Fault detection method and device and electronic equipment

Abstract

The invention relates to the technical field of motors, and discloses a fault detection method and device and electronic equipment. The fault detection method comprises the following steps: acquiring real-time operation parameters of a to-be-detected motor; inputting the real-time operation parameters into the trained reconstruction model for encoding and decoding, and obtaining real-time reconstruction errors of the real-time operation parameters; the reconstruction model is obtained by training operation parameters of the motor in a normal state; under the condition that the real-time reconstruction error is larger than a first error threshold value, the real-time operation parameters are input into the fault detection model, and a fault detection result is obtained. According to the invention, the accuracy and reliability of fault detection can be improved.

Description

Technical Field

[0001] This application relates to the technical field of motors, for example, to a fault detection method, device, and electronic device. Background Technique

[0002] Motors are widely used in all aspects of production and life, such as in various equipment and machines like machine tools, printing machines, etc., and in household appliances such as electric fans, air conditioners, etc. During the installation process of motors, problems such as inaccurate positioning or loose mechanical structures can easily lead to the situation where the rotor (or rotating) center of the motor is misaligned with the stator center, that is, the eccentricity fault. The eccentricity fault will cause uneven torque during the operation of the motor, resulting in increased vibration and noise, and will also generate additional mechanical losses, reducing the efficiency of the motor and even posing potential safety hazards. Therefore, diagnosing the eccentricity fault of the motor has important industrial value.

[0003] The related technology discloses a test method for diagnosing the eccentricity fault of an asynchronous motor, including the following steps: obtaining the historical fault data of the eccentricity fault of the asynchronous motor, and extracting the eccentricity fault characteristics from the historical fault data; diagnosing whether the asynchronous motor has an eccentricity fault according to the eccentricity fault characteristics, and if an eccentricity fault occurs, outputting the primary fault data; obtaining the current data of the asynchronous motor and the corresponding detection environment, screening the quality of the current data according to the detection environment to form current spectrum data; according to the current spectrum data, extracting the frequency and amplitude in the current spectrum data, and testing whether the asynchronous motor has an eccentricity fault according to the frequency and amplitude and outputting the test result; if the test result is that the asynchronous motor has an eccentricity fault, obtaining the monitoring image during the operation of the asynchronous motor, and extracting the vibration data of the asynchronous motor by combining the attention mechanism; obtaining the vibration modes of different components of the asynchronous motor, and combining the vibration data to confirm the eccentricity position and the severity of the eccentricity to obtain the fault result.

[0004] Although the related technology can achieve the diagnosis of the eccentricity fault of the motor, in practical applications, it is often difficult and costly to obtain a large amount of labeled historical fault data of the motor eccentricity fault. The scarcity of fault samples easily leads to the situation that the model cannot fully learn the fault characteristics during the training process, so it is difficult to accurately distinguish the normal state and the fault state during the diagnosis stage, reducing the diagnostic accuracy.

[0005] It should be noted that the information disclosed in the above background technical part is only used to strengthen the understanding of the background of this application, and thus may include information that does not constitute the prior art known to those of ordinary skill in the art. Summary of the Invention

[0006] To provide a basic understanding of some aspects of the disclosed embodiments, a simple summary is given below. This summary is not a general review, nor is it intended to identify key / important elements or delineate the scope of protection of these embodiments, but rather serves as a preamble to the detailed description that follows.

[0007] Embodiments of the present disclosure provide a fault detection method, apparatus, and electronic device, which can improve the accuracy and reliability of fault detection.

[0008] In some embodiments, a fault detection method is provided, including: obtaining real-time operating parameters of a motor to be detected; inputting the real-time operating parameters into a trained reconstruction model for encoding and decoding, and obtaining a real-time reconstruction error of the real-time operating parameters; the reconstruction model is trained using the operating parameters of the motor in a normal state; in the case where the real-time reconstruction error is greater than a first error threshold, inputting the real-time operating parameters into a fault detection model to obtain a fault detection result.

[0009] Optionally, the reconstruction model is trained in the following manner: obtaining the operating parameters of the motor in a normal state as training data; preprocessing the training data; the preprocessing includes one or more of data cleaning, standardization, and dimensionality reduction; training the reconstruction model using the preprocessed training data.

[0010] Optionally, the reconstruction model includes an encoder and a decoder; training the reconstruction model using the preprocessed training data includes: adding noise to the operating parameters in the preprocessed training data; inputting the operating parameters with added noise into the encoder for encoding to obtain encoded data; inputting the encoded data into the decoder for decoding to reconstruct the operating parameters without added noise.

[0011] Optionally, training the reconstruction model using the preprocessed training data further includes: taking the operating parameters before noise addition as the original data; and taking the reconstructed operating parameters without added noise as the reconstructed data; using the mean square error loss function to evaluate the training reconstruction error between the original data and the reconstructed data; obtaining the trained reconstruction model in the case where the training reconstruction error is less than or equal to a second error threshold.

[0012] Optionally, inputting the real-time operating parameters into the fault detection model to obtain a fault detection result includes: extracting target features from the real-time operating parameters; the target features refer to features related to eccentricity faults; inputting the target features into the fault detection model to obtain a fault detection result.

