Variable load friction and wear testing device and wear monitoring method thereof

Abstract

The application relates to a variable load friction and wear test device and a wear monitoring method thereof. The variable load friction and wear test device is matched with an existing rotating shaft and a driving module, a loading device is arranged, the loading device is arranged in a pneumatic loading mode to load a pin sample, the loading device is controlled through a control module, and therefore the stability of the applied load can be guaranteed. In addition, a result module is arranged to acquire vibration signals, acoustic emission signals and power signals when the pin sample and a disc sample are rubbed, the vibration signals, the acoustic emission signals and the power signals are subjected to correlation analysis to obtain a fusion feature vector, finally, a support vector machine state monitoring algorithm is adopted to obtain the wear amount of the disc sample based on the fusion feature vector, so that the disadvantages caused by the collection of single signals are overcome, and the demand of online real-time monitoring of the wear condition of the sample can be met.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of friction and wear detection, in particular to a variable load friction and wear test device and a wear monitoring method thereof. BACKGROUND

[0002] The wear state monitoring method is divided into direct monitoring and indirect monitoring. The direct monitoring method judges the wear condition of the sample by directly monitoring the shape change, volume change and mass change of the sample in the friction and wear test. The direct monitoring method mainly includes contact detection method, ray detection method and optical detection method. The indirect monitoring method mainly maps the wear state of the sample in the friction and wear test by analyzing the sensor signal to establish a model, and then indirectly obtains the current wear state of the sample. At present, the indirect monitoring method mainly includes vibration monitoring, acoustic emission monitoring and power monitoring.

[0003] However, the direct monitoring method needs to stop measuring, that is, to disassemble after stopping, and the disassembly will introduce clamping errors, and the process is cumbersome and the economic benefit is not high.

[0004] The indirect monitoring method is beneficial to real-time monitoring and has little effect on production and processing, and has become the mainstream method of online monitoring of sample wear. However, the selection of signal characteristic values and the data processing method of the method will affect the prediction accuracy of the wear state. In addition, in the actual friction and wear process, relying on a single sensor or multiple single-type sensors to obtain the original information of the friction pair sample cannot effectively monitor the wear condition of the sample. SUMMARY

[0005] The technical problem to be solved by the present application is how to accurately and effectively monitor the wear condition of the sample. To solve the above technical problems of the prior art, the present application provides a variable load friction and wear test device and a wear monitoring method thereof, which comprises a variable load friction and wear test device and a wear monitoring method of the variable load friction and wear test device.

[0006] The variable load friction and wear test device provided by the present application comprises a rotating shaft and a driving module for driving the rotating shaft to rotate around its axis, and the top of the rotating shaft is provided with a connecting part which is detachably connected with a disc sample. The driving module is connected with the rotating shaft, and further comprises:

[0007] A loading device is provided with a clamp which is detachably connected with a pin sample, and is used for enabling the pin sample to contact with the disc sample and loading the pin sample with load through a pneumatic loading mode.

[0008] The control module is electrically connected with the loading device and is configured to acquire an error and an error change rate of the loading load and a target load during the loading process, then acquire proportional gain, integral gain and differential gain of a proportional-integral-differential adjustment algorithm by using the error and the error change rate through a neural network algorithm, and finally acquire a loading amount of the next step by using the error and the error change rate through the proportional-integral-differential adjustment algorithm, and call the loading device to perform loading according to the loading amount.

[0009] The result module is configured to acquire vibration signals, acoustic emission signals and power signals of the disc sample in a worn state when the pin sample and the disc sample rub, acquire a fusion feature vector by performing correlation analysis on the vibration signals, the acoustic emission signals and the power signals, and finally acquire the wear amount of the disc sample based on the fusion feature vector by using a state monitoring algorithm of a support vector machine.

[0010] The variable load friction and wear test device disclosed by the application can apply variable load pin-disc friction and can monitor the wear amount in real time, which provides an important basis for mastering the friction and wear performance of materials under actual working conditions and improving the service life of workpieces.

[0011] In a possible implementation, the loading device includes a pneumatic loading device, and the pneumatic loading device is electrically connected with the control module, so that large load loading and variable load loading can be realized, and the loading amount is controllable.

