Variable load friction wear test device and wear monitoring method thereof

Abstract

The invention relates to a variable load friction and wear test device and a wear monitoring method thereof, and the variable load friction and wear test device is provided with a loading device on the basis of cooperation of an existing rotating shaft and a rotation driving module, and the loading device is arranged to load a pin sample in a pneumatic loading mode. And the loading device is controlled through the control module, so that the stability of the applied load can be ensured. Besides, a result module is arranged to obtain a vibration signal, an acoustic emission signal and a power signal when friction occurs between the pin sample and the disc sample, and a fusion feature vector is obtained by performing correlation analysis on the vibration signal, the acoustic emission signal and the power signal. And finally, the abrasion loss of the disc sample is obtained based on the fused feature vector by adopting a state monitoring algorithm of a support vector machine, so that the defect caused by collecting a single signal is overcome, and the requirement of monitoring the abrasion condition of the sample on line in real time can be met.

Description

Technical Field

[0001] The present invention relates to the technical field of friction and wear detection, and in particular to a variable load friction and wear testing device and a wear monitoring method thereof. Background Art

[0002] Wear state monitoring methods are divided into two categories: direct monitoring and indirect monitoring. The direct monitoring method determines the wear condition of the sample by directly monitoring the shape change, volume change, mass change, etc. of the sample in the friction and wear test. Direct monitoring methods mainly include: contact detection method, X-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 methods mainly include vibration monitoring, acoustic emission monitoring and power monitoring.

[0003] However, the direct monitoring method requires shutdown measurement, that is, disassembly after shutdown, which will introduce clamping errors, and the process is cumbersome and has low economic benefits.

[0004] The indirect monitoring method is conducive to real-time monitoring and has little impact on production and processing. It has become the mainstream method for online monitoring of sample wear. However, the selection of signal characteristic values ​​and data processing methods of this method will affect the prediction accuracy of the wear state. In addition, in the actual friction and wear process, relying solely 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 of the invention

[0005] The technical problem to be solved by the present invention is how to accurately and effectively monitor the wear condition of the sample. In order to solve the above-mentioned problems of the prior art, the present invention provides a variable load friction and wear testing device and a wear monitoring method thereof, comprising a variable load friction and wear testing device and a wear monitoring method for a variable load friction and wear testing device.

[0006] The present invention provides a variable load friction and wear test device, comprising a rotating shaft and a driving module for driving the rotating shaft to rotate around its axis, wherein a connecting portion detachably matched with a disc sample is provided on the top of the rotating shaft, and the driving module is connected to the rotating shaft, and further comprises:

[0007] A loading device, on which a fixture is provided that is detachably matched with the pin sample, and is used to make the pin sample contact with the disc sample, and to load the pin sample by pneumatic loading;

[0008] a control module, electrically connected to the loading device, and configured to obtain an error and an error change rate 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 using the error and the error change rate through a neural network algorithm, and finally obtain a load amount for the next loading step through the proportional-integral-differential adjustment algorithm using the error and the error change rate, and call the loading device to perform loading according to the load amount;

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

[0010] The variable load friction and wear test device disclosed in the present invention aims at the above problems. On the basis of the existing rotation shaft and the driving module, a loading device is set, and a clamp that can be detachably matched with the pin sample is provided on the loading device. The loading device is set to load the pin sample by pneumatic loading, and the loading device is controlled by the control module, so as to ensure the stability of the applied load. In addition, a result module is set to obtain vibration signals, acoustic emission signals and power signals when friction occurs between the pin sample and the disk sample, and a fusion feature vector is obtained by performing correlation analysis on the vibration signal, the acoustic emission signal and the power signal. Finally, the state monitoring algorithm of the support vector machine is used to obtain the wear amount of the disk sample based on the fusion feature vector. The wear volume of the disk sample in the friction and wear process can be obtained by using the acoustic emission signal. The vibration signal and the power signal correspond to the vibration condition and the rotation power of the disk sample respectively, thereby overcoming the disadvantages brought by collecting a single signal, meeting the needs of online real-time monitoring of the wear condition of the sample, and the accuracy and effectiveness of monitoring the wear condition of the sample are guaranteed. Therefore, the variable load friction and wear testing device disclosed in the present invention can not only apply variable load pin-disc friction, but also monitor the wear amount in real time, providing an important basis for understanding 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 to the control module; thereby ensuring that large load loading and variable load loading are achieved, and the loading amount is controllable.

