Vacuum tube maglev transportation system fault diagnosis method and system

Abstract

The application provides a vacuum tube maglev transportation system fault diagnosis method and system. The method comprises the following steps: obtaining relevant operation parameters of the maglev transportation system; removing abnormal points and noises in the relevant operation parameters; segmenting the relevant operation parameters according to different operation stages; respectively performing sliding segmentation on acceleration segmented data of the relevant operation parameters, uniform speed segmented data of the relevant operation parameters and deceleration segmented data of the relevant operation parameters according to a predetermined time interval and a predetermined step length to obtain a plurality of sliding segmented data; extracting corresponding time domain features and frequency domain features for each sliding segment; performing correlation analysis on each sliding segmented data and the corresponding time domain features and frequency domain features by using linear and nonlinear correlation analysis methods to obtain first correlation analysis results and second correlation analysis results; and performing vacuum tube maglev transportation system fault diagnosis according to the first correlation analysis results or the second correlation analysis results.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of vacuum tube maglev, and particularly relates to a vacuum tube maglev transportation system fault diagnosis method and system. BACKGROUND

[0002] The super-speed low-vacuum tube maglev transportation system adopts superconducting electric suspension technology, and generates suspension force, guiding force and propulsion force required for train operation through interaction between superconducting magnets installed on the vehicle and ground coil modules. Its normal operation involves electromagnetic thermal force multi-physical field coupling, and external disturbances such as magnetic field, stress, vibration and heating can affect its stability, leading to faults and threatening train safety. Therefore, it is urgent to develop a fault diagnosis technology for the super-speed low-vacuum tube maglev transportation system to ensure its safe and reliable operation.

[0003] The existing fault diagnosis methods mainly include: (1) an analytical model-based method, (2) a signal processing-based method and (3) a knowledge-based diagnosis method.

[0004] The analytical model-based method is based on a mathematical model of a diagnosed object, and processes measured information according to a certain mathematical method for diagnosis. It can be divided into state estimation method, equivalent space method and parameter estimation method.

[0005] The signal processing-based method usually directly analyzes measurable signals by using signal processing technologies such as frequency spectrum, autoregressive moving average and wavelet transform, and extracts characteristic values such as variance, amplitude and frequency to detect faults.

[0006] The knowledge-based fault diagnosis method does not require an accurate mathematical model of an object, and has certain 'intelligent' characteristics. The knowledge-based fault diagnosis method mainly includes: expert system fault diagnosis method, fault tree fault diagnosis method, fuzzy fault diagnosis method and neural network fault diagnosis method.

[0007] Due to the complex working mechanism of the super-speed low-vacuum tube maglev transportation system, it is difficult to establish an accurate physical diagnosis model. Moreover, the entire system is in the stage of development and improvement, and lacks relevant field knowledge for fault diagnosis. Meanwhile, the frequency modulation, amplitude modulation and phase modulation of test signals under variable speed conditions make the signals complex. Therefore, the traditional single fault diagnosis method based on accurate modeling, signal processing and knowledge is difficult to effectively detect potential abnormalities and faults in the system operation. SUMMARY

[0008] The present application provides a vacuum tube maglev transportation system fault diagnosis method and system, which can solve the technical problems in the prior art.

[0009] The present application provides a vacuum tube maglev transportation system fault diagnosis method, wherein the method comprises:

[0010] obtaining relevant operation parameters of the maglev transportation system, the relevant operation parameters including normal data and fault data;

[0011] preprocessing the relevant operation parameters to remove abnormal points and noises in the relevant operation parameters;

[0012] segmenting the relevant operation parameters according to different operation stages to obtain accelerated segmented data of the relevant operation parameters, uniform speed segmented data of the relevant operation parameters and decelerated segmented data of the relevant operation parameters;

[0013] sliding segmenting the accelerated segmented data of the relevant operation parameters, the uniform speed segmented data of the relevant operation parameters and the decelerated segmented data of the relevant operation parameters according to a predetermined time interval and a predetermined step length to obtain a plurality of sliding segmented data;

[0014] extracting corresponding time domain features and frequency domain features for each sliding segment;

[0015] performing correlation analysis on each sliding segmented data and the corresponding time domain features and frequency domain features by using linear and nonlinear correlation analysis methods to obtain first correlation analysis results between each two different operation parameters in the relevant operation parameters and second correlation analysis results between different sliding segmented data of the same operation parameter;

[0016] performing vacuum tube maglev transportation system fault diagnosis according to the first correlation analysis results or the second correlation analysis results.

