driven damage index are weighted and summed to determine the comprehensive damage index; The comprehensive damage index is substituted into the preset life prediction formula to calculate and determine the life prediction result of the stepper motor. The preset lifespan prediction formula can be defined by the following expression: ， in, This indicates the preset total lifespan of the stepper motor. Indicates the first The comprehensive damage index corresponding to the sampling time. Indicates the first The life prediction result of the stepper motor corresponding to the sampling time.

2. The method according to claim 1, characterized in that, The electrical parameters include: number of motor winding turns, constant magnetomotive force, number of motor pole pairs, and bearing length. The multiphysics data includes: two-phase current, bearing temperature, and rotor position mechanical angle. Determining the permanent magnet demagnetization rate and thermally induced displacement based on the electrical parameters and the multiphysics data includes: The magnetic flux density is obtained based on the number of motor pole pairs, the rotor position mechanical angle, the constant magnetomotive force, the number of motor winding turns, and the two-phase current. The demagnetization rate of the permanent magnet is obtained based on the bearing temperature and the magnetic flux density. The thermally induced displacement is obtained based on the bearing length, the bearing temperature, and the ambient temperature.

3. The method according to claim 1, characterized in that, Before inputting the multidimensional feature vector into the trained data-driven model to obtain the data-driven damage index corresponding to the stepper motor, the method further includes: Obtain a sample training set, wherein the sample training set includes: multiple training multidimensional feature vectors, and label data-driven damage indexes corresponding to the training multidimensional feature vectors; The sample training set is input into the initial data-driven model for training. The weight parameters of the model are adjusted according to the preset loss function until the model converges, and the trained data-driven model is obtained.

4. The method according to claim 3, characterized in that, Obtaining the multidimensional feature vector corresponding to the multiphysics data includes: Obtain the time-domain and frequency-domain characteristics of the multiphysics data, permanent magnet demagnetization rate, thermally induced displacement, and magnetic flux density, respectively. A multidimensional feature vector is determined based on multiple time-domain features and multiple frequency-domain features.

5. The method according to claim 4, characterized in that, The acquisition of the time-domain and frequency-domain characteristics corresponding to the multiphysics data, permanent magnet demagnetization rate, thermally induced displacement, and magnetic flux density includes: The mean and variance of the multiphysics field data, permanent magnet demagnetization rate, thermally induced displacement and magnetic flux density are calculated to obtain multiple time-domain features. Fast Fourier transform operations are performed on the multiphysics field data, permanent magnet demagnetization rate, thermally induced displacement, and magnetic flux density to obtain multiple frequency domain features.

6. A stepper motor life prediction system based on multiphysics coupling, characterized in that, The system includes a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the stepper motor life prediction method based on multiphysics coupling as described in any one of claims 1-5.

Images