A fault identification method for permanent magnet synchronous motor

Abstract

The application relates to the field of motor fault identification, and discloses a permanent magnet synchronous motor fault identification method, which comprises a preset permanent magnet synchronous motor fault prediction model comprising a quantum heuristic neural network module, a double-flow convolutional neural network module and an SVM classifier connected in sequence. Through the quantum heuristic neural network mode, the weak features of early faults of the permanent magnet synchronous motor can be effectively mined, the feature expression capability is enhanced by unique rotation and entanglement operations of the quantum heuristic neural network, the feature extraction and fusion capability of the double-flow convolutional neural network module and the accurate classification capability of the SVM classifier are combined, the detection sensitivity of early weak faults is significantly improved, the fault degree of the permanent magnet synchronous motor is more accurately distinguished, and the fault type is effectively identified, so that reliable guarantee is provided for stable operation of the permanent magnet synchronous motor.

Description

Technical Field

[0001] This invention relates to the field of motor fault identification, and more particularly to a method for identifying faults in a permanent magnet synchronous motor. Background Technology

[0002] In the operation and maintenance of permanent magnet synchronous motors, fault identification is a crucial step in ensuring their stable and reliable operation. However, current fault identification for permanent magnet synchronous motors faces numerous challenges.

[0003] Early fault characteristics are extremely subtle, making it difficult to accurately distinguish the degree of fault. In the early stages, changes in fault severity are not obvious, and fault features used to characterize the evolution trend of early faults have very low discriminative power. Traditional fault prediction models for permanent magnet synchronous motors mainly rely on conventional time-frequency feature extraction methods. These methods have limited ability to detect complex nonlinear fault modes, resulting in low sensitivity for detecting subtle early faults, which is insufficient to meet the needs of accurate and timely identification of motor faults in practical engineering. Summary of the Invention

[0004] Based on this, it is necessary to propose a fault identification method for permanent magnet synchronous motors to address the above problems. This method can effectively uncover the weak features of early faults in permanent magnet synchronous motors, significantly improve the detection sensitivity of early weak faults, and achieve more accurate differentiation of the degree of faults and effective identification of fault types, thus providing a reliable guarantee for the stable operation of permanent magnet synchronous motors.

[0005] To achieve the above objectives, the present invention provides a method for fault identification of a permanent magnet synchronous motor in a first aspect, the method comprising:

[0006] Obtain the vibration signal of the permanent magnet synchronous motor;

[0007] The vibration signal is subjected to a short-time Fourier transform to obtain a first time-frequency diagram, and the vibration signal is subjected to a synchronous compressed wavelet transform to obtain a second time-frequency diagram.

[0008] The first time-frequency graph is mapped and encoded to obtain the first global quantum state tensor, and the second time-frequency graph is mapped and encoded to obtain the second global quantum state tensor;

[0009] The first global quantum state tensor and the second global quantum state tensor are input into a preset permanent magnet synchronous motor fault prediction model to obtain fault classification and identification results;

[0010] The preset permanent magnet synchronous motor fault prediction model includes a quantum heuristic neural network module, a two-stream convolutional neural network module, and an SVM classifier connected in sequence.

[0011] The quantum heuristic neural network module is used to perform rotation and entanglement operations on both the first global quantum state tensor and the second global quantum state tensor to obtain a first enhanced feature vector and a second enhanced feature vector;

[0012] The dual-stream convolutional neural network module is used to extract and fuse features from the first enhanced feature vector and the second enhanced feature vector to obtain a dual-stream fused feature vector.

[0013] The SVM classifier is used to classify the dual-stream fused feature vectors to obtain the fault classification and identification results.

[0014] Optionally, the step of performing rotation and entanglement operations on both the first and second global quantum state tensors to obtain the first and second enhanced eigenvectors includes:

[0015] Obtain the rotation matrix corresponding to each pixel in the first time-frequency image and the rotation matrix corresponding to each pixel in the second time-frequency image;

[0016] Using the rotation matrix corresponding to the nth pixel in the first time-frequency diagram, the nth quantum state in the first global quantum state tensor is rotated to obtain the nth rotated quantum state in the third global quantum state tensor. Similarly, using the rotation matrix corresponding to the mth pixel in the second time-frequency diagram, the mth quantum state in the second global quantum state tensor is rotated to obtain the mth rotated quantum state in the fourth global quantum state tensor. A convolution operation is used to simulate entanglement, performing a cross-time and frequency entanglement operation between the nth rotated quantum state in the third global quantum state tensor and the remaining rotated quantum states, resulting in the nth rotated quantum state in the third global quantum state tensor and the remaining rotated quantum states. The first correlation between the rotated quantum states, and the entanglement operation across time and frequency of the m-th rotated quantum state in the fourth global quantum state tensor with the remaining rotated quantum states, are used to obtain the second correlation between the m-th rotated quantum state in the fourth global quantum state tensor and the remaining rotated quantum states; where n takes integer values ​​greater than 0 until it is equal to the total number of pixels in the first time-frequency map, the third global quantum state tensor and the first correlation vector composed of all the first correlations are obtained, and m takes integer values ​​greater than 0 until it is equal to the total number of pixels in the second time-frequency map, the fourth global quantum state tensor and the second correlation vector composed of all the second correlations are obtained;

[0017] The third global quantum state tensor and the first correlation vector are fused and spliced ​​together to obtain a first spliced ​​feature vector, and the fourth global quantum state tensor and the second correlation feature vector are fused and spliced ​​together to obtain a second spliced ​​feature vector;

[0018] The first concatenated feature vector is mapped and decoded to obtain the first enhanced feature vector, and the second concatenated feature vector is mapped and decoded to obtain the second enhanced feature vector.

[0019] Optionally, obtaining the rotation matrix corresponding to each pixel in the first time-frequency image and the rotation matrix corresponding to each pixel in the second time-frequency image includes:

[0020] Obtain the speed signal of the permanent magnet synchronous motor;

[0021] Based on the rotation speed signal, determine the rotation speed corresponding to each pixel in the first time-frequency diagram and the rotation speed corresponding to each pixel in the second time-frequency diagram;

[0022] Based on the vibration signal, determine the signal entropy corresponding to each pixel in the first time-frequency diagram and the signal entropy corresponding to each pixel in the second time-frequency diagram;

[0023] Based on the energy corresponding to all pixels in the first time-frequency graph, a first maximum energy is determined, and based on the energy corresponding to all pixels in the second time-frequency graph, a second maximum energy is determined.

[0024] Based on the rotational speed, signal entropy, and energy corresponding to each pixel in the first time-frequency diagram, and the first maximum energy, the rotation angle corresponding to each pixel in the first time-frequency diagram is determined; and based on the rotational speed, signal entropy, and energy corresponding to each pixel in the second time-frequency diagram, and the second maximum energy, the rotation angle corresponding to each pixel in the second time-frequency diagram is determined.

[0025] Based on the rotation angle corresponding to each pixel in the first time-frequency image, a rotation matrix corresponding to each pixel in the first time-frequency image is constructed; and based on the rotation angle corresponding to each pixel in the second time-frequency image, a rotation matrix corresponding to each pixel in the second time-frequency image is constructed.

[0026] Optionally, the rotation angle corresponding to each pixel in the first time-frequency image is determined according to the following formula:

[0027] ;

[0028] The rotation angle corresponding to each pixel in the second time-frequency graph is determined according to the following formula;

[0029] ;

[0030] in, Let be the rotation angle corresponding to the nth pixel in the first time-frequency graph. Let n be the coordinates of the nth pixel in the first time-frequency graph. For speed coefficient, The rotational speed corresponds to the nth pixel in the first time-frequency graph. The signal entropy coefficient, Let be the signal entropy corresponding to the nth pixel in the first time-frequency graph. The energy coefficient, Let be the energy corresponding to the nth pixel in the first time-frequency graph. For the first maximum energy, Let be the rotation angle corresponding to the m-th pixel in the second time-frequency diagram. Let m be the coordinates of the m-th pixel in the second time-frequency graph. Let m be the rotational speed corresponding to the m-th pixel in the second time-frequency diagram. Let be the signal entropy corresponding to the m-th pixel in the second time-frequency diagram. Let m be the energy corresponding to the m-th pixel in the second time-frequency graph. This is the second maximum energy.

[0031] Optionally, before constructing the rotation matrix corresponding to each pixel in the first time-frequency image based on the rotation angle corresponding to each pixel in the first time-frequency image, and before constructing the rotation matrix corresponding to each pixel in the second time-frequency image based on the rotation angle corresponding to each pixel in the second time-frequency image, the method further includes:

[0032] In the first time-frequency diagram and the second time-frequency diagram, if there is a pixel whose rotation angle does not meet the preset rotation angle range, then according to the rotation angle corresponding to the corresponding pixel and the preset rotation angle range, the rotation angle corresponding to the corresponding pixel is clamped to the preset rotation angle range to obtain the clamped rotation angle corresponding to the corresponding pixel.

[0033] The clamped rotation angle corresponding to the corresponding pixel is then used as the rotation angle corresponding to the corresponding pixel.

[0034] Optionally, the step of clamping the rotation angle corresponding to the corresponding pixel to the preset rotation angle range based on the rotation angle corresponding to the corresponding pixel and the preset rotation angle range, to obtain the clamped rotation angle corresponding to the corresponding pixel, includes:

[0035] If the rotation angle corresponding to the corresponding pixel is less than the lower limit of the preset rotation angle range, the lower limit of the preset rotation angle range shall be used as the clamped rotation angle corresponding to the corresponding pixel.

[0036] If the rotation angle corresponding to a given pixel is less than the upper limit of the preset rotation angle range, the upper limit of the preset rotation angle range shall be used as the clamped rotation angle corresponding to the given pixel.

[0037] Optionally, before constructing the rotation matrix corresponding to each pixel in the first time-frequency image based on the rotation angle corresponding to each pixel in the first time-frequency image, and before constructing the rotation matrix corresponding to each pixel in the second time-frequency image based on the rotation angle corresponding to each pixel in the second time-frequency image, the method further includes:

[0038] In the first time-frequency diagram and the second time-frequency diagram, if there is a pixel whose rotation angle does not meet the preset rotation angle range, then the rotation angle corresponding to the corresponding pixel is transformed to the preset rotation angle range according to the rotation angle corresponding to the corresponding pixel, so as to obtain the transformed rotation angle corresponding to the corresponding pixel.

[0039] The transformed rotation angle corresponding to the corresponding pixel is used as the rotation angle corresponding to the corresponding pixel again.

[0040] Alternatively, the transformed rotation angle corresponding to the corresponding pixel can be obtained according to the following formula:

[0041] ;

[0042] in, This represents the transformed rotation angle corresponding to the respective pixel. This represents the rotation angle corresponding to the respective pixel. The remainder symbol is used. Pi is the mathematical constant of a circle.