[0017] Preferably, the preprocessing of the relevant operation parameters to remove abnormal points and noises in the relevant operation parameters comprises:

[0018] detecting the abnormal points in the relevant operation parameters by using the 3σ principle, and removing the detected abnormal points by using a cubic spline interpolation method and a nearest neighbor interpolation method;

[0019] removing noises of the relevant operation parameters by using a wavelet threshold method to obtain denoised parameters.

[0020] Preferably, the removing of the noises of the relevant operation parameters by using the wavelet threshold method to obtain the denoised parameters comprises:

[0021] performing wavelet transform on the relevant operation parameters to obtain a group of wavelet coefficients;

[0022] performing threshold processing on the obtained group of wavelet coefficients to obtain estimated wavelet coefficients;

[0023] performing wavelet reconstruction according to the estimated wavelet coefficients to obtain the denoised parameters.

[0024] Preferably, the vacuum tube maglev transportation system fault diagnosis according to the first correlation analysis result comprises:

[0025] The first correlation analysis result of the normal data and the first correlation analysis result of the fault data are compared to obtain a sensitive parameter of fault characterization;

[0026] The correlation analysis result of the sensitive parameter is used as a training set and a test set to train a convolutional neural network model and verify the model;

[0027] The vacuum tube maglev transportation system fault diagnosis is performed according to the trained convolutional neural network model and the verified model.

[0028] Preferably, the vacuum tube maglev transportation system fault diagnosis according to the second correlation analysis result comprises:

[0029] According to the correlation coefficient change trend of the second correlation analysis result, the threshold range of the correlation coefficient change in the normal state is determined;

[0030] The vacuum tube maglev transportation system fault diagnosis is performed according to the determined threshold range.

[0031] The present application also provides a vacuum tube maglev transportation system fault diagnosis system, wherein the system comprises:

[0032] The acquisition unit is used for acquiring relevant operation parameters of the maglev transportation system, and the relevant operation parameters include normal data and fault data;

[0033] The preprocessing unit is used for preprocessing the relevant operation parameters to remove abnormal points and noise in the relevant operation parameters;

[0034] The first segmentation unit is used for segmenting the relevant operation parameters according to different operation stages to obtain accelerated segmented data of the relevant operation parameters, uniform speed segmented data of the relevant operation parameters and decelerated segmented data of the relevant operation parameters;

[0035] The second segmentation unit is used for respectively performing sliding segmentation on the accelerated segmented data of the relevant operation parameters, the uniform speed segmented data of the relevant operation parameters and the decelerated segmented data of the relevant operation parameters according to a predetermined time interval and a predetermined step length to obtain a plurality of sliding segmented data;

[0036] The feature extraction unit is used for extracting corresponding time domain features and frequency domain features for each sliding segment;

[0037] a correlation analysis unit configured to perform correlation analysis on each of the sliding segment data and corresponding time domain features and frequency domain features by using linear and nonlinear correlation analysis methods, to obtain first correlation analysis results between each two different operating parameters in the operating parameters, and to obtain second correlation analysis results between different sliding segment data of the same operating parameter;

[0038] a fault diagnosis unit configured to perform fault diagnosis of the vacuum tube maglev transportation system according to the first correlation analysis results or the second correlation analysis results.

[0039] Preferably, the preprocessing unit is configured to preprocess the operating parameters, and to remove abnormal points and noise in the operating parameters, including:

[0040] detecting the abnormal points in the operating parameters by using a 3σ principle, and removing the detected abnormal points by using a cubic spline interpolation method and a nearest neighbor interpolation method;

[0041] removing noise in the operating parameters by using a wavelet threshold method to obtain denoised parameters.

