Hydraulic motor wear monitoring method and system

Abstract

The invention discloses a hydraulic motor abrasion monitoring method and system, and belongs to the technical field of abrasion fault prediction.The method specifically comprises the steps that multi-dimensional data signals of a hydraulic motor are collected in real time and preprocessed; the preprocessed multi-dimensional data of the hydraulic motor are processed, the early wear characteristics of the hydraulic motor are extracted, and the processing comprises decomposition of the preprocessed multi-dimensional data of the hydraulic motor, construction of a decomposition tree, reservation of nodes with preset frequency in the decomposition tree, and reconstruction, difference calculation and window moving average suppression of the reserved nodes; fusing the early wear characteristics of the hydraulic motor, and generating a comprehensive health index through a dimension reduction algorithm; judging whether the hydraulic motor has early-stage fine wear or not according to the comparison of the comprehensive health index and a dynamic threshold value, and giving an alarm according to a judgment result; according to the method, early-stage fine wear signs of the hydraulic motor can be found, a maintenance plan is made in advance, and production interruption caused by sudden equipment failures is avoided.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of wear failure prediction, and particularly relates to a hydraulic motor wear monitoring method and system. BACKGROUND

[0002] Hydraulic motors are widely used in engineering machinery, ships, metallurgy and many other fields, and undertake important tasks of power output and braking during equipment operation. Due to long-term operation under high load and complex working conditions, internal parts of the hydraulic motor, such as the piston, sealing element and brake pad, are prone to wear. Wear can cause equipment performance degradation, such as reduced hydraulic motor output torque, unstable rotation speed and other problems, and can even cause equipment failure, production interruption and safety accidents. Traditional wear monitoring mainly relies on manual periodic disassembly inspection, which is labor-intensive, costly and unable to monitor the wear condition of the equipment in real time, and often the wear is found to be serious.

[0003] The existing hydraulic motor wear monitoring method is inefficient and not timely, and cannot meet the real-time and accurate monitoring needs of the equipment. Manual disassembly inspection can affect the normal operation of the equipment and is difficult to find early signs of wear. In addition, there is a lack of effective analysis means for wear changes under different working conditions, which is not conducive to formulating maintenance plans in advance and is difficult to ensure reliable operation of the equipment. SUMMARY

[0004] To overcome the shortcomings of the prior art, the application provides a hydraulic motor wear monitoring method and system based on differential signal features and multi-sensor fusion online monitoring to achieve high sensitivity identification of early wear.

[0005] To achieve the above purpose, the application provides the following technical solutions:

[0006] The hydraulic motor wear monitoring method comprises:

[0007] Real-time acquisition of hydraulic motor multi-dimensional data signals and preprocessing;

[0008] Processing of the preprocessed hydraulic motor multi-dimensional data to extract early wear features of the hydraulic motor, including time domain features and frequency domain features, the processing comprising decomposition of the preprocessed hydraulic motor multi-dimensional data, construction of a decomposition tree, reservation of nodes at a preset frequency in the decomposition tree, and reconstruction, differential calculation and window moving average suppression of the reserved nodes;

[0009] Fusion of the early wear features of the hydraulic motor to generate a comprehensive health index through a dimension reduction algorithm;

[0010] Comparison of the comprehensive health index with a dynamic threshold to determine whether the hydraulic motor has early and subtle wear, and alarm according to the determination result.

[0011] Specifically, the pre-processed hydraulic motor multi-dimensional data is processed to extract early wear characteristics of the hydraulic motor, including:

[0012] The pre-processed hydraulic motor multi-dimensional data signal is filtered according to a preset digital band-pass filter, phase distortion is eliminated, and the waveform characteristics of the hydraulic motor multi-dimensional data signal are retained;

[0013] The band-pass filtered hydraulic motor multi-dimensional data signal is decomposed to retain the hydraulic motor multi-dimensional data signal of a preset frequency;

[0014] The hydraulic motor multi-dimensional data signal of the preset frequency is subjected to difference calculation, and the window moving average suppression is performed on the difference calculation result to suppress numerical jitter;

[0015] The time domain characteristics and frequency domain characteristics of the hydraulic motor multi-dimensional data signal after window moving average are extracted, the time domain characteristics include peak value, root mean square, skewness, kurtosis, and the frequency domain characteristics include frequency band energy ratio, spectral entropy and main frequency.

[0016] Specifically, the band-pass filtered hydraulic motor multi-dimensional data signal is decomposed to retain the hydraulic motor multi-dimensional data signal of a preset frequency, including:

[0017] Set the mother wavelet, determine the decomposition layer number L according to the sampling rate and the target bandwidth;

[0018] The band-pass filtered hydraulic motor multi-dimensional data signal is decomposed and layered, the root node is initialized at the 0th layer, filtering and downsampling are performed at the same time to generate 2 child nodes, at the 2nd layer, filtering and downsampling are performed on each node respectively to generate 4 child nodes, and the process is repeated to the Lth layer to form 2 L The end nodes, and a decomposition tree is constructed;

[0019] The nodes of the preset frequency in the decomposition tree are retained and reconstructed to obtain the hydraulic motor multi-dimensional data signal of the preset frequency.

