Vibration monitoring method for cutting part of heading machine
By collecting and processing the vibration signals and speed signals of the cutting part of the boring machine in real time, combining neural network technology to identify working parameters and propose control strategies, the problem of excessive vibrations in the cutting part of the boring machine is solved, and the equipment stability and service life are improved.
Patent Information
- Application Number
- CN202411669584.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-21
- Publication Date
- 2025-03-28
AI Technical Summary
During the excavation process of the excavation machine, the cutting part vibration is too strong due to changes in the coal rock composition and the changes in the working parameters of the excavation machine, resulting in a reduction in the life of the cutting part.
A vibration monitoring method for cutting part of the boring machine is adopted, and the vibration signal of the cutting part and the speed signal of the cutting head is collected in real time, polynomial fitting denoising processing is used, combined with artificial neural network to identify working parameters, establish a control scheme model, and propose an optimal control strategy to reduce vibration.
It effectively improves the working stability of the cutting part, reduces the risk of equipment wear and failure caused by vibration, greatly extends the service life of the equipment, and also improves the excavation efficiency.
Smart Images
Figure CN119714512A_ABST
Abstract
Description
Technical Field The invention relates to the technical field of tunnel boring machines, and in particular to a vibration monitoring method for a cutting part of a tunnel boring machine. Background Art In recent years, with the vigorous development of the coal industry, the roadheader has become an important equipment in mine construction due to its stable structure, high working efficiency and good quality, and its application in the field of coal mining has become more and more extensive. Due to the different ore conditions of each coal mine, when the roadheader mines the ore with higher hardness, due to the continuous collision between the cutting part and the ore rock, it will cause severe wear, loosening or deformation of the alloy head at the front end of the pick, and the collapse or direct fracture of the tooth part. These failures are one of the important factors that currently restrict the efficient and high-yield mining of mine ore in my country. In addition, when excavating a rock wall with a large Proctor hardness coefficient, the cutting part of the tunnel boring machine will be affected by dynamic loads. Due to the different directions of the dynamic loads it bears, the cutting head will vibrate violently, which will cause some of its structures to fail prematurely. Among them, due to installation errors, wear of the fastening parts and some potential defects, the picks may become loose as the work intensity increases. In severe cases, the picks may even fall off and be lost, which not only increases the replacement and production costs of the picks, but also aggravates the waste of manpower and material resources. Moreover, if the loose and fallen picks cannot be tightened and replaced in time, the tunneling speed of the tunnel boring machine will drop sharply, thereby affecting the production efficiency of the entire production process. This places high demands on the tunnel boring machine operator. Therefore, in order to improve the intelligence and simplification of operation of the tunnel boring machine, a vibration monitoring device for the cutting part of the tunnel boring machine is proposed, which can monitor the vibration state of the cutting part of the tunnel boring machine, so that the operator can more clearly understand the working state of the tunnel boring machine and make adjustments. Summary of the invention In view of the above technical problems, the present invention aims to propose a vibration monitoring method for the cutting part of a tunnel boring machine. The method can collect the vibration signal of the cutting part and the speed signal of the cutting head in real time during the operation of the tunnel boring machine, so as to solve the problem of reduced life of the cutting part due to excessive vibration of the cutting part caused by changes in coal and rock composition and changes in the working parameters of the tunnel boring machine itself during the tunneling process. In order to achieve the above technical objectives, the present invention adopts the following technical means: A method for monitoring vibration of a cutting part of a tunnel boring machine comprises the following steps: S1, using a vibration signal acquisition device to collect a vibration signal of the cutting part; using a rotation speed signal acquisition device to collect a rotation speed signal of the cutting head; S2, performing polynomial fitting denoising processing on the cutting part vibration signal and cutting head speed signal collected in step S1 through a fitting formula to obtain a denoised cutting part vibration signal and cutting head speed signal; S3. Collect the current