[0043] Optionally, the nth rotated quantum state in the third global quantum state tensor is obtained according to the following formula:

[0044] ;

[0045] The m-th rotated quantum state in the fourth global quantum state tensor is obtained according to the following formula:

[0046] ;

[0047] in, This refers to the nth rotated quantum state in the third global quantum state tensor. Let n be the coordinates of the nth pixel in the first time-frequency graph. Let be the rotation matrix corresponding to the nth pixel in the first time-frequency graph. This refers to the quantum state corresponding to the nth pixel in the first time-frequency diagram. It is a cosine function. Let be the rotation angle corresponding to the nth pixel in the first time-frequency graph. It is a sine function. This refers to the m-th rotated quantum state in the fourth global quantum state tensor. Let m be the coordinates of the m-th pixel in the second time-frequency graph. Let be the rotation matrix corresponding to the m-th pixel in the second time-frequency diagram. Let m be the quantum state corresponding to the m-th pixel in the second time-frequency diagram. The rotation angle is the angle corresponding to the m-th pixel in the second time-frequency graph.

[0048] Optionally, the first correlation between the nth rotated quantum state and the remaining rotated quantum states in the third global quantum state tensor can be obtained according to the following formula:

[0049] ;

[0050] The second correlation between the m-th rotated quantum state and the remaining rotated quantum states in the fourth global quantum state tensor is obtained according to the following formula:

[0051] ;

[0052] in, This represents the first correlation between the nth rotated quantum state and the remaining rotated quantum states in the third global quantum state tensor. Let N be the coordinates of the Nth pixel in the first time-frequency graph. The total number of pixels in the first time-frequency graph. Let be the coordinates of the i-th pixel in the first time-frequency graph. Let n be the coordinates of the nth pixel in the first time-frequency graph. For the kernel function of the entanglement operation, The quantum state inner product is the product of the nth rotated quantum state and the ith rotated quantum state in the third global quantum state tensor. It is the dual state of the nth rotated quantum state in the third global quantum state tensor. Let i be the i-th rotated quantum state in the third global quantum state tensor. The second correlation between the m-th rotated quantum state and the remaining rotated quantum states in the fourth global quantum state tensor. Let M be the coordinates of the Mth pixel in the second time-frequency graph. The total number of pixels in the second time-frequency graph. Let J be the coordinates of the j-th pixel in the second time-frequency graph. Let m be the coordinates of the m-th pixel in the second time-frequency graph. The quantum state inner product is the product of the m-th rotated quantum state and the j-th rotated quantum state in the fourth global quantum state tensor. It is the dual state of the m-th rotated quantum state in the fourth global quantum state tensor. Let j be the j-th rotated quantum state in the fourth global quantum state tensor.

[0053] To achieve the above objectives, the present invention provides a fault identification device for a permanent magnet synchronous motor in a second aspect, the device comprising:

[0054] The acquisition module is used to acquire the vibration signal of the permanent magnet synchronous motor;

[0055] The transformation module is used to perform a short-time Fourier transform on the vibration signal to obtain a first time-frequency diagram, and to perform a synchronous compressed wavelet transform on the vibration signal to obtain a second time-frequency diagram;

[0056] The mapping and encoding module is used to map and encode the first time-frequency graph to obtain a first global quantum state tensor, and to map and encode the second time-frequency graph to obtain a second global quantum state tensor;

[0057] The model prediction module is used to input the first global quantum state tensor and the second global quantum state tensor into a preset permanent magnet synchronous motor fault prediction model to obtain fault classification and identification results;

[0058] The preset permanent magnet synchronous motor fault prediction model includes a quantum heuristic neural network module, a two-stream convolutional neural network module, and an SVM classifier connected in sequence.

[0059] The quantum heuristic neural network module is used to perform rotation and entanglement operations on both the first global quantum state tensor and the second global quantum state tensor to obtain a first enhanced feature vector and a second enhanced feature vector;

[0060] The dual-stream convolutional neural network module is used to extract and fuse features from the first enhanced feature vector and the second enhanced feature vector to obtain a dual-stream fused feature vector.

[0061] The SVM classifier is used to classify the dual-stream fused feature vectors to obtain the fault classification and identification results.

[0062] To achieve the above objectives, the present invention provides, in a third aspect, a computer-readable storage medium storing a computer program, which, when executed by a processor, causes the processor to perform the permanent magnet synchronous motor fault identification method as described in any one of the first aspects.

[0063] To achieve the above objectives, the present invention provides a computer device in a fourth aspect, including a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor performs the permanent magnet synchronous motor fault identification method as described in any one of the first aspects.

[0064] The present invention has the following beneficial effects: The above method acquires the vibration signal of a permanent magnet synchronous motor, performs a short-time Fourier transform on the vibration signal to obtain a first time-frequency diagram, and performs a synchronous compressed wavelet transform on the vibration signal to obtain a second time-frequency diagram. Then, the first time-frequency diagram is mapped and encoded to obtain a first global quantum state tensor, and the second time-frequency diagram is mapped and encoded to obtain a second global quantum state tensor. Finally, the first and second global quantum state tensors are input into a preset permanent magnet synchronous motor fault prediction model to obtain fault classification and identification results. The preset permanent magnet synchronous motor fault prediction model includes a quantum heuristic neural network module, a two-stream convolutional neural network module, and an SVM classifier connected in sequence. The quantum heuristic neural network module is used to perform rotation operations and entanglement operations on both the first and second global quantum state tensors. The process involves obtaining a first enhanced feature vector and a second enhanced feature vector. A dual-stream convolutional neural network module is used to extract and fuse these two enhanced feature vectors to obtain a dual-stream fused feature vector. An SVM classifier is then used to classify the dual-stream fused feature vector to obtain the fault classification and identification results. In other words, this quantum-inspired neural network approach can effectively uncover the subtle features of early faults in permanent magnet synchronous motors. By utilizing the unique rotation and entanglement operations of the quantum-inspired neural network to enhance feature representation capabilities, combined with the feature extraction and fusion capabilities of the dual-stream convolutional neural network module and the accurate classification capabilities of the SVM classifier, the detection sensitivity of early subtle faults is significantly improved. This enables more accurate differentiation of the degree of faults in permanent magnet synchronous motors and effective identification of fault types, providing a reliable guarantee for the stable operation of permanent magnet synchronous motors. Attached Figure Description

[0065] 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, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0066] in:

[0067] Figure 1 This is a schematic diagram of a fault identification method for a permanent magnet synchronous motor according to an embodiment of this application;

[0068] Figure 2 This is a schematic diagram of a permanent magnet synchronous motor fault identification device in an embodiment of this application;

[0069] Figure 3 This is a diagram showing the internal structure of a computer device in some embodiments. Detailed Implementation

[0070] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0071] In the operation and maintenance of permanent magnet synchronous motors, fault identification is a crucial step in ensuring their stable and reliable operation. However, current fault identification for permanent magnet synchronous motors faces numerous challenges.

[0072] Early fault characteristics are extremely subtle, making it difficult to accurately distinguish the degree of fault. In the early stages, changes in fault severity are not obvious, and fault features used to characterize the evolution trend of early faults have very low discriminative power. Traditional fault prediction models for permanent magnet synchronous motors mainly rely on conventional time-frequency feature extraction methods. These methods have limited ability to detect complex nonlinear fault modes, resulting in low sensitivity for detecting subtle early faults, which is insufficient to meet the needs of accurate and timely identification of motor faults in practical engineering.

[0073] To address the aforementioned issues, this application proposes a fault identification method for permanent magnet synchronous motors (PMSMs). This method effectively uncovers the subtle characteristics of early-stage faults in PMSMs, significantly improving the detection sensitivity of these early-stage faults. It enables more accurate differentiation of the degree of faults and effective identification of fault types, providing a reliable guarantee for the stable operation of PMSMs. The specific implementation principle will be described in detail in the following embodiments.

[0074] This application provides a method for fault identification of permanent magnet synchronous motors in its first aspect.

[0075] Please see Figure 1 This is a schematic diagram of a fault identification method for a permanent magnet synchronous motor according to an embodiment of this application. The method includes:

[0076] Step 110: Obtain the vibration signal of the permanent magnet synchronous motor.

[0077] Regarding the method of acquiring vibration signals, in some embodiments, vibration sensors can be used to acquire the vibration signals of permanent magnet synchronous motors.

[0078] Furthermore, in some embodiments, the number of vibration sensors can be multiple, and the multiple vibration sensors can correspondingly acquire multiple vibration signals.

[0079] Step 120: Perform a short-time Fourier transform on the vibration signal to obtain the first time-frequency diagram, and perform a synchronous compressed wavelet transform on the vibration signal to obtain the second time-frequency diagram.

[0080] Regarding the determination of the first and second time-frequency maps, in some embodiments, the short-time Fourier transform and synchronous compressed wavelet transform can be replaced with other similar types of time-frequency analysis techniques to transform the vibration signal and obtain the first and second time-frequency maps; for example, the short-time Fourier transform can be replaced with Fourier transform, Hilbert-Huang transform, etc., and the synchronous compressed wavelet transform can be replaced with wavelet transform, continuous wavelet transform, etc.

[0081] Step 130: Map and encode the first time-frequency graph to obtain the first global quantum state tensor, and map and encode the second time-frequency graph to obtain the second global quantum state tensor.

[0082] In some embodiments, the determination of the first and second global quantum state tensors can be achieved by mapping and encoding each pixel in the first time-frequency diagram to obtain the quantum state corresponding to each pixel, and by mapping and encoding each pixel in the second time-frequency diagram to obtain the quantum state corresponding to each pixel. Then, the first global quantum state tensor is determined based on the quantum states corresponding to all pixels in the first time-frequency diagram, and the second global quantum state tensor is determined based on the quantum states corresponding to all pixels in the second time-frequency diagram; wherein the horizontal and vertical coordinates of the pixels are time and frequency, respectively.

[0083] Furthermore, in some embodiments, the quantum states corresponding to all pixels in the first time-frequency image can be tensor-producted sequentially according to the coordinate order of the pixels to obtain the first global quantum state tensor, and the quantum states corresponding to all pixels in the second time-frequency image can be tensor-producted sequentially to obtain the second global quantum state tensor.

[0084] In this application, by mapping and encoding quantum states, pixels in the time-frequency graph are mapped to quantum states and a global quantum state tensor is constructed. This fully utilizes the unique properties of quantum states, enabling more effective extraction and characterization of weak features of early faults in permanent magnet synchronous motors. This significantly improves the detection capability for complex nonlinear fault modes, thereby enhancing the detection sensitivity of early weak faults and providing a stronger guarantee for the reliable operation of permanent magnet synchronous motors.

[0085] In some embodiments, the amplitude corresponding to each pixel in the first time-frequency image can be normalized to obtain the normalized amplitude corresponding to each pixel in the first time-frequency image, and the amplitude corresponding to each pixel in the second time-frequency image can be normalized to obtain the normalized amplitude corresponding to each pixel in the second time-frequency image. Then, based on the normalized amplitude and phase corresponding to each pixel in the first time-frequency image, the quantum state corresponding to each pixel in the first time-frequency image is determined, and based on the normalized amplitude and phase corresponding to each pixel in the second time-frequency image, the quantum state corresponding to each pixel in the second time-frequency image is determined.