[0020] Specifically, the hydraulic motor multi-dimensional data signal of the preset frequency is subjected to difference calculation, and the window moving average suppression is performed on the difference calculation result to suppress numerical jitter, including:

[0021] Select a difference operator to perform difference calculation on each sampling point in the hydraulic motor multi-dimensional data signal of the preset frequency, and process the first and last points by using the same boundary extension or directly discarding the first and last samples;

[0022] Set the window half-width M to satisfy 2M+1∈[5,11], and perform moving average calculation on the difference calculation result according to the window half-width;

[0023] The normalized result of the moving average calculation is obtained as a window moving average hydraulic motor multi-dimensional data signal.

[0024] Specifically, the early wear characteristics of the hydraulic motor are fused, and a comprehensive health index is generated through a dimension reduction algorithm, including:

[0025] The time domain features and frequency domain features of the window moving average hydraulic motor multi-dimensional data signal are spliced by column to obtain a feature fusion matrix;

[0026] The covariance matrix of the feature fusion matrix is calculated, the eigenvalue decomposition is performed on the covariance matrix, the first k principal components are selected in descending order of eigenvalue size, and a projection matrix is obtained;

[0027] The feature fusion matrix is projected onto the first principal component to obtain a first comprehensive health index;

[0028] A bottleneck network is constructed, the feature fusion matrix is input into the bottleneck network, the training target of the bottleneck network is set to minimize the reconstruction error, and the reconstruction error output by the bottleneck network is taken as a second comprehensive health index;

[0029] The minimum value of the first comprehensive health index and the second comprehensive health index is selected as the final comprehensive health index.

[0030] Specifically, the comparison between the comprehensive health index and the dynamic threshold is used to determine whether the hydraulic motor has early fine wear, and an alarm is given according to the determination result, including:

[0031] The comprehensive health index sequence within a preset time under an idle condition is collected after the hydraulic motor is first put into operation or maintenance, an initial comprehensive health index threshold is set, the initial comprehensive health index threshold is updated in real time within the preset time to obtain a comprehensive health index threshold, and a linear fitting slope k of the comprehensive health index within the preset time is calculated.

[0032] When the final comprehensive health index is greater than the comprehensive health index threshold, it is determined that the wear interval is entered, and a first-level alarm is triggered;

[0033] The linear fitting slope k of the final comprehensive health index at A time points is calculated A If k A > k and continuously lasts for B sampling periods, it is determined that the hydraulic motor has early fine wear, and a second-level alarm is triggered.

[0034] Specifically, the hydraulic motor multi-dimensional data signal includes: vibration signal, pressure signal, temperature data, acoustic signal and abrasive particle concentration; the preprocessing includes: denoising, normalization, compensation correction and space-time synchronization;

[0035] The denoising is used for removing noise in the vibration signal and the pressure signal.

[0036] The normalization is used for normalizing the abrasive grain concentration.

[0037] The compensation correction is used for compensating and correcting the temperature data.

[0038] The space-time synchronization is used for processing time stamps corresponding to the multi-dimensional data signals of the hydraulic motor to a unified time grid, and establishing a space mapping relationship between the physical positions of the sensors and the structure of the hydraulic motor.

[0039] The hydraulic motor wear monitoring system is used for implementing the hydraulic motor wear monitoring method, and comprises a data processing module, an early feature extraction module, a score generation module and a comparison and determination module.

[0040] The data processing module is used for collecting the multi-dimensional data signals of the hydraulic motor in real time and performing preprocessing.

[0041] The early feature extraction module is used for processing the preprocessed multi-dimensional data of the hydraulic motor, extracting early wear features of the hydraulic motor, including time domain features and frequency domain features, and the processing includes decomposing the preprocessed multi-dimensional data of the hydraulic motor, constructing a decomposition tree, retaining nodes of a preset frequency in the decomposition tree, and performing reconstruction, difference calculation and window moving average suppression.

[0042] The score generation module is used for fusing the early wear features of the hydraulic motor, and generating a comprehensive health index through a dimension reduction algorithm.

[0043] The comparison and determination module determines early and subtle wear of the hydraulic motor and alarms according to comparison of the comprehensive health index and a dynamic threshold.

[0044] Specifically, the early feature extraction module comprises a decomposition unit, a difference suppression unit and a feature extraction unit.

[0045] The decomposition unit decomposes the multi-dimensional data signals of the hydraulic motor after band pass filtering, and retains the multi-dimensional data signals of the hydraulic motor of a preset frequency.

[0046] The difference suppression unit is used for performing difference calculation on the multi-dimensional data signals of the hydraulic motor of the preset frequency, and performing window moving average suppression on the difference calculation result to suppress numerical jitter.