[0013] Optionally, the real-time operating parameters include real-time current data; inputting the real-time operating parameters into a fault detection model to obtain a fault detection result, including: performing variational mode decomposition on the real-time current data to obtain multiple modal components; determining a target modal component corresponding to the real-time current data from the multiple modal components; converting the target modal component into an image and inputting it into the fault detection model to obtain a fault detection result.

[0014] Optionally, the fault detection result includes a fault degree and a fault type; the fault detection method further includes: obtaining a fault level output by a reconstruction model; when the fault degree and the fault level are the same, sending the fault degree and the fault type to a target terminal device for display; when the fault degree and the fault level are different, sending the fault level and the fault type to the target terminal device for display.

[0015] Optionally, the fault detection result includes a fault degree and a fault type; the fault detection method further includes: obtaining a fault level output by a reconstruction model; when the numerical values corresponding to the fault degree and the fault level are different, updating the fault detection model based on the fault level and the fault type.

[0016] In some embodiments, a fault detection device is provided, including: an acquisition module configured to acquire real-time operating parameters of a motor to be detected; a reconstruction module configured to encode and decode the real-time operating parameters by inputting them into a trained reconstruction model, and obtain a real-time reconstruction error of the real-time operating parameters; the reconstruction model is trained using the operating parameters of the motor in a normal state; a detection module configured to input the real-time operating parameters into a fault detection model to obtain a fault detection result when the real-time reconstruction error is greater than a first error threshold.

[0017] In some embodiments, a fault detection device is provided, including a processor and a memory storing program instructions, and the processor is configured to execute the fault detection method as described in the above embodiments when running the program instructions.

[0018] In some embodiments, an electronic device is provided, including: a device body; the fault detection device as described in the above embodiments, installed on the device body.

[0019] The fault detection method, device, and electronic device provided by the embodiments of the present disclosure can achieve the following technical effects:

[0020] In the embodiments of the present disclosure, the reconstruction model is trained using the operating parameters of the motor in the normal state, and learns the normal behavior pattern of the motor. By inputting the acquired real-time operating parameters into the pre-trained reconstruction model, through the encoding and decoding processes, the reconstructed operating parameters are generated, and the error between the real-time operating parameters and the reconstructed operating parameters is obtained, that is, the real-time reconstruction error. The real-time reconstruction error reflects the difference between the real-time operating parameters and the normal behavior pattern predicted by the model. If the real-time reconstruction error is greater than the first error threshold, it can be considered that the motor to be detected has a fault. At this time, the real-time operating parameters are input into the fault detection model to obtain a more specific fault detection result.

[0021] Compared with the related art, the reconstruction model in the embodiments of the present disclosure is trained using the operating parameters of the motor in the normal state, and there is no need to obtain a large amount of historical fault data with labeled motor eccentricity faults. In addition, since the reconstruction model can adaptively adapt to the normal operating mode of the motor. By comparing the real-time reconstruction error with the first error threshold, it can be quickly determined whether the motor has abnormal behavior, thereby providing guidance for the judgment of the subsequent fault detection model, so as to improve the accuracy of the fault detection model for fault diagnosis, and thus improve the accuracy and reliability of the overall fault detection.

[0022] The above general description and the following description are only exemplary and explanatory, and are not used to limit the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] One or more embodiments are exemplarily illustrated by the corresponding drawings. These exemplary illustrations and the drawings do not constitute a limitation on the embodiments. Elements with the same reference numerals in the drawings are shown as similar elements. The drawings do not constitute a scale limitation, and in which:

[0024] Figure 1 is a schematic diagram of an electronic device provided by an embodiment of the present disclosure;

[0025] Figure 2 is a schematic diagram of a fault detection method provided by an embodiment of the present disclosure;

[0026] Figure 3 is a schematic diagram of a training method of a reconstruction model provided by an embodiment of the present disclosure;

[0027] Figure 4 is a schematic diagram of a reconstruction model provided by an embodiment of the present disclosure;

[0028] Figure 5 is a schematic diagram of a fault detection method provided by another embodiment of the present disclosure;

[0029] Figure 6 is a schematic diagram of a fault detection method provided by another embodiment of the present disclosure;

[0030] Figure 7 It is a schematic diagram of a fault detection device provided by an embodiment of the present disclosure;

[0031] Figure 8 It is a schematic diagram of a fault detection device provided by another embodiment of the present disclosure. Detailed implementation manners

[0032] In order to be able to understand the features and technical content of the embodiments of the present disclosure in more detail, the implementation of the embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings. The accompanying drawings are only for reference and explanation, and are not used to limit the embodiments of the present disclosure. In the following technical description, for the sake of explanation, numerous details are provided to give a thorough understanding of the disclosed embodiments. However, one or more embodiments may still be implemented without these details. In other instances, well-known structures and devices may be shown in a simplified manner to simplify the drawings.

[0033] In the description of the embodiments of the present disclosure, the terms "first", "second", etc. in the specification and claims of the embodiments of the present disclosure and the above accompanying drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that such data may be interchanged under appropriate circumstances so as to implement the embodiments of the present disclosure described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion.

[0034] Unless otherwise specified, the term "plurality" means two or more.

[0035] In the embodiments of the present disclosure, the character " / " indicates that the objects before and after are in an "or" relationship. For example, A / B means: A or B.

[0036] The term "and / or" is a description of the association relationship of an object, indicating that three relationships can exist. For example, A and / or B means: the three relationships of A, B, and A and B.