[0086] In this application, the ability to characterize fault features of quantum states and the robustness of the encoding are significantly improved by using amplitude normalization and phase fusion encoding.

[0087] Furthermore, in some embodiments, the quantum state corresponding to each pixel in the first time-frequency graph can be determined according to the following formula:

[0088] ;

[0089] The quantum state corresponding to each pixel in the second time-frequency graph is determined using the following formula:

[0090] ;

[0091] in, This represents the quantum state corresponding to the nth pixel in the first time-frequency diagram. Let n be the coordinates of the nth pixel in the first time-frequency graph. This represents the normalized amplitude corresponding to the nth pixel in the first time-frequency graph. It is a natural constant. The imaginary unit, This represents the phase corresponding to the nth pixel in the first time-frequency diagram. and Let be the orthogonal basis vectors of the two-dimensional Hilbert space in quantum state encoding. Let m be the quantum state corresponding to the m-th pixel in the second time-frequency diagram. Let m be the coordinates of the m-th pixel in the second time-frequency graph. This represents the normalized amplitude corresponding to the m-th pixel in the second time-frequency graph. This represents the phase corresponding to the m-th pixel in the second time-frequency diagram.

[0092] In this application, by normalizing the amplitude and phase parameters and using a combined quantum state encoding formula, the quantum characterization capability and pattern recognition accuracy of fault features are significantly improved.

[0093] In some embodiments, the first global quantum state tensor can be determined according to the following formula:

[0094] ;

[0095] The second global quantum state tensor is determined according to the following formula:

[0096] ;

[0097] in, This is the first global quantum state tensor. The symbol for tensor product is... Let N be the coordinates of the Nth pixel in the first time-frequency graph. This represents the total number of pixels in the first time-frequency graph. Let n be the coordinates of the nth pixel in the first time-frequency graph. This represents the quantum state corresponding to the nth pixel in the first time-frequency diagram. This is the second global quantum state tensor. Here are the coordinates of the Mth pixel in the second time-frequency graph. This represents the total number of pixels in the second time-frequency graph. Let m be the coordinates of the m-th pixel in the second time-frequency graph. This represents the quantum state corresponding to the m-th pixel in the second time-frequency diagram.

[0098] In this embodiment, a global quantum state tensor is constructed through tensor product, thereby enabling high-order correlation analysis and mode decoupling of fault characteristics.

[0099] It should be noted that the mapping encoding in the above embodiments uses quantum state mapping encoding. In other embodiments, customized quantum state mapping encoding can also be used, that is:

[0100] In other embodiments, the method may involve acquiring the rotational speed signal of the permanent magnet synchronous motor, determining the rotational speed corresponding to each pixel in the first time-frequency image and the rotational speed corresponding to each pixel in the second time-frequency image based on the rotational speed corresponding to each pixel in the first time-frequency image, mapping and encoding each pixel in the first time-frequency image to obtain a custom quantum state corresponding to each pixel in the first time-frequency image, and mapping and encoding each pixel in the second time-frequency image based on the rotational speed corresponding to each pixel in the second time-frequency image to obtain a custom quantum state corresponding to each pixel in the second time-frequency image, determining a first global custom quantum state tensor based on the custom quantum states corresponding to all pixels in the first time-frequency image, and determining a second global custom quantum state tensor based on the custom quantum states corresponding to all pixels in the second time-frequency image, and finally using the first global custom quantum state tensor as the first global quantum state tensor and the second custom quantum state tensor as the second global quantum state tensor; wherein the horizontal and vertical coordinates of the pixel are time and frequency, respectively.

[0101] Furthermore, similar to the method for determining the global quantum state tensor by mapping and encoding quantum states, in some embodiments, the custom quantum states corresponding to all pixels in the first time-frequency image can be sequentially multiplied by tensor according to the coordinate order of the pixels to obtain the first global custom quantum state tensor, and the custom quantum states corresponding to all pixels in the second time-frequency image can be sequentially multiplied by tensor to obtain the second global custom quantum state tensor.

[0102] It should be noted that, since the horizontal and vertical coordinates of the pixels in the first and second time-frequency maps are time and frequency, respectively, and the rotational speed signal is a signal that changes with time, in some embodiments, the time in the rotational speed signal can be matched with the time corresponding to the pixels in the first and second time-frequency maps to determine the rotational speed corresponding to each pixel in the first time-frequency map and the rotational speed corresponding to each pixel in the second time-frequency map.

[0103] It should also be noted that in practical applications, the rotational speed of a permanent magnet synchronous motor, as a dynamically changing parameter, has a significant impact on fault characteristics and can limit the accuracy and reliability of fault identification. Therefore, this application introduces the rotational speed corresponding to the pixel in the time-frequency diagram when mapping and encoding the pixel. That is, by combining the rotational speed corresponding to the pixel in the time-frequency diagram, the pixel in the time-frequency diagram is mapped and encoded, and a quantum state related to the rotational speed is customized for the pixel in the time-frequency diagram. This fully considers the influence of rotational speed on fault characteristics and can further improve the accuracy and reliability of fault identification.

[0104] In this application, by mapping and encoding such customized quantum states, quantum states related to rotational speed are customized for pixels in the time-frequency graph, and a globally customized quantum state tensor is constructed. This fully considers the influence of rotational speed on fault characteristics, and can more accurately extract and characterize early weak fault features related to rotational speed. This effectively improves the fault prediction model's ability to detect complex nonlinear fault modes, significantly improves the detection sensitivity of early weak faults and the accuracy of fault identification, and provides a more reliable guarantee for the safe and stable operation of permanent magnet synchronous motors.

[0105] Regarding the method for determining the custom quantum state, in some embodiments, a first maximum rotational speed can be determined based on the rotational speeds corresponding to all pixels in the first time-frequency image, and a second maximum rotational speed can be determined based on the rotational speeds corresponding to all pixels in the second time-frequency image; a rotational speed modulation weight corresponding to each pixel in the first time-frequency image can be determined based on the rotational speeds corresponding to each pixel in the first time-frequency image and the first maximum rotational speed, and a rotational speed modulation weight corresponding to each pixel in the second time-frequency image can be determined based on the rotational speeds corresponding to each pixel in the second time-frequency image and the second maximum rotational speed; each pixel in the first time-frequency image is mapped and encoded based on the rotational speed modulation weights corresponding to each pixel in the first time-frequency image to obtain the custom quantum state corresponding to each pixel in the first time-frequency image, and the same applies to the second time-frequency image.

[0106] Furthermore, in some embodiments, the quotient between the rotational speed corresponding to each pixel in the time-frequency graph and the maximum rotational speed can be used as the rotational speed modulation weight corresponding to each pixel in the time-frequency graph.

[0107] In this application, by optimizing the quantum state encoding through rotational speed modulation weights, the extraction accuracy of early weak fault features and the ability to distinguish fault modes are significantly improved.

[0108] Regarding the method for determining the rotational speed modulation weight, in some embodiments, the frequency corresponding to each pixel in the first time-frequency image and the frequency corresponding to each pixel in the second time-frequency image can be obtained; the rotational speed modulation weight corresponding to each pixel in the first time-frequency image can be determined based on the frequency and rotational speed corresponding to each pixel in the first time-frequency image and the first maximum rotational speed; and the rotational speed modulation weight corresponding to each pixel in the second time-frequency image can be determined based on the frequency and rotational speed corresponding to each pixel in the second time-frequency image and the second maximum rotational speed.

[0109] In this application, by integrating frequency and rotation speed information to optimize weight calculation, the ability of customized quantum state coding to characterize complex fault features is significantly improved, and the robustness of fault mode recognition is enhanced.

[0110] Furthermore, in some embodiments, the rotational speed modulation weight corresponding to each pixel in the first time-frequency graph can be determined according to the following formula:

[0111] ;

[0112] The rotational speed modulation weight corresponding to each pixel in the second time-frequency graph is determined according to the following formula:

[0113] ;

[0114] in, This represents the rotational speed modulation weight corresponding to the nth pixel in the first time-frequency graph. Let n be the coordinates of the nth pixel in the first time-frequency graph. The rotational speed corresponds to the nth pixel in the first time-frequency graph. The first maximum speed, It is a sine function. Pi This represents the frequency corresponding to the nth pixel in the first time-frequency graph. This represents the rotational speed modulation weight corresponding to the m-th pixel in the second time-frequency diagram. Let m be the coordinates of the m-th pixel in the second time-frequency graph. Let m be the rotational speed corresponding to the m-th pixel in the second time-frequency graph. The second maximum speed, This is the frequency corresponding to the m-th pixel in the second time-frequency diagram.

[0115] In some embodiments, for It can also be represented as the ordinate of the nth pixel in the first time-frequency graph. It can also be represented as the ordinate of the m-th pixel in the second time-frequency graph.

[0116] In this application, by introducing a sine function to construct a frequency-speed joint modulation weighting formula, the analytical capability and diagnostic robustness of the customized quantum state coding for complex fault characteristics are significantly improved.

[0117] Furthermore, in some embodiments, the amplitude corresponding to each pixel in the first time-frequency image can be normalized to obtain the normalized amplitude corresponding to each pixel in the first time-frequency image, and the amplitude corresponding to each pixel in the second time-frequency image can be normalized to obtain the normalized amplitude corresponding to each pixel in the second time-frequency image; the customized quantum state corresponding to each pixel in the first time-frequency image is determined based on the rotational speed modulation weight, normalized amplitude, and phase corresponding to each pixel in the first time-frequency image, and the customized quantum state corresponding to each pixel in the second time-frequency image is determined based on the rotational speed modulation weight, normalized amplitude, and phase corresponding to each pixel in the second time-frequency image.

[0118] In this application, by using rotation speed modulation weighting, amplitude normalization and phase fusion coding, the fault characteristic characterization capability and coding robustness of customized quantum states are significantly improved.

[0119] Furthermore, the custom quantum state corresponding to each pixel in the first time-frequency graph can be determined using the following formula:

[0120] ;

[0121] The custom quantum state corresponding to each pixel in the second time-frequency graph is determined according to the following formula:

[0122] ;

[0123] in, This represents the custom quantum state corresponding to the nth pixel in the first time-frequency graph. Let n be the coordinates of the nth pixel in the first time-frequency graph. This represents the rotational speed modulation weight corresponding to the nth pixel in the first time-frequency graph. This represents the normalized amplitude corresponding to the nth pixel in the first time-frequency graph. It is a natural constant. The imaginary unit, This represents the phase corresponding to the nth pixel in the first time-frequency diagram. and Let be the orthogonal basis vectors of the two-dimensional Hilbert space in quantum state encoding. This represents the custom quantum state corresponding to the m-th pixel in the second time-frequency diagram. Let m be the coordinates of the m-th pixel in the second time-frequency graph. This represents the rotational speed modulation weight corresponding to the m-th pixel in the second time-frequency diagram. This represents the normalized amplitude corresponding to the m-th pixel in the second time-frequency graph. This represents the phase corresponding to the m-th pixel in the second time-frequency diagram.

