Fault Identification Method and Related Equipment for Permanent Magnet Synchronous Motors Based on Customized Quantum States

Abstract

This invention relates to the field of motor fault identification, and discloses a method and related equipment for permanent magnet synchronous motor fault identification based on customized quantum states. The method includes: mapping and encoding each pixel in the time-frequency diagram according to the rotational speed corresponding to each pixel, thereby obtaining a customized quantum state corresponding to each pixel. This customized quantum state encoding method introduces the rotational speed signal to encode the pixels in the time-frequency diagram, fully utilizing multi-dimensional information during motor operation, effectively enhancing the expression capability of early weak fault characteristics, more accurately capturing the evolution trend of early faults, improving the detection capability of complex nonlinear fault modes, significantly enhancing the detection sensitivity of early weak faults, and achieving more accurate and efficient identification of permanent magnet synchronous motor faults, providing strong support for motor maintenance and operation management.

Description

Technical Field

[0001] This invention relates to the field of motor fault identification, and in particular to a method and related equipment for fault identification of permanent magnet synchronous motors based on customized quantum states. Background Technology

[0002] Permanent magnet synchronous motors, as key power equipment, play a vital role in numerous industrial scenarios. Timely and accurate fault identification is crucial for ensuring production safety and improving production efficiency.

[0003] In the fault identification process of permanent magnet synchronous motors, early fault features are weak and difficult to capture, making it difficult to distinguish the degree of fault. Especially when the degree of early fault does not change significantly, the distinguishability of features characterizing the fault evolution trend is extremely small. Traditional fault prediction models are based on conventional time-frequency feature extraction, which is difficult to detect complex nonlinear fault modes. This results in low sensitivity for detecting early weak faults, which cannot meet the needs of rapid and accurate diagnosis of motor faults in actual production. Summary of the Invention

[0004] Based on this, it is necessary to address the above problems by proposing a fault identification method and related equipment for permanent magnet synchronous motors based on customized quantum states. By introducing speed signals to encode the pixels of the time-frequency diagram using customized quantum states, this method fully utilizes multi-dimensional information during motor operation, effectively enhances the ability to express early weak fault characteristics, more accurately captures the evolution trend of early faults, improves the detection capability of complex nonlinear fault modes, significantly enhances the detection sensitivity of early weak faults, and achieves more accurate and efficient identification of permanent magnet synchronous motor faults, providing strong support for motor maintenance and operation management.

[0005] To achieve the above objectives, the present invention provides, in a first aspect, a method for fault identification of permanent magnet synchronous motors based on customized quantum states, the method comprising:

[0006] Acquire vibration and speed signals 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] 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;

[0009] Based on the rotational speed corresponding to each pixel in the first time-frequency diagram, each pixel in the first time-frequency diagram is mapped and encoded to obtain the customized quantum state corresponding to each pixel in the first time-frequency diagram. Similarly, based on the rotational speed corresponding to each pixel in the second time-frequency diagram, each pixel in the second time-frequency diagram is mapped and encoded to obtain the customized quantum state corresponding to each pixel in the second time-frequency diagram. The horizontal and vertical coordinates of the pixel are time and frequency, respectively.

[0010] Based on the custom quantum states corresponding to all pixels in the first time-frequency graph, a first global custom quantum state tensor is determined, and based on the custom quantum states corresponding to all pixels in the second time-frequency graph, a second global custom quantum state tensor is determined.

[0011] The first globally customized quantum state tensor and the second globally customized quantum state tensor are input into the preset permanent magnet synchronous motor fault prediction model to obtain the fault classification and identification results.

[0012] Optionally, the step of mapping and encoding each pixel in the first time-frequency image according to the rotational speed corresponding to each pixel in the first time-frequency image to obtain a customized quantum state corresponding to each pixel in the first time-frequency image, and mapping and encoding each pixel in the second time-frequency image according to the rotational speed corresponding to each pixel in the second time-frequency image to obtain a customized quantum state corresponding to each pixel in the second time-frequency image, includes:

[0013] Based on the rotational speeds corresponding to all pixels in the first time-frequency graph, a first maximum rotational speed is determined, and based on the rotational speeds corresponding to all pixels in the second time-frequency graph, a second maximum rotational speed is determined.

[0014] Based on the rotational speed corresponding to each pixel in the first time-frequency diagram and the first maximum rotational speed, determine the rotational speed modulation weight corresponding to each pixel in the first time-frequency diagram; and based on the rotational speed corresponding to each pixel in the second time-frequency diagram and the second maximum rotational speed, determine the rotational speed modulation weight corresponding to each pixel in the second time-frequency diagram.

[0015] Based on the rotational speed modulation weight corresponding to each pixel in the first time-frequency diagram, each pixel in the first time-frequency diagram is mapped and encoded to obtain the customized quantum state corresponding to each pixel in the first time-frequency diagram. Similarly, based on the rotational speed modulation weight corresponding to each pixel in the second time-frequency diagram, each pixel in the second time-frequency diagram is mapped and encoded to obtain the customized quantum state corresponding to each pixel in the second time-frequency diagram.

[0016] Optionally, the step of determining the rotational speed modulation weight corresponding to each pixel in the first time-frequency image based on the rotational speed corresponding to each pixel in the first time-frequency image and the first maximum rotational speed, and determining the rotational speed modulation weight corresponding to each pixel in the second time-frequency image based on the rotational speed corresponding to each pixel in the second time-frequency image and the second maximum rotational speed, includes:

[0017] Obtain the frequency corresponding to each pixel in the first time-frequency graph and the frequency corresponding to each pixel in the second time-frequency graph;

[0018] Based on the frequency and rotational speed corresponding to each pixel in the first time-frequency diagram, and the first maximum rotational speed, the rotational speed modulation weight corresponding to each pixel in the first time-frequency diagram is determined; and based on the frequency and rotational speed corresponding to each pixel in the second time-frequency diagram, and the second maximum rotational speed, the rotational speed modulation weight corresponding to each pixel in the second time-frequency diagram is determined.

[0019] Optionally, the rotational speed modulation weight corresponding to each pixel in the first time-frequency graph is determined according to the following formula:

[0020] ;

[0021] The rotational speed modulation weight corresponding to each pixel in the second time-frequency graph is determined according to the following formula:

[0022] ;

[0023] in, The rotational speed modulation weight is the value 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 The frequency corresponding to the nth pixel in the first time-frequency graph. The rotational speed modulation weight is the value 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. This is the second maximum speed. This is the frequency corresponding to the m-th pixel in the second time-frequency diagram.

[0024] Optionally, the step of mapping and encoding each pixel in the first time-frequency image according to the rotational speed modulation weight corresponding to each pixel in the first time-frequency image to obtain a customized quantum state corresponding to each pixel in the first time-frequency image, and mapping and encoding each pixel in the second time-frequency image according to the rotational speed modulation weight corresponding to each pixel in the second time-frequency image to obtain a customized quantum state corresponding to each pixel in the second time-frequency image, includes:

[0025] The amplitude corresponding to each pixel in the first time-frequency graph is normalized to obtain the normalized amplitude corresponding to each pixel in the first time-frequency graph, and the amplitude corresponding to each pixel in the second time-frequency graph is normalized to obtain the normalized amplitude corresponding to each pixel in the second time-frequency graph.

[0026] Based on the rotational speed modulation weight, normalized amplitude, and phase corresponding to each pixel in the first time-frequency diagram, the custom quantum state corresponding to each pixel in the first time-frequency diagram is determined; and based on the rotational speed modulation weight, normalized amplitude, and phase corresponding to each pixel in the second time-frequency diagram, the custom quantum state corresponding to each pixel in the second time-frequency diagram is determined.