[0037] The term "corresponding" may refer to an association relationship or a binding relationship. A corresponding to B means that there is an association relationship or a binding relationship between A and B.

[0038] It should be noted that, without conflict, the embodiments in the embodiments of the present disclosure and the features in the embodiments may be combined with each other.

[0039] Combined with Figure 1 As shown, an embodiment of the present disclosure provides an electronic device 1, including a device body 10 and a fault detection device 70(80). The fault detection device 70(80) is installed on the device body 10.

[0040] In the electronic device 1 provided by the embodiments of the present disclosure, the fault detection device 70(80) is installed on the device body 10. The installation relationship described here is not limited to being placed inside the device body 10, but also includes installation connections with other components of the electronic device 1, including but not limited to physical connections, electrical connections, or signal transmission connections, etc. Those skilled in the art can understand that the fault detection device 70(80) can be adapted to a feasible electronic device 1, thereby implementing other feasible embodiments.

[0041] Optionally, the fault detection device 80 includes a processor 800. The processor 800 can obtain the real-time operation parameters of the motor to be detected; can input the real-time operation parameters into the trained reconstruction model for encoding and decoding, and obtain the real-time reconstruction error of the real-time operation parameters; and can input the real-time operation parameters into the fault detection model to obtain the fault detection result when the real-time reconstruction error is greater than the first error threshold.

[0042] Combined with Figure 1 and Figure 8 the electronic device 1 shown, the embodiments of the present disclosure provide a fault detection method. As Figure 2 shown, the fault detection method includes:

[0043] S201, the processor obtains the real-time operation parameters of the motor to be detected.

[0044] In this step, the real-time operation parameters of the motor to be detected include but are not limited to the vibration signal, current, voltage, temperature, etc. of the motor to be detected.

[0045] S202, the processor inputs the real-time operation parameters into the trained reconstruction model for encoding and decoding, and obtains the real-time reconstruction error of the real-time operation parameters.

[0046] The reconstruction model is trained using the operation parameters of the motor in the normal state.

[0047] S203, the processor inputs the real-time operation parameters into the fault detection model to obtain the fault detection result when the real-time reconstruction error is greater than the first error threshold.

[0048] In the fault detection method provided by the embodiments of the present disclosure, the reconstruction model is trained using the operating parameters of the motor in the normal state, and learns the normal behavior pattern of the motor. By inputting the obtained real-time operating parameters into the pre-trained reconstruction model, through the encoding and decoding processes, the reconstructed operating parameters are generated, and the error between the real-time operating parameters and the reconstructed operating parameters is obtained, that is, the real-time reconstruction error. The real-time reconstruction error reflects the difference between the real-time operating parameters and the normal behavior pattern predicted by the model. If the real-time reconstruction error is greater than the first error threshold, it can be considered that the motor to be detected has a fault. At this time, the real-time operating parameters are input into the fault detection model to obtain a more specific fault detection result.

[0049] Compared with the related art, the reconstruction model in the embodiments of the present disclosure is trained using the operating parameters of the motor in the normal state, and there is no need to obtain a large amount of historical fault data with labeled motor eccentricity faults. In addition, since the reconstruction model can adaptively adapt to the normal operation mode of the motor. By comparing the real-time reconstruction error with the first error threshold, it can be quickly determined whether the motor has abnormal behavior, thereby providing guidance for the judgment of the subsequent fault detection model to improve the accuracy of the fault detection model for fault diagnosis, and thus improving the accuracy and reliability of the overall fault detection.

[0050] In some embodiments, the reconstruction model is trained in the following manner. As Figure 3 shown, the embodiments of the present disclosure provide a training method for a reconstruction model, including:

[0051] S301, the processor obtains the operating parameters of the motor in the normal state as training data.

[0052] In this step, the operating parameters of the motor in the normal state reflect the normal operating state of the motor when no fault occurs. The operating parameters of the motor in the normal state include but are not limited to vibration signals, current, voltage, speed, temperature, etc. of the motor in the normal state.

[0053] S302, the processor preprocesses the training data.

[0054] In this step, the preprocessing includes one or more of data cleaning, standardization, and dimensionality reduction. Among them, data cleaning includes removing outliers and / or filling in missing values. Standardization is used to scale the training data to a specific range. Dimensionality reduction refers to reducing the data dimension of the training data, and dimensionality reduction can be achieved by the principal component analysis (PCA) method.

[0055] S303, the processor trains the reconstruction model using the preprocessed training data.

[0056] The training method for the reconstruction model provided by the embodiments of the present disclosure can preprocess the training data before training the reconstruction model to improve the quality of the training data and the training effect of the model. By training the reconstruction model, the reconstruction model can accurately reconstruct the normal operating parameters of the motor. And a first error threshold is set as the criterion for identifying potential faults of the motor to achieve real-time fault detection of the motor.

[0057] Specifically, the trained reconstruction model will show a relatively low error when reconstructing the operating parameters of the motor in the normal state. However, when facing the operating parameters in the fault state, since these operating parameters deviate from the normal operating state internalized by the model, the reconstruction error is relatively large. In this way, the fault detection of the motor is realized, and it is determined whether the motor has a fault according to the magnitude of the reconstruction error, thereby providing guidance for the judgment of the subsequent fault detection model and improving the accuracy and reliability of the overall fault detection.