[0012] In a possible implementation, the control module includes:

[0013] A loading force sensor, used for obtaining the loading load of the pneumatic loading device in real time;

[0014] A back propagation neural network, used to obtain the proportional gain, the integral gain and the differential gain of the proportional-integral-differential regulation algorithm;

[0015] A regulator, used for executing the proportional-integral-derivative regulation algorithm to obtain the load;

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

[0017] in,

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

[0019] This solution uses the central processing unit as the control core and the load force sensor as the signal acquisition device. It not only realizes the controllable loading, but also ensures the control accuracy and achieves the effect of closed-loop control of the loading amount.

[0020] In a possible implementation, the loading force sensor is a resistive strain force sensor; thus, the loading load of the pneumatic loading device can be obtained more accurately, and the sensor is relatively small in size.

[0021] In a possible implementation, the proportional-integral-derivative adjustment algorithm is calculated as follows:

[0022]

[0023] In the formula,

[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 the sampling period;

[0029] a represents the current moment;

[0030] e(t) represents the error function determined by the error between all the loading loads obtained during a sampling period from the current moment and the target load;

[0031] represents the error change rate of the sampling starting point;

[0032] This solution can effectively reduce the computational complexity while ensuring that the load loading is accurately controllable, thereby reducing resource waste and improving control efficiency and speed.

[0033] In a possible implementation, the central processing unit is configured to perform the following steps:

[0034] A1: Retrieving all the loading loads obtained by the loading force sensor during a period from the current moment to the end of a sampling period, and respectively calculating the errors between these loading loads and the target load to obtain an error distribution;

[0035] A2: According to the result obtained in step A1, the error change rate at the current moment is obtained by using the error at the current moment and the error at the next sampling moment after the current moment;

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

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

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

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

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

[0041] If not, then go back to step A1;

[0042] This scheme obtains the error and error change rate based on the loading load obtained by the loading force sensor in a sampling period, and uses the error and error change rate to manipulate the back propagation neural network to obtain the proportional gain, integral gain and differential gain. Then the regulator runs, and the proportional gain, integral gain and differential gain obtained by the back propagation neural network are used as the proportional gain, integral gain and differential gain of the proportional-integral-differential algorithm, and finally the loading amount is obtained. According to the loading amount, the pneumatic loading device is called to perform loading, ensuring that the loading is carried out reasonably and orderly, and the efficiency is further improved.

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

[0044] An acoustic emission sensor, used to obtain the acoustic emission signal;

[0045] A vibration sensor, used for acquiring the vibration signal;

[0046] A power sensor, used to obtain the power signal;

[0047] A signal amplifier, used to amplify the acoustic emission signal, the vibration signal and the power signal respectively to form an amplified signal;

[0048] A data acquisition card, used for performing analog-to-digital conversion on the amplified signal obtained by the signal amplifier to obtain digital information;

[0049] A support vector machine module is configured to obtain the wear amount through a condition monitoring algorithm of a support vector machine;

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

[0051] in,

[0052] The signal amplifier is electrically connected to the acoustic emission sensor, the vibration sensor and the power sensor at the same time, the data acquisition card is electrically connected to the signal amplifier, and the recording and analysis device is electrically connected to the data acquisition card and the support vector machine module at the same time;

[0053] This solution uses acoustic emission sensors, vibration sensors and power sensors to collect information, and uses signal amplifiers to achieve signal conditioning. This enables real-time monitoring of vibration signals, acoustic emission signals and power signals containing original relevant information on the wear status of the disk sample when the friction and wear test begins. In addition, a support vector machine module is used to monitor the status of the sample, and the sample wear amount 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: preprocessing the digital information by removing invalid data and performing wavelet threshold noise reduction processing to remove interference signals and obtain a preprocessing result;