working parameters of the roadheader, including: the traction speed of the cutting part and the swing speed of the cutting arm. Through the identification of the three working parameters of the traction speed of the cutting part, the swing speed of the cutting arm and the rotation speed of the cutting head, an intelligent judgment method based on artificial neural network is used to learn the nonlinear mapping relationship between different working parameters and vibration characteristics in the corresponding vibration characteristics by using the neural network algorithm. A training sample set of the neural network is established through the denoised cutting part vibration signal and the three working parameters of the roadheader. A corresponding control scheme model is established through training to propose an optimal control strategy in the scheme model library: that is, according to the current working parameters of the roadheader, the parameters that currently have the greatest impact on the vibration of the cutting part are analyzed, and integrated and adjusted in combination with the other two working parameters to achieve the purpose of reducing vibration; S4. The optimal control strategy is transmitted to the control end, and the operator selects the control. The fitting formula in step S2 is: a=polyfit(t,x,m); m-order polynomial fitting; y = x-polyval(a, t); polynomial numerical prediction; Among them, x is the original signal vector; y is the signal vector after eliminating the trend term; a is the polynomial coefficient; m is the order of the fitting polynomial, which is taken as 4, and t is the discrete time vector. In step S1, when the content of gangue in the coal rock exceeds 15%, the first method is selected to collect the vibration signal of the cutting part: Method 1: Set the vibration threshold. When the collected vibration signal of the cutting part exceeds the vibration threshold, the control module sends a signal to activate the clock chip. When the clock chip is activated for more than time A, the clock chip sends a signal to the control center through the communication module to ask whether to collect the signal. Then the operator sets the collection duration and time interval of the cutting part vibration signal, or chooses not to collect the cutting part vibration signal. In the first method, when the vibration signal of the cutting part decreases below the vibration threshold and the clock chip is not activated for more than time C, the clock chip enters the sleep state again. When the clock chip is not activated for more than time C, the value of time C is not less than 5 minutes. In the first method, when the clock chip is activated for more than time A, the value of time A is not less than 5 minutes. In step S1, when the content of interbedded gangue in the cut coal seam is less than 15%, the second method is selected to collect the vibration signal of the cutting part: Method 2: After the tunnel boring machine has been running for a certain period of time, the collection duration and time interval are manually set until the tunnel boring machine stops and the collection of the cutting part vibration signal is completed. The collection duration and collection time interval are manually set after the tunnel boring machine runs for time B, and the value of time B is not less than 5 minutes. The vibration signal acquisition device is a three-axis acceleration sensor, and the vibration threshold is 0.8g, where g is gravity acceleration and the unit is m / s 2 In step S3, the traction speed of the cutting part and the swing speed of the cutting arm are obtained by integrating the collected vibration signal once; The rotation speed signal acquisition device is a three-axis gyroscope sensor. The vibration signal acquisition device, the rotation speed signal acquisition device and the clock chip are integrated into a module and installed in a data acquisition box, and the data acquisition box is installed at the tail of the cutter head of the cutting part. Beneficial effects: The present invention provides a method for monitoring vibration of the cutting part of a tunnel boring machine, which has the following technical advantages compared with the existing tunnel boring machine working method: First, by using neural network technology, through learning and analyzing a large amount of cutting part working data, it can find the nonlinear mapping relationship between different working parameters and vibration characteristics from complex working condition information. When facing the key problem of cutting head vibration, the solution based on neural network technology can fully consider a variety of influencing factors, such as the cutting head's traction speed, yaw speed, rotation speed, coal rock hardness changes, etc. After a lot of simulations and calculations, the optimal solution to reduce the cutting head vibration was finally obtained, which effectively improved the working stability of the cutting part, reduced the equipment wear and failure risks caused by vibration, greatly extended the service life of the equipment, and also improved the excavation efficiency. Second, it can select the most appropriate data collection