[0124] In this application, a quantum state encoding formula is customized by jointly using three parameters: rotation speed modulation weight, normalized amplitude, and phase, which significantly improves the quantum characterization capability and pattern recognition accuracy of fault features.

[0125] In some embodiments, the first globally customized quantum state tensor can be determined according to the following formula:

[0126] ;

[0127] The second globally customized quantum state tensor is determined according to the following formula:

[0128] ;

[0129] in, Customize the first global quantum state tensor. The symbol for tensor product is... Let N be the coordinates of the Nth pixel in the first time-frequency graph. This represents the total number of pixels in the first time-frequency graph. Let n be the coordinates of the nth pixel in the first time-frequency graph. This represents the custom quantum state corresponding to the nth pixel in the first time-frequency graph. Customize the second global quantum state tensor. Here are the coordinates of the Mth pixel in the second time-frequency graph. This represents the total number of pixels in the second time-frequency graph. Let m be the coordinates of the m-th pixel in the second time-frequency graph. This is the custom quantum state corresponding to the m-th pixel in the second time-frequency diagram.

[0130] In this embodiment, a globally customized quantum state tensor is constructed through tensor product, thereby realizing high-order correlation analysis and mode decoupling of fault characteristics.

[0131] It should be noted that, since this application uses the first global customized quantum state tensor as the first global quantum state tensor and the second customized quantum state tensor as the second global quantum state tensor when employing the mapping encoding of customized quantum states, the first global quantum state tensor and the second global quantum state tensor can be obtained by quantum state mapping encoding or by customized quantum states. In the subsequent description of embodiments, if the processing methods of the first global quantum state tensor and the second global quantum state tensor obtained by quantum state mapping encoding differ from those obtained by customized quantum state mapping encoding in the preset permanent magnet synchronous motor fault prediction model, different embodiments can be used under the conditions of quantum state mapping encoding or customized quantum state mapping encoding for special explanation. Of course, if the processing methods are the same, no further special explanation will be given to avoid redundancy.

[0132] Step 140: Input the first global quantum state tensor and the second global quantum state tensor into the preset permanent magnet synchronous motor fault prediction model to obtain the fault classification and identification results.

[0133] Here, the preset permanent magnet synchronous motor fault prediction model refers to a pre-trained model used to predict the output fault classification and identification results based on the input first global quantum state tensor and second global quantum state tensor.

[0134] Regarding the acquisition method of the preset permanent magnet synchronous motor fault prediction model, in some embodiments, it can be obtained by the training method of the model in the prior art, which will not be elaborated here.

[0135] In some embodiments, the preset permanent magnet synchronous motor fault prediction model includes a quantum heuristic neural network module, a two-stream convolutional neural network module, and an SVM classifier connected in sequence. The quantum heuristic neural network module is used to perform rotation and entanglement operations on both the first global quantum state tensor and the second global quantum state tensor to obtain a first enhanced feature vector and a second enhanced feature vector. The two-stream convolutional neural network module is used to extract and fuse features from the first enhanced feature vector and the second enhanced feature vector to obtain a two-stream fused feature vector. The SVM classifier is used to classify the two-stream fused feature vector to obtain the fault classification and identification result.

[0136] It should be noted that the dual-stream convolutional neural network module can employ existing feature fusion techniques during the feature extraction and fusion process of the first and second enhanced feature vectors. However, to further improve the accuracy of fault identification, this application also customizes an innovative fusion method, namely:

[0137] In other embodiments, the signal entropy corresponding to each pixel in the first time-frequency image can be determined based on the vibration signal. Then, based on the first time-frequency image, the second time-frequency image, and the signal entropy corresponding to each pixel in the first time-frequency image, the fusion weight corresponding to each pixel in the first time-frequency image and the fusion weight corresponding to each pixel in the second time-frequency image can be determined. The fusion weight corresponding to each pixel in the first time-frequency image and the fusion weight corresponding to each pixel in the second time-frequency image are then input into a preset permanent magnet synchronous motor fault prediction model. This allows the dual-stream convolutional neural network module to perform feature extraction and fusion on the first enhanced feature vector and the second enhanced feature vector based on the fusion weight corresponding to each pixel in the first time-frequency image and the fusion weight corresponding to each pixel in the second time-frequency image, thereby obtaining a dual-stream fused feature vector.

[0138] Furthermore, in some embodiments, the type of signal entropy includes, but is not limited to, Shannon entropy, sample entropy, etc., and this application preferably uses Shannon entropy as signal entropy.

[0139] It should be noted that, since the horizontal and vertical coordinates of the pixels in the first time-frequency graph are time and frequency, respectively, and the vibration signal is a signal that changes with time, in some embodiments, the signal entropy corresponding to each time can be determined based on the vibration signal, and matched with the time corresponding to the pixels in the first time-frequency graph to determine the signal entropy corresponding to each pixel in the first time-frequency graph; wherein, the signal entropy corresponding to each time can be the signal entropy for each moment, or the signal entropy for each time window.

[0140] It should also be noted that, since the horizontal and vertical coordinates of the pixels in the first and second time-frequency maps are time and frequency, respectively, in some embodiments, the frequency corresponding to each pixel in the first time-frequency map can be determined based on the first time-frequency map, and the frequency corresponding to each pixel in the second time-frequency map can be determined based on the second time-frequency map. Then, based on the frequency and signal entropy corresponding to each pixel in the first time-frequency map, and the frequency corresponding to each pixel in the second time-frequency map, the fusion weight corresponding to each pixel in the first time-frequency map is determined. Finally, the difference between 1 and the fusion weight corresponding to each pixel in the first time-frequency map is used as the fusion weight corresponding to each pixel in the second time-frequency map.

[0141] In this application, this customized fusion approach fully leverages the advantages of both short-time Fourier transform and synchronous compressed wavelet transform, effectively extracting and fusing different feature information. This enhances the ability to capture early, weak fault features and significantly improves the distinguishability of fault features. Simultaneously, it better adapts to the real-time characteristics of non-stationary signals in permanent magnet synchronous motors, enabling the fault prediction model to more accurately distinguish different early faults. This greatly improves the accuracy, reliability, and real-time performance of fault identification in permanent magnet synchronous motors, providing strong support for ensuring the safe and stable operation of the motor.

[0142] Regarding the method for determining the fusion weights, in some embodiments, the energy corresponding to each pixel in the first time-frequency image can be normalized to obtain the normalized energy corresponding to each pixel in the first time-frequency image, and the normalized local frequency change rate corresponding to each pixel in the second time-frequency image; based on the normalized energy and signal entropy corresponding to each pixel in the first time-frequency image, and the normalized local frequency change rate corresponding to each pixel in the second time-frequency image, the fusion weights corresponding to each pixel in the first time-frequency image and the fusion weights corresponding to each pixel in the second time-frequency image are determined.

[0143] Furthermore, regarding the method of determining energy, in some embodiments, the square of the modulus of each pixel in the first time-frequency image can be used as the energy corresponding to each pixel in the first time-frequency image.

[0144] Furthermore, regarding the method for determining the local frequency change rate, in some embodiments, the instantaneous frequency corresponding to each pixel in the second time-frequency image can be obtained, and then time difference can be performed on the instantaneous frequency corresponding to each pixel in the second time-frequency image to obtain the local frequency change rate corresponding to each pixel in the second time-frequency image; of course, in other embodiments, frequency difference can also be performed on the instantaneous frequency corresponding to each pixel in the second time-frequency image to obtain the local frequency change rate corresponding to each pixel in the second time-frequency image.

[0145] In this application, by extracting the energy of the first time-frequency map and the local frequency change rate of the second time-frequency map, and combining it with the signal entropy, the rationality and accuracy of the calculation of the fusion weight are improved, thereby enhancing the fault feature extraction effect and improving the reliability of fault identification.

[0146] Furthermore, in some embodiments, the fusion weight corresponding to each pixel in the first time-frequency image and the fusion weight corresponding to each pixel in the second time-frequency image can be determined according to the following formula:

[0147] ;

[0148] in, Here are the fusion weights corresponding to each pixel in the first time-frequency image. Let n be the coordinates of the nth pixel in the first time-frequency graph. This represents the normalized energy corresponding to each pixel in the first time-frequency graph. For adjustment coefficients, Let be the signal entropy corresponding to each pixel in the first time-frequency graph. This represents the normalized local frequency change rate corresponding to each pixel in the second time-frequency graph. Let m be the coordinates of the m-th pixel in the second time-frequency graph. This represents the fusion weight corresponding to each pixel in the second time-frequency graph.

[0149] The value of the adjustment coefficient can be obtained and preset by the operator based on a large amount of experience, experimentation or statistics; preferably, the adjustment coefficient is set to 0.5 in this application.

[0150] In this application, by introducing quantitative indicators such as normalized energy, signal entropy, and normalized local frequency change rate, and combining them with adjustment coefficients, a mathematically formulated weight calculation model is constructed. This realizes the scientific quantification and dynamic optimization of the fusion weight, significantly improving the accuracy and adaptability of fault feature fusion, thereby enhancing the reliability and real-time performance of fault identification.

[0151] In some embodiments, the dual-stream convolutional neural network module is used to extract key features from the first enhanced feature vector and the second enhanced feature vector to obtain the first key feature vector and the second key feature vector, and to perform weighted feature fusion of the first key feature vector and the second key feature vector according to the fusion weight corresponding to each pixel in the first time-frequency image and the fusion weight corresponding to each pixel in the second time-frequency image to obtain the dual-stream fused feature vector.

[0152] It should be noted that the dual-stream convolutional neural network module of this application does not contain a softmax classifier. This application improves the accuracy of fault identification by introducing an SVM classifier to replace the softmax classifier in the dual-stream convolutional neural network module.

[0153] In this application, the accuracy and reliability of fault classification are significantly improved by the co-design of a two-stream convolutional neural network module and an SVM classifier.

[0154] Furthermore, in some embodiments, the dual-stream fusion feature vector can be obtained according to the following formula:

[0155] ;

[0156] in, For the r-th feature in the dual-stream fusion feature vector, Here are the fusion weights corresponding to each pixel in the first time-frequency image. Let n be the coordinates of the nth pixel in the first time-frequency graph. The nth feature in the first key feature vector. Here are the fusion weights corresponding to each pixel in the second time-frequency graph. Let m be the coordinates of the m-th pixel in the second time-frequency graph. This is the m-th feature in the second key feature vector.

[0157] In this application, a formulaic weighted fusion strategy is adopted to achieve dynamic optimization and integration of multi-dimensional features, which significantly improves the discriminativeness and classification reliability of fault feature representation.