[0012] In a possible implementation, the control module includes a proportional-integral-differential adjustment algorithm module, a neural network algorithm module and a proportional gain, integral gain and differential gain acquisition module.

[0013] The loading force sensor is configured to acquire the loading load of the pneumatic loading device in real time.

[0014] a back propagation neural network for obtaining the proportional gain, the integral gain and the differential gain of the proportional-integral-differential adjustment algorithm;

[0015] an adjuster for executing the proportional-integral-differential adjustment algorithm to obtain the loading amount;

[0016] a central processing unit configured to obtain the error and the error change rate according to the loading load obtained by the loading force sensor, and to control the back propagation neural network and the adjuster to operate to obtain the loading amount by using the error and the error change rate, and to call the pneumatic loading device to perform loading according to the loading amount;

[0017] wherein,

[0018] the loading force sensor is arranged on the pneumatic loading device, and the central processing unit is electrically connected with the loading force sensor, the back propagation neural network, the adjuster and the pneumatic loading device at the same time;

[0019] This scheme takes the central processing unit as the control core and takes the loading force sensor as the signal acquisition device, so that not only the loading is controllable, but also the control precision is guaranteed, and the effect of closed-loop control of the loading amount is achieved.

[0020] In a possible implementation, the loading force sensor is a resistance strain type force sensor, so that the loading load of the pneumatic loading device can be obtained more accurately, and the sensor has a smaller volume.

[0021] In a possible implementation, the formula of the proportional-integral-differential adjustment algorithm is as follows:

[0022]

[0023] wherein,

[0024] P represents the loading amount;

[0025] K1 represents the proportional gain;

[0026] K2 represents the integral gain;

[0027] K3 represents the differential gain;

[0028] T represents a sampling period;

[0029] a represents a current time;

[0030] e(t) represents an error function determined by the error of all the loading loads obtained in a period of time starting from the current time and ending at the current time plus the sampling period and the target load.

[0031] a rate of change of error representing the sampling start point;

[0032] The scheme can effectively reduce the operation complexity under the premise of ensuring the accurate controllability of the load loading amount, thereby reducing resource waste, improving control efficiency and rate.

[0033] In one possible implementation, the central processor is configured to perform the following steps:

[0034] A1: calling all loading loads obtained by the loading force sensor in a period of time from the current time and calculating the errors of the loading loads and the target load respectively to obtain error distribution;

[0035] A2: according to the results obtained in step A1, using the error at the current time and the error at the next sampling time after the current time to obtain the rate of change of error at the current time;

[0036] A3: calling the back propagation neural network to obtain the proportional gain, the integral gain and the differential gain using the error at the current time and the rate of change of error at the current time as input;

[0037] A4: calling the regulator according to the results obtained in steps A1 and A3 to obtain the loading amount, and calling the pneumatic loading device to perform loading according to the loading amount;

[0038] A5: calling the loading load obtained by the loading force sensor at this time, and calculating the error value of the loading load obtained at this time and the target load;

[0039] A6: judging whether the error value obtained in step A5 is less than a threshold value;

[0040] If yes, the pneumatic loading device is controlled to suspend loading;

[0041] If no, the step A1 is executed again;

[0042] The scheme obtains the error and the rate of change of error according to the loading loads obtained by the loading force sensor in a sampling period, and uses the error and the rate of change of error to control the back propagation neural network to obtain the proportional gain, the integral gain and the differential gain. Subsequently, the regulator is operated, and the proportional gain, the integral gain and the differential gain obtained by the back propagation neural network are used as the proportional gain, the integral gain and the differential gain of the proportional-integral-differential algorithm. Finally, the loading amount is obtained, and the pneumatic loading device is called to perform loading according to the loading amount, so that the loading is reasonable and orderly, and the efficiency is further improved.