[0027] Optionally, the custom quantum state corresponding to each pixel in the first time-frequency graph is determined according to the following formula:

[0028] ;

[0029] The custom quantum state corresponding to each pixel in the second time-frequency graph is determined according to the following formula:

[0030] ;

[0031] in, This refers to the customized 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. The rotational speed modulation weight is the value corresponding to the nth pixel in the first time-frequency graph. The normalized amplitude corresponds to the nth pixel in the first time-frequency graph. It is a natural constant. The imaginary unit, The phase corresponding to the nth pixel in the first time-frequency graph. and Let be the orthogonal basis vectors of the two-dimensional Hilbert space in quantum state encoding. This refers to the customized 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. The rotational speed modulation weight is the value 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 refers to the phase corresponding to the m-th pixel in the second time-frequency diagram.

[0032] Optionally, the first globally customized quantum state tensor is determined according to the following formula:

[0033] ;

[0034] The second globally customized quantum state tensor is determined according to the following formula:

[0035] ;

[0036] 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. 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 refers to the customized quantum state corresponding to the nth pixel in the first time-frequency graph. For the second globally customized 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 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.

[0037] To achieve the above objectives, in a second aspect, the present invention provides a fault identification device for permanent magnet synchronous motors based on customized quantum states, the device comprising:

[0038] The acquisition module is used to acquire the vibration signal and speed signal of the permanent magnet synchronous motor;

[0039] 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;

[0040] The rotation speed determination module is used to 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 rotation speed signal.

[0041] The mapping and encoding module is used to map and encode each pixel in the first time-frequency diagram according to the rotation speed corresponding to each pixel in the first time-frequency diagram to obtain the customized quantum state corresponding to each pixel in the first time-frequency diagram, and to map and encode each pixel in the second time-frequency diagram according to the rotation speed corresponding to each pixel in the second time-frequency diagram to obtain the customized quantum state corresponding to each pixel in the second time-frequency diagram, wherein the horizontal and vertical coordinates of the pixel are time and frequency, respectively.

[0042] The tensor determination module is used to determine a first global custom quantum state tensor based on the custom quantum states corresponding to all pixels in the first time-frequency image, and to determine a second global custom quantum state tensor based on the custom quantum states corresponding to all pixels in the second time-frequency image.

[0043] The model prediction module is used to input the first globally customized quantum state tensor and the second globally customized quantum state tensor into a preset permanent magnet synchronous motor fault prediction model to obtain fault classification and identification results.

[0044] 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 fault identification method for permanent magnet synchronous motors based on customized quantum states as described in any one of the first aspects.

[0045] To achieve the above objectives, the present invention provides a computer device in a fourth aspect, including a memory and a processor, the memory storing a computer program, which, when executed by the processor, causes the processor to perform the fault identification method for permanent magnet synchronous motors based on customized quantum states as described in any one of the first aspects.

[0046] The present invention has the following beneficial effects: The above method acquires the vibration signal and rotational speed 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, based on the rotational speed signal, it determines the rotational speed corresponding to each pixel in the first time-frequency diagram and the rotational speed corresponding to each pixel in the second time-frequency diagram. Based on the rotational speed corresponding to each pixel in the first time-frequency diagram, it performs mapping encoding on each pixel in the first time-frequency diagram to obtain a customized quantum state corresponding to each pixel in the first time-frequency diagram. Similarly, based on the rotational speed corresponding to each pixel in the second time-frequency diagram, it performs mapping encoding on each pixel in the second time-frequency diagram to obtain a customized quantum state corresponding to each pixel in the second time-frequency diagram. The horizontal and vertical coordinates of the pixels are time and frequency, respectively. Then, based on the rotational speed corresponding to each pixel in the first time-frequency diagram... The first global customized quantum state tensor is determined by identifying the customized quantum states corresponding to all pixels in the second time-frequency graph. The second global customized quantum state tensor is then determined based on the customized quantum states corresponding to all pixels in the second time-frequency graph. Finally, the first and second global customized quantum state tensors are input into a preset permanent magnet synchronous motor fault prediction model to obtain fault classification and identification results. In other words, this customized quantum state encoding method introduces speed signals to encode the pixels in the time-frequency graph, fully utilizing multi-dimensional information during motor operation. This effectively enhances the expression of early, weak fault characteristics, more accurately captures the evolution trend of early faults, improves the detection capability for complex nonlinear fault modes, significantly enhances the detection sensitivity of early, weak faults, and achieves more accurate and efficient identification of permanent magnet synchronous motor faults, providing strong support for motor maintenance and operation management. Attached Figure Description

[0047] 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.

[0048] in:

[0049] Figure 1 This is a schematic diagram of the fault identification method for permanent magnet synchronous motors based on customized quantum states in an embodiment of this application;

[0050] Figure 2 This is a schematic diagram of a permanent magnet synchronous motor fault identification device based on a customized quantum state in an embodiment of this application.

[0051] Figure 3 This is a diagram showing the internal structure of a computer device in some embodiments. Detailed Implementation

[0052] 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.

[0053] Permanent magnet synchronous motors, as key power equipment, play a vital role in numerous industrial scenarios. Timely and accurate fault identification is crucial for ensuring production safety and improving production efficiency.

[0054] In the fault identification process of permanent magnet synchronous motors, early fault features are weak and difficult to capture, making it difficult to distinguish the degree of fault. Especially when the degree of early fault does not change significantly, the distinguishability of features characterizing the fault evolution trend is extremely small. Traditional fault prediction models are based on conventional time-frequency feature extraction, which is difficult to detect complex nonlinear fault modes. This results in low sensitivity for detecting early weak faults, which cannot meet the needs of rapid and accurate diagnosis of motor faults in actual production.

[0055] To address the aforementioned issues, this application proposes a fault identification method and related equipment for permanent magnet synchronous motors based on customized quantum states. By introducing speed signals to encode the pixels of the time-frequency diagram using customized quantum states, this method fully utilizes multi-dimensional information during motor operation, effectively enhancing the expressive ability of early weak fault features. It can more accurately capture the evolution trend of early faults, improve the detection capability for complex nonlinear fault modes, and significantly enhance the detection sensitivity of early weak faults. This enables more accurate and efficient identification of permanent magnet synchronous motor faults, providing strong support for motor maintenance and operation management. The specific implementation principle will be described in detail in the following embodiments.

[0056] In its first aspect, this application provides a method for fault identification of permanent magnet synchronous motors based on customized quantum states.

[0057] Please see Figure 1 This is a schematic diagram of a fault identification method for permanent magnet synchronous motors based on customized quantum states in an embodiment of this application. The method includes:

[0058] Step 110: Obtain the vibration signal and speed signal of the permanent magnet synchronous motor.

[0059] Regarding the acquisition methods of vibration signals and speed signals, in some embodiments, vibration signals of the permanent magnet synchronous motor can be acquired through vibration sensors, and speed signals of the permanent magnet synchronous motor can be acquired through Hall sensors.

[0060] Furthermore, in some embodiments, the number of vibration sensors can be multiple, and the multiple vibration sensors can correspondingly acquire multiple vibration signals.

[0061] 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.

[0062] 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.

[0063] Step 130: Based on the rotational speed signal, determine the rotational speed corresponding to each pixel in the first time-frequency graph and the rotational speed corresponding to each pixel in the second time-frequency graph.

[0064] 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.