[0058] In some embodiments, the reconstruction model includes an encoder and a decoder. The encoder is responsible for mapping the input data to a low-dimensional representation, and the decoder is responsible for restoring this low-dimensional representation to an output as close as possible to the original input. The processes of encoding and decoding force the reconstruction model to learn to extract the key features in the input data, thereby realizing an effective representation of the data.

[0059] Training the reconstruction model with the preprocessed training data includes: adding noise to the operating parameters in the preprocessed training data; inputting the operating parameters with added noise into the encoder of the reconstruction model for encoding to obtain encoded data; inputting the encoded data into the decoder of the reconstruction model for decoding to reconstruct the operating parameters without added noise.

[0060] In this embodiment, the reconstruction model can add noise to the input data and attempt to recover the original data from it, thereby learning the internal structure and features of the input data. As Figure 4 shown, the reconstruction model includes an encoder and a decoder. In the encoding process, the encoder is responsible for converting the input data into an internal representation. This process is achieved by reducing the dimension of the data, that is, mapping the input data to a low-dimensional representation, thereby learning the compressed form of the input data. This process can be represented by the following formula: h i = f(Wx i + b); where, x i represents the i-th input data (the i-th operating parameter in this embodiment), the value of i is 1, 2,..., n, n represents the number of input data, W is the weight matrix of the encoder, b is the bias term, f is the activation function of the encoder, and h i is the output data of the encoder, that is, the encoded data.

[0061] The structure of the decoder is a mirror image of the encoder. During the decoding process, the decoder is responsible for receiving the encoded data output by the encoder and attempting to reconstruct the original form of the input data. This process is achieved by gradually increasing the dimension of the data until it reaches the size of the original input data. This process can be represented by the following formula: y i = g(W′h i + b′); where y i represents the output data of the i-th decoder (in this embodiment, it is the i-th reconstructed operating parameter without added noise), the value of i is 1, 2, …, n, n represents the number of input data, W' is the weight matrix of the decoder, b' is the bias term, and g is the activation function of the decoder.

[0062] Optionally, when training the reconstruction model with the preprocessed training data, it further includes: using the operating parameter before noise addition as the original data; and using the reconstructed operating parameter without added noise as the reconstructed data; using the mean squared error loss function to evaluate the training reconstruction error between the original data and the reconstructed data; obtaining the trained reconstruction model when the training reconstruction error is less than or equal to the second error threshold; the second error threshold is less than or equal to the first error threshold.

[0063] In this embodiment, the normal operating parameter of the motor before noise addition is used as the original data, that is, the target data that the reconstruction model needs to recover. The operating parameter obtained after the reconstruction model reconstructs the input data with added noise is used as the reconstructed data, that is, the output data of the reconstruction model, which is used to compare with the original data. The mean squared error (MSE) loss function is used to evaluate the training reconstruction error between the original data and the reconstructed data, which is used to measure the difference degree between the two data sets. By clearly defining the original data and the reconstructed data and using the mean squared error loss function to evaluate the training reconstruction error, the reconstruction performance of the reconstruction model can be measured more accurately, so as to adjust the model parameters in time during the training process and improve the reconstruction ability and fault detection accuracy of the model.

[0064] The mean squared error loss function calculates the average of the squares of the differences of each corresponding element between the original data and the reconstructed data. Specifically, for a given original data set {x 1 , x 2 , …, x n}, the mean squared error loss function is defined as: where x i is the i-th original data, y i is the reconstructed data obtained after reconstructing the i-th original data x i , the value of i is 1, 2, …, n, and n represents the number of input data.

[0065] In this embodiment, a second error threshold is preset to determine whether the reconstruction model has been trained. During the training process, the training reconstruction error is continuously calculated and compared with the second error threshold. If the training reconstruction error is less than or equal to the second error threshold, it is considered that the reconstruction model can basically reconstruct the original data with a small error, and the reconstruction model has been trained well, and the training process can be stopped. By setting the second error threshold as the training stop condition, overfitting or underfitting of the model is avoided.

[0066] In some embodiments, the reconstruction model includes multiple encoders and multiple decoders. The multiple encoders and multiple decoders are arranged at intervals in sequence. An adjacent encoder and decoder form a group, and multiple groups of encoders and decoders are stacked together to form the reconstruction model.

[0067] In this embodiment, the reconstruction model is composed of multiple groups of encoders and decoders stacked together. Each layer gradually learns a higher-level abstract representation of the input data. The output data of each layer can be used as the input data to train the next layer, thus forming a deep neural network. By learning the hierarchical structure of the data layer by layer, the reconstruction model can capture the complex structure and features in the data. By learning the hierarchical structure of the data layer by layer, the reconstruction model can capture the complex structure and features in the data, thereby improving the reconstruction ability of the model and the accuracy of fault detection. Since the reconstruction model can learn the complex structure and features of the data, when there are significant differences between the real-time operating parameters of the motor and the normal state (i.e., a fault condition), the reconstruction error will increase significantly, thereby improving the sensitivity of fault detection. Since noise is added and denoising processing is performed in each layer of the reconstruction model, the model has stronger robustness to the noise of the input data. Even if the operating parameters of the motor are disturbed by noise during the actual operation process, the reconstruction model can still accurately reconstruct the normal operating state of the motor.

