A method for adaptive stress elimination system of coal mining machine pick based on ultrasonic wave

Abstract

The present invention discloses an ultrasonic-based self-adaptive stress elimination system for coal mining machine picks. The system first constructs a stress distribution model of the pick according to on-site conditions, then integrates the corresponding relationships among the on-site working environment, the stress distribution of the pick, and the working mode of a self-tuning system into a database and substitutes them into a wavelet neural network for training. Finally, the self-adaptive stress elimination system performs self-adaptive stress elimination on the pick according to the output result and provides real-time feedback on the strain elimination status, thereby effectively improving the stress elimination efficiency and reducing the potential safety hazards caused by stress elimination on site.

Description

Technical Field

[0001] The invention relates to the technical field of self-adaptive stress elimination of cutting hobbing gears, and in particular to a method of a self-adaptive stress elimination system of a coal mining machine cutting gear based on ultrasonic waves. Background Art

[0002] During the operation of the coal mining machine, its picks are in direct contact with the coal seam, which is often mixed with hard minerals such as quartz and pyrite. When the drum rotates, the picks evenly distributed on the outer surface of the drum in a spiral line are in a periodic impact coal breaking state, accompanied by extrusion, shearing, crushing and other stages. During this period, the picks are in a high cutting and grinding state, and the stress on the picks is aggravated. The existence of stress is the main reason that affects the life of the picks and causes the failure of the picks. The failure of the picks can cause abnormal loads on the coal mining machine. The unbalanced impact load generated by it can easily make the cutting part of the coal mining machine lose stability, causing abnormal vibration of the fuselage, abnormal operation of the transmission device, broken walking wheels and loose connection components, etc. It will also cause the coal loading capacity of the coal mining machine drum to decrease, resulting in too high a bottom of the cut coal, which in turn affects the movement of the bracket and scraper and damage to the supporting structure of the coal mining machine.

[0003] Aging treatment can eliminate the internal stress of the workpiece, stabilize the structure and size, improve the mechanical properties, etc. At present, there are four aging treatment methods: natural aging, thermal aging, vibration aging and ultrasonic impact aging. Among them, ultrasonic impact aging is the latest stress elimination method. Summary of the invention

[0004] In view of the above technical deficiencies, the purpose of the present invention is to provide a method for an ultrasonic-based coal mining machine pick stress adaptive elimination system, which first constructs a pick stress distribution model according to the on-site conditions, then integrates the corresponding relationship between the on-site working environment, the pick stress distribution, and the working mode of the self-tuning system into a database and substitutes it into the wavelet neural network for training, and finally the stress adaptive elimination system performs stress adaptive elimination on the pick according to the output results and provides real-time feedback on the strain elimination situation. This effectively improves the efficiency of stress elimination and reduces the potential safety hazards caused by stress elimination on site.

[0005] In order to solve the above technical problems, the present invention adopts the following technical solutions:

[0006] The present invention provides a method for a coal mining machine pick stress adaptive elimination system based on ultrasonic wave, comprising the following steps:

[0007] Step M1. According to the working conditions on site, collect the rotation speed, temperature, stress condition, elastic modulus, and thermal expansion coefficient of the pick;

[0008] Step M2. Substituting the obtained parameters into the inherent stress mathematical model to obtain the values ​​of compressive plastic stress and tensile plastic stress;

[0009] Step M3. Adding the compressive plastic stress and the tensile plastic stress in the pick to obtain the final inherent stress;

[0010] Step M4. Integrate the obtained inherent stress, and then perform field experimental sampling and correction to obtain the final mathematical model of transverse and longitudinal inherent stress distribution and the mathematical model of transverse and longitudinal bending stress distribution;

[0011] Step M5. Conduct multiple groups of experiments to obtain a database of the correspondence between the on-site working environment, the stress distribution of cutting and hobbing, and the working mode of the stress adaptive elimination system;

[0012] Step M6. Substitute the database into the wavelet neural network to train its weights, obtain the corresponding relationship between the three in step M5, extract the corresponding parameters of the pick required for stress relief as input information, and obtain the setting of the system's working mode;

[0013] Step M7. The output data of the wavelet neural network is transmitted to the industrial control PC, and the industrial control PC controls the stress adaptive elimination system to eliminate stress on the pick;

[0014] Step M8. At the same time, the stress feedback detection device in the stress adaptive relief system feeds back the stress relief situation to the industrial control PC in real time, so as to fine-tune the working parameters of the stress adaptive relief system until the stress relief is completed.