[0158] In some embodiments, the dual-stream convolutional neural network module includes two convolutional neural network units, a fusion layer, and a fully connected layer. Both convolutional neural network units are connected to the fusion layer, which in turn is connected to the fully connected layer. The first convolutional neural network unit is used to extract key features from a first enhanced feature vector to obtain a first key feature vector. The second convolutional neural network unit is used to extract key features from a second enhanced feature vector to obtain a second key feature vector. The fusion layer is used to perform weighted feature fusion of the first and second key feature vectors based on the fusion weights corresponding to each pixel in the first and second time-frequency maps to obtain an initial dual-stream fused feature vector. The fully connected layer is used to perform feature mapping on the initial dual-stream fused feature vector to obtain the final dual-stream fused feature vector.

[0159] In this application, the discriminative power and classification reliability of fault feature representation are significantly improved by using a two-stream convolutional neural network module for phased feature extraction and weighted fusion, combined with feature mapping optimization of the fully connected layer.

[0160] In some embodiments, each convolutional neural network unit includes an input layer, a first feature extraction block, a second feature extraction block, a first connection layer, and a second connection layer connected in sequence. The first feature extraction block and the second feature extraction block each include a convolutional layer, a batch normalization layer, an activation function layer, a max pooling layer, and a Dropout layer connected in sequence.

[0161] In this application, a convolutional neural network unit with hierarchical feature extraction and regularization design is used to achieve in-depth mining and efficient expression of time-frequency features, which significantly improves the robustness and discriminativeness of fault feature extraction.

[0162] It should be noted that, since the preset permanent magnet synchronous motor fault prediction model includes a quantum heuristic neural network module, the data input to the preset permanent magnet synchronous motor fault prediction model is the first global quantum state tensor and the second global quantum state tensor. If the preset permanent magnet synchronous motor fault prediction model does not include a quantum heuristic neural network module, then the data input to the preset permanent magnet synchronous motor fault prediction model can be the first time-frequency diagram and the second time-frequency diagram, that is:

[0163] In other embodiments, when the preset permanent magnet synchronous motor fault prediction model includes a dual-stream convolutional neural network module and an SVM classifier connected in sequence, the first enhanced feature vector and the second enhanced feature vector are replaced with the first time-frequency map and the second time-frequency map. That is, the first time-frequency map, the second time-frequency map, the fusion weight corresponding to each pixel in the first time-frequency map, and the fusion weight corresponding to each pixel in the second time-frequency map are input into the preset permanent magnet synchronous motor fault prediction model to obtain the fault classification and identification result.

[0164] In this application, this customized fusion approach fully leverages the advantages of both short-time Fourier transform and synchronous compressed wavelet transform, effectively extracting and fusing different feature information. This enhances the ability to capture early, weak fault features and significantly improves the distinguishability of fault features. Simultaneously, it better adapts to the real-time characteristics of non-stationary signals in permanent magnet synchronous motors, enabling the fault prediction model to more accurately distinguish different early faults. This greatly improves the accuracy, reliability, and real-time performance of fault identification in permanent magnet synchronous motors, providing strong support for ensuring the safe and stable operation of the motor.

[0165] In this embodiment of the application, the quantum heuristic neural network approach can effectively uncover the subtle features of early faults in permanent magnet synchronous motors. By utilizing the unique rotation and entanglement operations of the quantum heuristic neural network to enhance feature representation capabilities, and combining the feature extraction and fusion capabilities of the dual-stream convolutional neural network module with the accurate classification capabilities of the SVM classifier, the detection sensitivity of early subtle faults is significantly improved. This enables more accurate differentiation of the degree of faults in permanent magnet synchronous motors and effective identification of fault types, providing a reliable guarantee for the stable operation of permanent magnet synchronous motors.

[0166] In addition to the effects mentioned above, this permanent magnet synchronous motor fault identification method also has the following advantages: Complementary multi-time-frequency analysis: It employs both short-time Fourier transform and synchronous compressed wavelet transform to obtain time-frequency maps, fully utilizing the characteristics of different time-frequency analysis methods. Short-time Fourier transform can provide signal features at a certain time and frequency resolution, while synchronous compressed wavelet transform has advantages in processing non-stationary signals. The combination of the two can mine signal information from different angles, providing a richer foundation for subsequent fault feature extraction and enhancing the coverage of complex fault modes; Flexible time-frequency analysis replacement: The method mentions that short-time Fourier transform can be used to replace other time-frequency analysis methods. The Fourier transform and synchronous compressed wavelet transform are replaced with other similar time-frequency analysis techniques, such as Fourier transform, Hilbert-Huang transform, wavelet transform, and continuous wavelet transform. This flexibility allows the method to select the most suitable time-frequency analysis method based on different motor operating conditions, fault types, and actual needs, further improving the effectiveness and relevance of fault feature extraction. Comprehensive feature information preservation: In the mapping and encoding process of the time-frequency diagram, not only the amplitude and phase information of pixels are considered, but also various feature parameters such as rotational speed, signal entropy, energy, and local frequency change rate are introduced in the customized quantum state mapping and encoding. By employing multi-parameter joint encoding, fault feature information in the signal can be more comprehensively preserved, avoiding feature loss that may occur with single-parameter encoding, thus providing a more sufficient basis for accurate fault identification. Quantum state encoding enhances feature discrimination: through quantum state mapping encoding, pixels in the time-frequency graph are mapped to quantum states and a global quantum state tensor is constructed. Utilizing the unique properties of quantum states, such as rotational superposition and entanglement, weak features of early faults in permanent magnet synchronous motors can be extracted and characterized more effectively. Compared with traditional methods, this encoding method significantly improves the detection capability for complex nonlinear fault modes, enabling the identification of different fault degrees and fault characteristics. The feature differentiation between types is greater, which is conducive to more accurate fault classification and identification; the customized quantum state takes into account dynamic factors: the mapping and encoding method of customized quantum state fully considers the influence of the dynamic change parameter of permanent magnet synchronous motor speed on fault features. By combining the speed corresponding to the pixel in the time-frequency map, a quantum state related to the speed is customized for the pixel, and a global customized quantum state tensor is constructed. This method can extract and characterize early weak fault features related to speed more accurately, effectively solve the problem of inaccurate fault identification caused by ignoring the dynamic change of speed in traditional methods, and improve the adaptability of the fault prediction model to actual operating conditions;Innovative fusion method enhances feature fusion effect: An innovative feature fusion method is adopted in the dual-stream convolutional neural network module. By determining the signal entropy based on the vibration signal, the fusion weights corresponding to each pixel in the first and second time-frequency maps are determined. This allows the dual-stream convolutional neural network module to extract and fuse features from the first and second enhanced feature vectors based on these fusion weights. This fusion method fully utilizes the advantages of both short-time Fourier transform and synchronous compressed wavelet transform, effectively extracting and fusing different feature information, enhancing the ability to capture early weak fault features, and significantly improving the distinguishability of fault features. Modular design facilitates optimization and expansion: Preset permanent magnet synchronous motor faults... The prediction model employs a modular design, including a quantum heuristic neural network module, a two-stream convolutional neural network module, and an SVM classifier. This modular structure allows each module to be independently optimized and improved. For example, the rotation and entanglement operations of the quantum heuristic neural network module can be optimized for different fault types or operating conditions, or the structure and parameters of the two-stream convolutional neural network module can be adjusted. Simultaneously, the modular design facilitates model expansion according to actual needs, such as adding new feature extraction modules or classifiers to further improve fault identification performance and enhance motor operational reliability and safety. This method can significantly improve the detection sensitivity of early, subtle faults in permanent magnet synchronous motors. More accurate differentiation of fault severity and effective identification of fault types, by timely detection of early potential faults during motor operation and accurate judgment of fault type and severity, allows for targeted maintenance measures to prevent further deterioration of the fault, thereby improving the reliability and safety of motor operation, reducing production accidents and equipment damage caused by motor failures, and ensuring the smooth operation of the production process; reducing maintenance costs and downtime: Traditional motor maintenance methods often employ periodic maintenance or reactive repair, both of which have certain limitations. Periodic maintenance may lead to over-maintenance, increasing unnecessary maintenance costs, while reactive repair may lead to the expansion of faults due to untimely fault detection, increasing repair difficulty and costs. This method, based on real-time monitoring and accurate fault identification, enables predictive maintenance. It provides early warnings and schedules maintenance before faults occur, avoiding over-maintenance and fault escalation, effectively reducing maintenance costs and downtime, and improving production efficiency and economic benefits. Furthermore, it adapts to complex and changing industrial environments: Permanent magnet synchronous motors are widely used in industry, operating in complex and variable environments, facing various interferences and uncertainties. This method, by comprehensively considering multiple characteristic parameters and employing advanced signal processing and model building techniques, possesses strong anti-interference capabilities and adaptability. It can accurately identify motor faults in complex and changing industrial environments, providing strong support for the stable operation of industrial production.

[0167] In one feasible implementation, the rotation and entanglement operations performed on both the first and second global quantum state tensors in the above embodiments to obtain the first and second enhanced eigenvectors include: obtaining the rotation matrix corresponding to each pixel in the first time-frequency image and the rotation matrix corresponding to each pixel in the second time-frequency image; using the rotation matrix corresponding to the nth pixel in the first time-frequency image to rotate the nth quantum state in the first global quantum state tensor to obtain the nth rotated quantum state in the third global quantum state tensor; and using the rotation matrix corresponding to the mth pixel in the second time-frequency image to rotate the mth quantum state in the second global quantum state tensor to obtain the mth rotated quantum state in the fourth global quantum state tensor; and using a convolution operation to simulate entanglement operations to perform cross-time and frequency entanglement operations on the nth rotated quantum state in the third global quantum state tensor and the remaining rotated quantum states to obtain the nth rotated quantum state in the third global quantum state tensor and the remaining rotated quantum states. The first correlation between the two states is obtained by performing time-frequency entanglement operations on the m-th rotated quantum state in the fourth global quantum state tensor and the remaining rotated quantum states. Here, n takes integer values ​​greater than 0 until it equals the total number of pixels in the first time-frequency map, resulting in the third global quantum state tensor and the first correlation vector composed of all the first correlations. m takes integer values ​​greater than 0 until it equals the total number of pixels in the second time-frequency map, resulting in the fourth global quantum state tensor and the second correlation vector composed of all the second correlations. The third global quantum state tensor and the first correlation vector are fused and concatenated to obtain the first concatenated feature vector. The fourth global quantum state tensor and the second correlation feature vector are fused and concatenated to obtain the second concatenated feature vector. The first concatenated feature vector is mapped and decoded to obtain the first enhanced feature vector. The second concatenated feature vector is mapped and decoded to obtain the second enhanced feature vector.

[0168] It should be noted that, regarding mapping decoding, the opposite of mapping encoding, that is, in some embodiments, during mapping decoding, the... and The coefficients are reassembled into a new time-frequency diagram, and the new time-frequency diagram is the spliced ​​feature vector.

[0169] Regarding the determination of the concatenated feature vector, in some embodiments, a fusion concatenation method can be used to fuse and concatenate the quantum states in the global quantum state tensor with the correlations in the correlation vector in a one-to-one correspondence to obtain the concatenated feature vector. Of course, in other embodiments, the learnable weights obtained from pre-training can also be obtained, and then weighted fusion concatenation can be used. According to the learnable weights, the quantum states in the global quantum state tensor with the correlations in the correlation vector in a one-to-one correspondence can be fused and concatenated to obtain the concatenated feature vector. The learnable weights take values ​​in the range of [0, 1], the weights of the quantum states in the global quantum state tensor are the learnable weights, and the correlations in the correlation vector are the difference between 1 and the learnable weights.