[0068] In some embodiments, the reconstruction model is trained with a denoising autoencoder or a stacked denoising autoencoder as the framework.

[0069] In some embodiments, the real-time operating parameters are input into the fault detection model to obtain a fault detection result, including: extracting target features from the real-time operating parameters; the target features refer to the features related to the eccentricity fault; inputting the target features into the fault detection model to obtain the fault detection result.

[0070] In this embodiment, by extracting target features from the real-time operating parameters, the information most sensitive to the eccentricity fault is extracted from the real-time operating parameters, such as the vibration frequency and vibration amplitude of the vibration signal, the fluctuation patterns of the current and voltage, the temperature rising rate, etc. The extracted target features are input into the trained fault detection model, and the fault detection model outputs a fault detection result according to the input target features. In this embodiment, by directly extracting the target features, the amount of data input into the fault detection model can be reduced, thereby reducing the computational complexity of the model.

[0071] In some embodiments, the fault detection model can be obtained by training a support vector machine, a random forest, or a two-dimensional convolutional neural network. Specifically, the operating parameters of the motor in the normal state, different eccentricity types, and different eccentricity degrees can be collected through pre-experiments; the operating parameters include, but are not limited to, the vibration signal, current, voltage, temperature, etc. of the motor; the collected operating parameters are marked; and the marked operating parameters are used as training data to train the support vector machine, random forest, or two-dimensional convolutional neural network to obtain the fault detection model. Exemplarily, the eccentricity types include parallel eccentricity and angular eccentricity. Among them, the parallel eccentricity amounts (i.e., the eccentricity degrees) of the parallel eccentricity are 0.5 mm (millimeters), 1 mm, and 1.5 mm respectively, and the eccentricity angle values (i.e., the eccentricity degrees) of the angular eccentricity are 0.8°, 1.2°, and 1.5° respectively.

[0072] In some embodiments, the real-time operating parameters include real-time current data. Inputting the real-time operating parameters into the fault detection model to obtain a fault detection result includes: performing variational mode decomposition on the real-time current data to obtain a plurality of modal components; determining the target modal component corresponding to the real-time current data from the plurality of modal components; converting the target modal component into a grayscale image and inputting it into the fault detection model to obtain a fault detection result.

[0073] Variational mode decomposition (VMD, Variational Mode Decomposition) is an adaptive and non-recursive method for signal processing, aiming to decompose a complex multi-component signal into a series of intrinsic mode functions (IMF, Intrinsic Mode Function) with sparse characteristics. These IMF components are compact and bandwidth-limited in the frequency domain, and the center frequency and bandwidth of each IMF component will adaptively change with the decomposition process. The core idea of VMD is to decompose the signal into multiple IMF components so that the sum of the estimated bandwidths of each IMF component is minimized, that is, to find a solution through iterative optimization to minimize the bandwidth of each IMF component.

[0074] In this embodiment, the target modal component refers to the modal component among multiple modal components that is related to the characteristics representing the operating state of the motor. The target modal component can accurately reflect the operating state characteristics of the motor. Through variational mode decomposition, the current data is decomposed into multiple modal components, and each modal component represents different characteristics in the current data, realizing a more refined capture of the characteristic information in the current data, especially the minute changes related to the eccentricity fault.

[0075] Although feature extraction is also carried out in the related art, it is impossible to deeply analyze the detailed information in the current signal. Compared with the related art, the embodiment of the present disclosure can more deeply and effectively extract the fault characteristics in the current data of the motor through variational mode decomposition and image processing, thereby further improving the accuracy of fault detection.

[0076] In this embodiment, before the model performs fault detection, the target modal component can be converted into a grayscale image first. A grayscale image is an image that only contains luminance information, and the luminance change is closely related to the fluctuation and change pattern of the current data. Based on the grayscale image, the characteristic changes of the current data can be analyzed more clearly, and the relationship between the current data and the fault can be better understood, thereby improving the accuracy of fault detection. In addition, compared with a color image, the data processing amount of the grayscale image is greatly reduced, reducing the computational complexity and storage requirements, and improving the speed and efficiency of data processing.

[0077] Optionally, determining the target modal component corresponding to the real-time current data from multiple modal components includes: calculating the correlation coefficient between the real-time current data and each modal component corresponding to the real-time current data respectively; taking the modal component with the largest correlation coefficient among the multiple modal components corresponding to each real-time current data as the target modal component corresponding to the real-time current data.

[0078] The correlation coefficient method is a statistical method used to measure the strength and direction of the linear relationship between two variables. In this embodiment, by calculating the correlation coefficient between the real-time current data and the decomposed modal components, the similarity or relevance between the real-time current data and each modal component is measured. The modal component with the largest correlation coefficient has the strongest correlation with the real-time current data and can best reflect the operating state characteristics of the motor in the real-time current data. By taking the modal component with the largest correlation coefficient as the target modal component corresponding to the real-time current data, it is ensured to select the modal component that best matches the real-time current data, thereby further improving the accuracy and efficiency of detection.

[0079] Combined with Figure 5 As shown, the embodiment of the present disclosure provides another fault detection method, including:

[0080] S501, the processor acquires the real-time operating parameters of the motor to be detected.

[0081] S502, the processor inputs the real-time operation parameters into the reconstruction model for encoding and decoding, and obtains the real-time reconstruction error of the real-time operation parameters.