method according to different coal and rock conditions. For coal mines with a gangue content of more than 15%, the vibration of the cutting part of the roadheader will increase, and the need to collect data will increase. Therefore, sensor control is used to collect data in a timely manner. Coal mines with a gangue content of less than 15% use software control, that is, the collection time and time interval are set after the roadheader works stably until the roadheader stops working, which can reduce the power consumption of the equipment and increase the use time. This differentiated data collection method for different coal and rock conditions enables the monitoring system to accurately obtain key data when facing various complex and changeable coal and rock conditions, providing a solid foundation for further analysis of the working status of the cutting part. Third, the present invention can accurately and flexibly set the data collection time and time interval through clock chip technology. This adjustable setting method makes the collection process no longer continuous and uninterrupted, but can be intermittently collected according to actual needs. In this way, a large amount of useless or duplicate data can be avoided, thereby significantly reducing the subsequent data processing volume. It provides a high-quality data foundation for subsequent analysis and decision-making. BRIEF DESCRIPTION OF THE DRAWINGS Figure 1 It is a schematic diagram of the overall structure of the working monitoring device of the cutting part of the tunnel boring machine of the present invention; Among them, 1 is the data acquisition module; 2 is the communication and control module; 3 is the data processing and display module; Figure 2 It is a structural schematic diagram of the data acquisition box of the present invention; Among them, 10 is the battery compartment; 100 is the lithium battery; 11 is a vibration sensor compartment; 110 is a three-axis acceleration sensor; 111 is a three-axis gyroscope sensor; 112 is a clock chip, 12 is an antenna chamber; 120 is a PTFE plate; 13 is a housing; 131 is a sealing groove; 132 is a waterproof connector; Figure 3 It is a data collection flow chart of the present invention; Figure 4 It is a schematic diagram of the vibration data processing process in the data processing module of the present invention; Figure 5 It is a flow chart of the method of the present invention. DETAILED DESCRIPTION The technical solution of the present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments of the specification. This article aims to solve the problem of reduced life of the cutting part due to excessive vibration of the cutting part caused by changes in coal and rock composition and changes in the working parameters of the tunnel boring machine during the tunneling process. In view of this, the purpose of the present application is to provide a method for monitoring vibration of a cutting part of a roadheader, comprising the following steps: S1, using a vibration signal acquisition device to collect a vibration signal of the cutting part; using a rotation speed signal acquisition device to collect a rotation speed signal of the cutting head; S2, performing polynomial fitting denoising processing on the cutting part vibration signal and cutting head speed signal collected in step S1 through a fitting formula to obtain a denoised cutting part vibration signal and cutting head speed signal; S3, differentiate the vibration signal of the cutting part once to obtain the current working parameters of the roadheader, including: the traction speed of the cutting part and the swing speed of the cutting arm. By identifying the three working parameters of the traction speed of the cutting part, the swing speed of the cutting arm and the rotation speed of the cutting head, an intelligent judgment method based on artificial neural network is used to learn the nonlinear mapping relationship between different working parameters and vibration characteristics in the corresponding vibration characteristics by using the neural network algorithm. The denoised vibration signal of the cutting part and the working parameters of the roadheader obtained in step S2 are used to establish a training sample set of the neural network. The corresponding control scheme model is established through training to propose the optimal control strategy in the scheme model library: that is, according to the current working parameters of the roadheader, the parameters that currently have the greatest impact on the vibration of the cutting part are analyzed, and the other two working parameters are combined for integration and adjustment to achieve the purpose of reducing vibration; S4. The optimal control strategy is transmitted to the control end, and the operator selects the control. There are two ways to collect cutting section vibration data. The first is sensor control: Set the acceleration sensor threshold according to the actual situation of the tunnel boring machine on site. It is generally set to 0.8g, where g is the gravitational acceleration in m / s. 2 When the vibration of the cutting part exceeds the threshold of the acceleration sensor, the clock chip