[0170] In the embodiments of this application, the ability to express fault features is significantly enhanced by the rotation and entanglement operations of quantum states. Combined with correlation analysis and fusion splicing strategies, high-sensitivity extraction and accurate classification of early weak fault features are achieved.

[0171] Understandably, rotation operations enhance feature discriminative power: by assigning an independent rotation matrix to each pixel, the quantum states in the global quantum state tensor are rotated in a targeted manner. This operation can amplify the differences in weak fault features in the quantum state space. Entanglement operations capture cross-spatial-temporal correlations: by using convolution operations to simulate quantum entanglement, the correlation between quantum states is calculated across time and frequency dimensions, which can extract the propagation law of fault features in the time-frequency domain. This cross-dimensional correlation analysis can effectively capture the dynamic evolution characteristics of complex nonlinear fault modes and make up for the shortcomings of traditional time-frequency analysis methods in modeling global correlations. Fusion and splicing achieve multimodal feature complementarity: by fusing and splicing the rotated global quantum state tensor with the correlation vector (such as weighted fusion or direct splicing), a composite feature vector containing local features and global correlations is constructed. This multimodal feature fusion significantly improves the model's ability to identify mixed fault modes.

[0172] In one feasible implementation, obtaining the rotation matrix corresponding to each pixel in the first time-frequency image and the rotation matrix corresponding to each pixel in the second time-frequency image in the above embodiments includes: obtaining the rotation speed signal of the permanent magnet synchronous motor; determining the rotation speed corresponding to each pixel in the first time-frequency image and the rotation speed corresponding to each pixel in the second time-frequency image based on the rotation speed signal; determining the signal entropy corresponding to each pixel in the first time-frequency image and the signal entropy corresponding to each pixel in the second time-frequency image based on the vibration signal; determining the first maximum energy based on the energy corresponding to all pixels in the first time-frequency image and the first maximum energy based on the energy corresponding to all pixels in the second time-frequency image. The energy corresponding to each point is used to determine the second maximum energy; based on the rotational speed, signal entropy, and energy corresponding to each pixel in the first time-frequency image, and the first maximum energy, the rotation angle corresponding to each pixel in the first time-frequency image is determined; based on the rotational speed, signal entropy, and energy corresponding to each pixel in the second time-frequency image, and the second maximum energy, the rotation angle corresponding to each pixel in the second time-frequency image is determined; based on the rotation angle corresponding to each pixel in the first time-frequency image, a rotation matrix corresponding to each pixel in the first time-frequency image is constructed; and based on the rotation angle corresponding to each pixel in the second time-frequency image, a rotation matrix corresponding to each pixel in the second time-frequency image is constructed.

[0173] It should be noted that the embodiment here uses a method for determining the rotation matrix under the condition of quantum state mapping encoding. If a method for determining the rotation matrix under the condition of customized quantum state mapping encoding is used, the following embodiment will be adopted:

[0174] In other embodiments, the rotational speed signal of the permanent magnet synchronous motor can be acquired. Based on the rotational speed signal, the rotational speed corresponding to each pixel in the first time-frequency image and the rotational speed corresponding to each pixel in the second time-frequency image can be determined. Then, based on the rotational speed corresponding to each pixel in the first time-frequency image, the rotational angle corresponding to each pixel in the first time-frequency image can be determined. Finally, based on the rotational angle corresponding to each pixel in the first time-frequency image, a rotation matrix corresponding to each pixel in the first time-frequency image can be constructed. And based on the rotational angle corresponding to each pixel in the second time-frequency image, a rotation matrix corresponding to each pixel in the second time-frequency image can be constructed.

[0175] In this application, a dynamic rotation matrix is ​​constructed by rotating the rotation speed, which significantly improves the fault feature enhancement capability of customized quantum state rotation operation and achieves high-sensitivity capture of weak fault features under complex working conditions.

[0176] In this embodiment, a dynamic rotation matrix is ​​constructed by fusing rotation speed, signal entropy, and energy, which significantly improves the fault feature enhancement capability of quantum state rotation operation and achieves high-sensitivity capture of weak fault features under complex working conditions.

[0177] Understandably, multi-dimensional feature fusion enhances feature discrimination: combining speed, signal entropy, and energy features, a rotation angle calculation model is constructed, and the three work together to make the rotation angle dynamically change with fault features; maximum energy normalization improves model robustness: by introducing the maximum energy value of the time-frequency graph for normalization, the influence of energy benchmark differences under different operating conditions is effectively eliminated; dynamic rotation matrix achieves precise feature enhancement: each pixel is equipped with an independent rotation matrix, realizing pixel-level precise control of fault features; and the ability to adapt to operating conditions is significantly improved: the rotation matrix construction process automatically incorporates the speed signal, enabling the model to have the ability to adapt to operating conditions.

[0178] In one feasible implementation, the rotation angle corresponding to each pixel in the first time-frequency image is determined according to the following formula:

[0179] ;

[0180] The rotation angle corresponding to each pixel in the second time-frequency graph is determined according to the following formula;

[0181] ;

[0182] in, Let be the rotation angle corresponding to the nth pixel in the first time-frequency graph. Let n be the coordinates of the nth pixel in the first time-frequency graph. For speed coefficient, The rotational speed corresponds to the nth pixel in the first time-frequency graph. The signal entropy coefficient, Let be the signal entropy corresponding to the nth pixel in the first time-frequency graph. The energy coefficient, This represents the energy corresponding to the nth pixel in the first time-frequency graph. The first and greatest energy, Let be the rotation angle corresponding to the m-th pixel in the second time-frequency graph. Let m be the coordinates of the m-th pixel in the second time-frequency graph. Let m be the rotational speed corresponding to the m-th pixel in the second time-frequency graph. Let be the signal entropy corresponding to the m-th pixel in the second time-frequency diagram. Let m be the energy corresponding to the m-th pixel in the second time-frequency graph. It is the second largest energy.

[0183] The values ​​of the speed coefficient, signal entropy coefficient, and energy coefficient can be obtained and preset by the operator based on extensive experience, experiments, or statistics. Preferably, the speed coefficient is set to 0.4, the signal entropy coefficient is set to 0.3, and the energy coefficient is set to 0.3.

[0184] It should be noted that the embodiment here uses the rotation angle calculation formula under the condition of quantum state mapping encoding. If the rotation angle calculation formula under the condition of customized quantum state mapping encoding is used, the following embodiment will be used, namely:

[0185] In other embodiments, the rotation angle corresponding to each pixel in the first time-frequency image can also be determined according to the following formula:

[0186] ;

[0187] The rotation angle corresponding to each pixel in the second time-frequency graph is determined using the following formula:

[0188] ;

[0189] in, To customize the speed coefficient.

[0190] The value of the customized speed coefficient can be obtained and preset by the operator based on a large amount of experience, experiments or statistics; preferably, the customized speed coefficient is set to 0.7 in this application.

[0191] In this application, the rotation angle is dynamically calculated by rotation speed to construct a rotation matrix, which significantly improves the fault feature enhancement capability of customized quantum state rotation operation and achieves high-sensitivity capture and accurate classification of weak fault features under complex working conditions.

[0192] In this embodiment, the rotation angle is dynamically calculated by fusing rotation speed, signal entropy and energy to construct a rotation matrix, which significantly improves the fault feature enhancement capability of quantum state rotation operation and achieves high sensitivity capture and accurate classification of weak fault features under complex working conditions.

[0193] Understandably, multi-dimensional feature fusion enhances feature discrimination: the formula combines the triple features of rotational speed, signal entropy, and energy, and through the weighted combination of rotational speed coefficient, signal entropy coefficient, and energy coefficient, the rotation angle dynamically changes with the fault features, which significantly improves the discrimination of fault features and enhances feature expression capabilities.

[0194] In one feasible implementation, before constructing the rotation matrix corresponding to each pixel in the first time-frequency image based on the rotation angle corresponding to each pixel in the first time-frequency image, and before constructing the rotation matrix corresponding to each pixel in the second time-frequency image based on the rotation angle corresponding to each pixel in the second time-frequency image, the method further includes: if there is a pixel in the first time-frequency image and the second time-frequency image whose rotation angle does not meet the preset rotation angle range, then clamping the rotation angle corresponding to the corresponding pixel to the preset rotation angle range according to the rotation angle corresponding to the corresponding pixel and the preset rotation angle range to obtain the clamped rotation angle corresponding to the corresponding pixel; and reusing the clamped rotation angle corresponding to the corresponding pixel as the rotation angle corresponding to the corresponding pixel.

[0195] The preset rotation angle range can be obtained and set in advance by the operator based on a large amount of experience, experiments or statistics. Of course, it can also be set in advance by the operator according to actual needs. There is no limitation here.

[0196] Regarding the value of the preset rotation angle range, in some embodiments, this application preferably sets the preset rotation angle range to [0, π / 2].

[0197] In this embodiment, the stability of the rotation matrix construction is ensured by the rotation angle clamping mechanism, avoiding interference from extreme angle values ​​on quantum state rotation operations, while improving the convergence of model training and the reliability of fault feature enhancement.

[0198] Understandably, this mechanism serves several purposes: First, it avoids interference from extreme angles. A preset rotation angle range limits extreme values. When a pixel's rotation angle exceeds this range, a clamping operation forces it to adjust to a reasonable range, preventing the quantum state rotation operation from failing due to excessively large or small angles, thus ensuring the effectiveness of feature enhancement. Second, it improves model training stability. Extreme rotation angles can cause numerical instability in the quantum state tensor after rotation. The clamping mechanism, by constraining the angle range, makes the distribution of quantum states more concentrated after rotation, reducing numerical fluctuations during training, accelerating model convergence, and improving generalization ability. Third, it enhances the robustness of fault feature enhancement. The clamped rotation angle ensures that the rotation operation of all pixels is within a controllable range, preventing global feature enhancement from failing due to abnormal angles of individual pixels, thus improving the robustness of feature enhancement. Fourth, it adapts to quantum state rotation. Quantum state rotation angles usually need to meet specific constraints. The clamping operation, by limiting the angle range, indirectly ensures the legality of the rotation matrix, making the quantum state rotation operation more consistent with the rules, thereby improving the accuracy of feature representation.

[0199] In one feasible implementation, the step of clamping the rotation angle corresponding to the corresponding pixel to the preset rotation angle range based on the rotation angle corresponding to the corresponding pixel and the preset rotation angle range in the above embodiments to obtain the clamped rotation angle corresponding to the corresponding pixel includes: if the rotation angle corresponding to the corresponding pixel is less than the lower limit of the preset rotation angle range, the lower limit of the preset rotation angle range is used as the clamped rotation angle corresponding to the corresponding pixel; if the rotation angle corresponding to the corresponding pixel is less than the upper limit of the preset rotation angle range, the upper limit of the preset rotation angle range is used as the clamped rotation angle corresponding to the corresponding pixel.