[0082] The reconstruction model is obtained by training with the operation parameters of the motor in the normal state.

[0083] S503, when the real-time reconstruction error is greater than the first error threshold, the processor inputs the real-time operation parameters into the fault detection model to obtain the fault detection result.

[0084] The fault detection result includes the fault degree and the fault type. In this step, the fault type may refer to the eccentricity type in the above embodiments, and the fault degree may refer to the eccentricity degree in the above embodiments.

[0085] S504, the processor sends the fault degree and the fault type to the target terminal device for display.

[0086] In this step, the target terminal device refers to the terminal device corresponding to the staff such as the motor maintenance personnel or technicians, and may include but is not limited to the console of the monitoring center, the mobile devices of the maintenance personnel (such as mobile phones, tablets), etc.

[0087] The fault detection method of the embodiments of the present disclosure can identify the fault degree and the fault type, and send the obtained fault degree and fault type to the target terminal device for display, so that the relevant personnel can quickly understand the fault situation and take corresponding countermeasures, improving the timeliness and accuracy of fault handling.

[0088] It should be noted that the fault degree in the embodiments of the present disclosure can directly output the eccentricity. For example, when the fault type is parallel eccentricity, the parallel eccentricity is output: 0.5mm, 1mm or 1.5mm; when the fault type is angular eccentricity, the eccentricity angle value is output: 0.8°, 1.2° or 1.5°, to characterize the fault degree. It is also possible to mark the fault degree for different eccentricities during the model training process. The fault degree markings include mild, moderate and severe. Exemplarily, a parallel eccentricity of 0.5mm or an eccentricity angle value of 0.8° corresponds to a mild fault degree, a parallel eccentricity of 1mm or an eccentricity angle value of 1.2° corresponds to a moderate fault degree, and a parallel eccentricity of 1.5mm or an eccentricity angle value of 1.5° corresponds to a severe fault degree, so as to output the fault degree marking (mild, moderate or severe) corresponding to the eccentricity after the fault detection to characterize the fault degree.

[0089] In some embodiments, the fault detection method further includes: obtaining the fault level output by the reconstruction model; when the fault degree and the fault level are the same, sending the fault degree and the fault type to the target terminal device for display; when the fault degree and the fault level are different, sending the fault level and the fault type to the target terminal device for display.

[0090] In this embodiment, the reconstruction model can output a fault level to characterize the severity of the fault. By comparing the fault degree output by the fault detection model with the fault level output by the reconstruction model, it is determined whether the classifications corresponding to the fault degree and the fault level are the same. When the classifications corresponding to the fault degree and the fault level are the same, the fault degree and the fault type are sent to the target terminal device for display to ensure the accuracy of the information. When the classifications corresponding to the fault degree and the fault level are different, the fault level and the fault type output by the reconstruction model are preferentially sent to the target terminal device for display.

[0091] In this embodiment, the output of the fault level of the reconstruction model can be achieved by presetting multiple error thresholds. Exemplarily, a first error threshold, a third error threshold, and a fourth error threshold are preset. Among them, the first error threshold < the third error threshold < the fourth error threshold. When the real-time reconstruction error is greater than the first error threshold and less than the third error threshold, the fault level is determined to be mild; when the real-time reconstruction error is greater than the third error threshold and less than the fourth error threshold, the fault level is determined to be moderate; when the real-time reconstruction error is greater than the fourth error threshold, the fault level is determined to be severe.

[0092] Combined with Figure 6 As shown, another fault detection method provided by the embodiments of the present disclosure includes:

[0093] S601, the processor obtains the real-time operating parameters of the motor to be detected.

[0094] S602, the processor inputs the real-time operating parameters into the reconstruction model for encoding and decoding, and obtains the real-time reconstruction error of the real-time operating parameters.

[0095] The reconstruction model is trained using the operating parameters of the motor in the normal state.

[0096] S603, when the real-time reconstruction error is greater than the first error threshold, the processor inputs the real-time operating parameters into the fault detection model to obtain a fault detection result.

[0097] The fault detection result includes the fault degree and the fault type.

[0098] S604, the processor obtains the fault level output by the reconstruction model.

[0099] S605. When the degrees and levels of faults are different, the processor updates the fault detection model based on the fault level and fault type.

[0100] The fault detection method according to the embodiments of the present disclosure can retrain the fault detection model based on the fault level and fault type when the degrees and levels of faults are different, so as to update the fault detection model. Specifically, the real-time operation parameters can be marked, and the corresponding fault level and fault type of the real-time operation parameters are marked. The marked real-time operation parameters are used as new training samples to retrain the fault detection model, so as to realize the update of the fault detection model. Through the update, the fault detection model can more accurately reflect the actual fault situation, and improve the accuracy and reliability of fault detection.

[0101] It should be noted that the specific values of the first error threshold, the second error threshold, the third error threshold and the fourth error threshold involved in the embodiments of the present disclosure need to be preset by those skilled in the art according to the nature of the actual specific task and the characteristics of the input data, and are not specifically limited herein.

