Bridge support sliding plate wear condition monitoring method and system

Abstract

The invention discloses a bridge support sliding plate wear condition monitoring method and system. The method comprises the following steps: S100, selecting a sliding plate material which is the same as that in a support, dividing the sliding plate material into a plurality of samples, dividing the samples into a plurality of groups, carrying out a wear test on a testing machine, marking a training label according to a test result, and collecting test data to form a comparison database; s200, a force transducer, an acoustic emission sensor and a data collector are arranged on a middle lining plate of the support, and stress data of the support and abrasion data of the sliding plate are collected; s300, analyzing and processing the support stress data and the sliding plate wear data to obtain monitoring data, calling corresponding test data from a comparison database, and comparing the two pieces of data; and S400, according to a comparison result, calling a training label in the test data, and outputting the training label as the wear condition of the support sliding plate. According to the bridge support sliding plate wear condition monitoring method and system, the actual wear degree of the sliding plate can be accurately judged, the wear evaluation precision is improved, and safe and stable operation of the support is ensured.

Description

Technical Field

[0001] The present invention belongs to the technical field of bridge monitoring, and more specifically, relates to a method and system for monitoring the wear condition of a bridge bearing slide plate. Background Art

[0002] In the structure of a large-span cable bridge, the main beam is always in a high-frequency and low-amplitude motion state under the action of temperature loads, vehicle loads, wind loads, etc. The large daily cumulative displacement leads to frequent excessive wear of the sliding wear-resistant plates of the bearings. Excessive wear of the sliding wear-resistant plates of the bearings is a common problem in large-span cable bridges. Excessive wear of the sliding wear-resistant plates will cause steel-to-steel friction in the bearings, significantly increase the friction resistance of the bearings, and even change the force system of the bridge structure, causing a significant adverse effect on the normal service condition of the bridge.

[0003] The thickness of the exposed wear of the bearing sliding wear plate is generally 3mm. At present, the wear condition of the exposed thickness of the slide plate mainly relies on manual on-site inspection, and the exposed thickness of the slide plate is measured by a feeler gauge. The results of manual feeler gauge inspection usually have certain subjectivity, uncertainty in the inspection position and timeliness of the inspection results, which leads to the detection and evaluation of the wear condition of the bearing sliding wear plate is not objective and comprehensive, and is prone to misjudgment and missed judgment. Especially in large-span cable bridges, the bearings are usually tension and compression bearings. When the bearings are stretched during service, the exposed thickness of the slide plate measured by the feeler gauge will increase, resulting in distorted measurement results. At present, due to the limitations of manual inspection of the exposed thickness of the slide plate, it is impossible to accurately and real-time evaluate the service working condition of the bearing slide plate, which is not conducive to the later management and maintenance of the bearings of large-span cable bridges.

[0004] Therefore, a method and system for monitoring the wear condition of bridge bearing slides is needed. By monitoring the wear condition of the exposed thickness of the bearing slides through a data signal acquisition system, the service working status of the bearing slides can be intuitively and conveniently known in real time, thereby achieving comprehensive real-time monitoring of the service condition of the bearing sliding wear-resistant plate and ensuring the operation of the bearing throughout its life cycle. Summary of the invention

[0005] In response to the above defects or improvement needs of the prior art, the present invention provides a method and system for monitoring the wear condition of a bridge bearing slide. By conducting wear tests on samples of different materials and establishing a comparative database, and installing multiple sensors in the actual use environment to collect real operating data, an accurate assessment of the wear condition of the bearing slide is achieved. By utilizing comparative analysis technology, the test data is matched with the on-site monitoring data, and combined with preset training labels, the actual degree of wear of the slide can be accurately determined, thereby improving the accuracy of wear assessment and providing effective technical support for the timely detection and prevention of bearing failures, thereby helping to ensure the safe and stable operation of related facilities.

[0006] To achieve the above objectives, according to a first aspect of an embodiment of the present invention, a method for monitoring the wear condition of a bridge bearing slide plate is provided, comprising the following steps:

[0007] S100, select the same skateboard material as that in the support, divide the skateboard material into multiple samples and then divide them into multiple groups, conduct a wear test on each group of samples on a testing machine, mark training labels according to the test results, and collect all test data to form a comparison database;

[0008] S200, a force sensor, an acoustic emission sensor and a data collector are arranged on the middle lining plate of the support to collect the force and the wear data of the slide plate during the working process of the support;

[0009] S300, analyzing and processing the bearing force and slide wear data to obtain monitoring data, calling corresponding test data from a comparison database, and comparing the monitoring data with the test data;

[0010] S400: Based on the comparison result, call the training label in the test data as the wear condition output of the support slide.