[0043] In a possible implementation, the result module comprises:

[0044] an acoustic emission sensor configured to acquire the acoustic emission signal;

[0045] a vibration sensor configured to acquire the vibration signal;

[0046] a power sensor configured to acquire the power signal;

[0047] a signal amplifier configured to amplify the acoustic emission signal, the vibration signal and the power signal respectively to form amplified signals;

[0048] a data acquisition card configured to convert the amplified signals obtained by the signal amplifier into digital information;

[0049] a support vector machine module configured to obtain the wear amount by a state monitoring algorithm of the support vector machine;

[0050] a record analysis device configured to obtain a fusion feature vector by performing correlation analysis on the digital information, and finally call the support vector machine module to obtain the wear amount of the disc sample based on the fusion feature vector;

[0051] wherein,

[0052] the signal amplifier is electrically connected with the acoustic emission sensor, the vibration sensor and the power sensor, the data acquisition card is electrically connected with the signal amplifier, and the record analysis device is electrically connected with the data acquisition card and the support vector machine module;

[0053] This scheme acquires information by the acoustic emission sensor, the vibration sensor and the power sensor, and adjusts signals by the signal amplifier, so that the vibration signal, the acoustic emission signal and the power signal containing the original relevant information of the wear state of the disc sample can be monitored in real time when the friction and wear test is started. In addition, the support vector machine module is used to monitor the state of the sample, and then the wear amount of the sample with high prediction accuracy can be output.

[0054] In a possible implementation, the record analysis device is configured to perform the following steps:

[0055] B1: pre-process the digital information by invalid data removal and wavelet threshold denoising to eliminate interference signals, and obtain a pre-processing result;

[0056] B2: perform time domain, frequency domain and time-frequency domain feature extraction on the pre-processing result to obtain feature information;

[0057] B3: performing correlation analysis on the feature information to screen out sensitive feature variables with a correlation with the wear amount of the disc sample exceeding a specified value;

[0058] B4: finding the sensor corresponding to the sensitive feature variable from the acoustic emission sensor, the vibration sensor and the power sensor, and calling the digital information formed by the signal obtained by the sensor corresponding to the sensitive feature variable to obtain the fusion feature vector;

[0059] B5: calling the support vector machine module to obtain the wear amount of the disc sample based on the fusion feature vector;

[0060] The scheme pre-processes the collected original signal in a manner of invalid data removal and wavelet threshold denoising to eliminate interference signals caused by environmental noise interference and poor collection parameter setting, thereby improving the accuracy of wear state monitoring. In addition, the vibration signal, acoustic emission signal and power signal data after pre-processing are subjected to time domain, frequency domain and time-frequency domain feature extraction, and a correlation analysis method is used to screen out sensitive feature variables with a higher correlation with the wear amount of the disc sample, thereby effectively representing the wear characteristics of the disc sample. In addition, the multi-sensor signal feature quantities after feature screening are combined into a fusion feature vector, a support vector machine module is called to monitor the state of the sample, and then the wear amount of the sample with high prediction accuracy is output.

[0061] In a possible implementation, the result module further comprises a display for displaying the loading load obtained by the loading force sensor and the wear amount of the disc sample, and the display is electrically connected with the recording and analyzing device and the central processing unit.

[0062] Another technical solution of the present application is to provide a wear monitoring method of a variable load friction and wear test device, which comprises the following steps:

[0063] S1: installing a disc sample on a connecting portion provided on a rotating shaft, and installing a pin sample on a clamp provided on a loading device, so that the pin sample contacts the disc sample;

[0064] S2: controlling the control module to call the loading device to load the pin sample, and driving the rotating shaft to rotate around its axis center by the driving module;

[0065] S3: acquiring vibration signals, acoustic emission signals and power signals of the disc sample in a wear state when the pin sample and the disc sample are in friction by the result module;

[0066] S4: obtaining a fusion feature vector by the result module in a manner of performing correlation analysis on the vibration signals, acoustic emission signals and power signals.

[0067] S5: obtaining the wear amount of the disc sample based on the fusion feature vector by the result module using a state monitoring algorithm of a support vector machine.