is activated. When the clock chip is activated for more than 5 minutes, the clock chip sends a signal to the control center through the communication module to ask whether to collect data. The operator then sets the data collection time or chooses not to collect data. The second is software control: Generally, the collection duration and time interval are manually set after the tunnel boring machine has been running for 3-5 minutes, and the collection is completed after the tunnel boring machine stops. The sensor control is suitable for use when the gangue content in the coal rock exceeds 15%. When the gangue content in the cut coal seam is less than 15%, the software control is selected to collect the vibration signal of the cutting part. Obtain the time domain and frequency domain information and vibration characteristic parameters of the cutting part vibration signal. After receiving the monitoring data, first analyze the cutting part vibration signal into three-axis acceleration and time, and then intercept the cutting part vibration signal according to the analysis requirements. The sensor error, change and surrounding environment interference generate noise and trend items in the monitoring data. Due to the existence of the trend item, the residual is integrated, resulting in waveform distortion. Then use MATLAB to write polyfit and polyval function calls to realize polynomial fitting:
[0038] a=polyfitt,x,m; m-order polynomial fitting;
[0039] y = x-polyvala, t; polynomial numerical prediction; Among them, x is the original signal vector; y is the signal vector after eliminating the trend term; a is the polynomial coefficient; m is the order of the fitting polynomial, which is taken as 4, and t is the discrete time vector. Generally speaking, the frequency of the noise signal is significantly different from the actual signal frequency, and the filter can effectively reduce or eliminate the noise. Through the above analysis, the polynomial fitting and filtering are combined to obtain the expected results, and then the acceleration is integrated in the first and second order to obtain the velocity and displacement. A vibration monitoring device for the cutting part of a roadheader, fixed on a cutter head by welding, comprises a data acquisition module 1, a communication and control module 2, and a data processing and display module 3; The data acquisition module 1 includes a battery compartment 10 , a vibration sensor board compartment 11 , an antenna compartment 12 , and a housing 13 . A large-capacity rechargeable lithium battery 100 is installed in the battery compartment 10 of the data acquisition module 1 to continuously provide power to the sensor board compartment. The vibration sensor board warehouse 11 includes three sensors, namely a three-axis acceleration sensor 110, a three-axis gyroscope sensor 111 and a clock chip 112. The vibration state of the cutting part and the rotation state of the cutting head are monitored by the three-axis acceleration sensor and the three-axis gyroscope of the vibration sensor board warehouse, so the three-axis vibration sensor, the three-axis gyroscope and the clock chip are integrated into one module; The acquisition time is set by the clock chip, and data acquisition generally starts after the tunnel boring machine runs smoothly; The three-axis accelerometer is equipped with a mass block on each axis, and the acceleration is calculated by monitoring the displacement of the mass block. Each axis works independently, and the range of the accelerometer is adjusted to a maximum range of 2g according to the actual working environment. The side plate 12 of the antenna compartment is made of polytetrafluoroethylene (PTFE) plate 120 to ensure the signal transmission quality; the wireless signal is normally transmitted through the antenna compartment; All cover plates in the housing 13 are provided with sealing grooves 131 and waterproofed using waterproof connectors 132 . The communication module is used as a bridge between the data acquisition module and the system software. It is mainly responsible for the transmission of data and commands. The LoRa spread spectrum communication technology is used to ensure that the signal can have good penetration and anti-multipath attenuation capabilities in a strong interference environment. The working frequency band is set to 433HMz. The tunnel boring machine is controlled by software through the control module. The system software is installed in the PLC of the control end of the tunnel boring machine. After the cutting head enters a stable working state, the software sends a data acquisition instruction to the sensor board. The sensor board enters the working state and continues to collect data for a specified time. Then the sensor board enters sleep mode to reduce power consumption. The system software is used to perform functions such as data management, data processing, result display and user management. The data management function mainly includes data storage, historical data query and memory card data input. The result display function provides visualization of acceleration, velocity and displacement result data, as well as storage of result data and images.