[0011] Furthermore, step S100 specifically includes the following steps:

[0012] S110, the wear stage of the slide plate is divided into three stages: initial normal sliding wear, mid-term dry friction and late steel-to-steel friction;

[0013] S120, selecting the same slide material as that in the support, dividing the slide material into a plurality of samples and then into a plurality of large sample groups, and each large sample group is further divided into three small sample groups;

[0014] S130, providing characteristics of three wear stages for the samples in the three small sample groups in each large sample group, and then performing wear tests on each large sample group according to different characteristic parameters;

[0015] S140, using an acoustic emission sensor to collect and record AE signal data of each sample, and using wavelet packet transform to filter and perform eigenvalue analysis on the collected AE signal;

[0016] S150, integrate the data obtained from the analysis, label the samples with different test results with training labels, and collect the test data of all samples to form a comparison database.

[0017] Furthermore, step S140 specifically includes the following steps:

[0018] S141, preprocessing the collected AE signal data including DC bias and filtering, and then selecting a suitable wavelet basis according to the characteristics of the AE signal data;

[0019] S142, selecting the number of signal decomposition layers according to the frequency bandwidth and frequency resolution of the AE signal data, and decomposing the AE signal data into AE sub-signals of multiple frequency bands;

[0020] S143. Extract experimental features useful for evaluating the wear state of the slide plate from each AE sub-signal, and combine the extracted features into an experimental feature vector.

[0021] Furthermore, in step S142, the AE signal data decomposition process is as follows:

[0022]

[0023] Among them, cA j [k] is the approximate coefficient of the jth layer of the low-frequency part,

[0024] cD j [k is the detail coefficient of the jth layer of the high frequency part,

[0025] h[n] is the impulse response of the low-pass filter,

[0026] g[n] is the impulse response of the high-pass filter,

[0027] x[n] is the input signal,

[0028] k is the index of the sub-signal.

[0029] For multi-layer decomposition, each layer of decomposition will produce two sub-signals, specifically:

[0030]

[0031]

[0032] Furthermore, in step S143, the extracted test features include energy features E i , root mean square characteristic RMS i And the kurtosis characteristic K i , the energy characteristic E i for:

[0033]

[0034] Among them, c i [n] is the coefficient of the i-th sub-signal.

[0035] The root mean square characteristic RMS i for:

[0036]

[0037] Wherein, N is the length of the sub-signal;

[0038] The kurtosis characteristic K i for:

[0039]

[0040] Among them, μ i is the mean of the ith sub-signal.

[0041] Furthermore, the test feature vector F is composed of the energy feature E i , root mean square characteristic RMS i And the kurtosis characteristics are combined, specifically:

[0042] F=[E1,E2,...,E n ,RMS1,RMS2,...,RMS n , K1, K i2 , ..., K n ] T .

[0043] Furthermore, step S300 specifically includes:

[0044] S310, after processing the slide wear data according to the method in step S140, obtain monitoring data, and select the monitoring feature vector F from the monitoring data. mon ;

[0045] S320, based on the monitoring feature vector F mon And the experimental feature vector F is used to calculate the distance metric and similarity metric between the two;

[0046] S330, using the obtained distance metric and similarity metric and a weighted fusion method to comprehensively score the monitored data;

[0047] S340. According to the comprehensive score, the closest sample is found from the comparison database, and the wear label of the sample is used as the result of the monitoring data.

[0048] Furthermore, in step S320, the distance metric dF mon , F) is the Euclidean distance d O (F mon , F) or Mahalanobis distance d M (F mon , F), the Euclidean distance d O (F mon , F) is:

[0049]

[0050] Among them, m is the dimension of the test feature vector;

[0051]

[0052] Where S is the covariance matrix of the experimental eigenvectors.

[0053] The mean μ of the sample feature vector in the comparison database is:

[0054]

[0055] The similarity measure is the cosine similarity sim(F mon , F i ), specifically:

[0056]

[0057] Furthermore, in step S330, the comprehensive score S i Specifically:

[0058] S i =w d ·d(F mon , F i )+w s ·(1-sim(F mon , F i )),

[0059] Among them, w d and w s are the weights of distance metric and similarity metric respectively, and w d +w s =1.