[0047] The feature extraction unit is used for extracting time domain features and frequency domain features of the multi-dimensional data signals of the hydraulic motor after window moving average.

[0048] Specifically, the score generation module comprises a feature fusion unit, a first score generation unit, a second score generation unit and a final score generation unit.

[0049] The feature fusion unit is configured to splice the time domain features and the frequency domain features of the window moving average hydraulic motor multidimensional data signal by column to obtain a feature fusion matrix.

[0050] The first score generation unit is configured to calculate a covariance matrix of the feature fusion matrix, perform eigenvalue decomposition on the covariance matrix, select the first k principal components in descending order of eigenvalue to obtain a projection matrix, project the feature fusion matrix to the first principal component to obtain a first comprehensive health index.

[0051] The second score generation unit is configured to construct a bottleneck network, input the feature fusion matrix into the bottleneck network, set the training target of the bottleneck network as minimizing the reconstruction error, and take the reconstruction error output by the bottleneck network as a second comprehensive health index.

[0052] The final score generation unit is configured to select the minimum value of the first comprehensive health index and the second comprehensive health index as a final comprehensive health index.

[0053] Compared with the prior art, the present application has the following advantages:

[0054] The present application provides a hydraulic motor wear monitoring method and system, which uses high-frequency band-pass filtering and wavelet packet decomposition to capture transient high-frequency signals generated by wear, extracts features such as peak value and kurtosis through a difference method, significantly improves the early wear identification ability, and quantifies the comprehensive health index. According to the comparison of the comprehensive health index and the dynamic threshold, based on the fitting slope and the cycle, it is determined whether to enter the wear period or to occur early and subtle wear, the early and subtle wear of the hydraulic motor is accurately identified and graded alarm, the risk of equipment downtime caused by sudden failure of the hydraulic motor is reduced, and the operation safety and production efficiency are improved. BRIEF DESCRIPTION OF DRAWINGS

[0055] Figure 1 The present application provides a hydraulic motor wear monitoring method flow chart;

[0056] Figure 2 The present application provides an early feature extraction flow chart;

[0057] Figure 3 The present application provides an early wear determination schematic diagram;

[0058] Figure 4 The present application provides a hydraulic motor wear monitoring system architecture diagram. DETAILED DESCRIPTION

[0059] The application will be described in detail below with reference to specific embodiments. The following embodiments will help those skilled in the art to further understand the application, but are not intended to limit the application in any form. It should be noted that those skilled in the art can make several modifications and improvements without departing from the concept of the application. These are all within the scope of protection of the application.

[0060] In order to make the purpose, technical scheme and advantages of the application more clear, the application will be further described in detail below with reference to the drawings and examples. It should be understood that the specific examples described herein are only used to explain the application and do not limit the application.

[0061] It should be noted that the various features in the embodiments of the application can be combined with each other without conflict, and are within the scope of protection of the application. In addition, although the functional modules are divided in the device schematic diagram, and the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order from the module division in the device or the order in the flowchart. In addition, the "first", "second", "third" and the like used in the application do not limit the data and execution order, but only distinguish the same items or similar items with basically the same function and effect.

[0062] Unless otherwise defined, all technical and scientific terms used in the specification have the same meaning as understood by those skilled in the art to which the application belongs. The terms used in the specification of the application are only for the purpose of describing the specific embodiments of the application, and are not intended to limit the application. The term "and / or" used in the specification includes any and all combinations of one or more related listed items.

[0063] Example 1

[0064] Please refer to Figures 1-3 The application provides a hydraulic motor wear monitoring method, which comprises the following specific steps:

[0065] Step S1: install vibration, pressure, temperature, acoustic and abrasive particle concentration sensors at key parts of the hydraulic motor, collect real-time multi-dimensional data signals of the hydraulic motor, and perform pretreatment;

[0066] In this embodiment, pressure sensors are installed at the inlet and outlet flanges to monitor minute pulsations and sudden changes in oil pressure in real time. Early wear causes slight changes in the geometry of the flow channel, resulting in characteristic pressure fluctuations at high frequencies. Vibration sensors are installed on the side plate of the housing near the main bearing. A metal bracket is welded first, and then the sensor is fixed with a magnetic base to ensure good coupling and easy maintenance and replacement. This sensor is used to detect high-frequency vibrations in the motor housing caused by the minute wear of internal components (gears, bearings). Temperature sensors are used to monitor changes in oil temperature. Early wear friction can cause local temperature rises. Acoustic sensors are used to capture high-frequency acoustic emission signals, such as ultrasonic waves generated by minute cracks, cavitation, or metal friction. Abrasive particle concentration sensors are used to monitor changes in the concentration of wear particles in the oil, and abnormal wear stages are determined by sudden changes in the number of abrasive particles.