[0102] Combined with Figure 7 As shown, the embodiments of the present disclosure provide a fault detection device 70, including an acquisition module 710, a reconstruction module 720 and a detection module 730. The acquisition module 710 is configured to acquire the real-time operation parameters of the motor to be detected; the reconstruction module 720 is configured to input the real-time operation parameters into the trained reconstruction model for encoding and decoding, and obtain the real-time reconstruction error of the real-time operation parameters; the reconstruction model is trained by using the operation parameters of the motor in the normal state; the detection module 730 is configured to input the real-time operation parameters into the fault detection model to obtain a fault detection result when the real-time reconstruction error is greater than the first error threshold.

[0103] The fault detection device 70 provided by the embodiments of the present disclosure can execute the fault detection method described in the above embodiments. Therefore, the technical effects possessed by the fault detection method described in the above embodiments are all possessed by the embodiments of the present disclosure, and will not be elaborated herein.

[0104] Optionally, the fault detection device 70 further includes a training module 740. The training module 740 is configured to acquire the operation parameters of the motor in the normal state as training data; perform preprocessing on the training data; the preprocessing includes one or more of data cleaning, standardization, and dimensionality reduction; and train the reconstruction model by using the preprocessed training data.

[0105] Optionally, the reconstruction model includes an encoder and a decoder. The training module 740 is further configured to add noise to the operating parameters in the preprocessed training data; input the operating parameters with added noise into the encoder for encoding to obtain encoded data; and input the encoded data into the decoder for decoding to reconstruct the operating parameters without added noise.

[0106] Optionally, the training module 740 is further configured to use the operating parameters before noise addition as the original data; and use the reconstructed operating parameters without added noise as the reconstructed data; evaluate the training reconstruction error between the original data and the reconstructed data using the mean square error loss function; and obtain the trained reconstruction model when the training reconstruction error is less than or equal to the second error threshold.

[0107] Optionally, the detection module 730 is further configured to extract target features from the real-time operating parameters; the target features refer to the features related to the eccentricity fault; and input the target features into the fault detection model to obtain the fault detection result.

[0108] Optionally, the real-time operating parameters include real-time current data. The detection module 730 is further configured to perform variational mode decomposition on the real-time current data to obtain multiple mode components; determine the target mode component corresponding to the real-time current data from the multiple mode components; convert the target mode component into an image and input it into the fault detection model to obtain the fault detection result.

[0109] Optionally, the fault detection result includes the fault degree and the fault type. The fault detection device 70 further includes an execution module 750. The execution module 750 is configured to obtain the fault level output by the reconstruction model; when the fault degree and the fault level are the same, send the fault degree and the fault type to the target terminal device for display; and when the fault degree and the fault level are different, send the fault level and the fault type to the target terminal device for display.

[0110] Optionally, the execution module 750 is further configured to obtain the fault level output by the reconstruction model; and when the numerical values corresponding to the fault degree and the fault level are different, update the fault detection model based on the fault level and the fault type.

[0111] Combined with Figure 8As shown in the figure, an embodiment of the present disclosure provides a fault detection device 80, which includes a processor 800 and a memory 801. Optionally, the device 80 may further include a communication interface 802 and a bus 803. Among them, the processor 800, the communication interface 802, and the memory 801 can complete mutual communication through the bus 803. The communication interface 802 can be used for information transmission. The processor 800 can call the logical instructions in the memory 801 to execute the fault detection method of the above embodiment.

[0112] In addition, when the logical instructions in the above-mentioned memory 801 are implemented in the form of a software functional unit and sold or used as an independent product, they can be stored in a computer-readable storage medium.

[0113] As a computer-readable storage medium, the memory 801 can be used to store software programs and computer-executable programs, such as the program instructions / modules corresponding to the methods in the embodiments of the present disclosure. The processor 800 executes functional applications and data processing by running the program instructions / modules stored in the memory 801, that is, implements the fault detection method in the above embodiment.

[0114] The memory 801 may include a program storage area and a data storage area. Among them, the program storage area can store an operating system and application programs required for at least one function; the data storage area can store data created according to the use of the terminal device, etc. In addition, the memory 801 may include a high-speed random access memory and may also include a non-volatile memory.

[0115] An embodiment of the present disclosure provides a computer-readable storage medium storing computer-executable instructions, and the computer-executable instructions are set to execute the above-mentioned fault detection method.

[0116] The technical solution of the embodiment of the present disclosure can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes one or more instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in the embodiment of the present disclosure. The foregoing storage medium may be a non-transitory storage medium, such as: a USB flash drive, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk, or an optical disc, etc., which are various media that can store program codes.

[0117] The above description and the accompanying drawings fully illustrate the embodiments of the present disclosure, enabling those skilled in the art to practice them. Other embodiments may include structural, logical, electrical, process, and other changes. The embodiments merely represent possible variations. Unless explicitly required, individual components and functions are optional, and the order of operations may vary. Parts and features of some embodiments may be included in or replace parts and features of other embodiments. Moreover, the terms used in this application are only for describing the embodiments and do not limit the claims. As used in the description of the embodiments and the claims, unless the context clearly indicates otherwise, the singular forms "a", "an", and "the" are intended to also include the plural forms. Similarly, as used in this application, the term "and / or" refers to any and all possible combinations including one or more of the associated listed items. Additionally, when used in this application, the term "comprise" and its variants "comprises" and / or "comprising" etc. mean the presence of the stated features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or groups of these. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, method, or device comprising the element. Herein, what each embodiment focuses on may be the differences from other embodiments, and the same or similar parts among the embodiments may be referred to each other. For the methods, products, etc. disclosed in the embodiments, if they correspond to the method parts disclosed in the embodiments, the relevant parts may refer to the description of the method parts.