[0060] In step S340, the evaluation based on the comprehensive score is:

[0061]

[0062] Among them, L best is the wear label of the closest specimen found in the comparison database.

[0063] According to a second aspect of an embodiment of the present invention, a bridge bearing slide wear condition monitoring system is provided, comprising:

[0064] Test module: used to select the same skateboard material as the support, divide the skateboard material into multiple samples and then into multiple groups. Each group of samples is subjected to abrasion test on the testing machine, and training labels are marked according to the test results. All test data are collected to form a comparison database;

[0065] Data acquisition module: used to configure a force sensor, an acoustic emission sensor and a data collector on the middle lining plate of the support to collect the force and slide wear data during the working process of the support;

[0066] Data processing module: used to obtain monitoring data after analyzing and processing the bearing force and slide wear data, call the corresponding test data from the comparison database, and compare the monitoring data with the test data;

[0067] Output module: used to call the training labels in the test data according to the comparison results and output the wear condition of the support slide;

[0068] Prediction module: used to establish a machine learning model, which is trained to predict the wear status of the skateboard based on the sample data in the comparison database.

[0069] In general, the above technical solutions conceived by the present invention can achieve the following beneficial effects compared with the prior art:

[0070] 1. The monitoring method of the present invention, by conducting wear tests on samples of different materials and establishing a comparative database, combined with installing a variety of sensors in the actual use environment to collect real operating data, realizes an accurate assessment of the wear condition of the bearing slide. By using comparative analysis technology, the test data is matched with the on-site monitoring data, and combined with preset training labels, the actual degree of wear of the slide can be accurately determined, thereby improving the accuracy of wear assessment and providing effective technical support for the timely detection and prevention of bearing failures, which helps to ensure the safe and stable operation of related facilities.

[0071] 2. The monitoring method of the present invention, by refining the three stages of skateboard wear and designing a specific wear test for each stage, comprehensively simulates the wear process of the skateboard in actual use, combines the acoustic emission sensor to collect AE signals, and uses the wavelet packet transform technology for signal processing, thereby ensuring high-precision identification of wear characteristics, helping to timely discover early signs of skateboard wear, prevent the occurrence of major safety accidents, and ensure safe and efficient operation of equipment.

[0072] 3. The monitoring method of the present invention matches the closest sample wear label from the comparison database according to the score, which can not only quickly and accurately identify the specific wear stage of the skateboard, but also effectively predict potential failures, providing a scientific basis for timely maintenance measures, thereby ensuring the safe and stable operation of the equipment, reducing unplanned downtime and maintenance costs, and improving overall operational efficiency.

[0073] 4. The monitoring method of the present invention establishes a machine learning model and uses the sample data in the comparison database for training, so that the model can accurately predict the wear state of the skateboard and learn the complex characteristics of different wear stages, so as to detect signs of wear earlier in practical applications, timely warn of potential faults, optimize maintenance plans, reduce losses caused by sudden failures, and improve the operating safety and economic benefits of the equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0074] Figure 1 A schematic flow chart of a method for monitoring the wear condition of a bridge bearing slide plate according to an embodiment of the present invention;

[0075] Figure 2 This is a specific flow chart of step S100 in a method for monitoring the wear condition of a bridge bearing slide plate according to an embodiment of the present invention;

[0076] Figure 3 This is a specific flow chart of step S140 in a method for monitoring the wear condition of a bridge bearing slide plate according to an embodiment of the present invention;

[0077] Figure 4 The figure is a specific flow chart of step S300 in a method for monitoring the wear condition of a bridge bearing slide plate according to an embodiment of the present invention. DETAILED DESCRIPTION

[0078] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention. In addition, the technical features involved in the various embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0079] As the bearings are put into service, the wear of the bearing slide plate can be mainly divided into the initial normal sliding wear condition, the mid-term dry friction condition after the silicone grease is worn out, and the late stage steel-to-steel friction condition after the slide plate is worn out. The initial wear stage is mainly the friction loss condition of the slide plate under silicone grease lubrication. The friction coefficient is small in this stage, and the wear amount is usually small; the mid-term wear stage is mainly the dry friction loss condition of the bearing slide plate and the stainless steel plate in the friction pair when the silicone grease in the slide plate grease tank is exhausted. The friction coefficient increases in this stage, and the wear amount increases accordingly; the late wear stage is mainly manifested as the steel-to-steel friction of the friction pair after the exposed thickness of the slide plate is worn out. The friction coefficient increases significantly in this stage, and the wear of the slide plate is more serious.