[0067] The preprocessing includes: noise reduction, normalization, compensation correction, and spatiotemporal synchronization;

[0068] Denoising includes: performing three-level wavelet decomposition on the original vibration signal to obtain detail coefficients and approximation coefficients for different frequency bands; applying an adaptive threshold adjustment mechanism to each level of detail coefficients to retain effective signals in the high-frequency band, taking into account the non-stationary characteristics of the wear signal; reconstructing the denoised signal, calculating the kurtosis enhancement factor, and verifying the denoising effect; the specific denoising formula is as follows: Where w'(t) represents the denoised vibration signal, w(t) represents the original vibration signal, including the wear signal (effective signal) and the noise signal, λ represents the correction coefficient, σ represents the noise standard deviation, T represents the total duration of the denoised vibration signal, t represents the current time, i.e., the time point in the vibration signal sequence, used to dynamically adjust the threshold at the current time, and sgn() represents the sign function, used to determine the positive or negative sign of the vibration signal. This represents the time factor, which monotonically decreases from approaching infinity to as t increases. A nonlinear attenuation curve is formed, and the noise sensitivity and noise standard deviation are adjusted by the correction coefficient to adapt to different noise levels under different working conditions. The time factor matches the non-stationary characteristics of the wear signal, forming a dynamic adaptive threshold strategy. This solves the problem that traditional fixed thresholds cannot take into account both early weak signal detection and later noise suppression. It is especially suitable for extracting weak impact signals in the early stage of hydraulic motor wear.

[0069] Normalization is performed by collecting normal operating data of the motor under four typical operating conditions: no load, 30% load, 60% load, and full load (each operating condition lasts for 30 minutes with no obvious wear). The mean and standard deviation of abrasive particle concentration under each operating condition are calculated and processed using a normalization formula to eliminate the influence of oil flow fluctuations under different loads or oil temperatures on the abrasive particle concentration detection value.

[0070] The pressure signal is noise-removed using a filter, and the temperature signal is compensated and corrected.

[0071] Spatiotemporal synchronization: Add timestamps with microsecond accuracy to the data of each sensor, process the timestamps to a unified time grid, and establish a spatial mapping relationship between the physical location of the sensor and the structure of the hydraulic motor.

[0072] Step S2: Process the preprocessed multi-dimensional data of the hydraulic motor to extract the early wear characteristics of the hydraulic motor;

[0073] like Figure 2 As shown, the specific steps of step S2 are as follows:

[0074] Step S201: Filter the preprocessed hydraulic motor multi-dimensional data signal according to the preset digital bandpass filter to eliminate phase distortion and retain the waveform characteristics of the hydraulic motor multi-dimensional data signal;

[0075] It should be noted that finite impulse response digital bandpass filters are typically used to preserve the target frequency band and eliminate phase distortion. For hydraulic motors, the 5–50 kHz frequency band contains the high-frequency impact response caused by wear and is the main frequency domain region for wear identification.

[0076] Step S202: Decompose the multi-dimensional data signal of the hydraulic motor after bandpass filtering and retain the multi-dimensional data signal of the hydraulic motor at a preset frequency;

[0077] The specific steps of step S202 are as follows:

[0078] Step S2021: Set the mother wavelet and select the number of decomposition layers L according to the sampling rate and target bandwidth;

[0079] Specifically, such as Figure 2 As shown, Figure 2 The left side shows the signal decomposition hierarchy diagram, which shows that the filtered multi-dimensional data signal of the hydraulic motor is decomposed into multiple frequencies using the mother wavelet. The signal is divided into different frequency band sub-signals layer by layer. The mother wavelet is set to db4, the number of decomposition layers L=4, the 100kHz bandwidth is subdivided into 16, and the models between 5-50kHz are selectively retained to ensure the time domain positioning accuracy.

[0080] Step S2022: Decompose and layer the multi-dimensional data signal of the hydraulic motor after bandpass filtering. Initialize the root node in layer 0, and simultaneously filter and downsample the low and high frequencies to generate 2 child nodes. In layer 2, filter and downsample each node again to generate 4 child nodes. Repeat this process until layer L, forming 2 L Build a decomposition tree from the last node;

[0081] like Figure 2 As shown, Figure 2The middle left part is a decomposition tree structure diagram. Sub-nodes corresponding to the 5-50 kHz frequency band are selected from the decomposition tree for reservation to construct the decomposition tree.

[0082] Step S2023: Reserving nodes of the preset frequency in the decomposition tree and reconstructing to obtain the hydraulic motor multi-dimensional data signal of the preset frequency.

