Online fault detection method and system for improving stability of propeller

By calculating the correlation coefficient and abnormal coefficient of the propeller during operation, adaptively adjusting the threshold for denoising, the problem of poor denoising effect in the fault detection of underwater thruster propeller is solved, and the accuracy of fault detection is improved.

CN118928701AActive Publication Date: 2024-11-12SHIHANG INTELLIGENT TECHNOLOGY (SUZHOU) CO LTD
View PDF 9 Cites 0 Cited by

Patent Information

Application Number
CN202410984841.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-22
Publication Date
2024-11-12
Estimated Expiration
2044-07-22

AI Technical Summary

Technical Problem

In the fault detection of underwater propeller propeller, the noise removal effect is poor, resulting in low detection accuracy and it is difficult to distinguish between actual faults and noises in fixed threshold settings.

Method used

By obtaining the monitoring data of each parameter during the propeller operation and navigation speed, calculating the actual correlation coefficient, dynamic factor value and fluctuation abnormal coefficient, adaptively adjusting the small wave dynamic threshold, and performing denoising processing to improve detection accuracy.

Benefits of technology

It significantly improves the accuracy of monitoring data after denoising, enhances the accuracy of fault detection, and avoids the confusion between noise interference and actual abnormalities.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118928701A_ABST
    Figure CN118928701A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of data processing, in particular to an online fault detection method and system for improving the stability of a propeller. The method comprises the following steps: acquiring an actual correlation coefficient between every two parameters according to monitoring data of each parameter; determining a dynamic factor value of each segment based on the sailing speed of the propeller; on the basis of the monitoring data of each parameter and the sailing speed of the propeller, a fluctuation abnormal coefficient of each data point is obtained; obtaining an abnormal suspicious coefficient of each data point based on the fluctuation abnormal coefficient, the dynamic factor value and the actual correlation coefficient; obtaining de-noised monitoring data according to the abnormal suspicious coefficient and the monitoring data of each parameter during the operation of the propeller; and performing fault detection on the denoised monitoring data to obtain a fault detection result. The objective of the invention is to solve the problem of low detection precision caused by poor denoising effect of propeller monitoring data in an existing detection method.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to an online fault detection method and system for improving thruster stability. Background Art

[0002] Underwater thrusters play a very important role as tools for underwater operations or as national defense weapons and equipment. With the development of marine strategy, various indicators of underwater thrusters must be improved accordingly, and reliability is particularly important. The propeller is one of the core components of the underwater thruster, and as an important part of the propulsion device, the reliability and safety of the propeller must be very high. Therefore, fault detection of the propeller in the underwater thruster is a crucial task.

[0003] At present, for the detection of propellers, sensors are installed to collect data during navigation, and then the navigation data of the propellers when working is processed by signal means. Conventional denoising for propellers usually uses wavelet thresholds, which decomposes the data and removes noise from different levels, thereby achieving a better denoising effect. However, due to the characteristics of the propeller equipment in the current scenario, the data itself has certain fluctuations, and the characteristics of the actual abnormalities reflected in the data are similar to the noise, both of which are abnormal fluctuations with large amplitudes. Usually, a fixed threshold set by artificial experience is used for wavelet threshold denoising, but if the threshold is set too high, it will cause data fluctuations for the actual fault, and then lose fault information, while if the threshold is too small, it will lead to poor noise removal. Summary of the invention

[0004] In order to solve the technical problem that conventional propeller monitoring data has poor denoising effect and low detection accuracy, the purpose of the present invention is to provide an online fault detection method and system for improving propeller stability. The technical solution adopted is as follows:

[0005] An online fault detection method for improving thruster stability, the method comprising:

[0006] Obtain monitoring data of each parameter of the propeller in the underwater propeller during operation and the navigation speed of the underwater propeller;

[0007] According to the monitoring data of each parameter, obtaining the actual correlation coefficient between every two parameters;

[0008] Based on the navigation speed of the propeller, determining the dynamic factor value of each segment of the data curve in the monitoring data of each parameter;

[0009] Based on the monitoring data of each parameter and the navigation speed of the propeller, the fluctuation anomaly coefficient of each data point in the monitoring data of each parameter is obtained;

[0010] Based on the fluctuation abnormal coefficient, the dynamic factor value and the actual correlation coefficient, the abnormal suspicious coefficient of each data point in each segment of each parameter is obtained;

[0011] Obtaining denoised monitoring data based on the abnormal suspicious coefficient and the monitoring data of each parameter during the operation of the propeller;

[0012] Fault detection is performed on the denoised monitoring data to obtain a fault detection result.