[0056] B2: performing time domain, frequency domain and time-frequency domain feature extraction on the preprocessing results to obtain feature information;

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

[0058] B4: Finding a sensor corresponding to the sensitive characteristic variable from the acoustic emission sensor, the vibration sensor, and the power sensor, and retrieving digital information formed by a signal obtained by the sensor corresponding to the sensitive characteristic variable to obtain the fused feature vector;

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

[0060] This scheme preprocesses the collected original signals by removing invalid data and performing wavelet threshold denoising to eliminate interference signals caused by environmental noise and poor acquisition parameter settings, thereby improving the accuracy of wear status monitoring; in addition, by extracting time domain, frequency domain and time-frequency domain features from the preprocessed 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 prediction of disk sample wear, the wear characteristics of the disk sample can be effectively characterized; in addition, the feature quantities of multi-sensor signals that have undergone feature screening are combined into a fused feature vector, and the support vector machine module is called to monitor the status of the sample, thereby outputting the sample wear with high prediction accuracy.

[0061] In a possible implementation, the result module further includes a display, which is used to display the loading load obtained by the loading force sensor and the wear amount of the disk sample, and the display is electrically connected to the recording and analysis device and the central processing unit at the same time.

[0062] Another technical solution of the present invention is to provide a wear monitoring method for a variable load friction and wear testing device, the method comprising the following steps:

[0063] S1: Install the disc sample on the connection portion provided on the rotating shaft, and install the pin sample on the fixture provided on the 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 through the driving module;

[0065] S3: obtaining, through a result module, a vibration signal, an acoustic emission signal, and a power signal of the disk sample in a worn state when the pin sample and the disk sample rub against each other;

[0066] S4: Obtaining a fusion feature vector by performing correlation analysis on the vibration signal, the acoustic emission signal and the power signal through the result module;

[0067] S5: Obtaining the wear amount of the disc sample based on the fused feature vector by using the condition monitoring algorithm of the support vector machine through the result module.

[0068] The method disclosed by the present invention, after installing the disk sample and the pin sample, loads the pin sample through a loading device, and drives the rotating shaft to rotate around its axis through a driving module, and then obtains a fused feature vector by performing correlation analysis on the vibration signal, the acoustic emission signal and the power signal through a result module; and obtains the wear amount of the disk sample based on the fused feature vector by using a state monitoring algorithm of a support vector machine, thereby overcoming the disadvantages brought by collecting a single signal, meeting the demand for online real-time monitoring of the wear condition of the sample, and ensuring the accuracy and effectiveness of monitoring the wear condition of the sample, and can apply pin-disk friction with variable load, and can monitor the wear amount in real time, providing 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. BRIEF DESCRIPTION OF THE DRAWINGS

[0069] Figure 1 It is a schematic structural diagram of a variable load friction and wear testing device disclosed in an embodiment of the present invention;

[0070] Figure 2 It is a flow chart of the operation of the central processing unit disclosed in the embodiment of the present invention;

[0071] Figure 3 is an operation flow chart of the record analysis device disclosed in the embodiment of the present invention;

[0072] Figure 4 It is a flow chart of the method disclosed in the embodiment of the present invention. DETAILED DESCRIPTION

[0073] First, those skilled in the art should understand that these implementations are only used to explain the technical principles of the embodiments of the present application, and are not intended to limit the protection scope of the embodiments of the present application. Those skilled in the art can make adjustments to them as needed to adapt to specific application scenarios.

[0074] In the description of the embodiments of the present application, it should be noted that, unless otherwise clearly specified and limited, the terms "connected" and "connection" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be directly connected or indirectly connected through an intermediate medium. For ordinary technicians in this field, the specific meanings of the above terms in the embodiments of the present application can be understood according to specific circumstances.