[0042] Preferably, removing noise in the operating parameters by using a wavelet threshold method to obtain denoised parameters includes:

[0043] performing wavelet transform on the operating parameters to obtain a group of wavelet coefficients;

[0044] performing threshold processing on the obtained group of wavelet coefficients to obtain estimated wavelet coefficients;

[0045] performing wavelet reconstruction according to the estimated wavelet coefficients to obtain the denoised parameters.

[0046] Preferably, performing fault diagnosis of the vacuum tube maglev transportation system according to the first correlation analysis results includes:

[0047] comparing the first correlation analysis results of the normal data with the first correlation analysis results of the fault data to obtain sensitive parameters of fault characterization;

[0048] training a convolutional neural network model and verifying the model by using the correlation analysis results of the sensitive parameters as a training set and a test set;

[0049] performing fault diagnosis of the vacuum tube maglev transportation system according to the trained convolutional neural network model and the verified model.

[0050] Preferably, performing fault diagnosis of the vacuum tube maglev transportation system according to the second correlation analysis results includes:

[0051] determining a threshold range of correlation coefficient changes in a normal state according to a change trend of the correlation coefficients in the second correlation analysis results;

[0052] Perform vacuum tube maglev transportation system fault diagnosis according to the determined threshold range.

[0053] Through the technical solution, the related operation parameters of the maglev transportation system can be acquired, and the abnormal points and noises in the related operation parameters can be removed. Then, the related operation parameters can be segmented, and the segmented data can be respectively subjected to sliding segmentation. The corresponding time domain features and frequency domain features are extracted for each sliding segment. Then, the correlation analysis is performed on each sliding segment data and the corresponding time domain features and frequency domain features. The vacuum tube maglev transportation system fault diagnosis is performed according to the analysis result. Thus, the accurate and comprehensive fault diagnosis of the vacuum tube maglev transportation system can be realized. BRIEF DESCRIPTION OF DRAWINGS

[0054] The accompanying drawings, which are included to provide a further understanding of the embodiments of the application and constitute a part of this specification, illustrate embodiments of the application and together with the description help to explain the principles of the application. Obviously, the drawings in the following description are only some embodiments of the application, and other drawings can be obtained by those of ordinary skill in the art without creative effort on the basis of these drawings.

[0055] Figure 1 A flow chart of a vacuum tube maglev transportation system fault diagnosis method according to an embodiment of the application is shown;

[0056] Figure 2 A correlation coefficient matrix diagram of typical normal test data according to an embodiment of the application is shown;

[0057] Figure 3 A correlation coefficient matrix diagram of typical fault test data according to an embodiment of the application is shown. DETAILED DESCRIPTION

[0058] It should be noted that the embodiments in the present application and the features in the embodiments can be combined with each other without conflict. The technical solutions in the embodiments of the present application will be described clearly and completely with reference to the drawings of the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, but not all the embodiments. The description of the at least one exemplary embodiment is actually only illustrative, but not as any limitation on the present application and its application or use. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort fall within the scope of the present application.

[0059] It is to be understood that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and / or "comprising," when used in this specification, specify the presence of stated features, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, steps, operations, elements, components, and / or groups thereof.

[0060] The relative arrangement of parts and steps, numerical expressions, and numerical values set forth in the examples are not intended to limit the scope of the application unless otherwise specifically stated. It is to be understood that the drawings are not necessarily to scale as the dimensions of the parts shown are for the purpose of illustration and description only. Techniques, methods, and apparatus known to those of ordinary skill in the relevant art can not be discussed in detail but are intended to be understood as a part of the specification when appropriate. In all examples shown and discussed herein, any specific values are to be interpreted as illustrative only and not as a limitation. Thus, other examples of the exemplary embodiments can have different values. It is noted that like numbers and letters on the figures identify like parts throughout the disclosure, thus, once a part is defined in one figure, it is not necessary to discuss it further in connection with other figures.