[0118] Those skilled in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner may depend on the specific application and design constraints of the technical solution. The skilled person may use different methods for each specific application to implement the described functions, but such implementation should not be considered to exceed the scope of the embodiments of the present disclosure. The skilled person can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0119] In the embodiments disclosed in this document, the disclosed methods, products (including but not limited to devices, equipment, etc.) can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units can be merely a logical function division. In actual implementation, there can be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Additionally, the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of the devices or units can be in electrical, mechanical, or other forms. The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to implement this embodiment. Additionally, in the embodiments of the present disclosure, the various functional units can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit.

[0120] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram can represent a module, a program segment, or a part of code that contains one or more executable instructions for implementing the specified logical function. In some alternative implementations, the functions marked in the block can occur in a different order than that marked in the accompanying drawings. For example, two consecutive blocks can actually be executed substantially in parallel, and they can sometimes be executed in the reverse order, which can depend on the functions involved. In the descriptions corresponding to the flowcharts and block diagrams in the accompanying drawings, the operations or steps corresponding to different blocks can also occur in a different order than that disclosed in the description. Sometimes, there is no specific order between different operations or steps. For example, two consecutive operations or steps can actually be executed substantially in parallel, and they can sometimes be executed in the reverse order, which can depend on the functions involved. Each block in the block diagram and / or flowchart, as well as the combination of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or actions, or can be implemented by a combination of dedicated hardware and computer instructions.

Claims

1. A fault detection method, characterized in that: include: Obtain the real-time operating parameters of the motor to be tested; The real-time operating parameters are input into the trained reconstruction model for encoding and decoding, and the real-time reconstruction error of the real-time operating parameters is obtained; the reconstruction model is obtained by training using the operating parameters of the motor under normal conditions; When the real-time reconstruction error is greater than the first error threshold, the real-time operation parameter is input into the fault detection model to obtain a fault detection result.

2. The fault detection method according to claim 1, characterized in that: Train the refactored model as follows: Obtaining the operating parameters of the motor in a normal state as training data; Preprocess the training data; preprocessing includes one or more of data cleaning, standardization, and dimensionality reduction; The reconstruction model is trained using the preprocessed training data.

3. The fault detection method according to claim 2, characterized in that: The reconstruction model includes an encoder and a decoder; The reconstruction model is trained using the preprocessed training data, including: Adding noise to the operating parameters in the preprocessed training data; Inputting the operating parameters with added noise into the encoder for encoding to obtain encoded data; The encoded data is input into a decoder for decoding to reconstruct the operating parameters without the added noise.

4. The fault detection method according to claim 3, characterized in that: The reconstruction model is trained using the preprocessed training data, and also includes: The operating parameters before adding noise are used as original data; and the reconstructed operating parameters without adding noise are used as reconstructed data; The mean square error loss function is used to evaluate the training reconstruction error between the original data and the reconstructed data; When the training reconstruction error is less than or equal to the second error threshold, a trained reconstruction model is obtained.

5. The fault detection method according to any one of claims 1 to 4, characterized in that: Inputting the real-time operating parameters into the fault detection model to obtain the fault detection result, including: extracting target features from the real-time operating parameters; the target features refer to features related to the eccentricity fault; inputting the target features into the fault detection model to obtain the fault detection result; or, The real-time operating parameters include real-time current data; the real-time operating parameters are input into a fault detection model to obtain a fault detection result, including: performing variational modal decomposition on the real-time current data to obtain a plurality of modal components; determining a target modal component corresponding to the real-time current data from the plurality of modal components; converting the target modal component into an image and inputting the image into the fault detection model to obtain a fault detection result.

6. The fault detection method according to any one of claims 1 to 4, characterized in that: The fault detection results include fault degree and fault type; The fault detection method also includes: Obtaining the fault level of the reconstructed model output; When the fault degree and fault level are the same, the fault degree and fault type are sent to the target terminal device and displayed; In the case where the fault degree and fault grade are different, the fault grade and fault type are sent to the target terminal device and displayed.

7. The fault detection method according to any one of claims 1 to 4, characterized in that: The fault detection results include fault degree and fault type; The fault detection method also includes: Obtaining the fault level of the reconstructed model output; When the values ​​corresponding to the fault degree and the fault level are different, the fault detection model is updated based on the fault level and the fault type.

8. A fault detection device, characterized in that: include: An acquisition module is configured to acquire real-time operating parameters of the motor to be detected; A reconstruction module is configured to input the real-time operation parameters into the trained reconstruction model for encoding and decoding, and obtain a real-time reconstruction error of the real-time operation parameters; The reconstructed model is obtained by training with the operating parameters of the motor under normal conditions; The detection module is configured to input the real-time operation parameters into the fault detection model to obtain a fault detection result when the real-time reconstruction error is greater than a first error threshold.

9. A fault detection device, comprising a processor and a memory storing program instructions, characterized in that: The processor is configured to execute the fault detection method according to any one of claims 1 to 7 when running the program instructions.

10. An electronic device, characterized in that: include: Equipment body; The fault detection device as described in claim 8 or 9 is installed on the equipment body.

Images