[0015] Preferably, in step M2, the step of obtaining the values ​​of compressive plastic stress and tensile plastic stress according to corresponding data includes:

[0016] It includes two processes: the internal stress distribution of the drum pick is the comprehensive result of the influence of two situations, one is the influence of the force and friction heat on the drum pick during work, and the other is the stress change inside the drum pick when work stops; the total stress inside the pick during the whole process includes elastic stress, plastic stress, thermal stress and metal phase change stress, which can be expressed as follows

[0017] ε=ε e +ε p +ε t +ε x (13)

[0018] The inherent stress in the cutting and hobbing process is also called inelastic stress, that is,

[0019] ε * =ε-ε e =ε p +ε t +ε x (14)

[0020] Where ε represents the total stress, ε * is the inelastic stress, ε e is the elastic stress, ε p is the plastic stress, ε t is the thermal stress, ε x is the metal phase transition stress;

[0021] When the pick is not working, the thermal stress is considered to be zero; under the premise of ignoring the metal phase transformation stress, the residual plastic stress is equal to the inherent stress, that is,

[0022] ε * =ε p (15)

[0023] The tensile plastic stress, compressive plastic stress and tensile plastic stress are calculated by the following formula, that is, ε p1 =-a(T max -T0) (16)

[0024]

[0025] Among them, ε p1 is the compressive plastic stress, ε p2 is the tensile plastic stress, a is the thermal expansion coefficient, T max is the maximum friction heat that can be achieved when the pick is working, T0 is room temperature, T 2max The maximum change of the internal temperature of the pick when it stops working, σ y is the yield stress, E is the elastic modulus, A is the cross-sectional area of ​​the pick, L is the width of the inherent stress, k z is the elastic coefficient of the pick.

[0026] Preferably, in step M3, the final inherent stress is obtained by adding the compressive plastic stress and the tensile plastic stress in the pick, which is expressed by the following formula:

[0027]

[0028] In the formula, T c is the difference in average temperature in the plastic strain zone;

[0029] The transverse and longitudinal inherent stress values ​​are calculated by the following formula:

[0030]

[0031] In the formula is the transverse inherent stress, is the longitudinal inherent stress, T cx is the difference in the average transverse temperature of the plastic stress zone, T cy is the difference in the longitudinal average temperature of the plastic stress zone.

[0032] Preferably, step M4 includes the following process:

[0033] A set of stress values ​​is used to characterize the mathematical model of stress distribution of the entire pick. The mathematical model of stress distribution of the section perpendicular to the pick includes four parts: transverse and longitudinal inherent stress, transverse and longitudinal bending stress. The inherent stress is integrated and calculated. Finally, the obtained model is corrected through multiple on-site sampling experiments. The specific mathematical model of stress distribution is as follows:

[0034]

[0035] In the formula, x is the side direction of the pick, y is the height direction of the pick and z is perpendicular to the side direction of the pick, h is the thickness of the front section of the pick, c, d, f, g are the compensation coefficients of transverse and longitudinal inherent stresses, transverse and longitudinal bending stresses respectively.

[0036] Preferably, in step M6, the database is substituted into the wavelet neural network to train its weights, and the specific analysis is as follows:

[0037] The operation mechanism of wavelet neural network is mainly divided into two parts, namely the forward transmission of network input information and the reverse propagation of network calculation error. The specific training and application steps of BP neural network are as follows;

[0038] (1) Determination of network topology and initialization of related parameters;

[0039] (2) Learning of wavelet neural network: the on-site working environment data information is transmitted from the input layer to the output layer via the hidden layer. The output layer calculates and outputs the stress distribution of the pick cutter of the process network.