[0083] Specifically, as shown in FIG. 5, according to the sampling rate and the number of layers, sub-nodes corresponding to the 5-50 kHz frequency band are selected from the decomposition tree for reservation, and a reconstruction operation is performed on the selected nodes to accurately isolate the target frequency band, eliminate interference components irrelevant to wear, reserve signal parts most characteristic of wear response, discard irrelevant sub-bands, and eliminate background information related to the normal running state of the hydraulic motor but irrelevant to wear. Figure 2 Step S203: Performing difference calculation on the hydraulic motor multi-dimensional data signal of the reserved preset frequency, and performing window moving average suppression on the difference calculation result to suppress high-frequency value jitter;

[0084] The specific steps of step S203 are as follows:

[0085] Step S2031: Selecting a difference operator to perform difference calculation on each sampling point in the hydraulic motor multi-dimensional data signal of the preset frequency, processing the first and last points, and using the same boundary continuation or directly discarding the first and last samples;

[0086] In this embodiment, the difference operator includes forward difference, central difference and high-order difference. The purpose of difference calculation is to amplify the instantaneous change rate, highlight the sharp peaks or mutations caused by wear, and facilitate the detection of edge events.

[0087] For each sampling point in the reconstructed target frequency band signal sequence, a difference operator is applied to obtain a new sequence. After signal reconstruction in

[0088] a slight upward or mutation part can be observed, and the slope of the mutation area is increased by difference. Figure 2 Step S2032: Setting the window half-width as M, satisfying 2M+1∈[5,11], and performing moving average calculation on the difference calculation result according to the window half-width;

[0089] In this embodiment, as shown in FIG. 6, after the waveform after signal reconstruction is differentiated, a slight difference is observed, indicating that there is a local peak; in the moving average calculation and normalization stage, the signal is smoothed by window sliding, so that the mutation remains, but the noise edge is suppressed, and the output signal presents a smoother change trend.

[0090] Figure 2

[0091] ​​Step S2033: Normalize the result of the moving average calculation to obtain the window moving average hydraulic motor multi-dimensional data signal.

[0092] In this embodiment, Figure 2 The lower right is the window moving average noise reduction and normalized multi-dimensional data. After difference, moving average and normalization processing, the signal not only retains the wear trend, but also eliminates the amplitude difference between multiple channels, avoids the amplitude difference between different frequency bands or sensor channel signals interfering with feature extraction, and unifies the data scale of each channel.

[0093] The benefit of step S203 is that the transient changes caused by wear are amplified and extracted with low complexity and minimal delay, improving the sensitivity and reliability of feature discrimination.

[0094] Step S204: Extract the time domain features and frequency domain features of the window moving average hydraulic motor multi-dimensional data signal, the time domain features including peak value, root mean square, skewness, kurtosis, the frequency domain features including frequency band energy ratio, spectral entropy and main frequency.

[0095] In this embodiment, the peak value is calculated as the difference between the maximum value and the minimum value in each window, amplifying the transient impact amplitude and sensitively capturing the maximum vibration or pressure fluctuation caused by wear spikes; the root mean square measures the overall energy level of the signal, reflecting the average strength of continuous friction or abrasive particle impact; the skewness describes the waveform asymmetry, distinguishing between positive or negative mutations and identifying unilateral wear impact earlier; the kurtosis captures occasional spikes, and the high-amplitude pulse caused by the collision of small abrasive particles can significantly increase the kurtosis value.

[0096] The frequency band energy ratio is the energy of each sub-band; the spectral entropy measures the complexity of the spectral distribution, and the random high-frequency component caused by early micro-cracks or cavitation will increase; the main frequency is the frequency corresponding to the highest peak in the power spectrum.

[0097] The features extracted in step S204 constitute the input matrix of the subsequent comprehensive health assessment model. In actual application, these statistical features can sensitively reflect the small changes in wear, especially in the early stage, and have better diagnostic effect than manual inspection.

[0098] Step S3: Fuse the early wear features of the hydraulic motor to generate a comprehensive health index through dimension reduction algorithm.

[0099] The specific steps of step S3 are:

[0100] Step S301: Concatenate the time domain features and frequency domain features of the window moving average hydraulic motor multi-dimensional data signal by column to obtain a feature fusion matrix.

[0101] Step S302: Calculate the covariance matrix of the feature fusion matrix, perform eigenvalue decomposition on the covariance matrix, select the first k principal components in descending order of eigenvalue size to obtain the projection matrix;

[0102] Specifically, the covariance matrix of the feature fusion matrix is ​​constructed, eigenvalue decomposition is performed on the covariance matrix, and the original feature fusion matrix is ​​linearly transformed through the principal component matrix to obtain the dimensionality-reduced feature representation. The projection matrix is ​​constructed by selecting the first k principal components.

[0103] Step S303: Project the feature fusion matrix onto the first principal component to obtain the first comprehensive health index;

[0104] In this embodiment, Principal Component Analysis (PCA) performs eigenvalue decomposition on the covariance matrix, selects the k directions with the largest variance, projects the high-dimensional data into a low-dimensional subspace, reduces the dimensionality of the feature fusion matrix, retains only the principal components with the largest variance, and removes low-variance signals. The first principal component carries the largest variance information among all the original features and serves as the first comprehensive health indicator, which can most sensitively reflect state changes.

[0105] Step S304: Construct a bottleneck network, input the feature fusion matrix into the bottleneck network, set the bottleneck network training objective to minimize the reconstruction error, and use the reconstruction error output by the bottleneck network as the second comprehensive health indicator.