[0065] Step 140: Based on the rotational speed corresponding to each pixel in the first time-frequency diagram, perform mapping encoding on each pixel in the first time-frequency diagram to obtain the customized quantum state corresponding to each pixel in the first time-frequency diagram. Similarly, based on the rotational speed corresponding to each pixel in the second time-frequency diagram, perform mapping encoding on each pixel in the second time-frequency diagram to obtain the customized quantum state corresponding to each pixel in the second time-frequency diagram. The horizontal and vertical coordinates of the pixel are time and frequency, respectively.

[0066] It should 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.

[0067] In this application, by using this customized quantum state mapping encoding, a speed-related quantum state is customized for each pixel in the time-frequency graph. This fully considers the influence of speed on fault characteristics, enabling more accurate extraction and characterization of early weak fault characteristics related to speed. This effectively improves the fault prediction model's ability to detect complex nonlinear fault modes, significantly enhances 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.

[0068] It should be noted that the mapping encoding in the above-described embodiment uses a custom quantum state mapping encoding. In other embodiments, quantum state mapping encoding may also be used, that is:

[0069] In other embodiments, each pixel in the first time-frequency image can be directly mapped and encoded to obtain the quantum state corresponding to each pixel in the first time-frequency image, and each pixel in the second time-frequency image can be directly mapped and encoded to obtain the quantum state corresponding to each pixel in the second time-frequency image. Then, the quantum states corresponding to all pixels in the first time-frequency image are used as the custom quantum states corresponding to all pixels in the first time-frequency image, and the quantum states corresponding to all pixels in the second time-frequency image are used as the custom quantum states corresponding to all pixels in the second time-frequency image; wherein the horizontal and vertical coordinates of the pixel are time and frequency, respectively.

[0070] It should be noted that, since this application uses quantum state mapping encoding, the quantum states corresponding to all pixels in the first time-frequency image are taken as the custom quantum states corresponding to all pixels in the first time-frequency image, and the quantum states corresponding to all pixels in the second time-frequency image are taken as the custom quantum states corresponding to all pixels in the second time-frequency image, the custom quantum states corresponding to all pixels in the first time-frequency image and the custom quantum states corresponding to all pixels in the second time-frequency image can be obtained by mapping encoding of custom quantum states or obtained directly from quantum states. In the following description of embodiments, if the processing methods of the custom quantum states corresponding to all pixels in the first time-frequency image and the custom quantum states corresponding to all pixels in the second time-frequency image obtained by mapping encoding of custom quantum states are different from those obtained by mapping encoding of quantum states, different embodiments can be used for special description under the condition of obtaining them by mapping encoding of quantum states or mapping encoding of custom quantum states. Of course, if the processing methods are the same, no special description will be given to avoid redundancy.

[0071] In this application, by mapping and encoding quantum states, pixels in the time-frequency diagram are mapped to quantum states. 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.

[0072] Step 150: Determine the first global custom quantum state tensor based on the custom quantum states corresponding to all pixels in the first time-frequency graph, and determine the second global custom quantum state tensor based on the custom quantum states corresponding to all pixels in the second time-frequency graph.

[0073] Regarding the determination of the first and second global custom quantum state tensors, in some embodiments, the custom 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 custom quantum state tensor, and the custom quantum states corresponding to all pixels in the second time-frequency image can be tensor-producted sequentially to obtain the second global custom quantum state tensor.

[0074] Step 160: Input the first global customized quantum state tensor and the second global customized quantum state tensor into the preset permanent magnet synchronous motor fault prediction model to obtain the fault classification and identification results.

[0075] 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 globally customized quantum state tensor and second globally customized quantum state tensor.

[0076] 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.

[0077] 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 customized quantum state tensor and the second customized 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.

[0078] Regarding the determination of the first and second enhanced feature vectors, in some embodiments, 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 can be obtained. Using the rotation matrix corresponding to the nth pixel in the first time-frequency image, the nth customized quantum state in the first global customized quantum state tensor is rotated to obtain the nth rotated customized quantum state in the third global customized quantum state tensor. Similarly, using the rotation matrix corresponding to the mth pixel in the second time-frequency image, the mth customized quantum state in the second global customized quantum state tensor is rotated to obtain the mth rotated customized quantum state in the fourth global customized quantum state tensor. A convolution operation is used to simulate entanglement, performing a cross-time and frequency entanglement operation on the nth rotated customized quantum state in the third global customized quantum state tensor and the remaining rotated customized quantum states to obtain the first correlation between the nth rotated customized quantum state in the third global customized quantum state tensor and the remaining rotated customized quantum states, and the first correlation between the nth rotated customized quantum state in the third global customized quantum state tensor and the remaining rotated customized quantum states. The m-th rotated custom quantum state in the custom quantum state tensor is entangled with the remaining rotated custom quantum states across time and frequency to obtain the second correlation between the m-th rotated custom quantum state in the fourth global custom quantum state tensor and the remaining rotated custom quantum states. Here, n takes successively greater than 0 integer values ​​until it equals the total number of pixels in the first time-frequency map, resulting in the third global custom quantum state tensor and the first correlation vector composed of all first correlations. Similarly, m takes successively greater than 0 integer values ​​until it equals the total number of pixels in the second time-frequency map, resulting in the fourth global custom quantum state tensor and the second correlation vector composed of all second correlations. The third global custom quantum state tensor and the first correlation vector are fused and concatenated to obtain the first concatenated feature vector. The fourth global custom 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.

[0079] 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.

[0080] Furthermore, regarding the determination method of the concatenated feature vector, in some embodiments, a fusion concatenation method can be used to fuse and concatenate the customized quantum states in the global customized 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 customized quantum states in the global customized 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; wherein, the value range of the learnable weights is [0, 1], the weight of the customized quantum states in the global customized quantum state tensor is the learnable weight, and the correlation in the correlation vector is the difference between 1 and the learnable weight.

[0081] In this application, the ability to express fault features is significantly enhanced by customizing 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.

[0082] Furthermore, regarding the construction method of the rotation matrix, in some embodiments, the rotation speed signal of the permanent magnet synchronous motor can be obtained. Based on the rotation speed signal, 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 can be determined. Then, based on the rotation speed corresponding to each pixel in the first time-frequency image, the rotation angle corresponding to each pixel in the first time-frequency image can be determined. Similarly, based on the rotation speed corresponding to each pixel in the second time-frequency image, the rotation angle corresponding to each pixel in the second time-frequency image can be determined. Finally, based on the rotation angle corresponding to each pixel in the first time-frequency image, the rotation matrix corresponding to each pixel in the first time-frequency image can be constructed, and based on the rotation angle corresponding to each pixel in the second time-frequency image, the rotation matrix corresponding to each pixel in the second time-frequency image can be constructed.

[0083] 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.

[0084] It should be noted that the embodiment here uses a method for determining the rotation matrix under the condition of mapping encoding of customized quantum states. If a method for determining the rotation matrix under the condition of mapping encoding of quantum states is used, the following embodiment will be adopted, namely:

[0085] 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 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 a first maximum energy based on the energy corresponding to all pixels in the first time-frequency image and a second maximum energy based on the energy corresponding to all pixels in the second time-frequency image; determining the rotation angle corresponding to each pixel in the first time-frequency image based on the rotational speed, signal entropy, energy, and first maximum energy; determining the rotation angle corresponding to each pixel in the second time-frequency image based on the rotational speed, signal entropy, energy, and second maximum energy; constructing a 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 constructing a 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.

[0086] Furthermore, regarding the type of signal entropy, 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 the signal entropy.

[0087] It should be noted that, since the horizontal and vertical axes of the pixels in the time-frequency graph represent 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 point can be determined based on the vibration signal, and matched with the time corresponding to the pixel in the time-frequency graph to determine the signal entropy corresponding to each pixel in the time-frequency graph; wherein, the signal entropy corresponding to each time point can be the signal entropy for each instant or the signal entropy for each time window.