[0040] (3) Calculate the error between the network data pick stress distribution and the expected value in the database, and propagate the error information back to the input layer, while adjusting the weights and thresholds between the layers;

[0041] (4) Iterate steps (2) and (3) to gradually reduce the calculation error until the error reaches the set target error or the number of iterations reaches the set maximum number;

[0042] (5) Obtaining the optimal weights and thresholds;

[0043] (6) Extract the on-site working parameters of the test sample, and use the optimal weights and thresholds obtained in step (5) to calculate the stress distribution of the test sample. Finally, the corresponding working mode of the stress adaptive relief system is obtained based on the obtained stress distribution.

[0044] Preferably, in step M7, the stress adaptive elimination system includes an industrial PC, a multi-degree-of-freedom platform, an induction heating device and an infrared detection device; the industrial PC runs a wavelet neural network and outputs corresponding parameter settings for controlling the multi-degree-of-freedom platform, the induction heating device and the infrared detection device; the multi-degree-of-freedom platform drives the induction heating device to perform different degrees of stress adaptive elimination on other different positions according to the stress distribution of different picks; the induction heating device controls the heating temperature change to achieve different degrees of stress elimination; the stress feedback detection device monitors the stress changes of the pick in real time and feeds back the fine-tuning parameters, and cooperates with the ultrasonic wave to accurately complete the stress elimination of the pick.

[0045] The beneficial effects of the present invention are:

[0046] 1. The present invention collects relevant parameters of the pick working on site, constructs a mathematical model of the stress distribution of the pick, and compares it with the actual situation, so that the desired model is more consistent with the actual stress distribution;

[0047] 3. The present invention establishes a database of the corresponding relationship between the on-site working conditions, the stress distribution of the pick, and the working mode of the stress adaptive elimination system, substitutes it into the wavelet neural network for training, and directly inputs the relevant data to obtain the stress distribution, and gives a reasonable working mode setting of the stress adaptive elimination system;

[0048] 5. The present invention uses an ultrasonic failure treatment method to eliminate the stress of cutting and hobbing gears, and adopts ultrasonic excitation with small amplitude and high frequency to avoid the risk of excessive deformation and cracking caused by low-frequency resonance effects.

[0049] 6. The present invention finally uses a stress feedback detection device in conjunction with ultrasonic waves to accurately eliminate the stress of the pick. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0051] Figure 1 The present invention provides a method flow chart of a coal mining machine pick stress adaptive elimination system based on wavelet neural network and ultrasonic wave.

[0052] Figure 2 The present invention provides a flow chart of the method for constructing a model of pick stress distribution.

[0053] Figure 3A flow chart of the method used by the wavelet neural network provided by the present invention.

[0054] Figure 4 A schematic diagram of a stress adaptive relief system according to an embodiment of the present invention.

[0055] Among them, 1. Industrial control PC, 2. Multi-degree-of-freedom platform, 3. Ultrasonic aging device, 4. Infrared detection device, 5. Cutting teeth. DETAILED DESCRIPTION

[0056] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0057] like Figures 1 to 4 As shown, a method for an ultrasonic-based coal mining machine pick stress adaptive elimination system comprises the following steps:

[0058] Step M1. According to the working conditions on site, collect the rotation speed, temperature, stress condition, elastic modulus, and thermal expansion coefficient of the pick;

[0059] Step M2. Substituting the obtained parameters into the inherent stress mathematical model to obtain the values ​​of compressive plastic stress and tensile plastic stress;

[0060] The steps for obtaining the values ​​of compressive plastic stress and tensile plastic stress based on the corresponding data include:

[0061] It includes two processes: the internal stress distribution of the drum pick is the comprehensive result of the influence of two situations, one is the influence of the force and friction heat on the drum pick during work, and the other is the stress change inside the drum pick when work stops; the total stress inside the pick during the whole process includes elastic stress, plastic stress, thermal stress and metal phase change stress, which can be expressed as follows