[0013] Preferably, the specific steps of obtaining the actual correlation coefficient between every two parameters according to the monitoring data of each parameter include:

[0014] According to the monitoring data of each parameter, confirm the Pearson coefficient of every two parameters in each identical segment and the cumulative value of the fitting deviation value of each parameter in each segment;

[0015] Based on the cumulative value of the Pearson coefficient of each two parameters in each segment and the fitting deviation value of each parameter in each segment, the actual correlation coefficient between each two parameters is obtained.

[0016] Preferably, the specific steps of confirming the Pearson coefficient of every two parameters in the same each segment and the cumulative value of the fitting deviation value of each parameter in each segment according to the monitoring data of each parameter include:

[0017] According to the monitoring data of each parameter, confirming a preliminary data curve formed by the monitoring data of each parameter;

[0018] Performing curve fitting processing on the preliminary data curve formed by the monitoring data of each parameter to obtain a monitoring data curve for each parameter;

[0019] Dividing the monitoring data curve of each parameter into segments, and confirming the Pearson coefficients of every two parameters in the same segments;

[0020] Based on the data points in the preliminary data curve formed by the monitoring data of each parameter and the data points in the monitoring data curve of each parameter, the cumulative value of the fitting deviation value of each parameter in each segment is obtained.

[0021] Preferably, based on the navigation speed of the propeller, the specific steps of confirming the dynamic factor value of each segment of the data curve in the monitoring data of each parameter include:

[0022] Based on the navigation speed of the propeller, obtaining speed data in each segment of the data curve in the monitoring data of each parameter;

[0023] Based on the speed data in each segment of the data curve in the monitoring data of each parameter, a dynamic factor value of each segment of the data curve in the monitoring data of each parameter is confirmed.

[0024] Preferably, based on the speed data in each segment of the data curve in the monitoring data of each parameter, the specific steps of confirming the dynamic factor value of each segment of the data curve in the monitoring data of each parameter include:

[0025] Based on the speed data in each segment of the data curve in the monitoring data of each parameter, obtaining the main component direction slope of the speed data in each segment and the accumulated value of the deviation value of the main component direction of the speed data in each segment;

[0026] Based on the accumulated value of the main component direction slope of the speed data in each segment and the deviation value of the main component direction of the speed data in each segment, the dynamic factor value of each segment of the data curve in the monitoring data of each parameter is obtained.

[0027] Preferably, based on the speed data in each segment of the data curve in the monitoring data of each parameter, the specific steps of obtaining the main component direction slope of the speed data in each segment and the accumulated value of the deviation value of the main component direction of the speed data in each segment include:

[0028] The principal component analysis algorithm is used to analyze and process the speed data in each segment of the data curve in the monitoring data of each parameter to obtain the principal component direction slope of the speed data in each segment and the accumulated value of the deviation value of the principal component direction of the speed data in each segment.

[0029] Preferably, the specific steps of obtaining the dynamic factor value of each segment of the data curve in the monitoring data of each parameter based on the accumulated value of the main component direction slope of the speed data in each segment and the main component direction deviation value of the speed data in each segment include:

[0030] The main component direction slope of the speed data in each segment and the accumulated value of the main component direction deviation value of the speed data in each segment are added together to obtain the dynamic factor value of each segment of the data curve in the monitoring data of each parameter.

[0031] Preferably, the specific steps of obtaining the abnormal suspicious coefficient of each data point in each segment in each parameter based on the fluctuation abnormal coefficient, the dynamic factor value and the actual correlation coefficient include:

[0032] The dynamic factor value and the actual correlation coefficient are respectively subjected to linear normalization processing to obtain a processed dynamic factor value and a processed actual correlation coefficient;

[0033] Based on the fluctuation anomaly coefficient, the processed dynamic factor value and the processed actual correlation coefficient, the abnormal suspicious coefficient of each data point in each segment in each parameter is obtained.

[0034] Preferably, the specific steps of obtaining the denoised monitoring data according to the abnormal suspicious coefficient and the monitoring data of each parameter during the operation of the propeller include:

[0035] Determining a wavelet dynamic threshold value according to the abnormal suspicious coefficient;

[0036] Based on the wavelet dynamic threshold, the monitoring data of each parameter during the operation of the propeller is denoised to obtain denoised monitoring data.