[0068] The method disclosed in the application, after installing the disc sample and the pin sample, loads the pin sample by the loading device, drives the rotating shaft to rotate around its axis by the driving module, and then obtains the fusion feature vector by the correlation analysis of the vibration signal, the acoustic emission signal and the power signal through the result module; and obtains the wear amount of the disc sample based on the fusion feature vector by using a state monitoring algorithm of a support vector machine, so as to overcome the disadvantages caused by collecting single signal, meet the demand of online real-time monitoring of the wear condition of the sample, and guarantee the accuracy and effectiveness of the monitoring of the wear condition of the sample, which can not only apply the variable load pin-disc friction, but also real-time monitor the wear amount, and provides an important basis for mastering the friction and wear performance of the material under the actual working condition and improving the service life of the workpiece. BRIEF DESCRIPTION OF DRAWINGS

[0069] Figure 1 It is a structure schematic view of the variable load friction and wear test device disclosed in the embodiments of the application.

[0070] Figure 2 It is a running flow chart of the central processing unit disclosed in the embodiments of the application.

[0071] Figure 3 It is a running flow chart of the recording analysis device disclosed in the embodiments of the application.

[0072] Figure 4 It is a method flow chart disclosed in the embodiments of the application. DETAILED DESCRIPTION

[0073] Firstly, those skilled in the art should understand that the embodiments are only used to explain the technical principles of the embodiments of the application, and are not intended to limit the protection scope of the embodiments of the application. Those skilled in the art can adjust them as needed to adapt to specific application occasions.

[0074] In the description of the embodiments of the application, it should be noted that, unless otherwise explicitly specified and limited, the terms "connected", "connected" should be understood in a broad sense, for example, it can be fixedly connected, or detachably connected, or integrally connected, it can be mechanically connected, or electrically connected, it can be directly connected, or indirectly connected through an intermediate medium. For those skilled in the art, the specific meaning of the above terms in the embodiments of the application can be understood according to the specific circumstances.

[0075] In the description of the embodiments of the present application, it should be noted that unless otherwise explicitly specified and limited, the terms "electrical connection", "electrical connection relationship" should be understood in a broad sense, namely, it refers to the connection mode with electrical relationship, for example, it can be through a conductive wire to realize the circuit connection, or through a wireless signal channel (channel) to realize the electrical connection, or a combination of the two. In addition, the "electrical connection", "electrical connection relationship" can be established on the basis of mechanical connection (such as the conductive wire is arranged in the connecting key); it can be directly connected, or indirectly connected through an intermediate medium. For those skilled in the art, the specific meaning of the above terms in the embodiments of the present application can be understood according to the specific circumstances.

[0076] In the embodiments of the present application, unless otherwise explicitly specified and limited, the first feature is "on" or "under" the second feature, which can be that the first and second features are in direct contact, or the first and second features are in indirect contact through an intermediate medium. Moreover, the first feature can be above or obliquely above the second feature, or it can only mean that the horizontal height of the first feature is higher than that of the second feature. The first feature can be below or obliquely below the second feature, or it can only mean that the horizontal height of the first feature is less than that of the second feature.

[0077] The present application will be further described in detail below in combination with the drawings and specific embodiments.

[0078] Referring to Figures 1-4 The embodiments of the present application disclose a variable load friction and wear test device, Figure 1 is a structural schematic diagram of the experimental device. The experimental device comprises a rotating shaft, a driving module, a loading device, a control module and a result module. The top of the rotating shaft is provided with a connecting part which is detachably matched with a disc sample. The loading device is provided with a clamp which is detachably matched with a pin sample. The driving module is connected with the rotating shaft, and is used for driving the rotating shaft to rotate around its axis. The control module is electrically connected with the loading device.

[0079] Referring to Figure 1 In the experimental device, the loading device is used for contacting the pin sample with the disc sample, and loading the pin sample through a pneumatic loading mode. The loading device comprises a pneumatic loading device and a shell for accommodating the pneumatic loading device. The pneumatic loading device is electrically connected with the control module. The clamp for mounting the pin sample is arranged on the shell. In addition, the shell is also provided with a loading channel for facilitating the pneumatic loading device to load the load.

[0080] Please continue to refer to Figure 1In the experimental device, the control module is configured to obtain an error and a change rate of the error between the loading load and the target load during the loading process, and then obtain a proportional gain, an integral gain and a differential gain of a proportional-integral-differential adjustment algorithm by using the error and the change rate of the error through a neural network algorithm, and finally obtain a loading amount of the next step by using the error and the change rate of the error through the proportional-integral-differential adjustment algorithm, and call the loading device to perform the loading according to the loading amount. The control module comprises a loading force sensor, a back propagation (BP for short) neural network, an adjuster and a central processing unit, wherein the loading force sensor is arranged on the pneumatic loading device, and the central processing unit is electrically connected with the loading force sensor, the back propagation neural network, the adjuster and the pneumatic loading device.