[0062] ε=ε e +ε p +ε t +ε x (25)

[0063] The inherent stress in the cutting and hobbing process is also called inelastic stress, that is,

[0064] ε * =ε-ε e =ε p +ε t +ε x (26)

[0065] Where ε represents the total stress, ε * is the inelastic stress, ε e is the elastic stress, ε p is the plastic stress, ε t is the thermal stress, ε x is the metal phase transition stress;

[0066] When the pick is not working, the thermal stress is considered to be zero; under the premise of ignoring the metal phase transformation stress, the residual plastic stress is equal to the inherent stress, that is,

[0067] ε * =ε p (27)

[0068] The tensile plastic stress, compressive plastic stress and tensile plastic stress are calculated by the following formula:

[0069] ε p1 =-a(T max -T0) (28)

[0070]

[0071] Among them, ε p1 is the compressive plastic stress, ε p2 is the tensile plastic stress, a is the thermal expansion coefficient, T max is the maximum friction heat that can be achieved when the pick is working, T0 is room temperature, T 2max The maximum change of the internal temperature of the pick when it stops working, σ y is the yield stress, E is the elastic modulus, A is the cross-sectional area of ​​the pick, L is the width of the inherent stress, k z is the elastic coefficient of the pick.

[0072] Step M3. Adding the compressive plastic stress and the tensile plastic stress in the pick to obtain the final inherent stress;

[0073] In step M3, the final inherent stress is obtained by adding the compressive plastic stress and the tensile plastic stress in the pick, which is expressed as follows:

[0074]

[0075] In the formula, T c is the difference in average temperature in the plastic strain zone;

[0076] The transverse and longitudinal inherent stress values ​​are calculated by the following formula:

[0077]

[0078] In the formula is the transverse inherent stress, is the longitudinal inherent stress, T cx is the difference in the average transverse temperature of the plastic stress zone, T cy is the difference in the longitudinal average temperature of the plastic stress zone.

[0079] Step M4. Integrate the obtained inherent stress, and then perform field experimental sampling and correction to obtain the final mathematical model of transverse and longitudinal inherent stress distribution and the mathematical model of transverse and longitudinal bending stress distribution;

[0080] The process includes:

[0081] A set of stress values ​​is used to characterize the mathematical model of stress distribution of the entire pick. The mathematical model of stress distribution of the section perpendicular to the pick includes four parts: transverse and longitudinal inherent stress, transverse and longitudinal bending stress. The inherent stress is integrated and calculated. Finally, the obtained model is corrected through multiple on-site sampling experiments. The specific mathematical model of stress distribution is as follows:

[0082]

[0083] In the formula, x is the side direction of the pick, y is the height direction of the pick and z is perpendicular to the side direction of the pick, h is the thickness of the front section of the pick, c, d, f, g are the compensation coefficients of transverse and longitudinal inherent stresses, transverse and longitudinal bending stresses respectively.

[0084] Step M5. Conduct multiple groups of experiments to obtain a database of the correspondence between the on-site working environment, the stress distribution of cutting and hobbing, and the working mode of the stress adaptive elimination system;

[0085] Step M6. Substitute the database into the wavelet neural network to train its weights, obtain the internal relationship, extract the corresponding parameters of the pick required for stress relief as input information, and obtain the setting of the system's working mode;

[0086] Substitute the database into the wavelet neural network to train its weights. The specific analysis is as follows:

[0087] The operation mechanism of wavelet neural network is mainly divided into two parts, namely the forward transmission of network input information and the reverse propagation of network calculation error. The specific training and application steps of BP neural network are as follows;

[0088] (1) Determination of network topology and initialization of related parameters;

[0089] (2) Learning of wavelet neural network: the on-site working environment data information is transmitted from the input layer to the output layer via the hidden layer. The output layer calculates and outputs the stress distribution of the pick cutter of the process network.