[0037] The present invention also provides an online fault detection system for improving propeller stability, comprising:

[0038] A data acquisition module, used to acquire monitoring data of each parameter of the propeller in the underwater propeller during operation and the navigation speed of the underwater propeller;

[0039] A first acquisition module, used for acquiring an actual correlation coefficient between every two parameters according to the monitoring data of each parameter;

[0040] A first confirmation module is used to confirm the dynamic factor value of each segment of the data curve in the monitoring data of each parameter based on the navigation speed of the propeller;

[0041] A second acquisition module is used to obtain a fluctuation anomaly coefficient of each data point in the monitoring data of each parameter based on the monitoring data of each parameter and the navigation speed of the propeller;

[0042] A second confirmation module is used to obtain an abnormal suspicious coefficient of each data point in each segment of each parameter based on the fluctuation abnormal coefficient, the dynamic factor value and the actual correlation coefficient;

[0043] A third acquisition module is used to obtain denoised monitoring data according to the abnormal suspicious coefficient and the monitoring data of each parameter when the propeller is running;

[0044] The detection module is used to perform fault detection on the denoised monitoring data to obtain a fault detection result.

[0045] The present invention has the following beneficial effects:

[0046] The present invention obtains the monitoring data of each parameter when the propeller in the underwater propeller is running and the navigation speed of the underwater propeller, and obtains the actual correlation coefficient between each two parameters according to the monitoring data of each parameter; based on the navigation speed of the propeller, confirms the dynamic factor value of each segment of the data curve in the monitoring data of each parameter; based on the monitoring data of each parameter and the navigation speed of the propeller, obtains the fluctuation abnormality coefficient of each data point in the monitoring data of each parameter; based on the fluctuation abnormality coefficient, the dynamic factor value and the actual correlation coefficient, obtains the abnormal suspicious coefficient of each data point in each segment of each parameter; according to the abnormal suspicious coefficient and the monitoring data of each parameter when the propeller is running, obtains the denoised monitoring data; performs fault detection on the denoised monitoring data to obtain the fault detection result. By obtaining the abnormal suspicious coefficient, the denoising of the monitoring data is completed, so as to realize the fault judgment of the denoised monitoring data. The present invention significantly improves the accuracy of the denoised monitoring data, thereby improving the detection accuracy of the fault. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0048] Figure 1 A flow chart of an online fault detection method for improving thruster stability provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0049] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of the online fault detection method and system for improving the stability of the thruster proposed by the present invention, its specific implementation method, structure, features and effects, in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0050] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0051] The specific scheme of an online fault detection method and system for improving thruster stability provided by the present invention is described in detail below in conjunction with the accompanying drawings.

[0052] When the propeller in the present invention is working underwater, it usually encounters faults such as foreign matter entanglement or blade damage. The manifestation of these faults is that the monitoring data is abnormal, which is reflected as abnormal fluctuations in the monitoring data, but the actual noise interference is also fluctuating. Therefore, in the case of confusion caused by noise interference, directly performing noise filtering by manually presetting empirical strength cannot achieve a good denoising effect.

[0053] When an actual abnormality occurs, for example, at the same speed, the torque increases abnormally and is unstable, the power consumption increases, or the vibration is unstable. That is, when an actual abnormality exists, it will be reflected in the parameters, and there is a correlation between different parameters, while the random interference of noise does not have a correlation. Therefore, the present invention analyzes the authenticity of the fluctuation through the correlation between multi-dimensional data, and adjusts the intensity of denoising based on the authenticity after analysis, thereby achieving denoising while retaining the information of the actual abnormality.

[0054] See also Figure 1 , which shows a flow chart of an online fault detection method for improving propeller stability provided by an embodiment of the present invention. The online fault detection method for improving propeller stability disclosed by the present invention comprises the following steps:

[0055] S100, obtaining the monitoring data of each parameter when the propeller is running and the navigation speed of the underwater propeller. In this embodiment, the monitoring data of each parameter when the propeller is running in the underwater propeller is obtained by installing sensors at various positions of the propeller and used to monitor the operating status of the propeller. The parameters specifically include: torque, speed, vibration and power data. The sampling accuracy of the monitoring data of each parameter can be adjusted by the specific implementer. In this embodiment, the sampling accuracy is 0.5 seconds. The sampled data is processed by standardization to obtain the monitoring data of each parameter and the navigation speed of the underwater propeller with the same timing characteristics and the elimination of dimensional differences.

[0056] S200: Obtaining an actual correlation coefficient between every two parameters according to the monitoring data of each parameter.

[0057] S300, based on the navigation speed of the propeller, confirm the dynamic factor value of each segment of the data curve in the monitoring data of each parameter.

[0058] S400, based on the monitoring data of each parameter and the navigation speed of the propeller, obtain the fluctuation anomaly coefficient of each data point in the monitoring data of each parameter.