[0200] In this embodiment, by taking upper and lower limits to transform extreme rotation angles to the standard range, the interference of abnormal angle values ​​on quantum state rotation operations is effectively eliminated, significantly improving the stability of model training and the reliability of feature enhancement.

[0201] In one feasible implementation, before constructing the rotation matrix corresponding to each pixel in the first time-frequency image based on the rotation angle corresponding to each pixel in the first time-frequency image, and before constructing the rotation matrix corresponding to each pixel in the second time-frequency image based on the rotation angle corresponding to each pixel in the second time-frequency image, the method further includes: if there is a pixel in the first time-frequency image and the second time-frequency image whose rotation angle does not meet the preset rotation angle range, then transforming the rotation angle corresponding to the corresponding pixel to the preset rotation angle range according to the rotation angle corresponding to the corresponding pixel to obtain the transformed rotation angle corresponding to the corresponding pixel; and using the transformed rotation angle corresponding to the corresponding pixel as the rotation angle corresponding to the corresponding pixel again.

[0202] In this embodiment, the stability of the rotation matrix construction is ensured by the rotation angle transformation mechanism, avoiding interference from extreme angle values ​​on quantum state rotation operations, while improving the convergence of model training and the reliability of fault feature enhancement.

[0203] In one feasible implementation, the transformed rotation angle corresponding to the respective pixel is obtained according to the following formula:

[0204] ;

[0205] in, This represents the transformed rotation angle corresponding to the respective pixel. This represents the rotation angle corresponding to the respective pixel. The remainder symbol is used. Pi is the mathematical constant of a circle.

[0206] In the embodiments of this application, the formula transforms the extreme rotation angle to the standard range by taking the remainder, effectively eliminating the interference of abnormal angle values ​​on quantum state rotation operations, and significantly improving the stability of model training and the reliability of feature enhancement.

[0207] In one feasible implementation, the nth rotated quantum state in the third global quantum state tensor is obtained according to the following formula:

[0208] ;

[0209] The m-th rotated quantum state in the fourth global quantum state tensor is obtained using the following formula:

[0210] ;

[0211] in, This represents the nth rotated quantum state in the third global quantum state tensor. Let n be the coordinates of the nth pixel in the first time-frequency graph. Let be the rotation matrix corresponding to the nth pixel in the first time-frequency graph. This represents the quantum state corresponding to the nth pixel in the first time-frequency diagram. It is a cosine function. Let be the rotation angle corresponding to the nth pixel in the first time-frequency graph. It is a sine function. This represents the m-th rotated quantum state in the fourth global quantum state tensor. Let m be the coordinates of the m-th pixel in the second time-frequency graph. Let be the rotation matrix corresponding to the m-th pixel in the second time-frequency graph. Let m be the quantum state corresponding to the m-th pixel in the second time-frequency diagram. The rotation angle corresponds to the m-th pixel in the second time-frequency graph.

[0212] In the embodiments of this application, the dynamic enhancement and phase calibration of fault characteristics are achieved through the quantum state rotation formula, which significantly improves the detection sensitivity and feature discrimination of early weak faults.

[0213] Understandably, the dynamic feature enhancement mechanism works as follows: the formula constructs a rotation matrix using cosine and sine functions and rotation angles, enabling the quantum state to rotate dynamically in Hilbert space. This amplifies the differences in weak faults within the quantum state space. Compared to traditional fixed methods, this dynamic rotation mechanism can more accurately capture the time-varying characteristics of fault features. Phase calibration improves feature stability: the rotation angle is strongly correlated with fault feature parameters. Through mapping, adaptive calibration of the quantum state phase is achieved. Nonlinear feature decoupling capability: through the combination of orthogonal rotation bases, the formula decomposes the original quantum state into two orthogonal components, representing the magnitude and phase characteristics of the fault, respectively. This decoupling mechanism effectively separates the nonlinear components in the fault features, thereby improving the accuracy of fault type identification.

[0214] In one feasible implementation, the first correlation between the nth rotated quantum state and the remaining rotated quantum states in the third global quantum state tensor is obtained according to the following formula:

[0215] ;

[0216] The second correlation between the m-th rotated quantum state and the remaining rotated quantum states in the fourth global quantum state tensor is obtained using the following formula:

[0217] ;

[0218] in, This represents the first correlation between the nth rotated quantum state and the remaining rotated quantum states in the third global quantum state tensor. Let N be the coordinates of the Nth pixel in the first time-frequency graph. This represents the total number of pixels in the first time-frequency graph. Let i be the coordinates of the i-th pixel in the first time-frequency graph. Let n be the coordinates of the nth pixel in the first time-frequency graph. For the kernel function of the entanglement operation, Let be the quantum state inner product between the nth rotated quantum state and the ith rotated quantum state in the third global quantum state tensor. Let n be the dual state of the nth rotated quantum state in the third global quantum state tensor. Let i be the i-th rotated quantum state in the third global quantum state tensor. This represents the second correlation between the m-th rotated quantum state and the remaining rotated quantum states in the fourth global quantum state tensor. Here are the coordinates of the Mth pixel in the second time-frequency graph. This represents the total number of pixels in the second time-frequency graph. Let j be the coordinates of the j-th pixel in the second time-frequency graph. Let m be the coordinates of the m-th pixel in the second time-frequency graph. Let be the quantum state inner product between the m-th rotated quantum state and the j-th rotated quantum state in the fourth global quantum state tensor. Let m be the dual state of the m-th rotated quantum state in the fourth global quantum state tensor. Let j be the j-th rotated quantum state in the fourth global quantum state tensor.

[0219] In this embodiment, by introducing the entanglement operation of the kernel function and the inner product of the quantum state, high-order correlation modeling across the time-frequency dimension is realized, which significantly improves the feature extraction capability and classification accuracy of complex nonlinear fault modes.

[0220] Understandably, the formula achieves several key benefits: Cross-dimensional correlation capture: It calculates the time-frequency domain correlation between rotated quantum states using kernel functions (such as Gaussian kernels), overcoming the limitations of traditional methods that rely solely on local features and effectively capturing the propagation patterns of fault features in the time-frequency domain; Enhanced feature discrimination through quantum state inner product: It directly measures the similarity between quantum states using the quantum state inner product. Compared to traditional Euclidean distance or cosine similarity, the inner product operation is more sensitive to the phase differences in the quantum state space, thus amplifying the discriminative power of weak fault features in the Hilbert space; Global and local feature fusion: The formula constructs a global correlation vector by traversing all pixels while retaining local rotation features. This global-local fusion strategy enables the model to capture both the macroscopic propagation trend of faults and the microscopic features of key pixels; Significantly enhanced noise resistance: The combination of quantum state inner product and kernel function has natural noise resistance. Even if a pixel is distorted due to noise interference, the kernel function can still provide smooth compensation through the correlation of surrounding pixels, thus ensuring the stability of fault feature extraction.

[0221] In a second aspect, this application provides a fault identification device for a permanent magnet synchronous motor.

[0222] Please see Figure 2 This is a schematic diagram of a fault identification device for a permanent magnet synchronous motor according to an embodiment of this application. The device 210 includes:

[0223] The acquisition module 211 is used to acquire the vibration signal of the permanent magnet synchronous motor;

[0224] The transformation module 212 is used to perform short-time Fourier transform on the vibration signal to obtain a first time-frequency diagram, and to perform synchronous compressed wavelet transform on the vibration signal to obtain a second time-frequency diagram;

[0225] The mapping and encoding module 213 is used to map and encode the first time-frequency graph to obtain the first global quantum state tensor, and to map and encode the second time-frequency graph to obtain the second global quantum state tensor.

[0226] The model prediction module 214 is used to input the first global quantum state tensor and the second global quantum state tensor into the preset permanent magnet synchronous motor fault prediction model to obtain the fault classification and identification results.

[0227] The preset permanent magnet synchronous motor fault prediction model includes a quantum heuristic neural network module, a two-stream convolutional neural network module, and an SVM classifier connected in sequence.

[0228] The quantum heuristic neural network module is used to perform rotation and entanglement operations on both the first global quantum state tensor and the second global quantum state tensor to obtain the first enhanced eigenvector and the second enhanced eigenvector.

[0229] The dual-stream convolutional neural network module is used to extract and fuse features from the first and second enhanced feature vectors to obtain a dual-stream fused feature vector.

[0230] The SVM classifier is used to classify the dual-stream fused feature vectors to obtain fault classification and identification results.

[0231] In this embodiment, the relevant content of the acquisition module 211, transformation module 212, mapping encoding module 213 and model prediction module 214 can be found in the following references. Figure 1 The contents of the illustrated embodiments will not be repeated here.

[0232] It should be noted that the device 210 of this application also includes other modules. It can be understood that the method of this application and the device 210 have a one-to-one correspondence. Therefore, the other modules of the device 210 of this application are the contents corresponding to the method of this application in the above embodiments.

[0233] In this embodiment of the application, the quantum heuristic neural network approach can effectively uncover the subtle features of early faults in permanent magnet synchronous motors. By utilizing the unique rotation and entanglement operations of the quantum heuristic neural network to enhance feature representation capabilities, and combining the feature extraction and fusion capabilities of the dual-stream convolutional neural network module with the accurate classification capabilities of the SVM classifier, the detection sensitivity of early subtle faults is significantly improved. This enables more accurate differentiation of the degree of faults in permanent magnet synchronous motors and effective identification of fault types, providing a reliable guarantee for the stable operation of permanent magnet synchronous motors.

[0234] In a third aspect, this application provides a computer-readable storage medium storing a computer program, which, when executed by a processor, causes the processor to perform a permanent magnet synchronous motor fault identification method as described in any of the first aspects.

[0235] This application provides a computer device in a fourth aspect, including a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor performs a permanent magnet synchronous motor fault identification method as described in any of the first aspects.

[0236] Figure 3 The diagram illustrates the internal structure of a computer device in some embodiments. This computer device may specifically be a terminal, a server, or a gateway. Figure 3 As shown, the computer device includes a processor, memory, and network interface connected via a system bus.

[0237] The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium of the computer device stores an operating system and may also store a computer program. When executed by a processor, this computer program causes the processor to perform the steps in the above method embodiments. The internal memory may also store a computer program, which, when executed by a processor, causes the processor to perform the steps in the above method embodiments. Those skilled in the art will understand that... Figure 3 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0238] 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 program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above methods.

[0239] Any references to memory, storage, database, or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may 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 RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM), etc.

[0240] 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.

[0241] The embodiments described above are merely examples of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these modifications and improvements all fall within the protection scope of this application.