[0106] In this embodiment, the bottleneck network is constructed as follows: a three-layer fully connected network is constructed, consisting of an input layer, a bottleneck layer, and an output layer; the activation function is ReLU, and the output layer is linearly activated; the input feature fusion matrix is ​​used, and the reconstruction error is calculated for any input window feature, and a reconstruction error sequence is obtained for all windows. Abnormal samples have poor reconstruction ability because they have not seen similar patterns, resulting in a significant increase in error. This can sensitively locate early micro-damage. Step S304 can capture nonlinear and coupled abnormal patterns in the original feature matrix that cannot be expressed by PCA, and amplify the small deviations caused by early wear into quantifiable reconstruction errors, which can then be used as a second comprehensive health indicator.

[0107] Step S305: Select the minimum value of the first comprehensive health index and the second comprehensive health index as the final comprehensive health index.

[0108] Specifically, the minimum value between the first and second comprehensive health indicators is selected to more promptly determine whether early wear has occurred, thus providing higher sensitivity and reliability for online fault early warning of hydraulic motors.

[0109] Step S4: Based on the comparison of comprehensive health indicators and dynamic thresholds, determine early minor wear and trigger an alarm.

[0110] like Figure 3 As shown, the specific steps of step S4 are as follows:

[0111] Step S401: After the hydraulic motor is put into operation for the first time or after maintenance, collect the comprehensive health index sequence within a preset time under no-load conditions, set the initial comprehensive health index threshold, update the initial comprehensive health index threshold in real time within the preset time to obtain the comprehensive health index threshold, and calculate the linear fitting slope k of the comprehensive health index within the preset time.

[0112] Specifically, there is no wear under no-load conditions after the initial commissioning or maintenance, so the value within this period is used as the threshold, including the linear fitting slope k.

[0113] Step S402: When the final comprehensive health index is greater than the comprehensive health index threshold, it is determined that the wear range has been entered, and a level one alarm is triggered;

[0114] Step S403: Calculate the linear fitting slope k of the final comprehensive health index at A time points. A If k A If the value is greater than k and continues for B sampling cycles, it is determined that the hydraulic motor has experienced early minor wear, triggering a level two alarm.

[0115] In this embodiment, a single threshold alarm can detect deviations in health indicators in a timely manner, but it is prone to false alarms due to short-term noise or transient fluctuations. Combining trend analysis can confirm the continuous upward trend of health indicators. The slope of the continuous rise can capture the trend inflection point before the health indicators exceed the threshold significantly, distinguishing between occasional pulses and true early minor wear and tear, and achieving earlier intervention. The dual strategy can achieve rapid response and high-confidence early warning, while suppressing false alarms.

[0116] exist Figure 3 In this context, A is set to 3. Those skilled in the art can adjust the value according to actual conditions. There exists a linear fitting slope k for the final comprehensive health index at the most recent A time points. A >k, but not a continuous B sampling period, so it does not meet the condition for early fine wear of the hydraulic motor. The points within the dashed box are the most recent A points. Calculate the slope of the data corresponding to these A time points. When k appears within a continuous B sampling period... A When the value is greater than k, early minor wear of the hydraulic motor is determined to have occurred; that is, the first point in B consecutive sampling cycles indicates early minor wear of the hydraulic motor. Because data fluctuations exist, and existing monitoring methods are inefficient and inaccurate, this application enables the detection of early minor wear signs within a very short period, providing maintenance personnel with ample time to develop reasonable maintenance plans and avoiding production interruptions due to sudden equipment failures. This reduces maintenance costs, improves equipment reliability and lifespan, ensures the continuity and safety of production processes in related industries, and enhances enterprise production efficiency.

[0117] Embodiment 2

[0118] Please refer to Figure 4 In another embodiment, the application provides a hydraulic motor wear monitoring system, comprising a data processing module, an early feature extraction module, a score generation module and a comparison and determination module.

[0119] The data processing module is configured to collect and pre-process the multi-dimensional data signals of the hydraulic motor in real time.

[0120] The early feature extraction module is configured to process the pre-processed multi-dimensional data of the hydraulic motor to extract early wear features of the hydraulic motor, including time domain features and frequency domain features.

[0121] The score generation module is configured to fuse the early wear features of the hydraulic motor and generate a comprehensive health index through a dimension reduction algorithm.

[0122] The comparison and determination module is configured to compare the comprehensive health index with a dynamic threshold to determine early and subtle wear of the hydraulic motor and issue an alarm.

[0123] The early feature extraction module comprises a decomposition unit, a difference suppression unit and a feature extraction unit.

[0124] The decomposition unit uses wavelet packets to decompose the band-pass filtered multi-dimensional data signals of the hydraulic motor and retains the multi-dimensional data signals of the hydraulic motor at a preset frequency.