[0059] S500: Based on the fluctuation abnormality coefficient, the dynamic factor value and the actual correlation coefficient, obtain the abnormal suspicious coefficient of each data point in each segment in each parameter.

[0060] S600: Obtain denoised monitoring data according to the abnormal suspicious coefficient and the monitoring data of each parameter during the operation of the propeller.

[0061] S700: Perform fault detection on the denoised monitoring data to obtain a fault detection result.

[0062] The present invention obtains the monitoring data of each parameter when the propeller in the underwater propeller is running and the navigation speed of the underwater propeller, and obtains the actual correlation coefficient between each two parameters according to the monitoring data of each parameter; based on the navigation speed of the propeller, confirms the dynamic factor value of each segment of the data curve in the monitoring data of each parameter; based on the monitoring data of each parameter and the navigation speed of the propeller, obtains the fluctuation abnormality coefficient of each data point in the monitoring data of each parameter; based on the fluctuation abnormality coefficient, the dynamic factor value and the actual correlation coefficient, obtains the abnormal suspicious coefficient of each data point in each segment of each parameter; according to the abnormal suspicious coefficient and the monitoring data of each parameter when the propeller is running, obtains the denoised monitoring data; performs fault detection on the denoised monitoring data to obtain the fault detection result. By obtaining the abnormal suspicious coefficient, the denoising of the monitoring data is completed, so as to realize the fault judgment of the denoised monitoring data. The present invention significantly improves the accuracy of the denoised monitoring data, thereby improving the detection accuracy of the fault.

[0063] In this embodiment, the strength of the correlation between each different parameter is different. In the same sequence, if a fluctuation of a certain monitoring data occurs, and the fluctuation intensity of the other parameters at the same time is very different from that of the parameter, the authenticity of the current fluctuation performance of the monitoring data is poor. Specifically, the specific steps of S200 include: according to the monitoring data of each parameter, confirming the Pearson coefficient of every two parameters in the same each segment and the cumulative value of the fitting deviation value of each parameter in each segment. This step is specifically: according to the monitoring data of each parameter, confirming the preliminary data curve formed by the monitoring data of each parameter.

[0064] The preliminary data curve formed by the monitoring data of each parameter is subjected to curve fitting processing to obtain the monitoring data curve of each parameter. In this embodiment, the preliminary data curve formed by the monitoring data of each parameter is subjected to curve fitting by the least squares fitting algorithm, wherein the order of the curve fitting is set to 5. The weak fluctuations in the preliminary data curve formed by the monitoring data of each parameter can be eliminated by the least squares fitting algorithm. At the same time, due to the characteristic difference between noise and actual abnormal fluctuations, the actual abnormal fluctuations are relatively long-lasting, while the noise is usually random and does not have persistence. Therefore, the interference of noise in the correlation can be removed to a certain extent by fitting.

[0065] The monitoring data curve of each parameter is divided into segments to confirm the Pearson coefficients of each two parameters in the same segment. In this embodiment, a fixed time length such as 5 minutes is set as a segment.

[0066] Based on the data points in the preliminary data curve formed by the monitoring data of each parameter and the data points in the monitoring data curve of each parameter, the cumulative value of the fitting deviation value of each parameter in each segment is obtained.

[0067] Based on the cumulative value of the Pearson coefficient of each two parameters in each segment and the fitting deviation value of each parameter in each segment, the actual correlation coefficient between each two parameters is obtained.

[0068] Specifically, taking the i-th parameter and the j-th parameter as examples, the calculation formula of the actual correlation coefficient is as follows:

[0069]

[0070] Among them, Q ij represents the actual correlation coefficient between the i-th parameter and the j-th parameter; q ijm represents the Pearson coefficient of the i-th parameter and the j-th parameter in the same segment m; w im represents the cumulative value of the fitting deviation value of the i-th parameter in the m-th segment; w jm represents the cumulative value of the fitting deviation value of the jth parameter in the mth segment; M represents the total number of segments in the monitoring data curve. When the propeller has an actual abnormality, although its abnormality is characterized by fluctuations, there is a certain trend, and it is not a mutation value. Therefore, even if the propeller has an abnormality, it will not deviate too much from the fitting trend when participating in the fitting. However, since the noise is completely contrary to the trend, its deviation value is relatively large. Therefore, the actual correlation coefficient is obtained by accumulating the deviation value as the weight of .

[0071] The specific steps of S300 include: based on the navigation speed of the propeller, obtaining speed data in each segment of the data curve in the monitoring data of each parameter.