Claims

1. A method for fault identification of a permanent magnet synchronous motor, characterized in that, The method includes: Obtain the vibration signal of the permanent magnet synchronous motor; The vibration signal is subjected to a short-time Fourier transform to obtain a first time-frequency diagram, and the vibration signal is subjected to a synchronous compressed wavelet transform to obtain a second time-frequency diagram. The first time-frequency graph is mapped and encoded to obtain the first global quantum state tensor, and the second time-frequency graph is mapped and encoded to obtain the second global quantum state tensor; The first global quantum state tensor and the second global quantum state tensor are input into a preset permanent magnet synchronous motor fault prediction model to obtain fault classification and identification results; The preset permanent magnet synchronous motor fault prediction model includes a quantum heuristic neural network module, a two-stream convolutional neural network module, and an SVM classifier connected in sequence. The quantum heuristic neural network module is used to perform rotation and entanglement operations on both the first global quantum state tensor and the second global quantum state tensor to obtain a first enhanced feature vector and a second enhanced feature vector; The dual-stream convolutional neural network module is used to extract and fuse features from the first enhanced feature vector and the second enhanced feature vector to obtain a dual-stream fused feature vector. The SVM classifier is used to classify the dual-stream fused feature vector to obtain the fault classification and identification result. The step of performing rotation and entanglement operations on both the first and second global quantum state tensors to obtain a first enhanced eigenvector and a second enhanced eigenvector includes: Obtain the rotation matrix corresponding to each pixel in the first time-frequency image and the rotation matrix corresponding to each pixel in the second time-frequency image; Using the rotation matrix corresponding to the nth pixel in the first time-frequency diagram, the nth quantum state in the first global quantum state tensor is rotated to obtain the nth rotated quantum state in the third global quantum state tensor. Similarly, using the rotation matrix corresponding to the mth pixel in the second time-frequency diagram, the mth quantum state in the second global quantum state tensor is rotated to obtain the mth rotated quantum state in the fourth global quantum state tensor. A convolution operation is used to simulate entanglement, performing a cross-time and frequency entanglement operation between the nth rotated quantum state in the third global quantum state tensor and the remaining rotated quantum states, resulting in the nth rotated quantum state in the third global quantum state tensor and the remaining rotated quantum states. The first correlation between the rotated quantum states, and the entanglement operation across time and frequency of the m-th rotated quantum state in the fourth global quantum state tensor with the remaining rotated quantum states, are used to obtain the second correlation between the m-th rotated quantum state in the fourth global quantum state tensor and the remaining rotated quantum states; where n takes integer values ​​greater than 0 until it is equal to the total number of pixels in the first time-frequency map, the third global quantum state tensor and the first correlation vector composed of all the first correlations are obtained, and m takes integer values ​​greater than 0 until it is equal to the total number of pixels in the second time-frequency map, the fourth global quantum state tensor and the second correlation vector composed of all the second correlations are obtained; The third global quantum state tensor and the first correlation vector are fused and concatenated to obtain a first concatenated feature vector, and the fourth global quantum state tensor and the second correlation vector are fused and concatenated to obtain a second concatenated feature vector; The first concatenated feature vector is mapped and decoded to obtain the first enhanced feature vector, and the second concatenated feature vector is mapped and decoded to obtain the second enhanced feature vector.

2. The fault identification method for permanent magnet synchronous motors according to claim 1, characterized in that, The step of obtaining the rotation matrix corresponding to each pixel in the first time-frequency image and the rotation matrix corresponding to each pixel in the second time-frequency image includes: Obtain the speed signal of the permanent magnet synchronous motor; Based on the rotation speed signal, determine the rotation speed corresponding to each pixel in the first time-frequency diagram and the rotation speed corresponding to each pixel in the second time-frequency diagram; Based on the vibration signal, determine the signal entropy corresponding to each pixel in the first time-frequency diagram and the signal entropy corresponding to each pixel in the second time-frequency diagram; Based on the energy corresponding to all pixels in the first time-frequency graph, a first maximum energy is determined, and based on the energy corresponding to all pixels in the second time-frequency graph, a second maximum energy is determined. Based on the rotational speed, signal entropy, and energy corresponding to each pixel in the first time-frequency diagram, and the first maximum energy, the rotation angle corresponding to each pixel in the first time-frequency diagram is determined; and based on the rotational speed, signal entropy, and energy corresponding to each pixel in the second time-frequency diagram, and the second maximum energy, the rotation angle corresponding to each pixel in the second time-frequency diagram is determined. Based on the rotation angle corresponding to each pixel in the first time-frequency image, a rotation matrix corresponding to each pixel in the first time-frequency image is constructed; and based on the rotation angle corresponding to each pixel in the second time-frequency image, a rotation matrix corresponding to each pixel in the second time-frequency image is constructed.

3. The fault identification method for permanent magnet synchronous motors according to claim 2, characterized in that, The rotation angle corresponding to each pixel in the first time-frequency graph is determined according to the following formula: ； The rotation angle corresponding to each pixel in the second time-frequency graph is determined according to the following formula; ； in, Let be the rotation angle corresponding to the nth pixel in the first time-frequency graph. Let n be the coordinates of the nth pixel in the first time-frequency graph. For speed coefficient, The rotational speed corresponds to the nth pixel in the first time-frequency graph. The signal entropy coefficient, Let be the signal entropy corresponding to the nth pixel in the first time-frequency graph. Energy coefficient Let be the energy corresponding to the nth pixel in the first time-frequency graph. For the first maximum energy, Let be the rotation angle corresponding to the m-th pixel in the second time-frequency diagram. Let m be the coordinates of the m-th pixel in the second time-frequency graph. Let m be the rotational speed corresponding to the m-th pixel in the second time-frequency diagram. Let be the signal entropy corresponding to the m-th pixel in the second time-frequency diagram. Let m be the energy corresponding to the m-th pixel in the second time-frequency graph. This is the second maximum energy.

4. The fault identification method for permanent magnet synchronous motors according to claim 2, characterized in that, Before constructing the rotation matrix corresponding to each pixel in the first time-frequency image based on the rotation angle corresponding to each pixel in the first time-frequency image, and before constructing the rotation matrix corresponding to each pixel in the second time-frequency image based on the rotation angle corresponding to each pixel in the second time-frequency image, the method further includes: In the first time-frequency diagram and the second time-frequency diagram, if there is a pixel whose rotation angle does not meet the preset rotation angle range, then according to the rotation angle corresponding to the corresponding pixel and the preset rotation angle range, the rotation angle corresponding to the corresponding pixel is clamped to the preset rotation angle range to obtain the clamped rotation angle corresponding to the corresponding pixel. The clamped rotation angle corresponding to the corresponding pixel is then used as the rotation angle corresponding to the corresponding pixel.

5. The fault identification method for permanent magnet synchronous motors according to claim 4, characterized in that, The step of clamping the rotation angle corresponding to the corresponding pixel to the preset rotation angle range based on the rotation angle corresponding to the corresponding pixel and the preset rotation angle range, to obtain the clamped rotation angle corresponding to the corresponding pixel, includes: If the rotation angle corresponding to the corresponding pixel is less than the lower limit of the preset rotation angle range, the lower limit of the preset rotation angle range shall be used as the clamped rotation angle corresponding to the corresponding pixel. If the rotation angle corresponding to a given pixel is less than the upper limit of the preset rotation angle range, the upper limit of the preset rotation angle range shall be used as the clamped rotation angle corresponding to the given pixel.

6. The fault identification method for permanent magnet synchronous motors according to claim 2, characterized in that, Before constructing the rotation matrix corresponding to each pixel in the first time-frequency image based on the rotation angle corresponding to each pixel in the first time-frequency image, and before constructing the rotation matrix corresponding to each pixel in the second time-frequency image based on the rotation angle corresponding to each pixel in the second time-frequency image, the method further includes: In the first time-frequency diagram and the second time-frequency diagram, if there is a pixel whose rotation angle does not meet the preset rotation angle range, then the rotation angle corresponding to the corresponding pixel is transformed to the preset rotation angle range according to the rotation angle corresponding to the corresponding pixel, so as to obtain the transformed rotation angle corresponding to the corresponding pixel. The transformed rotation angle corresponding to the corresponding pixel is used as the rotation angle corresponding to the corresponding pixel again.

7. The fault identification method for permanent magnet synchronous motors according to claim 6, characterized in that, The transformed rotation angle corresponding to the respective pixel can be obtained using the following formula: ； in, This represents the transformed rotation angle corresponding to the respective pixel. This represents the rotation angle corresponding to the respective pixel. The remainder symbol is used. Pi is the mathematical constant of a circle.

8. The fault identification method for permanent magnet synchronous motors according to claim 1, characterized in that, The nth rotated quantum state in the third global quantum state tensor is obtained according to the following formula: ； The m-th rotated quantum state in the fourth global quantum state tensor is obtained according to the following formula: ； in, This refers to the nth rotated quantum state in the third global quantum state tensor. Let n be the coordinates of the nth pixel in the first time-frequency graph. Let be the rotation matrix corresponding to the nth pixel in the first time-frequency graph. This refers to the quantum state corresponding to the nth pixel in the first time-frequency diagram. It is a cosine function. Let be the rotation angle corresponding to the nth pixel in the first time-frequency graph. It is a sine function. This refers to the m-th rotated quantum state in the fourth global quantum state tensor. Let m be the coordinates of the m-th pixel in the second time-frequency graph. Let be the rotation matrix corresponding to the m-th pixel in the second time-frequency diagram. Let m be the quantum state corresponding to the m-th pixel in the second time-frequency diagram. The rotation angle is the angle corresponding to the m-th pixel in the second time-frequency graph.

9. The fault identification method for permanent magnet synchronous motors according to claim 1, characterized in that, The first correlation between the nth rotated quantum state and the remaining rotated quantum states in the third global quantum state tensor is obtained according to the following formula: ； The second correlation between the m-th rotated quantum state and the remaining rotated quantum states in the fourth global quantum state tensor is obtained according to the following formula: ； in, This represents the first correlation between the nth rotated quantum state and the remaining rotated quantum states in the third global quantum state tensor. Let N be the coordinates of the Nth pixel in the first time-frequency graph. The total number of pixels in the first time-frequency graph. Let be the coordinates of the i-th pixel in the first time-frequency graph. Let n be the coordinates of the nth pixel in the first time-frequency graph. For the kernel function of the entanglement operation, The quantum state inner product is the product of the nth rotated quantum state and the ith rotated quantum state in the third global quantum state tensor. It is the dual state of the nth rotated quantum state in the third global quantum state tensor. Let i be the i-th rotated quantum state in the third global quantum state tensor. This refers to the second correlation between the m-th rotated quantum state and the remaining rotated quantum states in the fourth global quantum state tensor. Let M be the coordinates of the Mth pixel in the second time-frequency graph. The total number of pixels in the second time-frequency graph. Let J be the coordinates of the j-th pixel in the second time-frequency graph. Let m be the coordinates of the m-th pixel in the second time-frequency graph. The quantum state inner product is the product of the m-th rotated quantum state and the j-th rotated quantum state in the fourth global quantum state tensor. It is the dual state of the m-th rotated quantum state in the fourth global quantum state tensor. Let j be the j-th rotated quantum state in the fourth global quantum state tensor.

Images