[0061] Figure 1 A flow chart of a method for diagnosing faults of a vacuum tube maglev transportation system is shown.

[0062] The method can be applied to a super-high-speed low-vacuum tube maglev transportation system.

[0063] As shown in Figure 1 The method for diagnosing faults of a vacuum tube maglev transportation system provided by the embodiments of the present application comprises:

[0064] S100, obtaining relevant operation parameters of the maglev transportation system, the relevant operation parameters comprising normal data and fault data;

[0065] That is, various operation data in the operation process of the key equipment of the maglev transportation system can be obtained. The relevant operation parameters further comprise real-time data and offline data.

[0066] For example, the relevant operation parameters can be voltage U, current I, magnetic field B, temperature T, vibration V, and / or displacement D of the key equipment.

[0067] S102, preprocessing the relevant operation parameters to remove abnormal points and noise in the relevant operation parameters;

[0068] S104, segmenting the relevant operating parameter according to different operating stages to obtain acceleration segment data of the relevant operating parameter, uniform speed segment data of the relevant operating parameter and deceleration segment data of the relevant operating parameter;

[0069] That is, segmenting the relevant operating parameter according to different physical stages such as acceleration, uniform speed and deceleration to obtain acceleration segment data of the relevant operating parameter, uniform speed segment data of the relevant operating parameter and deceleration segment data of the relevant operating parameter.

[0070] S106, respectively segmenting the acceleration segment data of the relevant operating parameter, the uniform speed segment data of the relevant operating parameter and the deceleration segment data of the relevant operating parameter according to a predetermined time interval and a predetermined step to obtain a plurality of sliding segment data;

[0071] For example, the acceleration segment data of the relevant operating parameter, the uniform speed segment data of the relevant operating parameter and the deceleration segment data of the relevant operating parameter are respectively segmented according to a predetermined time interval T w and a predetermined step T st to obtain a plurality of sliding segment data, that is, Y N+(N-1)*Tst / fs …Y N+(N-1)*Tst / fs+Tw / fs , where N is a sliding window number and fs is a sampling frequency.

[0072] S108, extracting corresponding time domain features and frequency domain features for each sliding segment;

[0073] That is, the time domain features and frequency domain features reflecting the waveform characteristics of each sliding segment can be extracted according to the characteristics of the signal, that is, the maximum value max, the minimum value min, the mean value m, the effective value rms, the average change rate d, the zero crossing number n and the center frequency f. Specifically, the maximum value max = max |Y N+(N-1)*Tst / fs+1 …Y N+(N-1)*Tst / fs+Tw / fs |, the minimum value min = min |Y N+(N-1)*Tst / fs+1 …Y N+(N-1)*Tst / fs+Tw / fs |, the mean value m = mean |Y the effective value rms = rms |Y the average change rate d = d |Y

[0074] For example, taking the relevant operating parameter as the voltage U as an example, the maximum value max, the minimum value min, the mean value m, the effective value rms, the average change rate d, the zero crossing number n and the center frequency f correspond to the voltage maximum value, the voltage minimum value, the voltage mean value, the voltage effective value, the voltage average change rate, the voltage zero crossing number and the voltage center frequency.

[0075] S110, performing correlation analysis on each sliding segment data and corresponding time domain features and frequency domain features by using linear and nonlinear correlation analysis methods, obtaining first correlation analysis results between each two different operating parameters in the relevant operating parameters and second correlation analysis results between different sliding segment data of the same operating parameter;

[0076] In the linear correlation analysis method, Pearson coefficient, Spearman coefficient and Kendall coefficient can be used. Those skilled in the art should understand that the above coefficients are known coefficients, and in order not to confuse the present application, they will not be described here.

[0077] S112, performing vacuum tube maglev transportation system fault diagnosis according to the first correlation analysis results or the second correlation analysis results.