[0072] Based on the speed data in each segment of the data curve in the monitoring data of each parameter, the dynamic factor value of each segment of the data curve in the monitoring data of each parameter is confirmed. In this step, based on the speed data in each segment of the data curve in the monitoring data of each parameter, the principal component direction slope of the speed data in each segment and the cumulative value of the deviation value of the principal component direction of the speed data in each segment are obtained. Specifically, the principal component analysis algorithm is used to analyze and process the speed data in each segment of the data curve in the monitoring data of each parameter, and the principal component direction slope of the speed data in each segment and the cumulative value of the deviation value of the principal component direction of the speed data in each segment are obtained. In this embodiment, the principal component analysis algorithm is a PCA principal component analysis algorithm.

[0073] Based on the accumulated value of the main component direction slope of the speed data in each segment and the deviation value of the main component direction of the speed data in each segment, the dynamic factor value of each segment of the data curve in the monitoring data of each parameter is obtained. Specifically, the accumulated value of the main component direction slope of the speed data in each segment and the deviation value of the main component direction of the speed data in each segment are added together to obtain the dynamic factor value of each segment of the data curve in the monitoring data of each parameter. The calculation formula of the dynamic factor value of each segment is as follows:

[0074] D m =0.5k m +0.5d m ;

[0075] Among them, D m represents the dynamic factor value of the mth segment; k m represents the principal component direction slope of the velocity data in the mth segment; d m Indicates the accumulated value of the deviation value of the principal component direction of the speed data in the mth segment. When the speed of the current propeller is not stable, such as when acceleration or deceleration occurs, and when the speed curve is not smooth, the current propeller body may be in a dynamic change state, and the parameters corresponding to the propeller itself should not be relatively stable. At this time, the possibility of abnormal performance corresponding to the same degree of fluctuation is relatively weak.

[0076] Specifically, in the specific steps of S500, based on the monitoring data of each parameter, the deviation value of the fitting of each data point in each segment of each parameter and the mean size of the local interval of each data point in each segment of each parameter and the data size of each data point are obtained, and based on the navigation speed of the propeller, the deviation value of the principal component direction of the speed data in each segment of each parameter is obtained. In this embodiment, any monitoring data point in any parameter is taken as the center of the local interval, and the size of the local interval is set to 5 seconds. Among them, the calculation formula of the fluctuation anomaly coefficient of each data point in each segment of each parameter is as follows:

[0077] f imng =softmax(w imng ×t imng );

[0078]

[0079] Among them, ε imn represents the fluctuation anomaly coefficient of the nth data point in the mth segment of the i-th parameter, Indicates the mean value of the local interval of the nth data point in the mth segment of the ith parameter, a imng Indicates the data size of the gth data point in the local interval of the nth data point in the mth segment of the i-th parameter. imng represents the participation weight of the g-th data point in the local interval of the n-th data point in the m-th segment in the i-th parameter. imng It represents the deviation value when the gth data point in the local interval of the nth data point in the mth segment of the i-th parameter participates in the fitting, t imng It represents the deviation value of the principal component direction of the velocity data in the same sequence corresponding to the g-th data point in the local interval of the n-th data point in the m-th segment in the i-th parameter, and G represents the total number of data points in the local interval of each data point.

[0080] Because propeller anomalies are usually unstable, they are often expressed through fluctuations. The stronger the fluctuation, the stronger the anomaly in the current time series. In this embodiment, the greater the fluctuation anomaly of the fluctuation anomaly coefficient, the more abnormal the data in the local interval centered on the current data point.

[0081] In this embodiment, the specific step of S500 includes: performing linear normalization processing on the dynamic factor value and the actual correlation coefficient respectively to obtain the processed dynamic factor value and the processed actual correlation coefficient.

[0082] Based on the fluctuation anomaly coefficient, the processed dynamic factor value and the processed actual correlation coefficient, the abnormal suspicious coefficient of each data point in each segment of each parameter is obtained. The calculation formula of the abnormal suspicious coefficient of each data point in each segment of each parameter is as follows:

[0083]

[0084] Among them, y imn represents the abnormal suspicious coefficient of the nth data point of the ith parameter in the mth segment, ε imn represents the fluctuation anomaly coefficient of the local interval of the nth data point of the ith parameter in the mth segment, ε jmn It represents the fluctuation anomaly coefficient of the local interval of the nth data point of the jth parameter in the mth segment. Q′ ij It represents the actual correlation coefficient between the i-th parameter and the j-th parameter after processing. I represents the total number of parameters, I-1>0, and (I-1)×D′ m > 0. D′ m Represents the dynamic factor value after processing in the mth segment. By calculating the fluctuation anomaly difference between the ith parameter and the remaining I-1 parameters in the same sequence, the larger the difference is, the more likely it is noise if there is no abnormal correlation between the parameters. At the same time, based on the actual correlation coefficient obtained, the larger the correlation coefficient is, the higher the credibility of the suspicious situation due to the fluctuation anomaly difference between different parameters. At the same time, the larger the dynamic factor value is, the more unstable the propeller body where the current propeller is located is, so the difference in fluctuation anomalies shown in multiple parameters may not be caused by noise, so the fluctuation anomaly coefficient of each data point is constrained.