[0125] The difference suppression unit is configured to perform difference calculation on the multi-dimensional data signals of the hydraulic motor at the preset frequency and perform window moving average suppression on the difference calculation results to suppress high-frequency value jitter.

[0126] The feature extraction unit is configured to extract the time domain features and frequency domain features of the window moving average processed multi-dimensional data signals of the hydraulic motor.

[0127] The score generation module comprises a feature fusion unit, a first score generation unit, a second score generation unit and a final score generation unit.

[0128] The feature fusion unit is configured to concatenate the time domain features and frequency domain features of the window moving average processed multi-dimensional data signals of the hydraulic motor by column to obtain a feature fusion matrix.

[0129] The first score generation unit is configured to calculate a covariance matrix of the feature fusion matrix, perform eigenvalue decomposition on the covariance matrix, select the first k principal components in descending order of eigenvalues, obtain a projection matrix, project the feature fusion matrix to the first principal component, and obtain a first comprehensive health index;

[0130] The second score generation unit is configured to construct a bottleneck network, input the feature fusion matrix into the bottleneck network, set a training target of the bottleneck network as minimizing a reconstruction error, and take the reconstruction error output by the bottleneck network as a second comprehensive health index.

[0131] The final score generation unit is configured to select a minimum value of the first comprehensive health index and the second comprehensive health index as a final comprehensive health index.

[0132] In addition, the parts of the above technical solutions provided in the embodiments of the present application that are consistent with the implementation principles of the corresponding technical solutions in the prior art are not described in detail to avoid excessive redundancy.

[0133] The specific embodiments described above further illustrate the objects, technical solutions and advantages of the present application. It should be understood that the above description is only a specific embodiment of the present application and is not intended to limit the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A method of hydraulic motor wear monitoring, characterised by, The method comprises the following steps: Real-time acquisition of multi-dimensional data signals of the hydraulic motor and pre-processing; Processing of the pre-processed multi-dimensional data of the hydraulic motor, extraction of early wear features of the hydraulic motor, including time domain features and frequency domain features, the processing comprising decomposition of the pre-processed multi-dimensional data of the hydraulic motor, construction of a decomposition tree, reservation of nodes of a preset frequency in the decomposition tree, and reconstruction, difference calculation and window moving average suppression of the reserved nodes; Fusion of the early wear features of the hydraulic motor, generation of a comprehensive health index through a dimension reduction algorithm; Comparison of the comprehensive health index with a dynamic threshold value to determine whether the hydraulic motor has early and subtle wear, and alarm according to the determination result.

2. The hydraulic motor wear monitoring method of claim 1, wherein, The processing of the pre-processed multi-dimensional data of the hydraulic motor to extract the early wear features of the hydraulic motor comprises: Filtering of the pre-processed multi-dimensional data signals of the hydraulic motor according to a preset digital band-pass filter to eliminate phase distortion and retain the waveform features of the multi-dimensional data signals of the hydraulic motor; Decomposition of the band-pass filtered multi-dimensional data signals of the hydraulic motor to retain the multi-dimensional data signals of the hydraulic motor of a preset frequency; Difference calculation of the multi-dimensional data signals of the hydraulic motor of the preset frequency, and window moving average suppression of the difference calculation results to suppress numerical jitter; Extraction of the time domain features and the frequency domain features of the window moving average processed multi-dimensional data signals of the hydraulic motor, the time domain features including peak value, root mean square, skewness and kurtosis, and the frequency domain features including frequency band energy ratio, spectral entropy and main frequency.

3. The hydraulic motor wear monitoring method of claim 2, wherein, The decomposition of the band-pass filtered multi-dimensional data signals of the hydraulic motor to retain the multi-dimensional data signals of the hydraulic motor of a preset frequency comprises: Setting a mother wavelet, determining the decomposition layer number L according to the sampling rate and the target bandwidth; The multi-dimensional data signal of the hydraulic motor after band-pass filtering is decomposed and layered, a root node is initialized at the 0th layer, filtering and down-sampling are performed at the same time, 2 sub-nodes are generated, at the 2nd layer, filtering and down-sampling are performed on each node respectively, 4 sub-nodes are generated, and the process is repeated to the Lth layer, 2 L end nodes are formed, and a decomposition tree is constructed; Reserving nodes of a preset frequency in the decomposition tree and reconstructing to obtain the multi-dimensional data signals of the hydraulic motor of the preset frequency.

4. The hydraulic motor wear monitoring method of claim 2, wherein, The difference calculation of the multi-dimensional data signals of the hydraulic motor of the preset frequency and the window moving average suppression of the difference calculation results to suppress numerical jitter comprise: Selecting a difference operator to perform difference calculation on each sampling point in the multi-dimensional data signals of the hydraulic motor of the preset frequency, and using boundary extension or direct rejection to process the first and last points; Setting a window half-width M satisfying 2M+1∈[5,11], and performing moving average calculation on the difference calculation results according to the window half-width; Normalizing the results of the moving average calculation to obtain the window moving average processed multi-dimensional data signals of the hydraulic motor.