[0075] In the description of the embodiments of the present application, it should be noted that, unless otherwise clearly specified and limited, the terms "electrical connection" and "electrical connection relationship" should be understood in a broad sense, that is, referring to a connection method with an electrical relationship, for example, it can be a circuit connection through a conductive wire, or it can be an electrical connection through a radio signal channel (channel), or a combination of the two. In addition, "electrical connection" and "electrical connection relationship" can be based on mechanical connection (such as a conductive wire set in a connecting key); it can be a direct connection or an indirect connection through an intermediate medium. For those of ordinary skill in the art, the specific meanings of the above terms in the embodiments of the present application can be understood according to specific circumstances.

[0076] In the embodiments of the present application, unless otherwise clearly specified and limited, a first feature being "above" or "below" a second feature may mean 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, a first feature being "above", "above" or "above" a second feature may mean that the first feature is directly above or obliquely above the second feature, or simply means that the first feature is higher in level than the second feature. A first feature being "below", "below" or "below" a second feature may mean that the first feature is directly below or obliquely below the second feature, or simply means that the first feature is lower in level than the second feature.

[0077] The present application is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0078] See also Figure 1 to Figure 4 As shown, the embodiment of the present application discloses a variable load friction and wear test device, Figure 1 It is a structural schematic diagram of the experimental device, which includes 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 portion that can be detachably matched with the disk sample, the loading device is provided with a clamp that can be detachably matched with the pin sample, the driving module is connected to the rotating shaft, the driving module is used to drive the rotating shaft to rotate around its axis, and the control module is electrically connected to the loading device.

[0079] See also Figure 1 In the experimental device, the loading device is used to make the pin sample contact with the disk sample and load the pin sample by pneumatic loading. The loading device includes a pneumatic loading device and a shell for accommodating the pneumatic loading device. The pneumatic loading device is electrically connected to the control module, and the fixture for mounting the pin sample is set on the shell. In addition, a loading channel is opened on the shell to facilitate the pneumatic loading device to load.

[0080] Please continue to see Figure 1In the experimental device, the control module is configured to obtain the error and error change rate between the loading load and the target load during the loading process, and then obtain the proportional gain, integral gain and differential gain of the proportional-integral-differential adjustment algorithm using the error and error change rate through the neural network algorithm, and finally obtain the load amount for the next step of loading through the proportional-integral-differential adjustment algorithm using the error and error change rate, and call the loading device to perform loading according to the load amount. The control module includes a loading force sensor, a back propagation neural network (BP network for short), a regulator 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 to the loading force sensor, the back propagation neural network, the regulator and the pneumatic loading device at the same time.

[0081] In the control module, the loading force sensor is a resistive strain force sensor, which 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, integral gain and differential gain of the proportional-integral-differential control algorithm; the regulator is used to execute the proportional-integral-differential control algorithm to obtain the loading amount; the central processing unit is configured to obtain the error and the error change rate according to the loading load obtained by the loading force sensor, and use the error and the error change rate to control the back propagation neural network and the regulator to obtain the loading amount, and call the pneumatic loading device to perform loading according to the loading amount.

[0082] In the control module, the proportional-integral-derivative adjustment algorithm is calculated as follows:

[0083]

[0084] In the formula,

[0085] P represents the loading, which is predicted by the back-propagation neural network;

[0086] K1 represents the proportional gain, which is predicted by the back-propagation neural network;

[0087] K2 represents the integral gain, which is predicted by the back-propagation neural network;

[0088] K3 represents the differential gain;

[0089] T represents the sampling period;

[0090] a represents the current moment;

[0091] e(t) represents the error function determined by the error between all the loading loads and the target load obtained during a sampling period from the current moment;

[0092] Represents the error change rate at the sampling starting point, which is the change rate of the error function at the sampling starting point.

[0093] See also Figure 2 ,In the control module, the central processing unit is configured to perform the following steps;

[0094] A1: retrieve all the loading loads obtained by the loading force sensor during a sampling period from the current moment, and calculate the errors between these loading loads and the target load to obtain the error distribution.

[0095] In principle, the length of the sampling period should be smaller, for example, it can be set at the microsecond level or smaller, so as to reduce 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]. If all the loads obtained by the load sensor in the interval [a, a+T] are P1, P2, ..., P S , and the target load is set to The error between these applied loads and the target load is S is a natural number not less than 1.