[0085] In this embodiment, the fluctuation anomaly coefficients of each monitoring data point in each segment of each parameter are accumulated and then linearly normalized, and the result value after linear normalization is used as the accumulated value of the fluctuation anomaly coefficient corresponding to each segment of each parameter. The normalization range is the accumulated value of the fluctuation anomaly coefficients of multiple segments of the same parameter.

[0086] The specific steps of S600 include: determining a wavelet dynamic threshold according to the abnormal suspicious coefficient.

[0087] Based on the wavelet dynamic threshold, the monitoring data of each parameter during propeller operation is denoised to obtain the denoised monitoring data.

[0088] Specifically, the specific methods of adaptively setting the wavelet threshold through abnormal suspicious coefficients include the following two methods:

[0089] The first method: directly use the fluctuation anomaly coefficient Y in the mth segment of the i-th parameterim Perform wavelet threshold denoising on the monitoring data in the mth segment within the ith parameter.

[0090] The second method: Set the dynamic adjustment range. For example, set the minimum value of the dynamic adjustment range to 0.4, and the adjustment range is:

[0091] [0.4, 0.4+0.6×Y im ];

[0092] Among them, Y im It represents the cumulative value of the fluctuation anomaly coefficient in the mth segment of the i-th parameter. The adjustment range obtained at this time is 0.4~1.

[0093] You can choose any one of the above two methods.

[0094] At the same time, in step S700, the torque data analysis method, vibration data analysis method or speed data analysis method can be used to perform fault detection on the denoised monitoring data to obtain a fault detection result, so that the present invention significantly improves the accuracy of the data and further improves the accuracy of fault detection.

[0095] An online fault detection system for improving propeller stability provided by the present invention is described below. The online fault detection system for improving propeller stability described below and the online fault detection method for improving propeller stability described above can refer to each other.

[0096] The present invention also provides an online fault detection system for improving thruster stability, comprising a data acquisition module, a first acquisition module, a first confirmation module, a second acquisition module, a second confirmation module, a third acquisition module and a detection module.

[0097] The data acquisition module is used to obtain the monitoring data of each parameter of the propeller in the underwater propeller when it is running and the navigation speed of the underwater propeller.

[0098] The first acquisition module is used to acquire the actual correlation coefficient between every two parameters according to the monitoring data of each parameter.

[0099] The first confirmation module is used to confirm the dynamic factor value of each segment of the data curve in the monitoring data of each parameter based on the navigation speed of the propeller.

[0100] The second acquisition module is used to obtain the fluctuation anomaly coefficient of each data point in the monitoring data of each parameter based on the monitoring data of each parameter and the navigation speed of the propeller.

[0101] The second confirmation module is used to obtain the abnormal suspicious coefficient of each data point in each segment in each parameter based on the fluctuation abnormal coefficient, the dynamic factor value and the actual correlation coefficient.

[0102] The third acquisition module is used to obtain the denoised monitoring data according to the abnormal suspicious coefficient and the monitoring data of each parameter when the propeller is running.

[0103] The detection module is used to perform fault detection on the denoised monitoring data to obtain a fault detection result.

[0104] In this embodiment, the first acquisition module is specifically used to confirm the Pearson coefficient of every two parameters in each of the same segments and the cumulative value of the fitting deviation value of each parameter in each segment according to the monitoring data of each parameter. This step specifically includes:

[0105] According to the monitoring data of each parameter, a preliminary data curve formed by the monitoring data of each parameter is confirmed.

[0106] A curve fitting process is performed on the preliminary data curve formed by the monitoring data of each parameter to obtain a monitoring data curve of each parameter.

[0107] The monitoring data curve of each parameter is divided into sections, and the Pearson coefficients of every two parameters in the same sections are confirmed.

[0108] Based on the data points in the preliminary data curve formed by the monitoring data of each parameter and the data points in the monitoring data curve of each parameter, the cumulative value of the fitting deviation value of each parameter in each segment is obtained.