[0088] In this application, 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.

[0089] Regarding the method for determining the rotation angle, in some embodiments, the rotation angle corresponding to each pixel in the first time-frequency image can be determined according to the following formula:

[0090] ;

[0091] The rotation angle corresponding to each pixel in the second time-frequency graph is determined using the following formula:

[0092] ;

[0093] 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. To customize the speed coefficient, The rotational speed corresponds to the nth pixel in the first time-frequency graph. 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. This represents the rotational speed corresponding to the m-th pixel in the second time-frequency graph.

[0094] 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.

[0095] 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.

[0096] It should be noted that the embodiment here uses a method for determining the rotation angle under the condition of a customized quantum state mapping encoding. If a method for determining the rotation angle under the condition of a quantum state mapping encoding is used, the following embodiment will be adopted, namely:

[0097] 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:

[0098] ;

[0099] The rotation angle corresponding to each pixel in the second time-frequency graph is determined according to the following formula;

[0100] ;

[0101] 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 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.

[0102] 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.

[0103] In this application, 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.

[0104] Before constructing the rotation matrix, in some embodiments, the method further includes: in the first time-frequency image and the second time-frequency image, 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, clamp the rotation angle corresponding to the corresponding pixel to the preset rotation angle range to obtain the clamped rotation angle corresponding to the corresponding pixel; and use the clamped rotation angle corresponding to the corresponding pixel as the rotation angle corresponding to the corresponding pixel again.

[0105] 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.

[0106] Furthermore, 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].

[0107] In this application, a rotation angle clamping mechanism is used to ensure the stability of the rotation matrix construction, avoid the interference of extreme angle values ​​on the rotation operation of the customized quantum state, and improve the convergence of model training and the reliability of fault feature enhancement.

[0108] Furthermore, regarding the method for determining the rotation angle after clamping, in some embodiments, 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 can be used as the rotation angle after clamping 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 can be used as the rotation angle after clamping corresponding to the corresponding pixel.

[0109] In this application, 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.

[0110] Before constructing the rotation matrix, in some other embodiments, the method further includes: in the first time-frequency image and the second time-frequency image, 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, the rotation angle corresponding to the corresponding pixel is transformed to the preset rotation angle range to obtain the transformed rotation angle corresponding to the corresponding pixel; and the transformed rotation angle corresponding to the corresponding pixel is used again as the rotation angle corresponding to the corresponding pixel.

[0111] In this application, the stability of the rotation matrix construction is ensured by the rotation angle transformation mechanism, avoiding the interference of extreme angle values ​​on the rotation operation of the customized quantum state, while improving the convergence of model training and the reliability of fault feature enhancement.

[0112] Furthermore, regarding the method for determining the transformed rotation angle, in some embodiments, the transformed rotation angle corresponding to the corresponding pixel can be obtained according to the following formula:

[0113] ;

[0114] 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.

[0115] In this application, the formula transforms extreme rotation angles to the standard range by taking the remainder, effectively eliminating the interference of abnormal angle values ​​on the customized quantum state rotation operation, and significantly improving the stability of model training and the reliability of feature enhancement.

[0116] Regarding the determination of the rotated custom quantum state, in some embodiments, the nth rotated custom quantum state in the third global custom quantum state tensor can be obtained according to the following formula:

[0117] ;

[0118] The m-th rotated custom quantum state in the fourth global custom quantum state tensor is obtained using the following formula:

[0119] ;

[0120] in, For the nth rotated custom quantum state in the third global custom 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 custom quantum state corresponding to the nth pixel in the first time-frequency graph. 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. For the m-th rotated custom quantum state in the fourth global custom 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. This represents the custom 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.

[0121] In this application, a customized quantum state rotation formula is used to achieve dynamic enhancement and phase calibration of fault characteristics, which significantly improves the detection sensitivity and feature discrimination of early weak faults.

[0122] Regarding the determination of correlation, in some embodiments, the first correlation between the nth rotated custom quantum state and the remaining rotated custom quantum states in the third global custom quantum state tensor can be obtained according to the following formula:

[0123] ;

[0124] The second correlation between the m-th rotated custom quantum state and the remaining rotated custom quantum states in the fourth global custom quantum state tensor is obtained according to the following formula:

[0125] ;

[0126] in, The first correlation between the nth rotated custom quantum state and the remaining rotated custom quantum states in the third global custom 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, For the inner product of the custom quantum states after the nth rotation and the ith rotation in the third global custom quantum state tensor, The dual state of the nth rotated custom quantum state in the third global custom quantum state tensor. For the i-th rotated custom quantum state in the third global custom quantum state tensor, The second correlation between the m-th rotated custom quantum state and the remaining rotated custom quantum states in the fourth global custom 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 the inner product of the custom quantum states be the custom quantum states after the m-th rotation and the j-th rotation in the fourth global custom quantum state tensor. The dual state of the m-th rotated custom quantum state in the fourth global custom quantum state tensor. The j-th rotated custom quantum state in the fourth global custom quantum state tensor.

[0127] In this application, by introducing the entanglement operation of kernel function and custom quantum state inner product, high-order correlation modeling across time and frequency dimensions is realized, which significantly improves the feature extraction capability and classification accuracy of complex nonlinear fault modes.

[0128] 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:

[0129] 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.

[0130] 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, 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.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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:

[0137] ;

[0138] 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. The fusion weight is the weight corresponding to each pixel in the second time-frequency graph.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] Furthermore, in some embodiments, the dual-stream fusion feature vector can be obtained according to the following formula:

[0145] ;

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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 consists of the first globally customized quantum state tensor and the second globally customized 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 plot and the second time-frequency plot, that is:

[0153] 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.

[0154] 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.

[0155] In this embodiment, by introducing a customized quantum state encoding method, the rotational speed signal is used to perform customized quantum state encoding on the pixels of the time-frequency map. This fully utilizes the multi-dimensional information during motor operation, effectively enhances the ability to express early weak fault characteristics, more accurately captures the evolution trend of early faults, improves the detection capability of complex nonlinear fault modes, significantly enhances the detection sensitivity of early weak faults, and achieves more accurate and efficient identification of permanent magnet synchronous motor faults, providing strong support for motor maintenance and operation management.