[0078] Through the above technical solution, the relevant operating parameters of the maglev transportation system can be obtained, and the abnormal points and noise in the relevant operating parameters can be removed. Then, the relevant operating parameters can be segmented and the segmented data can be slidingly segmented. The corresponding time domain features and frequency domain features are extracted for each sliding segment. Then, correlation analysis is performed on each sliding segment data and corresponding time domain features and frequency domain features, and vacuum tube maglev transportation system fault diagnosis is performed according to the analysis results. Thus, accurate and comprehensive fault diagnosis of the vacuum tube maglev transportation system can be realized.

[0079] According to an embodiment of the present application, the pre-processing of the relevant operating parameters and the removal of the abnormal points and noise in the relevant operating parameters include:

[0080] The abnormal points in the relevant operating parameters are detected by using the 3σ principle, and the detected abnormal points are removed by using the cubic spline interpolation method and the nearest neighbor interpolation method.

[0081] The noise of the relevant operating parameters is removed by using the wavelet threshold method to obtain the denoised parameters.

[0082] For the case that the abnormal points are inside the data sequence, the cubic spline interpolation method is used to remove the abnormal points. For the case that the abnormal points are at the boundary of the data sequence, the nearest neighbor interpolation method is used to remove the abnormal points.

[0083] Thus, the removal of the abnormal points can be realized.

[0084] According to an embodiment of the present application, the wavelet threshold method is used to remove the noise of the relevant operating parameters to obtain the denoised parameters, which includes:

[0085] Performing wavelet transform on the relevant operating parameters to obtain a group of wavelet coefficients.

[0086] Perform threshold processing on the obtained set of wavelet coefficients to obtain estimated wavelet coefficients;

[0087] For example, when the obtained wavelet coefficient is less than or equal to a threshold, the estimated wavelet coefficient is 0; when the obtained wavelet coefficient is greater than the threshold, the estimated wavelet coefficient is the obtained wavelet coefficient.

[0088] Wavelet reconstruction is performed based on the estimated wavelet coefficients to obtain the denoised parameters (i.e., the estimated signal).

[0089] Therefore, the high-frequency noise is removed by the wavelet threshold method, and the useful signal is effectively retained.

[0090] According to one embodiment of the present invention, performing fault diagnosis of a vacuum tube maglev transportation system according to the first correlation analysis result includes:

[0091] Comparing the first correlation analysis result of the normal data with the first correlation analysis result of the fault data to obtain sensitive parameters representing the fault;

[0092] The correlation analysis results of sensitive parameters are used as training sets and test sets to train the convolutional neural network model and verify the model;

[0093] Fault diagnosis of vacuum tube maglev transportation system is performed based on the trained convolutional neural network model and verification model.

[0094] Among them, by training the convolutional neural network model and the verification model, the accuracy of the model can be improved accordingly.

[0095] Regarding the above-mentioned steps of performing fault diagnosis based on the trained model, those skilled in the art should understand that as long as the trained model is obtained, the existing method can be used to perform fault diagnosis based on the model. In order not to confuse the present invention, it will not be repeated here.

[0096] Figure 2 and Figure 3 (a) in the figure is the Pearson coefficient matrix, (b) is the Spearman coefficient matrix, (c) is the Kendall coefficient matrix, and (d) is the maximum information coefficient matrix.

[0097] like Figure 2 and 3 As shown, Figure 2 Normal test data in Figure 3 Compared with the correlation of the fault test data in , the correlation of the fault test data has changed significantly.

[0098] According to one embodiment of the present invention, performing fault diagnosis of a vacuum tube maglev transportation system according to the second correlation analysis result includes:

[0099] determine a threshold range of the correlation coefficient variation in the normal state according to the correlation coefficient variation trend of the second correlation analysis result;

[0100] Perform fault diagnosis of the vacuum tube maglev transportation system according to the determined threshold range.

[0101] That is, the threshold range of the correlation coefficient variation in the normal state can be determined by using the correlation coefficient variation trend of different sliding segment data of the same operation parameter, and then the fault diagnosis can be performed according to the threshold range.