[0109] Based on the cumulative value of the Pearson coefficient of each two parameters in each segment and the fitting deviation value of each parameter in each segment, the actual correlation coefficient between each two parameters is obtained.

[0110] The second acquisition module is specifically used to acquire speed data in each segment of the data curve in the monitoring data of each parameter based on the navigation speed of the propeller.

[0111] Based on the speed data in each segment of the data curve in the monitoring data of each parameter, the dynamic factor value of each segment of the data curve in the monitoring data of each parameter is confirmed. This step specifically includes: based on the speed data in each segment of the data curve in the monitoring data of each parameter, the principal component direction slope of the speed data in each segment and the cumulative value of the deviation value of the principal component direction of the speed data in each segment are obtained. Among them, this step specifically includes: using the principal component analysis algorithm, the speed data in each segment of the data curve in the monitoring data of each parameter is analyzed and processed, and the principal component direction slope of the speed data in each segment and the cumulative value of the deviation value of the principal component direction of the speed data in each segment are obtained.

[0112] Based on the accumulated value of the main component direction slope of the speed data in each segment and the deviation value of the main component direction of the speed data in each segment, the dynamic factor value of each segment of the data curve in the monitoring data of each parameter is obtained. Wherein, this step specifically includes: adding the accumulated value of the main component direction slope of the speed data in each segment and the deviation value of the main component direction of the speed data in each segment to obtain the dynamic factor value of each segment of the data curve in the monitoring data of each parameter.

[0113] The second confirmation module is specifically used to perform linear normalization processing on the dynamic factor value and the actual correlation coefficient respectively to obtain a processed dynamic factor value and a processed actual correlation coefficient;

[0114] Based on the fluctuation anomaly coefficient, the processed dynamic factor value and the processed actual correlation coefficient, the abnormal suspicious coefficient of each data point in each segment in each parameter is obtained.

[0115] The third acquisition module is specifically used to determine the wavelet dynamic threshold according to the abnormal suspicious coefficient.

[0116] Based on the wavelet dynamic threshold, the monitoring data of each parameter during the operation of the propeller is denoised to obtain denoised monitoring data.

[0117] It should be noted that the sequence of the above embodiments of the present invention is for description only and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0118] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

Claims

1. An online fault detection method for improving propeller stability, characterized in that: The method comprises: Obtain monitoring data of each parameter of the propeller in the underwater propeller during operation and the navigation speed of the underwater propeller; According to the monitoring data of each parameter, obtaining the actual correlation coefficient between every two parameters; Based on the navigation speed of the propeller, determining the dynamic factor value of each segment of the data curve in the monitoring data of each parameter; Based on the monitoring data of each parameter and the navigation speed of the propeller, the fluctuation anomaly coefficient of each data point in the monitoring data of each parameter is obtained; Based on the fluctuation abnormal coefficient, the dynamic factor value and the actual correlation coefficient, the abnormal suspicious coefficient of each data point in each segment of each parameter is obtained; Obtaining denoised monitoring data based on the abnormal suspicious coefficient and the monitoring data of each parameter during the operation of the propeller; Fault detection is performed on the denoised monitoring data to obtain a fault detection result.

2. The online fault detection method for improving propeller stability according to claim 1, characterized in that: According to the monitoring data of each parameter, the specific steps of obtaining the actual correlation coefficient between every two parameters include: According to the monitoring data of each parameter, confirm the Pearson coefficient of every two parameters in each identical segment and the cumulative value of the fitting deviation value of each parameter in each segment; Based on the cumulative value of the Pearson coefficient of each two parameters in each segment and the fitting deviation value of each parameter in each segment, the actual correlation coefficient between each two parameters is obtained.

3. The online fault detection method for improving propeller stability according to claim 2, characterized in that: The specific steps of confirming the Pearson coefficient of each two parameters in the same each segment and the cumulative value of the fitting deviation value of each parameter in each segment according to the monitoring data of each parameter include: According to the monitoring data of each parameter, confirming a preliminary data curve formed by the monitoring data of each parameter; Performing curve fitting processing on the preliminary data curve formed by the monitoring data of each parameter to obtain a monitoring data curve for each parameter; Dividing the monitoring data curve of each parameter into segments, and confirming the Pearson coefficients of every two parameters in the same segments; Based on the data points in the preliminary data curve formed by the monitoring data of each parameter and the data points in the monitoring data curve of each parameter, the cumulative value of the fitting deviation value of each parameter in each segment is obtained.