[0156] In addition to the effects mentioned above, the permanent magnet synchronous motor fault identification method and related equipment based on customized quantum states also have the following beneficial effects: Multi-dimensional information fusion innovation: Traditional methods may only be based on single or limited-dimensional signal features for fault identification. However, this application introduces speed signals to perform customized quantum state encoding on the pixels of the time-frequency map, deeply fusing multi-dimensional information such as motor vibration signals and speed signals. This fusion method breaks through the limitations of traditional methods, can characterize the motor's operating state from multiple angles, and provides a richer information source for fault feature extraction, thus reflecting the motor's fault situation more comprehensively and accurately; Quantum state characteristics for fault feature mining: Utilizing the unique properties of quantum states for mapping encoding, quantum states have characteristics such as rotational superposition and entanglement. These characteristics enable the mining of potential information that is difficult to discover using traditional methods when processing fault features. By mapping the pixels in the time-frequency map to quantum states, the weak features of early-stage faults in permanent magnet synchronous motors can be extracted and characterized more effectively. Especially for those subtle changes that are easily ignored in traditional feature extraction methods, quantum state encoding can better capture and amplify these features, improving the distinguishability of fault features; Dynamic feature enhancement: In In constructing the rotation matrix and correlation, multiple factors such as rotational speed, signal entropy, and energy are fully considered. The rotation matrix is ​​constructed by dynamically calculating the rotation angle based on the rotational speed, and the correlation is calculated by introducing the kernel function and the inner product of the customized quantum state. This achieves dynamic enhancement of fault features. This dynamic enhancement method can adjust the feature extraction parameters in real time according to the actual operating state of the motor, so that fault features can be accurately captured under different operating conditions, improving the adaptability and robustness of the fault identification method to complex operating conditions. The modular design facilitates optimization and expansion: The pre-set permanent magnet synchronous motor fault prediction model adopts 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 optimized and improved independently. For example, the rotation and entanglement operations in the quantum heuristic neural network module can be optimized according to actual needs, or the kernel size and number of layers in the two-stream convolutional neural network module can be adjusted without affecting the normal operation of other modules. At the same time, the modular design also facilitates the expansion of the model. When new feature extraction methods or classification algorithms appear, they can be easily integrated into the existing model to improve the overall performance of the model.To avoid overfitting and improve generalization ability: Batch normalization layers and Dropout layers are incorporated into the convolutional neural network units. Batch normalization layers normalize each batch of data, making the neural network more stable during training, accelerating convergence, and helping to prevent overfitting. Dropout layers randomly discard a portion of neurons during training, reducing co-adaptation between neurons and further enhancing the model's generalization ability. The introduction of these structures allows the model to maintain good performance when facing different datasets and real-world conditions, improving the accuracy and reliability of fault identification. SVM classifier improves classification accuracy: An SVM classifier is used to replace the dual-stream convolutional neural network module. The softmax classifier and SVM classifier, based on the principle of structural risk minimization, can find an optimal hyperplane to separate data of different categories, exhibiting good generalization ability and classification performance. Especially when dealing with small sample data and complex nonlinear classification problems, the SVM classifier shows significant advantages. In this application, through collaborative work with a quantum heuristic neural network module and a two-stream convolutional neural network module, the SVM classifier can more accurately classify faults, improving the accuracy of fault identification. Real-time performance and reliability are ensured for motor operation: this method can better adapt to the real-time characteristics of non-stationary signals in permanent magnet synchronous motors, quickly and accurately capturing early fault characteristics and providing timely fault information. The fault classification and identification results provide strong support for motor maintenance and operation management. In actual production, timely detection and handling of motor faults are crucial for ensuring production safety and improving production efficiency. The high real-time performance and reliability of this method ensure that early warnings are issued in the early stages of a fault, giving maintenance personnel sufficient time to take measures to prevent further deterioration of the fault, reduce downtime and production losses, and lower maintenance costs. Traditional motor fault identification methods may fail to detect early faults in a timely manner due to low detection sensitivity, leading to the fault developing into a serious stage before being discovered. At this point, not only is repair difficult and costly, but it may also cause irreversible damage to the motor. The method proposed in this application can significantly improve the early detection of minor faults. The high sensitivity of fault detection enables early warning and accurate diagnosis of faults. Timely detection and handling of early faults can prevent their escalation and deterioration, reduce maintenance costs, extend motor lifespan, and save companies significant maintenance expenses. It also provides a basis for optimized motor design: analysis and identification of large amounts of motor fault data can provide in-depth understanding of motor fault modes and characteristics under different operating conditions, offering valuable insights for optimized motor design. For example, fault identification results can reveal a higher failure rate at certain speeds or loads, allowing for reinforcement or improvement of these components during the motor design phase, enhancing overall motor performance and reliability, and further promoting the development and application of permanent magnet synchronous motor technology.

[0157] In one feasible implementation, step 140 in the above embodiment, which maps and encodes each pixel in the first time-frequency image according to the rotational speed corresponding to each pixel in the first time-frequency image to obtain a customized quantum state corresponding to each pixel in the first time-frequency image, and maps and encodes each pixel in the second time-frequency image according to the rotational speed corresponding to each pixel in the second time-frequency image to obtain a customized quantum state corresponding to each pixel in the second time-frequency image, includes: determining a first maximum rotational speed according to the rotational speed corresponding to all pixels in the first time-frequency image, and determining a second maximum rotational speed according to the rotational speed corresponding to all pixels in the second time-frequency image; and determining a first maximum rotational speed according to the rotational speed corresponding to all pixels in the second time-frequency image. Based on the corresponding rotational speed and the first maximum rotational speed, determine the rotational speed modulation weight corresponding to each pixel in the first time-frequency image; based on the rotational speed corresponding to each pixel in the second time-frequency image and the second maximum rotational speed, determine the rotational speed modulation weight corresponding to each pixel in the second time-frequency image; based on the rotational speed modulation weight corresponding to each pixel in the first time-frequency image, perform mapping encoding on each pixel in the first time-frequency image to obtain the customized quantum state corresponding to each pixel in the first time-frequency image; and based on the rotational speed modulation weight corresponding to each pixel in the second time-frequency image, perform mapping encoding on each pixel in the second time-frequency image to obtain the customized quantum state corresponding to each pixel in the second time-frequency image.

[0158] Regarding the method for determining the rotational speed adjustment weight, 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.

[0159] It should be noted that the embodiment here uses a method for determining the custom quantum state under the condition of mapping encoding of the custom quantum state. If the method for determining the quantum state under the condition of mapping encoding of the quantum state is used, this embodiment can be omitted.

[0160] In the embodiments of this application, the extraction accuracy of early weak fault features and the ability to distinguish fault modes are significantly improved by optimizing the quantum state encoding through rotational speed modulation weight.

[0161] Understandably, the dynamic weight allocation mechanism calculates the quotient of each pixel's rotational speed and the maximum rotational speed as the modulation weight, quantizing the rotational speed information into continuous weight parameters in the [0, 1] interval. This process preserves the dynamic variation characteristics of the rotational speed while avoiding coding imbalance caused by differences in absolute rotational speed values, allowing fault features in different rotational speed regions of the time-frequency graph to be encoded differently according to their contribution to fault evolution. The fault feature enhancement mechanism assigns higher weights to pixels in high-rotational-speed regions during the mapping and encoding process, and their corresponding customized quantum states carry stronger fault feature expressions. This weight allocation strategy effectively amplifies fault features strongly correlated with rotational speed while suppressing background noise interference in low-rotational-speed regions. Disturbances are particularly well-suited for early fault detection under fluctuating speed conditions; Nonlinear fault mode decoupling: By introducing speed modulation weights, fault features under different speed conditions are given unique quantum state encoding modes, enabling complex nonlinear fault modes that are difficult to distinguish using traditional methods to form separable feature clusters in the quantum state tensor, significantly improving the discrimination ability of the fault classifier; Encoding robustness is improved: Weight calculation uses relative speed ratios rather than absolute speed values, making the encoding method more adaptable to changes in motor operating conditions. Even if the maximum speed fluctuates under different load conditions, the weight allocation mechanism can still maintain the relative stability of fault feature encoding, avoiding misdiagnosis and missed diagnosis caused by changes in operating conditions.

[0162] In one feasible implementation, the process in the above embodiments of determining the rotational speed modulation weight corresponding to each pixel in the first time-frequency image based on the rotational speed corresponding to each pixel in the first time-frequency image and the first maximum rotational speed, and determining the rotational speed modulation weight corresponding to each pixel in the second time-frequency image based on the rotational speed corresponding to each pixel in the second time-frequency image and the second maximum rotational speed, includes: obtaining 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; determining the rotational speed modulation weight corresponding to each pixel in the first time-frequency image based on the frequency and rotational speed corresponding to each pixel in the first time-frequency image and the first maximum rotational speed; and determining the rotational speed modulation weight corresponding to each pixel in the second time-frequency image based on the frequency and rotational speed corresponding to each pixel in the second time-frequency image and the second maximum rotational speed.