[0090] (3) Calculate the error between the network data pick stress distribution and the expected value in the database, and propagate the error information back to the input layer, while adjusting the weights and thresholds between the layers;

[0091] (4) Iterate steps (2) and (3) to gradually reduce the calculation error until the error reaches the set target error or the number of iterations reaches the set maximum number;

[0092] (5) Obtaining the optimal weights and thresholds;

[0093] (6) Extract the on-site working parameters of the test sample, and use the optimal weights and thresholds obtained in step (5) to calculate the stress distribution of the test sample. Finally, the corresponding working mode of the stress adaptive relief system is obtained based on the obtained stress distribution.

[0094] Step M7. The output data of the wavelet neural network is transmitted to the industrial control PC, and the industrial control PC controls the stress adaptive elimination system to eliminate stress on the pick;

[0095] The stress adaptive elimination system includes an industrial control PC, a multi-degree-of-freedom platform, an induction heating device and an infrared detection device; the industrial control PC runs a wavelet neural network and outputs corresponding parameter settings for controlling the multi-degree-of-freedom platform, the induction heating device and the infrared detection device; the multi-degree-of-freedom platform drives the induction heating device to perform different degrees of stress adaptive elimination on other different positions according to the stress distribution of different picks; the induction heating device controls the heating temperature change to achieve different degrees of stress elimination; the stress feedback detection device monitors the stress change of the pick in real time and feeds back the fine-tuning parameters, and cooperates with the ultrasonic wave to accurately complete the stress elimination of the pick.

[0096] Step M8. At the same time, the stress feedback detection device in the stress adaptive relief system feeds back the stress relief situation to the industrial control PC in real time, and then the working parameters of the stress adaptive relief system can be fine-tuned until the stress relief is completed.

[0097] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A method for adaptively eliminating stress of coal mining machine pick based on ultrasonic wave, characterized in that: The following steps are involved: Step M1. According to the working conditions on site, collect the rotation speed, temperature, stress condition, elastic modulus and thermal expansion coefficient of the pick; Step M2. Substituting the obtained parameters into the inherent stress mathematical model to obtain the values ​​of compressive plastic stress and tensile plastic stress; The steps for obtaining the values ​​of compressive plastic stress and tensile plastic stress based on the corresponding data include: It includes two processes: the internal stress distribution of the drum pick is the comprehensive result of the influence of two situations, one is the influence of the force and friction heat on the drum pick during work, and the other is the stress change inside the drum pick when work stops; the total stress inside the pick during the whole process includes elastic stress, plastic stress, thermal stress and metal phase change stress, which can be expressed as follows e=e e +e p +e t +e x (1) The inherent stress in the cutting and hobbing process is also called inelastic stress, that is, e * =e-e e =e p +e t +e x (2) Where ε represents the total stress, ε * is the inelastic stress, ε e is the elastic stress, ε p is the plastic stress, ε t is the thermal stress, ε x is the metal phase transition stress; When the pick is not working, the thermal stress is considered to be zero; under the premise of ignoring the metal phase transformation stress, the residual plastic stress is equal to the inherent stress, that is, e * =e p (3) The tensile plastic stress, compressive plastic stress and tensile plastic stress are calculated by the following formula: ε p1 =-a(T max -T0) (4) Among them, ε p1 is the compressive plastic stress, ε p2 is the tensile plastic stress, a is the thermal expansion coefficient, T max is the maximum friction heat that can be achieved when the pick is working, T0 is room temperature, T 2max The maximum change of the internal temperature of the pick when it stops working, σ y is the yield stress, E is the elastic modulus, A is the cross-sectional area of ​​the pick, L is the width of the inherent stress, k z is the elastic coefficient of the pick; Step M3. Adding the compressive plastic stress and the tensile plastic stress in the pick to obtain the final inherent stress; The final inherent stress is obtained by adding the compressive plastic stress and the tensile plastic stress in the pick, which is expressed as follows: In the formula, T c is the difference in average temperature in the plastic strain zone; The transverse and longitudinal inherent stress values ​​are calculated by the following formula: In the formula is the transverse inherent stress, is the longitudinal inherent stress, T cx is the difference in the average transverse temperature of the plastic stress zone, T cy is the difference in the longitudinal average temperature of the plastic stress zone; Step M4. Integrate the obtained inherent stress, and then perform field experimental sampling and correction to obtain the final mathematical model of transverse and longitudinal inherent stress distribution and the mathematical model of transverse and longitudinal bending stress distribution; A set of stress values ​​is used to characterize the mathematical model of stress distribution of the entire pick. The mathematical model of stress distribution of the section perpendicular to the pick includes four parts: transverse and longitudinal inherent stress, transverse and longitudinal bending stress. The inherent stress is integrated and calculated. Finally, the obtained model is corrected through multiple on-site sampling experiments. The specific mathematical model of stress distribution is as follows: In the formula, x is the side direction of the pick, y is the height direction of the pick and z is the direction perpendicular to the side direction of the pick, h is the thickness of the front section of the pick, c, d, f, g are the compensation coefficients of transverse and longitudinal inherent stress, transverse and longitudinal bending stress respectively; Step M5. Conduct multiple groups of experiments to obtain a database of the correspondence between the on-site working environment, the distribution of cutting and hobbing stress, and the working mode of the stress adaptive elimination system; Step M6. Substitute the database into the wavelet neural network to train its weights, obtain the corresponding relationship between the three in step M5, extract the corresponding parameters of the pick required for stress relief as input information, and obtain the setting of the system's working mode; Step M7. The output data of the wavelet neural network is transmitted to the industrial control PC, and the industrial control PC controls the stress adaptive elimination system to eliminate stress on the pick; Step M8. At the same time, the stress feedback detection device in the stress adaptive relief system feeds back the stress relief situation to the industrial control PC in real time, so as to fine-tune the working parameters of the stress adaptive relief system until the stress relief is completed.