[0080] Example 1

[0081] like Figure 1 As shown, an embodiment of the present invention provides a method for monitoring the wear condition of a bridge bearing slide plate, which specifically includes the following steps:

[0082] S100, select the same skateboard material as that in the support, divide the skateboard material into multiple samples and then divide them into multiple groups, conduct a wear test on each group of samples on a testing machine, mark training labels according to the test results, and collect all test data to form a comparison database;

[0083] S200, a force sensor, an acoustic emission sensor and a data collector are arranged on the middle lining plate of the support to collect the force and the wear data of the slide plate during the working process of the support;

[0084] S300, analyzing and processing the bearing force and slide wear data to obtain monitoring data, calling corresponding test data from a comparison database, and comparing the monitoring data with the test data;

[0085] S400: Based on the comparison result, call the training label in the test data as the wear condition output of the support slide.

[0086] like Figure 2 As shown, step S100 specifically includes the following steps:

[0087] S110, the wear stage of the slide plate is divided into three stages: initial normal sliding wear, mid-term dry friction and late steel-to-steel friction;

[0088] S120, selecting the same slide material as that in the support, dividing the slide material into a plurality of samples and then into a plurality of large sample groups, and each large sample group is further divided into three small sample groups;

[0089] S130, providing characteristics of three wear stages for the samples in the three small sample groups in each large sample group, and then performing wear tests on each large sample group according to different characteristic parameters;

[0090] S140, using an acoustic emission sensor to collect and record AE signal data of each sample, and using wavelet packet transform to filter and perform eigenvalue analysis on the collected AE signal;

[0091] S150, integrate the data obtained from the analysis, label the samples with different test results with training labels, and collect the test data of all samples to form a comparison database.

[0092] In step S110, the initial normal sliding wear stage is characterized by: the friction loss condition of the skateboard under silicone grease lubrication, the friction coefficient in this stage is small, and the wear amount is usually small; the mid-term dry friction stage is characterized by: the dry friction loss condition of the support skateboard and the stainless steel plate in the friction pair when the silicone grease in the skateboard grease tank is exhausted, the friction coefficient increases in this stage, and the wear amount increases accordingly; the late steel-to-steel friction is characterized by: the friction pair steel-to-steel friction after the exposed thickness of the skateboard is worn out, the friction coefficient increases significantly in this stage, and the skateboard wear is more serious.

[0093] In step S130, the characteristic parameters include surface pressure, stroke, temperature, and displacement speed. The design value of the bearing surface pressure in the bridge is generally 45 MPa, and there is a certain deviation between the actual surface pressure value and the design value. Therefore, it is necessary to conduct simulation tests on the surface pressure range near the design value to simulate the wear of the skateboard under different surface pressures (30, 35, 40, 45, 50 MPa).

[0094] In step S140, the AE signal data is signal data emitted by the acoustic emission sensor, which is a technology for evaluating the health status of a material or structure by detecting elastic waves caused by tiny fractures, crack extensions or other forms of stress release inside the material or structure.

[0095] like Figure 3 As shown, step S140 specifically includes the following steps:

[0096] S141, preprocessing the collected AE signal data including DC bias and filtering, and then selecting a suitable wavelet basis according to the characteristics of the AE signal data;

[0097] S142, selecting the number of signal decomposition layers according to the frequency bandwidth and frequency resolution of the AE signal data, and decomposing the AE signal data into AE sub-signals of multiple frequency bands;

[0098] S143. Extract experimental features useful for evaluating the wear state of the slide plate from each AE sub-signal, and combine the extracted features into an experimental feature vector.

[0099] In step S142, the AE signal data decomposition process is as follows:

[0100]

[0101]

[0102] Among them, cA j [k] is the approximate coefficient of the jth layer of the low-frequency part,

[0103] cD j [k] is the detail coefficient of the jth layer of the high-frequency part,

[0104] h[n] is the impulse response of the low-pass filter,

[0105] g[n] is the impulse response of the high-pass filter,

[0106] x[n] is the input signal,

[0107] k is the index of the sub-signal.