[0102] For example, when the to-be-tested data is within the threshold range, the maglev transportation system is diagnosed as normal; and when the to-be-tested data is out of the threshold range, the maglev transportation system is diagnosed as faulty.

[0103] The embodiment of the application further provides a vacuum tube maglev transportation system fault diagnosis system, wherein the system comprises:

[0104] An acquisition unit is configured to acquire relevant operation parameters of the maglev transportation system, wherein the relevant operation parameters comprise normal data and faulty data;

[0105] A preprocessing unit is configured to preprocess the relevant operation parameters to remove abnormal points and noise in the relevant operation parameters;

[0106] A first segmenting unit is configured to segment the relevant operation parameters according to different operation stages to obtain accelerated segment data, uniform speed segment data and decelerated segment data of the relevant operation parameters;

[0107] A second segmenting unit is configured to segment the accelerated segment data, the uniform speed segment data and the decelerated segment data of the relevant operation parameters according to a predetermined time interval and a predetermined step length to obtain a plurality of sliding segment data;

[0108] A feature extraction unit is configured to extract time domain features and frequency domain features corresponding to each sliding segment;

[0109] A correlation analysis unit is configured to perform correlation analysis on each sliding segment data and the corresponding time domain features and frequency domain features by using linear and nonlinear correlation analysis methods to obtain first correlation analysis results between each two different operation parameters in the relevant operation parameters and to obtain second correlation analysis results between different sliding segment data of the same operation parameter;

[0110] A fault diagnosis unit is configured to perform fault diagnosis of the vacuum tube maglev transportation system according to the first correlation analysis results or the second correlation analysis results.

[0111] By the technical solution, the related operation parameters of the maglev transportation system can be acquired, and the abnormal points and noises in the related operation parameters can be removed, then the related operation parameters can be segmented and the segmented data can be respectively subjected to sliding segmentation, the corresponding time domain features and frequency domain features are extracted for each sliding segment, then the correlation analysis is performed on each sliding segment data and the corresponding time domain features and frequency domain features, and the vacuum tube maglev transportation system fault diagnosis is performed according to the analysis result. Therefore, the accurate and comprehensive fault diagnosis of the vacuum tube maglev transportation system can be realized.

[0112] According to an embodiment of the present application, the pre-processing unit pre-processes the related operation parameters, and removes the abnormal points and noises in the related operation parameters, including:

[0113] The abnormal points in the related operation parameters are detected by using the 3σ principle, and the detected abnormal points are removed by using the cubic spline interpolation method and the nearest neighbor interpolation method.

[0114] The noises in the related operation parameters are removed by using the wavelet threshold method, to obtain the de-noised parameters.

[0115] According to an embodiment of the present application, the wavelet threshold method is used to remove the noises in the related operation parameters, to obtain the de-noised parameters, including:

[0116] The wavelet transform is performed on the related operation parameters, to obtain a group of wavelet coefficients.

[0117] The threshold processing is performed on the obtained group of wavelet coefficients, to obtain estimated wavelet coefficients.

[0118] The wavelet reconstruction is performed according to the estimated wavelet coefficients, to obtain the de-noised parameters.

[0119] According to an embodiment of the present application, the vacuum tube maglev transportation system fault diagnosis is performed according to the first correlation analysis result, including:

[0120] The first correlation analysis result of the normal data and the first correlation analysis result of the fault data are compared, to obtain a sensitive parameter of the fault characterization.

[0121] The correlation analysis result of the sensitive parameter is taken as a training set and a test set to train the convolutional neural network model and verify the model.

[0122] The vacuum tube maglev transportation system fault diagnosis is performed according to the trained convolutional neural network model and the verified model.

[0123] According to an embodiment of the present application, the vacuum tube maglev transportation system fault diagnosis is performed according to the second correlation analysis result, including:

[0124] According to the correlation coefficient change trend of the second correlation analysis result, a threshold range of the correlation coefficient change in the normal state is determined;

[0125] According to the determined threshold range, fault diagnosis of the vacuum tube maglev transportation system is performed.