[0096]

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

[0098] A2: According to the error distribution obtained in step A1, the error at the current moment and the error at the next sampling moment after the current moment are used to obtain the error change rate at the current moment.

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

[0100]

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

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

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

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

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

[0106] If not, the process returns to step A1.

[0107] In the experimental device, the result module is set to obtain the vibration signal, acoustic emission signal and power signal of the disk sample in a worn state when the pin sample and the disk sample rub against each other, and obtain the fused feature vector by performing correlation analysis on the vibration signal, acoustic emission signal and power signal. Finally, the state monitoring algorithm of the support vector machine is used to obtain the wear amount of the disk sample based on the fused feature vector.

[0108] Please continue to see Figure 1 In this 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 analysis device and a display, wherein the signal amplifier is electrically connected to the acoustic emission sensor, the vibration sensor and the power sensor at the same time, the data acquisition card is electrically connected to the signal amplifier, the recording and analysis device is electrically connected to the data acquisition card and the support vector machine module at the same time, and the display is electrically connected to the recording and analysis 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 an amplified signal; the data acquisition card is used to perform analog-to-digital conversion on the amplified signal obtained by the signal amplifier to obtain digital information; the support vector machine module is configured to obtain the wear amount through the state monitoring algorithm of the support vector machine; the recording and analysis device is configured to obtain a fused feature vector by performing correlation analysis on the digital information, and finally the support vector machine module is called to obtain the wear amount of the disk sample based on the fused feature vector; the display is used to display the loading load obtained by the loading force sensor and the wear amount of the disk sample.

[0110] See also Figure 3In the result module, the recording and analysis device is configured to perform the following steps: B1: pre-process the digital information by removing invalid data and performing wavelet threshold noise reduction processing to eliminate interference signals and obtain pre-processing results; B2: extract the features of the pre-processing results in the time domain, frequency domain and time-frequency domain to obtain feature information; B3: perform correlation analysis on the feature information to screen out sensitive feature variables whose correlation with the wear amount prediction of the disk sample exceeds a specified value; B4: find the sensor corresponding to the sensitive feature variable from the acoustic emission sensor, vibration sensor and power sensor, and retrieve the digital information formed by the signal obtained by the sensor corresponding to the sensitive feature variable to obtain a fused feature vector; B5: call the support vector machine module to obtain the wear amount of the disk sample based on the fused feature vector.

[0111] The recorded analysis device pre-processes the collected original signal (i.e., digital information) by removing invalid data and performing wavelet threshold noise reduction processing to eliminate interference signals caused by environmental noise interference and poor acquisition parameter settings, thereby improving the accuracy of wear status monitoring; in addition, the pre-processed vibration signal, acoustic emission signal, and power signal data are subjected to time domain, frequency domain, and time-frequency domain feature extraction, and the correlation analysis method is used to screen out sensitive feature variables with a high correlation with the prediction of the disk sample wear amount, thereby achieving effective characterization of the disk sample wear characteristics; in addition, the feature quantities of the multi-sensor signal that have undergone feature screening are combined into a fused feature vector, and the support vector machine module is called to monitor the sample status, thereby outputting the sample wear amount with a high prediction accuracy.

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

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

[0114] S2: The control module calls the loading device to load the pin sample, and drives the rotating shaft to rotate around its axis through the driving module. The loading method can refer to steps A1 to A6.

[0115] S3: When the pin sample and the disk sample rub against each other, a vibration signal, an acoustic emission signal and a power signal of the disk sample in a worn state are obtained through the result module.

[0116] S4: Obtain a fused feature vector by performing correlation analysis on the vibration signal, the acoustic emission signal and the power signal through the result module. The process of obtaining the fused feature vector can be referred to steps B1 to B4.

[0117] S5: The wear amount of the disc sample is obtained based on the fused feature vector by using the condition monitoring algorithm of the support vector machine through the result module.