[0108] For multi-layer decomposition, each layer of decomposition will produce two sub-signals, specifically:

[0109]

[0110] In step S143, the extracted test features include energy features E i , root mean square characteristic RMS i And the kurtosis characteristic K i , the energy characteristic E i for:

[0111]

[0112] Among them, c i [n] is the coefficient of the i-th sub-signal;

[0113] The root mean square characteristic RMS i for:

[0114]

[0115] Wherein, N is the length of the sub-signal;

[0116] The kurtosis characteristic K i for:

[0117]

[0118] Among them, μ i is the mean of the ith sub-signal.

[0119] The experimental feature vector F is composed of the energy feature E i , root mean square characteristic RMS i And the kurtosis characteristics are combined, specifically:

[0120] F=[E1,E2,...,E n ,RMS1,RMS2,...,RMS n , K1, N2, ..., K n ] T .

[0121] In step S150, the training labels include: initial wear, mid-term wear and severe wear.

[0122] like Figure 4 As shown, step S300 specifically includes the following steps:

[0123] S310, after processing the slide wear data according to the method in step S140, obtain monitoring data, and select the monitoring feature vector F from the monitoring data. mon ;

[0124] S320, based on the monitoring feature vector Fmon And the experimental feature vector F is used to calculate the distance metric and similarity metric between the two;

[0125] S330, using the obtained distance metric and similarity metric and a weighted fusion method to comprehensively score the monitored data;

[0126] S340. According to the comprehensive score, the closest sample is found from the comparison database, and the wear label of the sample is used as the result of the monitoring data.

[0127] In step S320, the distance metric d(F mon , F) is the Euclidean distance d O (F mon , F) or Mahalanobis distance d M (F mon ,), the Euclidean distance d O (F mon , F) is:

[0128]

[0129] Among them, m is the dimension of the test feature vector;

[0130]

[0131] Where S is the covariance matrix of the experimental eigenvectors.

[0132] The covariance matrix S of the experimental eigenvector is specifically:

[0133]

[0134] Where L is the number of samples in the comparison database,

[0135] F i is the feature vector of the i-th sample in the comparison database,

[0136] μ is the mean of the sample feature vectors in the comparison database.

[0137] The mean μ of the sample feature vector in the comparison database is:

[0138]

[0139] The similarity measure is the cosine similarity sim(F mon , F i ), specifically:

[0140]

[0141] In step S330, the comprehensive score Si Specifically:

[0142] S i =w d ·d(F mon , F i )+w s ·(1-sim(F mon , F i )),

[0143] Among them, w d and w s are the weights of distance metric and similarity metric respectively, and w d +w s =1.

[0144] In step S340, the evaluation based on the comprehensive score is:

[0145]

[0146] Among them, L best is the wear label of the closest specimen found in the comparison database.

[0147] After step S400, the following steps are also included:

[0148] S500, establishing a machine learning model, and training the model based on the sample data in the comparison database to predict the wear state of the skateboard.

[0149] In step S500, a machine learning model is trained by a support vector machine (SVM), and the machine learning model is:

[0150]

[0151] Among them, α i is the Lagrange multiplier,

[0152] y i For wear labels,

[0153] K(F i , F j ) is the kernel function,

[0154] b is the bias term,

[0155] L is the number of samples in the comparison database.

[0156] In SVM, the original problem is to find the optimal hyperplane by minimizing an objective function. The objective function for training the machine learning model is:

[0157]

[0158] Among them, w is the weight vector,

[0159] b is the bias term,

[0160] ξ i is the slack variable,

[0161] C is the penalty parameter.

[0162] The constraints of the machine learning model training objective function are:

[0163] y i (w·F i +b)≥1-ξ i ,ξ i ≥0

[0164] In order to solve the original problem, it is transformed into a dual problem and the Lagrange multiplier α is introduced. i To solve, the Lagrangian function for:

[0165]

[0166] Among them, α i is the Lagrange multiplier,

[0167] r i is the Lagrange multiplier of the slack variable.

[0168] The weight vector w is:

[0169]

[0170] The objective function of the dual problem is:

[0171]

[0172] Among them, K(F i , F j ) is the kernel function.