[0081] In the control module, the loading force sensor is a resistance strain type force sensor, and is used to obtain the loading load of the pneumatic loading device in real time; the back propagation neural network is used to obtain the proportional gain, the integral gain and the differential gain of the proportional-integral-differential adjustment algorithm; the adjuster is used to execute the proportional-integral-differential adjustment algorithm to obtain the loading amount; and the central processing unit is configured to obtain the error and the change rate of the error according to the loading load obtained by the loading force sensor, and to control the back propagation neural network and the adjuster to run by using the error and the change rate of the error to obtain the loading amount, and to call the pneumatic loading device to perform the loading according to the loading amount.

[0082] In the control module, the formula of the proportional-integral-differential adjustment algorithm is as follows:

[0083]

[0084] In the formula, P represents the loading amount, which is obtained by prediction through the back propagation neural network;

[0085] P represents the loading amount, which is obtained by prediction through the back propagation neural network;

[0086] K1 represents the proportional gain, which is obtained by prediction through the back propagation neural network;

[0087] K2 represents the integral gain, which is obtained by prediction through the back propagation neural network;

[0088] K3 represents the differential gain;

[0089] T represents a sampling period;

[0090] a represents a current time;

[0091] e(t) represents an error function determined by all the errors between the loading load and the target load in a period of one sampling period starting from the current time;

[0092] The error change rate representing the sampling starting point is the change rate of the error function at the sampling starting point.

[0093] Referring to Figure 2 In the control module, the central processing unit is configured to perform the following steps:

[0094] A1: Call all loading loads obtained by the loading force sensor in the period from the current time to the next sampling time, and calculate the error of each loading load and the target load to obtain an error distribution.

[0095] In principle, the length of the sampling period should be small, such as can be set at the microsecond level or smaller, thereby reducing the calculation delay. Let the current time be a and the length of the sampling period be T, then the interval corresponding to the first period from the current time is [a, a+T], and if all the loading loads obtained by the loading force sensor in the interval [a, a+T] are P1, P2, …, P S , and the target load set is The error of these loading loads and the target load is S is a natural number not less than 1. Let

[0096]

[0097] Therefore, the error distribution is e1, e2, …, e S .

[0098] A2: According to the error distribution obtained in step A1, the error change rate at the current time is obtained using the error at the current time and the error at the next sampling time after the current time.

[0099] Specifically, the error at the current time is e1, the error at the next sampling time after the current time is e2, and the time interval of the sampling is ΔT. The error change rate at the current time is:

[0100]

[0101] A3: Call the back propagation neural network to obtain the proportional gain, integral gain and differential gain using the error at the current time and the error change rate as input quantities.

[0102] A4: Call the regulator according to the error distribution obtained in step A1 and the proportional gain, integral gain and differential gain obtained in step A3 to obtain the loading amount, and call the pneumatic loading device to perform loading according to the loading amount.

[0103] A5: Call the loading load obtained by the loading force sensor at this time, and calculate the error value of the loading load obtained at this time and the target load.

[0104] A6: judging whether the error value obtained in step A5 is less than a threshold value;

[0105] If yes, the pneumatic loading device is controlled to suspend loading;

[0106] If no, the step A1 is executed.

[0107] In the experimental device, the result module is configured to obtain the vibration signal, the acoustic emission signal and the power signal of the disc sample in the worn state when the pin sample and the disc sample are rubbed, to obtain the fusion feature vector by correlation analysis of the vibration signal, the acoustic emission signal and the power signal, and finally to obtain the wear amount of the disc sample based on the fusion feature vector by using the state monitoring algorithm of the support vector machine.