[0118] The variable load friction and wear test device disclosed in this embodiment is based on the existing cooperation between the rotating shaft and the driving module, and a loading device is provided on the loading device, and a fixture that can be detachably matched with the pin sample is provided, and the loading device is configured to load the pin sample by pneumatic loading, and the loading device is controlled by the control module, so as to ensure the stability of the applied load. In addition, a result module is set to obtain vibration signals, acoustic emission signals and power signals when friction occurs between the pin sample and the disk sample, and a fused feature vector is obtained by performing correlation analysis on the vibration signal, the acoustic emission signal and the power signal, and finally the state monitoring algorithm of the support vector machine is used to obtain the wear amount of the disk sample based on the fused feature vector, and the wear volume of the disk sample during 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 rotational power of the disk sample respectively, thereby overcoming the disadvantages brought by collecting a single signal, and meeting the needs of online real-time monitoring of the wear condition of the sample, and the accuracy and effectiveness of monitoring the wear condition of the sample are guaranteed. Therefore, the variable load friction and wear testing device disclosed in the present invention can not only apply variable load pin-disc friction, but also monitor the wear amount in real time, providing an important basis for understanding the friction and wear performance of materials under actual working conditions and improving the service life of workpieces.

[0119] In the description of the embodiments of the present application, it should be noted that in the description of the present application, terms such as "inside" and "outside" indicating directions or positional relationships are based on the directions or positional relationships shown in the drawings. This is only for the convenience of description, and does not indicate or imply that the device or component must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it cannot be understood as a limitation on the present application.

[0120] In the description of the present application, the description with reference to the terms "one embodiment", "some embodiments", "in the present embodiment", "specific example", or "some examples" etc. 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 this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, mechanisms, materials or characteristics described may be combined in a suitable manner in any one or more embodiments or examples. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0121] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A variable load friction and wear test device, comprising a rotating shaft and a driving module for driving the rotating shaft to rotate around its axis, wherein the top of the rotating shaft is provided with a connecting portion that can be detachably matched with a disc sample, and the driving module is connected to the rotating shaft, characterized in that: Also includes: A loading device, on which a fixture is provided that is detachably matched with the pin sample, and is used to make the pin sample contact with the disc sample, and to load the pin sample by pneumatic loading; a control module, electrically connected to the loading device, and configured to obtain an error and an error change rate 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 using the error and the error change rate through a neural network algorithm, and finally obtain a load amount for the next loading step through the proportional-integral-differential adjustment algorithm using the error and the error change rate, and call the loading device to perform loading according to the load amount; The result module is configured to obtain the vibration signal, acoustic emission signal and power signal of the disc sample in a worn state when the pin sample rubs against the disc sample, and obtain a fused feature vector by performing correlation analysis on the vibration signal, acoustic emission signal and power signal, and finally obtain the wear amount of the disc sample based on the fused feature vector using a state monitoring algorithm of a support vector machine.

2. The variable load friction and wear testing device according to claim 1, characterized in that: The loading device includes a pneumatic loading device, and the pneumatic loading device is electrically connected to the control module.

3. The variable load friction and wear testing device according to claim 2, characterized in that: The control module comprises: A loading force sensor, used for obtaining the loading load of the pneumatic loading device in real time; A back propagation neural network, used to obtain the proportional gain, the integral gain and the differential gain of the proportional-integral-differential regulation algorithm; A regulator, used for executing the proportional-integral-derivative regulation algorithm to obtain the load; A central processing unit is configured to obtain the error and the error change rate according to the loading load obtained by the loading force sensor, and use the error and the error change rate to control the back propagation neural network and the regulator to obtain the loading amount, and call the pneumatic loading device to perform loading according to the loading amount; in, The loading force sensor is arranged on the pneumatic loading device, and the central processing unit is electrically connected to the loading force sensor, the back propagation neural network, the regulator and the pneumatic loading device at the same time.

4. The variable load friction and wear testing device according to claim 3, characterized in that: The loading force sensor is a resistance strain type force sensor.

5. The variable load friction and wear testing device according to claim 4, characterized in that: The formula of the proportional-integral-derivative adjustment algorithm is as follows: In the formula, P represents the loading amount; K1 represents the proportional gain; K2 represents the integral gain; K3 represents the differential gain; T represents the sampling period; a represents the current moment; e(t) represents the error function determined by the error between all the loading loads obtained during a sampling period from the current moment and the target load; Represents the error change rate of the sampling starting point.