[0163] It should be noted that the embodiment here uses a method for determining the custom quantum state under the condition of mapping encoding of the custom quantum state. If the method for determining the quantum state under the condition of mapping encoding of the quantum state is used, this embodiment can be omitted.

[0164] In this embodiment, 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.

[0165] Understandably, the multi-physical quantity collaborative coding mechanism modulates the frequency information of each pixel in the time-frequency graph together with the speed parameter. This coding method breaks through the linear correlation limitation of a single speed or frequency, and can more comprehensively reflect the intrinsic relationship between the motor's operating state and fault characteristics. Dynamic weight allocation optimization involves introducing frequency parameters to perform secondary correction on the speed modulation weights, ensuring that the weight calculation considers both the dynamic changes in speed and the fault sensitivity of the frequency. For example, in rotor bar breakage faults, specific frequency components will exhibit nonlinear changes with speed fluctuations. This mechanism can effectively capture this coupling characteristic, improving the fault directionality of the coding. Enhanced anti-interference capability. The introduction of frequency information establishes a dual screening mechanism, which can distinguish background noise under different operating conditions by speed differences, and filter vibration components unrelated to faults by using frequency features; decoupling of complex fault modes: for multi-fault coupled scenarios (such as bearing wear and air gap eccentricity at the same time), traditional methods have difficulty separating overlapping features. This mechanism, through joint modulation of frequency and speed, enables different fault types to form separable feature clusters in quantum state space, improving fault classification accuracy compared to single speed coding; improved adaptability to operating conditions: the weight calculation adopts the relative relationship of frequency and speed rather than absolute values, making the coding method more adaptable to changes in motor operating conditions.

[0166] In one feasible implementation, the rotational speed modulation weight corresponding to each pixel in the first time-frequency graph is determined according to the following formula:

[0167] ;

[0168] The rotational speed modulation weight corresponding to each pixel in the second time-frequency graph is determined according to the following formula:

[0169] ;

[0170] 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.

[0171] 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.

[0172] It should be noted that the embodiment here uses a method for determining the custom quantum state under the condition of mapping encoding of the custom quantum state. If the method for determining the quantum state under the condition of mapping encoding of the quantum state is used, this embodiment can be omitted.

[0173] In this embodiment, by introducing a sine function to construct a frequency-speed joint modulation weighting formula, the ability of customized quantum state coding to resolve complex fault characteristics and its diagnostic robustness are significantly improved.

[0174] Understandably, the nonlinear feature enhancement mechanism transforms the linear relationship between frequency and speed into a periodic modulation signal, capturing the nonlinear characteristics of frequency components fluctuating with speed in faults such as rotor bar breakage, resulting in a clearer periodic distribution pattern of fault features in quantum state space. Multi-physical quantity coupling encoding, through dual modulation of frequency and speed, more accurately characterizes the multi-physical field coupling fault features in motor vibration signals compared to traditional linear weighting methods, improving the ability to separate complex faults. Dynamic weight adaptive adjustment, due to the periodicity of the sine function, makes the weight allocation condition-adaptive; when changes in motor load cause speed fluctuations... When the weight value can be automatically adjusted within the range of [0, 1], the relative stability of the fault feature encoding is maintained, avoiding misdiagnosis caused by sudden changes in operating conditions; Anti-noise interference optimization: The introduction of frequency parameters constructs a dual filtering mechanism, the speed component suppresses operating condition noise, the frequency component filters the background noise of mechanical vibration, and the periodic attenuation of noise energy is achieved through sinusoidal modulation, which significantly improves the signal-to-noise ratio; Fault mode decoupling capability: In the coupled scenario of air gap eccentricity and bearing fault, this encoding method can enable different fault types to form orthogonal feature clusters in quantum state space, and achieve spatial separation of fault features through nonlinear mapping of weight formula, which significantly improves the classification accuracy compared with traditional methods.

[0175] In one feasible implementation, the process described in the above embodiments of mapping and encoding each pixel in the first time-frequency image according to the rotational speed modulation weight corresponding to each pixel in the first time-frequency image to obtain a customized quantum state corresponding to each pixel in the first time-frequency image, and mapping and encoding each pixel in the second time-frequency image according to the rotational speed modulation weight corresponding to each pixel in the second time-frequency image to obtain a customized quantum state corresponding to each pixel in the second time-frequency image, includes: normalizing the amplitude corresponding to each pixel in the first time-frequency image to obtain a normalized amplitude corresponding to each pixel in the first time-frequency image, and normalizing the amplitude corresponding to each pixel in the second time-frequency image to obtain a normalized amplitude corresponding to each pixel in the second time-frequency image; determining the customized quantum state corresponding to each pixel in the first time-frequency image based on the rotational speed modulation weight, normalized amplitude, and phase corresponding to each pixel in the first time-frequency image, and determining the customized quantum state corresponding to each pixel in the second time-frequency image based on the rotational speed modulation weight, normalized amplitude, and phase corresponding to each pixel in the second time-frequency image.

[0176] It should be noted that the embodiment here uses a method for determining the custom quantum state under the condition of mapping encoding of the custom quantum state. If a method for determining the quantum state under the condition of mapping encoding of the quantum state is used, the following embodiment will be adopted, namely:

[0177] In other embodiments, the amplitude corresponding to each pixel in the first time-frequency image may 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 may 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 may be 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 may be determined.

[0178] 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.

[0179] In the embodiments of this application, the fault characteristic characterization capability and coding robustness of the customized quantum state are significantly improved by using rotation speed modulation weighting, amplitude normalization and phase fusion coding.

[0180] Understandably, feature standardization enhances comparability: normalizing the amplitude of pixels in the time-frequency graph unifies the amplitude of vibration signals of different magnitudes to the [0, 1] interval, effectively eliminating the problem of inconsistent feature scales caused by differences in sensor range or signal attenuation, making fault features under different operating conditions directly comparable, and providing a standardized input basis for subsequent quantum state coding; multi-physical quantity collaborative coding mechanism: jointly mapping the three parameters of rotational speed modulation weight, normalized amplitude, and phase, breaking through the limitations of single-parameter coding, where the rotational speed weight reflects the influence of dynamic operating conditions, the normalized amplitude characterizes the fault energy intensity, and the phase information retains the vibration time sequence characteristics. The fusion of the three enables the quantum state to comprehensively characterize the multi-dimensional fault. Features: Significantly improved anti-interference capability: Normalization suppresses noise interference caused by absolute amplitude fluctuations. Especially under variable load conditions, amplitude standardization can effectively filter background vibration energy changes caused by load variations. At the same time, the introduction of phase information constructs a time-series feature barrier, which can distinguish the phase difference between fault vibration and normal mechanical vibration. Fault mode decoupling optimization: In complex fault scenarios, multi-parameter encoding enables the features of different fault types to form separable feature clusters in quantum state space. The classification accuracy of complex faults is significantly improved compared with single-parameter encoding, which is significantly better than traditional time-frequency analysis methods. Enhanced adaptability to operating conditions: Through normalization and relative weight calculation, the encoding method is more adaptable to changes in motor operating conditions.

[0181] In one feasible implementation, the custom quantum state corresponding to each pixel in the first time-frequency graph is determined according to the following formula:

[0182] ;

[0183] The custom quantum state corresponding to each pixel in the second time-frequency graph is determined according to the following formula:

[0184] ;

[0185] 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.