[0108] Please continue to see Figure 1 In the embodiment, the result module includes an acoustic emission sensor, a vibration sensor, a power sensor, a signal amplifier, a data acquisition card, a support vector machine module, a recording and analyzing device and a display, wherein the signal amplifier is electrically connected with the acoustic emission sensor, the vibration sensor and the power sensor at the same time, the data acquisition card is electrically connected with the signal amplifier, the recording and analyzing device is electrically connected with the data acquisition card and the support vector machine module at the same time, and the display is electrically connected with the recording and analyzing device and the central processing unit at the same time.

[0109] In the result module, the acoustic emission sensor is used to obtain the acoustic emission signal, the vibration sensor is used to obtain the vibration signal, the power sensor is used to obtain the power signal, the signal amplifier is used to amplify the acoustic emission signal, the vibration signal and the power signal respectively to form amplified signals, the data acquisition card is used to convert the amplified signals obtained by the signal amplifier into digital information, the support vector machine module is configured to obtain the wear amount by using the state monitoring algorithm of the support vector machine, the recording and analyzing device is configured to obtain the fusion feature vector by correlation analysis of the digital information, and finally the wear amount of the disc sample is obtained based on the fusion feature vector by calling the support vector machine module, and the display is used to display the loading load obtained by the loading force sensor and the wear amount of the disc sample.

[0110] See Figure 3In the result module, the record analysis device is configured to perform the following steps: B1: pre-process the digital information by invalid data removal and wavelet threshold denoising to eliminate interference signals, and obtain a pre-processing result; B2: perform time domain, frequency domain and time-frequency domain feature extraction on the pre-processing result to obtain feature information; B3: perform correlation analysis on the feature information to screen out sensitive feature variables with a correlation with the wear amount of the disc sample exceeding a specified value; B4: find the sensor corresponding to the sensitive feature variable from the acoustic emission sensor, vibration sensor and power sensor, and call the digital information formed by the signals obtained by the sensor corresponding to the sensitive feature variable to obtain a fusion feature vector; and B5: call the support vector machine module to obtain the wear amount of the disc sample based on the fusion feature vector.

[0111] The record analysis device pre-processes the collected original signals (i.e., digital information) by invalid data removal and wavelet threshold denoising to eliminate interference signals caused by environmental noise interference and poor collection parameter settings, thereby improving the accuracy of wear state monitoring. In addition, by performing time domain, frequency domain and time-frequency domain feature extraction on the pre-processed vibration signal, acoustic emission signal and power signal data, and using correlation analysis to screen out sensitive feature variables with a high correlation with the wear amount of the disc sample, the wear characteristics of the disc sample are effectively represented. In addition, the multi-sensor signal feature quantities subjected to feature screening are combined into a fusion feature vector, and the support vector machine module is called to perform state monitoring on the sample, thereby outputting a sample wear amount with high prediction accuracy.

[0112] The detection method using the device will be further disclosed below, see Figure 4 The method comprises the following steps:

[0113] S1: install the disc sample on the connecting portion provided on the rotating shaft, and install the pin sample on the clamp provided on the loading device, so that the pin sample contacts the disc sample.

[0114] S2: control the control module to call the loading device to load the pin sample, and drive the rotating shaft to rotate around its axis center by the drive module. The loading method can be seen in steps A1-A6.

[0115] S3: acquire the vibration signal, acoustic emission signal and power signal of the disc sample in the wear state when the pin sample and the disc sample rub by the result module.

[0116] S4: obtain the fusion feature vector by the result module by performing correlation analysis on the vibration signal, acoustic emission signal and power signal. The process of obtaining the fusion feature vector can be seen in steps B1-B4.

[0117] S5: obtaining the wear amount of the disc sample based on the fusion feature vector by the result module using a state monitoring algorithm of a support vector machine.