[0126] The system described above corresponds to the method described above Figure 1 The system described above corresponds to the method described above Figure 1 The system described above corresponds to the method described above

[0127] As can be seen from the above embodiments, the diagnostic method and diagnostic system described in the application can perform correlation analysis on test data from multiple dimensions of normal and fault, history and real time, maximize the implicit relationship between data and characteristic parameters, and solve the problem of fault detection and diagnosis of the super-high-speed low-vacuum tube maglev transportation system under the condition of no accurate theoretical model and lack of expert knowledge.

[0128] In the description of the application, it should be understood that the orientation words such as "front, rear, upper, lower, left, right", "transverse, vertical, perpendicular, horizontal" and "top, bottom" and the like indicate the orientation or positional relationship shown in the drawings, which are only for the convenience of describing the application and simplifying the description, and do not indicate and imply that the devices or elements referred to must have a particular orientation or be constructed and operated in a particular orientation, therefore cannot be understood as a limitation on the protection scope of the application; the orientation words "inner, outer" refer to the inner and outer of the contour of each component itself.

[0129] For the convenience of description, spatial relative terms such as "above", "upper", "on", "upper surface", "upper", etc. can be used herein to describe the spatial position relationship of one device or feature with other devices or features as shown in the drawings. It should be understood that the spatial relative terms are intended to include different orientations in use or operation in addition to the orientation of the device described in the drawings. For example, if the device in the drawing is inverted, the device described as "above" or "above" other devices or structures will be positioned "below" or "below" other devices or structures. Thus, the exemplary term "above" can include both "above" and "below" orientations. The device can also be positioned in other different ways (rotated 90 degrees or in other orientations), and the spatial relative descriptions used herein are interpreted accordingly.

[0130] In addition, it should be noted that the use of the words "first", "second", etc. to define parts only facilitates the differentiation of corresponding parts, and the above words have no special meaning unless otherwise stated, therefore cannot be understood as a limitation on the protection scope of the application.

[0131] The above descriptions are only the preferred embodiments of the present application, not intended to limit the present application. Any modification, equivalent replacement and improvement made within the spirit and principle of the present application should be included in the scope of the present application.

Claims

1. A method for fault diagnosis of a vacuum tube maglev transportation system, characterized in that: The method includes: Obtain relevant operating parameters of the maglev transportation system, including normal data and fault data; Preprocess relevant operating parameters to remove abnormal points and noise in them; Segmenting the relevant operating parameters according to different operating stages to obtain acceleration segmented data of the relevant operating parameters, uniform speed segmented data of the relevant operating parameters, and deceleration segmented data of the relevant operating parameters; Sliding segmentation is performed on the acceleration segmentation data of the relevant operating parameters, the uniform speed segmentation data of the relevant operating parameters, and the deceleration segmentation data of the relevant operating parameters according to a predetermined time interval and a predetermined step size to obtain a plurality of sliding segmentation data; Extract the corresponding time domain features and frequency domain features for each sliding segment; Using linear and nonlinear correlation analysis methods, correlation analysis is performed on each sliding segment data and the corresponding time domain features and frequency domain features to obtain a first correlation analysis result between every two different operating parameters in the relevant operating parameters and a second correlation analysis result between different sliding segment data of the same operating parameter; Performing fault diagnosis of the vacuum tube maglev transportation system according to the first correlation analysis result or the second correlation analysis result; The fault diagnosis of the vacuum tube maglev transportation system based on the first correlation analysis results includes: Comparing the first correlation analysis result of the normal data with the first correlation analysis result of the fault data to obtain sensitive parameters representing the fault; The correlation analysis results of sensitive parameters are used as training sets and test sets to train the convolutional neural network model and verify the model; Fault diagnosis of vacuum tube maglev transportation system based on the trained convolutional neural network model and verification model; The fault diagnosis of the vacuum tube maglev transportation system based on the second correlation analysis results includes: Determining a threshold range of a normal correlation coefficient change based on a correlation coefficient change trend of the second correlation analysis result; Fault diagnosis of the vacuum tube maglev transportation system is performed based on the determined threshold range.