Claims
1. A method for monitoring vibration of a cutting part of a tunnel boring machine, characterized in that: The following steps are involved: S1, using a vibration signal acquisition device to collect a vibration signal of the cutting part; using a rotation speed signal acquisition device to collect a rotation speed signal of the cutting head; S2, performing polynomial fitting denoising processing on the cutting part vibration signal and cutting head speed signal collected in step S1 through a fitting formula to obtain a denoised cutting part vibration signal and cutting head speed signal; S3. Collect the current working parameters of the roadheader, including: the traction speed of the cutting part and the swing speed of the cutting arm. Through the identification of the three working parameters of the traction speed of the cutting part, the swing speed of the cutting arm and the rotation speed of the cutting head, an intelligent judgment method based on artificial neural network is used to learn the nonlinear mapping relationship between different working parameters and vibration characteristics in the corresponding vibration characteristics by using the neural network algorithm. A training sample set of the neural network is established through the denoised cutting part vibration signal and the three working parameters of the roadheader. A corresponding control scheme model is established through training to propose an optimal control strategy in the scheme model library: that is, according to the current working parameters of the roadheader, the parameters that currently have the greatest impact on the vibration of the cutting part are analyzed, and integrated and adjusted in combination with the other two working parameters to achieve the purpose of reducing vibration; S4. The optimal control strategy is transmitted to the control end, and the operator selects the control.
2. The method for monitoring vibration of the cutting part of a tunnel boring machine according to claim 1, characterized in that: The fitting formula in step S2 is: a=polyfit(t,x,m); m-order polynomial fitting; y = x-polyval(a, t); polynomial numerical prediction; Among them, x is the original signal vector; y is the signal vector after eliminating the trend term; a is the polynomial coefficient; m is the order of the fitting polynomial, which is taken as 4, and t is the discrete time vector.
3. The method for monitoring vibration of the cutting part of a tunnel boring machine according to claim 1, characterized in that: In step S1, when the content of gangue in the coal rock exceeds 15%, the first method is selected to collect the vibration signal of the cutting part: Method 1: Set the vibration threshold. When the collected vibration signal of the cutting part exceeds the vibration threshold, the control module sends a signal to activate the clock chip. When the clock chip is activated for more than time A, the clock chip sends a signal to the control center through the communication module to ask whether to collect the signal. Then the operator sets the collection duration and time interval of the cutting part vibration signal, or chooses not to collect the cutting part vibration signal.
4. The method for monitoring vibration of the cutting part of a tunnel boring machine according to claim 3, characterized in that: In the first method, when the vibration signal of the cutting part decreases below the vibration threshold and the clock chip is not activated for more than time C, the clock chip enters the sleep state again.
5. The method for monitoring vibration of the cutting part of a tunnel boring machine according to claim 4, characterized in that: When the clock chip is not activated for more than time C, the value of time C is not less than 5 minutes.
6. The method for monitoring vibration of the cutting part of a tunnel boring machine according to claim 3, characterized in that: In the first method, when the clock chip is activated for more than time A, the value of time A is not less than 5 minutes.
7. The method for monitoring vibration of the cutting part of a tunnel boring machine according to claim 1, characterized in that: In step S1, when the content of interbedded gangue in the cut coal seam is less than 15%, the second method is selected to collect the vibration signal of the cutting part: Method 2: After the tunnel boring machine has been running for a certain period of time, the collection duration and time interval are manually set until the tunnel boring machine stops and the collection of the cutting part vibration signal is completed.
8. The method for monitoring vibration of the cutting part of a tunnel boring machine according to claim 7, characterized in that: The collection duration and collection time interval are manually set after the tunnel boring machine runs for time B, and the value of time B is not less than 5 minutes.
9. The method for monitoring vibration of the cutting part of a tunnel boring machine according to claim 1, characterized in that: The vibration signal acquisition device is a three-axis acceleration sensor, and the vibration threshold is 0.8g, where g is gravity acceleration and the unit is m / s 2 In step S3, the traction speed of the cutting part and the swing speed of the cutting arm are obtained by integrating the collected vibration signal once; The rotation speed signal acquisition device is a three-axis gyroscope sensor.
10. The method for monitoring vibration of the cutting part of a tunnel boring machine according to claim 3, characterized in that: The vibration signal acquisition device, the rotation speed signal acquisition device and the clock chip are integrated into a module and installed in a data acquisition box, and the data acquisition box is installed at the tail of the cutter head of the cutting part.