[0118] The variable load friction and wear test device disclosed in the embodiment is based on the cooperation of the existing rotating shaft and the driving module, a loading device is arranged, the loading device is provided with a clamp which is detachably matched with the pin sample, the loading device is arranged to load the pin sample by a pneumatic loading mode, and the loading device is controlled by the control module, so that the stability of the applied load can be ensured. In addition, the vibration signal, the acoustic emission signal and the power signal are obtained when the pin sample and the disc sample are rubbed by arranging the result module, the fusion feature vector is obtained by correlatively analyzing the vibration signal, the acoustic emission signal and the power signal, finally, the wear amount of the disc sample is obtained based on the fusion feature vector by using a state monitoring algorithm of a support vector machine, the wear volume of the disc sample in the friction and wear process can be obtained by using the acoustic emission signal, and the vibration signal and the power signal correspond to the vibration condition and the rotating power of the disc sample respectively, so that the drawbacks caused by collecting a single signal can be overcome, the demand of online real-time monitoring of the wear condition of the sample can be met, and the accuracy and effectiveness of monitoring the wear condition of the sample are guaranteed. Therefore, the variable load friction and wear test device disclosed in the embodiment can not only apply variable load pin-disc friction, but also can realize real-time monitoring of the wear amount, which provides an important basis for mastering the friction and wear performance of the material under actual working conditions and improving the service life of the workpiece.

[0119] In the description of the embodiments of the present application, it should be noted that the terms indicating the direction or position relationship in the description of the present application are based on the direction or position relationship shown in the drawings, which is only for the convenience of description, and does not indicate or imply that the device or member must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present application.

[0120] In the description of the present application, the description of the terms "one embodiment", "some embodiments", "in the present embodiment", "specific examples", or "some examples" means that the specific features, mechanisms, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In the present specification, the illustrative description of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, mechanisms, materials or characteristics described can be combined in any appropriate manner in any one or more embodiments or examples. In addition, the person skilled in the art can combine and combine the different embodiments or examples described in the specification and the features of the different embodiments or examples without contradiction.

[0121] The above merely provides the specific implementation of the present application, but the protection scope of the present application is not limited to this. Any changes or replacements within the technical scope disclosed by the present application can be easily conceived by the person skilled in the art, and should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A variable load friction and wear testing device, comprising a rotating shaft and a rotating drive module for driving the rotating shaft to rotate around its axis, a top of the rotating shaft is provided with a connecting part detachably coupled with a disc sample, and the rotating drive module is connected with the rotating shaft, characterized in that, Also comprising: a loading device, which is provided with a clamp for detachable cooperation with a pin sample, for enabling the pin sample to contact the disc sample and loading the pin sample by a pneumatic loading mode; a control module, which is electrically connected with the loading device, is set to obtain an error and an error change rate of a loading load in a loading process, then obtain a proportional gain, an integral gain and a differential gain of a proportional-integral-differential adjustment algorithm by a neural network algorithm using the error and the error change rate, finally obtain a loading amount of a next loading by the proportional-integral-differential adjustment algorithm using the error and the error change rate, and call the loading device to execute loading according to the loading amount; a result module, which is set to obtain a vibration signal, an acoustic emission signal and a power signal of the disc sample in a worn state when the pin sample and the disc sample are rubbed, obtain a fusion feature vector by correlation analysis of the vibration signal, the acoustic emission signal and the power signal, and finally obtain a wear amount of the disc sample based on the fusion feature vector by a state monitoring algorithm of a support vector machine.

2. The variable load friction and wear test apparatus according to claim 1, wherein The loading device comprises a pneumatic loading device, which is electrically connected with the control module.

3. The variable load friction and wear test apparatus of claim 2, wherein, The control module comprises: a loading force sensor, which is used to obtain a loading load of the pneumatic loading device in real time; a back propagation neural network, which is used to obtain the proportional gain, the integral gain and the differential gain of the proportional-integral-differential adjustment algorithm; an adjuster, which is used to execute the proportional-integral-differential adjustment algorithm to obtain the loading amount; a central processing unit, which is set to obtain the error and the error change rate according to the loading load obtained by the loading force sensor, and manipulate the back propagation neural network and the adjuster to run to obtain the loading amount using the error and the error change rate, and call the pneumatic loading device to execute loading according to the loading amount; wherein, the loading force sensor is arranged on the pneumatic loading device, and the central processing unit is electrically connected with the loading force sensor, the back propagation neural network, the adjuster and the pneumatic loading device at the same time.

4. The variable load friction and wear test apparatus of claim 3, wherein The loading force sensor is a resistance strain type force sensor.