[0186] It should be noted that the embodiment here uses a method for determining the custom quantum state under the condition of mapping encoding of the custom quantum state. If a method for determining the quantum state under the condition of mapping encoding of the quantum state is used, the following embodiment will be adopted, namely:

[0187] In other embodiments, the quantum state corresponding to each pixel in the first time-frequency graph can also be determined according to the following formula:

[0188] ;

[0189] The quantum state corresponding to each pixel in the second time-frequency graph is determined using the following formula:

[0190] ;

[0191] in, This represents the quantum state corresponding to the nth pixel in the first time-frequency diagram. This represents the quantum state corresponding to the m-th pixel in the second time-frequency diagram.

[0192] In the embodiments of this application, the quantum state encoding formula, which combines normalized amplitude and phase parameters, significantly improves the quantum characterization capability and pattern recognition accuracy of fault features.

[0193] In this embodiment, the 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.

[0194] Understandably, the multi-physical quantity collaborative coding mechanism: the formula jointly maps the three parameters of speed modulation weight, normalized amplitude, and phase, breaking through the limitations of single-parameter coding. Among them, the speed weight reflects the influence of dynamic working conditions, the normalized amplitude characterizes the fault energy intensity, and the phase information retains the vibration timing characteristics. The fusion of the three enables the quantum state to comprehensively characterize the multi-dimensional features of the fault. Nonlinear feature enhancement capability: by introducing complex field coding with natural constant and imaginary unit, the traditional time-frequency features are converted into quantum states with phase rotation characteristics. This coding method can capture the nonlinear features of frequency components fluctuating with speed in faults such as rotor bar breakage, so that the fault features present a clearer periodic distribution pattern in the quantum state space.

[0195] In one feasible implementation, the first globally customized quantum state tensor is determined according to the following formula:

[0196] ;

[0197] The second globally customized quantum state tensor is determined according to the following formula:

[0198] ;

[0199] 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.

[0200] 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.

[0201] Understandably, the high-order feature fusion mechanism—tensor product operation—integrates scattered pixel-level quantum states into a global tensor structure, effectively capturing the nonlinear correlation characteristics of fault features in the spatiotemporal dimension. Compared with traditional vector concatenation, this structure can retain more interaction information between original features, thus improving the accuracy of fault pattern recognition. Multi-scale feature preservation capability: The formula constructs multi-scale feature representations while maintaining the original time-frequency resolution through the cumulative operation of pixel-by-pixel quantum states, improving the frequency resolution of bearing fault feature extraction compared to traditional methods. Quantum state space orthogonality guarantee: This is achieved by strictly adhering to the tensor product... The linear algebra rules ensure that the generated global tensor remains orthogonal in the Hilbert space. This property makes the features of different fault types naturally separable in the quantum state space, improving the feature separation index in the diagnosis of combined faults of air gap eccentricity and rotor bar breakage. Dynamic feature evolution tracking: The sequential accumulation property of the tensor product implies the temporal evolution information of the fault features. Combined with the subsequent quantum heuristic neural network module, it is possible to predict the fault development trend. Computational parallelization advantage: The tensor product operation can be decomposed into independent pixel-level quantum state generation subtasks, which are particularly suitable for parallel processing in quantum computing.

[0202] In a second aspect, this application provides a fault identification device for permanent magnet synchronous motors based on customized quantum states.

[0203] Please see Figure 2 This is a schematic diagram of a fault identification device for a permanent magnet synchronous motor based on a customized quantum state in an embodiment of this application. The device 210 includes:

[0204] The acquisition module 211 is used to acquire the vibration signal and speed signal of the permanent magnet synchronous motor;

[0205] 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;

[0206] The rotation speed determination module 213 is used to 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 rotation speed signal.

[0207] The mapping and encoding module 214 is used to map and encode each pixel in the first time-frequency diagram according to the rotation speed corresponding to each pixel in the first time-frequency diagram to obtain the customized quantum state corresponding to each pixel in the first time-frequency diagram, and to map and encode each pixel in the second time-frequency diagram according to the rotation speed corresponding to each pixel in the second time-frequency diagram to obtain the customized quantum state corresponding to each pixel in the second time-frequency diagram, wherein the horizontal and vertical coordinates of the pixel are time and frequency, respectively.

[0208] Tensor determination module 215 is used to determine a first global custom quantum state tensor based on the custom quantum states corresponding to all pixels in the first time-frequency image, and to determine a second global custom quantum state tensor based on the custom quantum states corresponding to all pixels in the second time-frequency image.

[0209] The model prediction module 216 is used to input the first global customized quantum state tensor and the second global customized quantum state tensor into the preset permanent magnet synchronous motor fault prediction model to obtain the fault classification and identification results.

[0210] In this embodiment, the relevant contents of the acquisition module 211, transformation module 212, rotation speed determination module 213, mapping encoding module 214, tensor determination module 215, and model prediction module 216 can be found in the following references. Figure 1 The contents of the illustrated embodiments will not be repeated here.

[0211] 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.

[0212] In this embodiment, by introducing a customized quantum state encoding method, the rotational speed signal is used to perform customized quantum state encoding on the pixels of the time-frequency map. This fully utilizes the multi-dimensional information during motor operation, effectively enhances the ability to express early weak fault characteristics, more accurately captures the evolution trend of early faults, improves the detection capability of complex nonlinear fault modes, significantly enhances the detection sensitivity of early weak faults, and achieves more accurate and efficient identification of permanent magnet synchronous motor faults, providing strong support for motor maintenance and operation management.

[0213] In a third aspect, this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, causes the processor to perform a fault identification method for permanent magnet synchronous motors based on customized quantum states, as described in any of the first aspects.

[0214] This application provides a computer device in a fourth aspect, including a memory and a processor, the memory storing a computer program, which, when executed by the processor, causes the processor to perform a fault identification method for permanent magnet synchronous motors based on customized quantum states as described in any of the first aspects.

[0215] 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.

[0216] 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.

[0217] 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.

[0218] 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.

[0219] 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.

[0220] 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 fault identification method for permanent magnet synchronous motors based on customized quantum states, characterized in that, The method includes: Acquire vibration and speed signals 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. 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 rotational speed corresponding to each pixel in the first time-frequency diagram, each pixel in the first time-frequency diagram is mapped and encoded to obtain the customized quantum state corresponding to each pixel in the first time-frequency diagram. Similarly, based on the rotational speed corresponding to each pixel in the second time-frequency diagram, each pixel in the second time-frequency diagram is mapped and encoded to obtain the customized quantum state corresponding to each pixel in the second time-frequency diagram. The horizontal and vertical coordinates of the pixel are time and frequency, respectively. Based on the custom quantum states corresponding to all pixels in the first time-frequency graph, a first global custom quantum state tensor is determined, and based on the custom quantum states corresponding to all pixels in the second time-frequency graph, a second global custom quantum state tensor is determined. The first globally customized quantum state tensor and the second globally customized quantum state tensor are input into the preset permanent magnet synchronous motor fault prediction model to obtain the fault classification and identification results; The step of mapping and encoding each pixel in the first time-frequency image according to the rotational speed corresponding to each pixel in the first time-frequency image to obtain a customized quantum state corresponding to each pixel in the first time-frequency image, and mapping and encoding each pixel in the second time-frequency image according to the rotational speed corresponding to each pixel in the second time-frequency image to obtain a customized quantum state corresponding to each pixel in the second time-frequency image, includes: Based on the rotational speeds corresponding to all pixels in the first time-frequency graph, a first maximum rotational speed is determined, and based on the rotational speeds corresponding to all pixels in the second time-frequency graph, a second maximum rotational speed is determined. Based on the rotational speed corresponding to each pixel in the first time-frequency diagram and the first maximum rotational speed, determine the rotational speed modulation weight corresponding to each pixel in the first time-frequency diagram; and based on the rotational speed corresponding to each pixel in the second time-frequency diagram and the second maximum rotational speed, determine the rotational speed modulation weight corresponding to each pixel in the second time-frequency diagram. Based on the rotational speed modulation weight corresponding to each pixel in the first time-frequency diagram, each pixel in the first time-frequency diagram is mapped and encoded to obtain the customized quantum state corresponding to each pixel in the first time-frequency diagram. Similarly, based on the rotational speed modulation weight corresponding to each pixel in the second time-frequency diagram, each pixel in the second time-frequency diagram is mapped and encoded to obtain the customized quantum state corresponding to each pixel in the second time-frequency diagram.