[0173] The constraints of the objective function of the dual problem are:

[0174]

[0175] The bias term b is:

[0176]

[0177] Example 2

[0178] The embodiment of the present invention provides another method for monitoring the wear condition of a bridge bearing slide plate, which specifically includes the following steps:

[0179] S100, select the same skateboard material as that in the support, divide the skateboard material into multiple samples and then divide them into multiple groups, conduct a wear test on each group of samples on a testing machine, mark training labels according to the test results, and collect all test data to form a comparison database;

[0180] S200, a force sensor, an acoustic emission sensor and a data collector are arranged on the middle lining plate of the support to collect the force and the wear data of the slide plate during the working process of the support;

[0181] S300, analyzing and processing the bearing force and slide wear data to obtain monitoring data, calling corresponding test data from a comparison database, and comparing the monitoring data with the test data;

[0182] S400, according to the comparison result, calling the training label in the test data as the wear condition output of the support slide plate;

[0183] S500, establishing a machine learning model, and training the model based on the sample data in the comparison database to predict the wear state of the skateboard.

[0184] In step S500, the machine learning model is trained by random forest, and the variance of a single decision tree is reduced by integrating multiple decision trees, thereby improving the generalization ability of the model. Each decision tree is trained on a different data subset, and randomization is also performed when selecting features at each node.

[0185] In step S500, for the classification task, the prediction results are summarized using the majority voting method, specifically:

[0186]

[0187] Among them, P(Y|F mon ) is the probability that the wear label is Y under the condition of a given monitoring data feature vector,

[0188] T is the number of decision trees in the random forest,

[0189] h t (F mon ) is the prediction result of the t-th decision tree for the feature vector,

[0190] I(h t (F mon )=Y) is an indicator function. When the prediction result of the tth decision tree is equal to the wear label, the value of the function is 1, otherwise it is 0.

[0191] Example 3

[0192] The embodiment of the present invention provides a bridge bearing slide wear condition monitoring system, which specifically includes:

[0193] Test module: used to select the same skateboard material as the support, divide the skateboard material into multiple samples and then into multiple groups. Each group of samples is subjected to abrasion test on the testing machine, and training labels are marked according to the test results. All test data are collected to form a comparison database;

[0194] Data acquisition module: used to configure a force sensor, an acoustic emission sensor and a data collector on the middle lining plate of the support to collect the force and slide wear data during the working process of the support;

[0195] Data processing module: used to obtain monitoring data after analyzing and processing the bearing force and slide wear data, call the corresponding test data from the comparison database, and compare the monitoring data with the test data;

[0196] Output module: used to call the training labels in the test data according to the comparison results and output the wear condition of the support slide;

[0197] Prediction module: used to establish a machine learning model, which is trained to predict the wear status of the skateboard based on the sample data in the comparison database.

[0198] It will be easily understood by those skilled in the art that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for monitoring the wear condition of a bridge bearing slide plate, characterized in that: The following steps are involved: S100, select the same skateboard material as that in the support, divide the skateboard material into multiple samples and then divide them into multiple groups, conduct a wear test on each group of samples on a testing machine, mark training labels according to the test results, and collect all test data to form a comparison database; S200, a force sensor, an acoustic emission sensor and a data collector are arranged on the middle lining plate of the support to collect the force and the wear data of the slide plate during the working process of the support; S300, analyzing and processing the bearing force and slide wear data to obtain monitoring data, calling corresponding test data from a comparison database, and comparing the monitoring data with the test data; S400: Based on the comparison result, call the training label in the test data as the wear condition output of the support slide.

2. A bridge bearing slide wear condition monitoring method according to claim 1, characterized in that: Step S100 specifically includes the following steps: S110, the wear stage of the slide plate is divided into three stages: initial normal sliding wear, mid-term dry friction and late steel-to-steel friction; S120, selecting the same slide material as that in the support, dividing the slide material into a plurality of samples and then into a plurality of large sample groups, and each large sample group is further divided into three small sample groups; S130, providing characteristics of three wear stages for the samples in the three small sample groups in each large sample group, and then performing wear tests on each large sample group according to different characteristic parameters; S140, using an acoustic emission sensor to collect and record AE signal data of each sample, and using wavelet packet transform to filter and perform eigenvalue analysis on the collected AE signal; S150, integrate the data obtained from the analysis, label the samples with different test results with training labels, and collect the test data of all samples to form a comparison database.