2. The method according to claim 1, characterized in that Preprocessing the relevant operating parameters and removing abnormal points and noise in the relevant operating parameters includes: The 3σ principle is used to detect abnormal points in relevant operating parameters, and the detected abnormal points are removed through cubic spline interpolation and nearest neighbor interpolation methods; The wavelet threshold method is used to remove the noise of relevant operating parameters and obtain the denoised parameters.

3. The method according to claim 2, characterized in that The wavelet threshold method is used to remove the noise of relevant operating parameters, and the denoised parameters include: Perform wavelet transform on relevant operating parameters to obtain a set of wavelet coefficients; Perform threshold processing on the obtained set of wavelet coefficients to obtain estimated wavelet coefficients; Wavelet reconstruction is performed based on the estimated wavelet coefficients to obtain the denoised parameters.

4. A vacuum tube maglev transportation system fault diagnosis system, characterized in that: The system includes: An acquisition unit, configured to acquire relevant operating parameters of the maglev transportation system, the relevant operating parameters including normal data and fault data; A preprocessing unit, used to preprocess relevant operating parameters and remove abnormal points and noise in the relevant operating parameters; The first segmentation unit is used to segment the relevant operating parameters according to different operating stages to obtain acceleration segmentation data of the relevant operating parameters, uniform speed segmentation data of the relevant operating parameters, and deceleration segmentation data of the relevant operating parameters; a second segmentation unit, configured to perform sliding segmentation on the acceleration segmentation data of the relevant operating parameters, the uniform speed segmentation data of the relevant operating parameters, and the deceleration segmentation data of the relevant operating parameters according to a predetermined time interval and a predetermined step length, to obtain a plurality of sliding segmentation data; A feature extraction unit, configured to extract corresponding time domain features and frequency domain features for each sliding segment; a correlation analysis unit, configured to perform correlation analysis on each sliding segment data and the corresponding time domain features and frequency domain features using linear and nonlinear correlation analysis methods, to obtain a first correlation analysis result between every two different operating parameters in the relevant operating parameters and a second correlation analysis result between different sliding segment data of the same operating parameter; a fault diagnosis unit, configured to perform fault diagnosis on the vacuum tube maglev transportation system according to the first correlation analysis result or the second correlation analysis result; The fault diagnosis of the vacuum tube maglev transportation system based on the first correlation analysis results includes: Comparing the first correlation analysis result of the normal data with the first correlation analysis result of the fault data to obtain sensitive parameters representing the fault; The correlation analysis results of sensitive parameters are used as training sets and test sets to train the convolutional neural network model and verify the model; Fault diagnosis of vacuum tube maglev transportation system based on the trained convolutional neural network model and verification model; The fault diagnosis of the vacuum tube maglev transportation system based on the second correlation analysis results includes: Determining a threshold range of a normal correlation coefficient change based on a correlation coefficient change trend of the second correlation analysis result; Fault diagnosis of the vacuum tube maglev transportation system is performed based on the determined threshold range.

5. The system according to claim 4, characterized in that The preprocessing unit preprocesses the relevant operating parameters and removes abnormal points and noise in the relevant operating parameters, including: The 3σ principle is used to detect abnormal points in relevant operating parameters, and the detected abnormal points are removed through cubic spline interpolation and nearest neighbor interpolation methods; The wavelet threshold method is used to remove the noise of relevant operating parameters and obtain the denoised parameters.

6. The system according to claim 5, characterized in that The wavelet threshold method is used to remove the noise of relevant operating parameters, and the denoised parameters include: Perform wavelet transform on relevant operating parameters to obtain a set of wavelet coefficients; Perform threshold processing on the obtained set of wavelet coefficients to obtain estimated wavelet coefficients; Wavelet reconstruction is performed based on the estimated wavelet coefficients to obtain the denoised parameters.

Images