6. The variable load friction and wear testing device according to any one of claims 3 to 5, characterized in that: The central processing unit is configured to perform the following steps: A1: Retrieving all the loading loads obtained by the loading force sensor during a period from the current moment to the end of a sampling period, and respectively calculating the errors between these loading loads and the target load to obtain an error distribution; A2: According to the result obtained in step A1, the error change rate at the current moment is obtained by using the error at the current moment and the error at the next sampling moment after the current moment; A3: calling the back propagation neural network to obtain the proportional gain, the integral gain and the differential gain by taking the error and the error change rate at the current moment as input; A4: calling the regulator to obtain the loading amount according to the results obtained in step A1 and step A3, and calling the pneumatic loading device to perform loading according to the loading amount; A5: Retrieving the loading load obtained by the loading force sensor at this time, and calculating the error value between the loading load obtained at this time and the target load; A6: Determine whether the error value obtained in step A5 is less than a threshold; If yes, the pneumatic loading device is controlled to stop loading; If not, the process returns to step A1.

7. The variable load friction and wear testing device according to claim 6, characterized in that: The result module includes: An acoustic emission sensor, used to obtain the acoustic emission signal; A vibration sensor, used for acquiring the vibration signal; A power sensor, used to obtain the power signal; A signal amplifier, used to amplify the acoustic emission signal, the vibration signal and the power signal respectively to form an amplified signal; A data acquisition card, used for performing analog-to-digital conversion on the amplified signal obtained by the signal amplifier to obtain digital information; A support vector machine module is configured to obtain the wear amount through a condition monitoring algorithm of a support vector machine; a recording and analyzing device, configured to obtain a fused feature vector by performing correlation analysis on the digital information, and finally calling the support vector machine module to obtain the wear amount of the disc sample based on the fused feature vector; in, The signal amplifier is electrically connected to the acoustic emission sensor, the vibration sensor and the power sensor at the same time, the data acquisition card is electrically connected to the signal amplifier, and the recording and analyzing device is electrically connected to the data acquisition card and the support vector machine module at the same time.

8. The variable load friction and wear testing device according to claim 7, characterized in that: The record analysis device is configured to perform the following steps: B1: preprocessing the digital information by removing invalid data and performing wavelet threshold noise reduction processing to remove interference signals and obtain a preprocessing result; B2: performing time domain, frequency domain and time-frequency domain feature extraction on the preprocessing results to obtain feature information; B3: performing correlation analysis on the characteristic information to screen out sensitive characteristic variables whose correlation with the wear amount prediction of the disc sample exceeds a specified value; B4: Finding a sensor corresponding to the sensitive characteristic variable from the acoustic emission sensor, the vibration sensor, and the power sensor, and retrieving digital information formed by a signal obtained by the sensor corresponding to the sensitive characteristic variable to obtain the fused feature vector; B5: Call the support vector machine module to obtain the wear amount of the disc sample based on the fused feature vector.

9. The variable load friction and wear testing device according to claim 7 or 8, characterized in that: The result module also includes a display, which is used to display the loading load obtained by the loading force sensor and the wear amount of the disk sample. The display is also electrically connected to the recording and analysis device and the central processing unit.

10. A wear monitoring method for a variable load friction and wear testing device, characterized in that: The variable load friction and wear testing device applicable to any one of claims 1 to 9 comprises the following steps: S1: Install the disc sample on the connection portion provided on the rotating shaft, and install the pin sample on the fixture provided on the loading device, so that the pin sample contacts the disc sample; 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 through the driving module; S3: obtaining, through a result module, a vibration signal, an acoustic emission signal, and a power signal of the disk sample in a worn state when the pin sample and the disk sample rub against each other; S4: Obtaining a fusion feature vector by performing correlation analysis on the vibration signal, the acoustic emission signal and the power signal through the result module; S5: Obtaining the wear amount of the disc sample based on the fused feature vector by using the condition monitoring algorithm of the support vector machine through the result module.

Images