4. The online fault detection method for improving propeller stability according to claim 1, characterized in that: Based on the navigation speed of the propeller, the specific steps of confirming the dynamic factor value of each segment of the data curve in the monitoring data of each parameter include: Based on the navigation speed of the propeller, obtaining speed data in each segment of the data curve in the monitoring data of each parameter; Based on the speed data in each segment of the data curve in the monitoring data of each parameter, a dynamic factor value of each segment of the data curve in the monitoring data of each parameter is confirmed.

5. The online fault detection method for improving propeller stability according to claim 4, characterized in that: The specific steps of confirming the dynamic factor value of each segment of the data curve in the monitoring data of each parameter based on the speed data in each segment of the data curve in the monitoring data of each parameter include: Based on the speed data in each segment of the data curve in the monitoring data of each parameter, obtaining the main component direction slope of the speed data in each segment and the accumulated value of the deviation value of the main component direction of the speed data in each segment; Based on the accumulated value of the main component direction slope of the speed data in each segment and the deviation value of the main component direction of the speed data in each segment, the dynamic factor value of each segment of the data curve in the monitoring data of each parameter is obtained.

6. The online fault detection method for improving propeller stability according to claim 5, characterized in that: Based on the speed data in each segment of the data curve in the monitoring data of each parameter, the specific steps of obtaining the main component direction slope of the speed data in each segment and the accumulated value of the deviation value of the main component direction of the speed data in each segment include: The principal component analysis algorithm is used to analyze and process the speed data in each segment of the data curve in the monitoring data of each parameter to obtain the principal component direction slope of the speed data in each segment and the accumulated value of the deviation value of the principal component direction of the speed data in each segment.

7. The online fault detection method for improving propeller stability according to claim 5, characterized in that: The specific steps of obtaining the dynamic factor value of each segment of the data curve in the monitoring data of each parameter based on the main component direction slope of the speed data in each segment and the accumulated value of the main component direction deviation value of the speed data in each segment include: The main component direction slope of the speed data in each segment and the accumulated value of the main component direction deviation value of the speed data in each segment are added together to obtain the dynamic factor value of each segment of the data curve in the monitoring data of each parameter.

8. The online fault detection method for improving propeller stability according to claim 1, characterized in that: Based on the fluctuation abnormal coefficient, the dynamic factor value and the actual correlation coefficient, the specific steps of obtaining the abnormal suspicious coefficient of each data point in each segment of each parameter include: The dynamic factor value and the actual correlation coefficient are respectively subjected to linear normalization processing to obtain a processed dynamic factor value and a processed actual correlation coefficient; Based on the fluctuation anomaly coefficient, the processed dynamic factor value and the processed actual correlation coefficient, the abnormal suspicious coefficient of each data point in each segment in each parameter is obtained.

9. The online fault detection method for improving propeller stability according to claim 1, characterized in that: The specific steps of obtaining the denoised monitoring data according to the abnormal suspicious coefficient and the monitoring data of each parameter during the operation of the propeller include: Determining a wavelet dynamic threshold value according to the abnormal suspicious coefficient; Based on the wavelet dynamic threshold, the monitoring data of each parameter during the operation of the propeller is denoised to obtain denoised monitoring data.

10. An online fault detection system for improving propeller stability, characterized in that: include: A data acquisition module, used to acquire monitoring data of each parameter of the propeller in the underwater propeller during operation and the navigation speed of the underwater propeller; A first acquisition module, used for acquiring an actual correlation coefficient between every two parameters according to the monitoring data of each parameter; A first confirmation module is used to confirm the dynamic factor value of each segment of the data curve in the monitoring data of each parameter based on the navigation speed of the propeller; A second acquisition module is used to obtain a fluctuation anomaly coefficient of each data point in the monitoring data of each parameter based on the monitoring data of each parameter and the navigation speed of the propeller; A second confirmation module is used to obtain an abnormal suspicious coefficient of each data point in each segment of each parameter based on the fluctuation abnormal coefficient, the dynamic factor value and the actual correlation coefficient; A third acquisition module is used to obtain denoised monitoring data according to the abnormal suspicious coefficient and the monitoring data of each parameter when the propeller is running; The detection module is used to perform fault detection on the denoised monitoring data to obtain a fault detection result.

Citation Information

Patent Citations

  • Autonomous underwater vehicle propeller fault diagnosis method based on improved isometric feature mapping algorithm ISOMAP

    CN108830218A

  • Fault detection method based on correlation probability model

    CN110348150A

  • On-line monitoring method and system for running state of magnetic driving pump

    CN116255344A

  • Intelligent regulation and control system for underground coal mine emulsification pump station based on data enhancement

    CN116335925A

  • Multi-source sensing information fusion and expansion method based on system state characterization

    CN116383615A