2. The method of the ultrasonic-based self-adaptive stress elimination system for coal mining machine picks according to claim 1, characterized in that: In step M6, the database is substituted into the wavelet neural network to train its weights. The specific analysis is as follows: The operation mechanism of wavelet neural network is divided into two parts, namely the forward transmission of network input information and the reverse propagation of network calculation error. The specific training and application steps of BP neural network are as follows; (1) Determination of network topology and initialization of related parameters; (2) Learning of wavelet neural network: the on-site working environment data information is transmitted from the input layer to the output layer through the hidden layer, and the output layer calculates and outputs the stress distribution of the pick cutter of the process network; (3) Calculate the error between the network data pick stress distribution and the expected value in the database, and propagate the error information back to the input layer, while adjusting the weights and thresholds between the layers; (4) Iterate steps (2) and (3) to gradually reduce the calculation error until the error reaches the set target error or the number of iterations reaches the set maximum number; (5) Obtaining the optimal weights and thresholds; (6) Extract the on-site working parameters of the test sample, and use the optimal weights and thresholds obtained in step (5) to calculate the stress distribution of the test sample. Finally, the corresponding working mode of the stress adaptive relief system is obtained based on the obtained stress distribution.

3. The method of the ultrasonic-based self-adaptive stress elimination system for coal mining machine picks according to claim 1, characterized in that: In step M7, the stress adaptive elimination system includes an industrial control PC, a multi-degree-of-freedom platform, an induction heating device and an infrared detection device; the industrial control PC runs a wavelet neural network and outputs corresponding parameter settings for controlling the multi-degree-of-freedom platform, the induction heating device and the infrared detection device; the multi-degree-of-freedom platform drives the induction heating device to perform different degrees of stress adaptive elimination on other different positions according to the stress distribution of different picks; the induction heating device controls the heating temperature change to achieve different degrees of stress elimination; the stress feedback detection device monitors the stress changes of the pick in real time and feeds back the fine-tuning parameters, and cooperates with the ultrasonic wave to accurately complete the stress elimination of the pick.

Images