2. The fault identification method for permanent magnet synchronous motors based on customized quantum states according to claim 1, characterized in that, The step of determining the rotational speed modulation weight corresponding to each pixel in the first time-frequency image based on the rotational speed corresponding to each pixel in the first time-frequency image and the first maximum rotational speed, and determining the rotational speed modulation weight corresponding to each pixel in the second time-frequency image based on the rotational speed corresponding to each pixel in the second time-frequency image and the second maximum rotational speed, includes: Obtain the frequency corresponding to each pixel in the first time-frequency graph and the frequency corresponding to each pixel in the second time-frequency graph; Based on the frequency and rotational speed corresponding to each pixel in the first time-frequency diagram, and the first maximum rotational speed, the rotational speed modulation weight corresponding to each pixel in the first time-frequency diagram is determined; and based on the frequency and rotational speed corresponding to each pixel in the second time-frequency diagram, and the second maximum rotational speed, the rotational speed modulation weight corresponding to each pixel in the second time-frequency diagram is determined.

3. The fault identification method for permanent magnet synchronous motors based on customized quantum states according to claim 2, characterized in that, The rotational speed modulation weight corresponding to each pixel in the first time-frequency graph is determined according to the following formula: ； The rotational speed modulation weight corresponding to each pixel in the second time-frequency graph is determined according to the following formula: ； in, The rotational speed modulation weight is the value 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 The frequency corresponding to the nth pixel in the first time-frequency graph. The rotational speed modulation weight is the value 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. This is the second maximum speed. This is the frequency corresponding to the m-th pixel in the second time-frequency diagram.

4. The fault identification method for permanent magnet synchronous motors based on customized quantum states according to claim 1, characterized in that, The step of mapping and encoding each pixel in the first time-frequency image according to the rotational speed modulation weight corresponding to each pixel in the first time-frequency image to obtain the customized quantum state corresponding to each pixel in the first time-frequency image, and mapping and encoding each pixel in the second time-frequency image according to the rotational speed modulation weight corresponding to each pixel in the second time-frequency image to obtain the customized quantum state corresponding to each pixel in the second time-frequency image, includes: The amplitude corresponding to each pixel in the first time-frequency graph is normalized to obtain the normalized amplitude corresponding to each pixel in the first time-frequency graph, and the amplitude corresponding to each pixel in the second time-frequency graph is normalized to obtain the normalized amplitude corresponding to each pixel in the second time-frequency graph. Based on the rotational speed modulation weight, normalized amplitude, and phase corresponding to each pixel in the first time-frequency diagram, the custom quantum state corresponding to each pixel in the first time-frequency diagram is determined; and based on the rotational speed modulation weight, normalized amplitude, and phase corresponding to each pixel in the second time-frequency diagram, the custom quantum state corresponding to each pixel in the second time-frequency diagram is determined.

5. The fault identification method for permanent magnet synchronous motors based on customized quantum states according to claim 4, characterized in that, The custom quantum state corresponding to each pixel in the first time-frequency graph is determined according to the following formula: ； The custom quantum state corresponding to each pixel in the second time-frequency graph is determined according to the following formula: ； in, This refers to the customized 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. The rotational speed modulation weight is the value corresponding to the nth pixel in the first time-frequency graph. The normalized amplitude corresponds to the nth pixel in the first time-frequency graph. It is a natural constant. The imaginary unit, The phase corresponding to the nth pixel in the first time-frequency graph. and Let be the orthogonal basis vectors of the two-dimensional Hilbert space in quantum state encoding. This refers to the customized 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. The rotational speed modulation weight is the value 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 refers to the phase corresponding to the m-th pixel in the second time-frequency diagram.

6. The fault identification method for permanent magnet synchronous motors based on customized quantum states according to claim 1, characterized in that, The first globally customized quantum state tensor is determined according to the following formula: ； The second globally customized quantum state tensor is determined according to the following formula: ； 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. 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 refers to the customized quantum state corresponding to the nth pixel in the first time-frequency graph. For the second globally customized 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 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.

7. A fault identification device for permanent magnet synchronous motors based on customized quantum states, characterized in that, The device includes: The acquisition module is used to acquire the vibration signal and speed signal of the permanent magnet synchronous motor; 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; The rotation speed determination module is used to 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 rotation speed signal. The mapping and encoding module is used to map and encode each pixel in the first time-frequency diagram according to the rotation speed corresponding to each pixel in the first time-frequency diagram to obtain the customized quantum state corresponding to each pixel in the first time-frequency diagram, and to map and encode each pixel in the second time-frequency diagram according to the rotation speed corresponding to each pixel in the second time-frequency diagram to obtain the customized quantum state corresponding to each pixel in the second time-frequency diagram, wherein the horizontal and vertical coordinates of the pixel are time and frequency, respectively. The tensor determination module is used to determine a first global custom quantum state tensor based on the custom quantum states corresponding to all pixels in the first time-frequency image, and to determine a second global custom quantum state tensor based on the custom quantum states corresponding to all pixels in the second time-frequency image. The model prediction module is used to input the first globally customized quantum state tensor and the second globally customized quantum state tensor into a preset permanent magnet synchronous motor fault prediction model to obtain fault classification and identification results; The step of mapping and encoding each pixel in the first time-frequency image according to the rotational speed corresponding to each pixel in the first time-frequency image to obtain a customized quantum state corresponding to each pixel in the first time-frequency image, and mapping and encoding each pixel in the second time-frequency image according to the rotational speed corresponding to each pixel in the second time-frequency image to obtain a customized quantum state corresponding to each pixel in the second time-frequency image, includes: Based on the rotational speeds corresponding to all pixels in the first time-frequency graph, a first maximum rotational speed is determined, and based on the rotational speeds corresponding to all pixels in the second time-frequency graph, a second maximum rotational speed is determined. Based on the rotational speed corresponding to each pixel in the first time-frequency diagram and the first maximum rotational speed, determine the rotational speed modulation weight corresponding to each pixel in the first time-frequency diagram; and based on the rotational speed corresponding to each pixel in the second time-frequency diagram and the second maximum rotational speed, determine the rotational speed modulation weight corresponding to each pixel in the second time-frequency diagram. Based on the rotational speed modulation weight corresponding to each pixel in the first time-frequency diagram, each pixel in the first time-frequency diagram is mapped and encoded to obtain the customized quantum state corresponding to each pixel in the first time-frequency diagram. Similarly, based on the rotational speed modulation weight corresponding to each pixel in the second time-frequency diagram, each pixel in the second time-frequency diagram is mapped and encoded to obtain the customized quantum state corresponding to each pixel in the second time-frequency diagram.

8. A computer-readable storage medium, characterized in that, The system contains a computer program that, when executed by a processor, causes the processor to perform the fault identification method for permanent magnet synchronous motors based on custom quantum states as described in any one of claims 1 to 6.

9. A computer device, characterized in that, The system includes a memory and a processor, the memory storing a computer program that, when executed by the processor, causes the processor to perform the fault identification method for permanent magnet synchronous motors based on custom quantum states as described in any one of claims 1 to 6.

Images