5. The variable load friction and wear test apparatus of claim 4, wherein, The formula of the proportional-integral-differential adjustment algorithm is as follows: wherein, P represents the loading amount; K1 represents the proportional gain; K2 represents the integral gain; K3 represents the differential gain; T represents a sampling period; a represents a current time; e(t) represents an error function determined by errors of all loading loads obtained in a period of one sampling period from the current time to the target load; The error rate representing the sampling start point.

6. The variable load friction and wear test apparatus according to any one of claims 3 to 5, wherein The central processing unit is set to execute the following steps: A1: call all loading loads obtained by the loading force sensor in a period of one sampling period from the current time, and calculate errors of these loading loads and the target load respectively to obtain an error distribution; A2: according to the result obtained in step A1, obtain an error change rate of the current time using the error of the current time and the error of the next sampling time after the current time. A3: calling the back propagation neural network to obtain the proportional gain, the integral gain and the differential gain with the error and the error change rate at the current time as input quantities; A4: calling the regulator to obtain the loading quantity according to the results obtained in steps A1 and A3, and calling the pneumatic loading device to perform loading according to the loading quantity; A5: calling the loading load obtained by the loading force sensor at this time, and calculating the error value of the loading load obtained at this time and the target load; A6: judging whether the error value obtained in step A5 is less than a threshold value; If yes, controlling the pneumatic loading device to suspend loading; If no, returning to execute step A1.

7. The variable load friction and wear test apparatus of claim 6, wherein, The result module comprises: an acoustic emission sensor for obtaining the acoustic emission signal; a vibration sensor for obtaining the vibration signal; a power sensor for obtaining the power signal; a signal amplifier for signal amplification of the acoustic emission signal, the vibration signal and the power signal to form an amplified signal; a data acquisition card for analog-to-digital conversion of the amplified signal obtained by the signal amplifier to obtain digital information; a support vector machine module configured to obtain the wear amount by a state monitoring algorithm of a support vector machine; a record analysis device configured to obtain a fusion feature vector by correlation analysis of the digital information, and finally call the support vector machine module to obtain the wear amount of the disc sample based on the fusion feature vector; wherein, the signal amplifier is electrically connected with the acoustic emission sensor, the vibration sensor and the power sensor simultaneously, the data acquisition card is electrically connected with the signal amplifier, and the record analysis device is electrically connected with the data acquisition card and the support vector machine module simultaneously.

8. The variable load friction and wear test apparatus of claim 7, wherein, The record analysis device is configured to execute the following steps: B1: pre-processing the digital information by invalid data removal and wavelet threshold denoising to eliminate interference signals to obtain a pre-processing result; B2: performing time domain, frequency domain and time-frequency domain feature extraction on the pre-processing result to obtain feature information; B3: performing correlation analysis on the feature information to screen out sensitive feature variables with a correlation with the wear amount prediction of the disc sample exceeding a specified value; B4: finding the sensor corresponding to the sensitive feature variable from the acoustic emission sensor, the vibration sensor and the power sensor, and calling the digital information formed by the signal obtained by the sensor corresponding to the sensitive feature variable to obtain the fusion feature vector; B5: calling the support vector machine module to obtain the wear amount of the disc sample based on the fusion feature vector.

9. The variable load friction and wear test apparatus according to claim 7 or 8, characterized in that, The result module further comprises a display for displaying the loading load obtained by the loading force sensor and the wear amount of the disc sample, and the display is electrically connected with the record analysis device and the central processing unit simultaneously.

10. A wear monitoring method of a variable load friction and wear testing apparatus, characterized by, The variable load friction and wear test device according to any one of claims 1-9 comprises the following steps: S1: mounting a disc sample on a connecting portion provided on a rotating shaft, and mounting a pin sample on a clamp provided on a loading device, so that the pin sample contacts the disc sample; S2: the control module is operated to call the loading device to load the pin sample, and the rotation module is operated to drive the rotation shaft to rotate around its axis; S3: the result module is operated to acquire vibration signals, acoustic emission signals and power signals of the disc sample in the worn state when the pin sample and the disc sample rub against each other; S4: the result module is operated to acquire a fusion feature vector by performing correlation analysis on the vibration signals, acoustic emission signals and power signals; S5: the result module is operated to acquire the wear amount of the disc sample based on the fusion feature vector by using a support vector machine state monitoring algorithm.

Images