5. The hydraulic motor wear monitoring method of claim 1, wherein, The fusion of the early wear features of the hydraulic motor and the generation of the comprehensive health index through the dimension reduction algorithm comprise: Concatenating the time domain features and the frequency domain features of the window moving average processed multi-dimensional data signals of the hydraulic motor by column to obtain a feature fusion matrix; Calculating the covariance matrix of the feature fusion matrix, performing eigenvalue decomposition on the covariance matrix, and selecting the first k principal components in descending order of eigenvalue to obtain a projection matrix; Projecting the feature fusion matrix to the first principal component to obtain a first comprehensive health index; The feature fusion matrix is input into the bottleneck network, a training target of the bottleneck network is set to minimize the reconstruction error, and the reconstruction error output by the bottleneck network is taken as the second comprehensive health index; The minimum value of the first comprehensive health index and the second comprehensive health index is taken as the final comprehensive health index.

6. The hydraulic motor wear monitoring method of claim 5, wherein, The comparison between the comprehensive health index and the dynamic threshold value is used to determine whether the hydraulic motor has early and slight wear, and an alarm is given according to the determination result, including: The comprehensive health index sequence within a preset time under an idle condition is collected after the hydraulic motor is first put into operation or maintained, an initial comprehensive health index threshold value is set, the initial comprehensive health index threshold value is updated in real time within the preset time to obtain a comprehensive health index threshold value, and a linear fitting slope k of the comprehensive health index within the preset time is calculated; When the final comprehensive health index is greater than the comprehensive health index threshold value, it is determined that the wear interval is entered, and a first-level alarm is triggered; calculating a linear fitting slope k of the final comprehensive health index of A time points A , if k A > k and continuously lasts for B sampling periods, it is determined that the hydraulic motor has early fine wear, triggering a secondary alarm.

7. The hydraulic motor wear monitoring method of claim 1, wherein, The multi-dimensional data signal of the hydraulic motor includes vibration signals, pressure signals, temperature data, acoustic signals and abrasive particle concentration; The preprocessing includes denoising, normalization, compensation correction and space-time synchronization; The denoising is used to remove noise in the vibration signals and the pressure signals; The normalization is used to normalize the abrasive particle concentration; The compensation correction is used to perform compensation correction processing on the temperature data; The space-time synchronization is used to process the time stamps corresponding to the multi-dimensional data signal of the hydraulic motor to a unified time grid, and establish a spatial mapping relationship between the physical positions of the sensors and the structure of the hydraulic motor.

8. A hydraulic motor wear monitoring system for implementing the hydraulic motor wear monitoring method of any one of claims 1-7, characterized by, It includes: A data processing module, an early feature extraction module, a score generation module and a comparison and determination module; The data processing module is used to collect the multi-dimensional data signal of the hydraulic motor in real time and perform preprocessing; The early feature extraction module is used to process the preprocessed multi-dimensional data of the hydraulic motor to extract early wear features of the hydraulic motor; The score generation module is used to fuse the early wear features of the hydraulic motor and generate a comprehensive health index through a dimension reduction algorithm; The comparison and determination module is used to determine whether the hydraulic motor has early and slight wear according to the comparison between the comprehensive health index and the dynamic threshold value, and give an alarm according to the determination result.

9. The hydraulic motor wear monitoring system of claim 8, wherein, The early feature extraction module includes a decomposition unit, a difference suppression unit and a feature extraction unit; The decomposition unit decomposes the band-pass filtered multi-dimensional data signal of the hydraulic motor to retain the multi-dimensional data signal of the hydraulic motor at a preset frequency; The difference suppression unit is used to perform difference calculation on the multi-dimensional data signal of the hydraulic motor at the preset frequency, and perform window moving average suppression on the difference calculation result to suppress numerical fluctuation; The feature extraction unit is used to extract the time domain features and frequency domain features of the window moving averaged multi-dimensional data signal of the hydraulic motor.

10. The hydraulic motor wear monitoring system of claim 9, wherein, The score generation module includes a feature fusion unit, a first score generation unit, a second score generation unit and a final score generation unit; The feature fusion unit is used to splice the time domain features and frequency domain features of the window moving averaged multi-dimensional data signal of the hydraulic motor by column to obtain a feature fusion matrix; The first score generation unit is configured to calculate a covariance matrix of the feature fusion matrix, perform eigenvalue decomposition on the covariance matrix, select the first k principal components in descending order of eigenvalues, obtain a projection matrix, project the feature fusion matrix to the first principal component, and obtain a first comprehensive health index; The second score generation unit is configured to construct a bottleneck network, input the feature fusion matrix into the bottleneck network, set a training target of the bottleneck network as minimizing a reconstruction error, and take the reconstruction error output by the bottleneck network as a second comprehensive health index. The final score generation unit is configured to select a minimum value of the first comprehensive health index and the second comprehensive health index as a final comprehensive health index.

Images