3. A bridge bearing slide wear condition monitoring method according to claim 2, characterized in that: Step S140 specifically includes the following steps: S141, preprocessing the collected AE signal data including DC bias and filtering, and then selecting a suitable wavelet basis according to the characteristics of the AE signal data; S142, selecting the number of signal decomposition layers according to the frequency bandwidth and frequency resolution of the AE signal data, and decomposing the AE signal data into AE sub-signals of multiple frequency bands; S143. Extract experimental features useful for evaluating the wear state of the slide plate from each AE sub-signal, and combine the extracted features into an experimental feature vector.

4. A bridge bearing slide wear condition monitoring method according to claim 3, characterized in that: In step S142, the AE signal data decomposition process is as follows: Among them, cA j [k] is the approximate coefficient of the jth layer of the low-frequency part, cD j [k] is the detail coefficient of the jth layer of the high-frequency part, h[n] is the impulse response of the low-pass filter, g[n] is the impulse response of the high-pass filter, x[n] is the input signal, k is the index of the sub-signal; For multi-layer decomposition, each layer of decomposition will produce two sub-signals, specifically:

5. A bridge bearing slide wear condition monitoring method according to claim 4, characterized in that: In step S143, the extracted test features include energy features E i , root mean square characteristic RMS i And the kurtosis characteristic K i , the energy characteristic E i for: Among them, c i [n] is the coefficient of the i-th sub-signal; The root mean square characteristic RMS i for: Wherein, N is the length of the sub-signal; The kurtosis characteristic K i for: Among them, μ i is the mean of the ith sub-signal.

6. A bridge bearing slide wear condition monitoring method according to claim 5, characterized in that: The experimental feature vector F is composed of the energy feature E i , root mean square characteristic RMS i And the kurtosis characteristics are combined, specifically: F=[E1,E2,......,E n ,RMS1,RMS2,...,RMS n ,,K1,K2,....,K n ] T 。 7. A bridge bearing slide wear condition monitoring method according to any one of claims 1 to 5, characterized in that: Step S300 specifically includes: S310, after processing the slide wear data according to the method in step S140, obtain monitoring data, and select the monitoring feature vector F from the monitoring data. mon ; S320, based on the monitoring feature vector F mon And the experimental feature vector F is used to calculate the distance metric and similarity metric between the two; S330, using the obtained distance metric and similarity metric and a weighted fusion method to comprehensively score the monitored data; S340. According to the comprehensive score, the closest sample is found from the comparison database, and the wear label of the sample is used as the result of the monitoring data.

8. A bridge bearing slide wear condition monitoring method according to claim 7, characterized in that: In step S320, the distance metric d(F mon , F) is the Euclidean distance d O (F mon , F) or Mahalanobis distance d M (F mon , F), the Euclidean distance d O (F mon , F) is: Among them, m is the dimension of the test feature vector; Among them, S is the covariance matrix of the experimental eigenvector; The mean μ of the sample feature vector in the comparison database is: The similarity measure is the cosine similarity sim(F mon , F i ), specifically:

9. A bridge bearing slide wear condition monitoring method according to claim 8, characterized in that: In step S330, the comprehensive score S i Specifically: S i =w d ·d(F mon ,F i )+w s ·(1-sim(F mon ,F i )), Among them, w d and w s are the weights of distance metric and similarity metric respectively, and w d +w s =1. In step S340, the evaluation based on the comprehensive score is: Among them, L best is the wear label of the closest specimen found in the comparison database.

10. A bridge bearing slide plate wear condition monitoring system, used to implement a bridge bearing slide plate wear condition monitoring method as claimed in any one of claims 1 to 9, characterized in that: include: Test module: used to select the same skateboard material as the support, divide the skateboard material into multiple samples and then into multiple groups. Each group of samples is subjected to abrasion test on the testing machine, and training labels are marked according to the test results. All test data are collected to form a comparison database; Data acquisition module: used to configure a force sensor, an acoustic emission sensor and a data collector on the middle lining plate of the support to collect the force and slide wear data during the working process of the support; Data processing module: used to obtain monitoring data after analyzing and processing the bearing force and slide wear data, call the corresponding test data from the comparison database, and compare the monitoring data with the test data; Output module: used to call the training labels in the test data according to the comparison results and output the wear condition of the support slide; Prediction module: used to establish a machine learning model, which is trained to predict the wear status of the skateboard based on the sample data in the comparison database.

Images