A cutting face coal rock identification method and identification device based on hardness characteristics

Abstract

The application discloses a cutting surface coal rock identification method and identification device based on hardness characteristics, which can automatically identify and distinguish coal seams and rocks through an ultrasonic identification system, and can reduce the damage of a heading machine cutting head by controlling the depth distance of the heading machine cutting head through a high-strength damper and a high-strength damping spring. The application is characterized in that the device is composed of a heading machine cutting head, a planetary column, an identification base, a rotating rocker arm, a planetary groove, a cutting head mounting column, a high-strength damper and a high-strength spring. One end of the identification base is arranged on the rotating rocker arm, the other end of the identification base is provided with the planetary groove, one end of the high-strength damper is arranged on the inner bottom surface of the planetary groove, the high-strength spring is sleeved on the side surface of the high-strength damper, the planetary column is inserted into the planetary groove and connected with the high-strength damper, and the other end of the high-strength damper is arranged on one end of the planetary column.

Description

Technical Field

[0001] This invention relates to a method and device for identifying coal and rock at a cutting face based on hardness characteristics. It is a method and device for identifying coal and rock at a cutting face that can reduce damage to the cutting head of a tunneling machine. It belongs to the field of coal and rock identification technology at a cutting face, and specifically relates to a method and device for identifying coal and rock at a cutting face that can automatically identify and distinguish coal seams and rocks through an ultrasonic identification system and control the cutting depth of the tunneling machine cutting head through a high-strength damper and a high-strength damping spring, thereby reducing damage to the cutting head of the tunneling machine. Background Technology

[0002] In coal mining and tunneling, accurately identifying the coal seam and rock on the cutting face is crucial for improving mining efficiency, protecting the tunneling machine's cutting head, and ensuring safe production when using a tunneling machine. Currently, identification of the coal seam and rock on the cutting face mainly relies on manual judgment by workers or simple physical detection methods, which is prone to misjudgment. This can lead to the tunneling machine encountering hard rock at excessive depths during coal mining, causing damage to the tunneling machine's cutting head and potentially triggering safety accidents.

[0003] Publication No. CN107575226B discloses an online identification cutting head for coal and rock hardness grades and its usage method. The online identification cutting head for coal and rock hardness grades includes a drum, multiple cutting tooth assemblies arranged on the outer surface of the drum, and a wireless transmitter fixed in the inner cavity of the drum. Each cutting tooth assembly includes a cutting tooth, a cutting tooth seat, a pressure sensor, an acoustic emission device, and a piezoelectric box. The cutting tooth is installed in the cutting tooth mounting hole of the cutting tooth seat, and the pressure sensor is also installed in the cutting tooth mounting hole and is in close contact with the end of the cutting tooth. The cutting tooth seat is also provided with a first mounting position and a second mounting position. The above method involves mounting the pressure sensor, acoustic emission device, and piezoelectric box on the cutting tooth holder. Although this method can identify the hardness level of the coal and rock being cut in real time during the cutting process, it requires manual adjustment of the cutting parameters of the coal mining machine based on the real-time detected coal and rock hardness level. It cannot control the depth of the cutting tooth assembly through a high-strength rebound mechanism based on the identified coal and rock hardness level, which can easily lead to the coal mining machine encountering hard rock and cutting too deeply, causing damage to the cutting tooth and triggering a safety accident. Summary of the Invention

[0004] To improve the above situation, the present invention provides a method and device for identifying coal and rock at the cutting face based on hardness characteristics. This method and device automatically identifies and distinguishes coal seams and rocks through an ultrasonic identification system, and controls the depth of the tunneling machine cutting head through a high-strength damper and a high-strength damping spring, thereby reducing damage to the tunneling machine cutting head.

[0005] The present invention discloses a method and device for identifying coal and rock at a cutting face based on hardness characteristics, which is implemented as follows: The device for identifying coal and rock at a cutting face based on hardness characteristics consists of a tunneling machine cutting head, a planetary column, an identification base, a rotating rocker arm, a planetary groove, a cutting head mounting column, a high-strength damper, and a high-strength spring. One end of the identification base is placed on a rotating rocker arm. Preferably, the identification base has a cylindrical structure, and the diameter of the identification base is larger than the diameter of the rotating rocker arm. The other end of the identification base has a planetary slot. One end of the high-strength damper is placed on the inner bottom surface of the planetary slot. Preferably, there are multiple high-strength dampers, and the multiple high-strength dampers are evenly distributed in the planetary slot. A high-strength spring is fitted on the side of the high-strength damper, and the planetary column is inserted into the planetary slot and connected to the high-strength damper. The other end of the high-strength damper is placed at one end of the planetary column. One end of the cutting head mounting post is placed at the other end of the planetary post. Preferably, the cutting head mounting post has a cylindrical structure, and the diameter of the cutting head mounting post is smaller than the diameter of the planetary post. The other end of the cutting head mounting column is placed on the bottom surface of the tunneling machine's cutting head. Preferably, the bottom diameter of the tunneling machine cutting head is larger than the outer diameter of the planetary column. The aforementioned coal and rock identification device based on hardness characteristics also includes an ultrasonic identification system, which comprises a monitoring backend, an ultrasonic transmitting module, an ultrasonic receiving module, a signal processing module, and a data analysis module. The ultrasonic transmitting module is placed on the identification base, the ultrasonic receiving module is placed on the identification base, and the signal processing module and the data analysis module are placed on the monitoring backend. The ultrasonic receiving module and the signal processing module establish signal interaction. The signal processing module and the data analysis module establish signal interaction. The ultrasonic transmitting module is used to generate high-frequency ultrasonic signals according to preset frequency and amplitude parameters, and transmit the high-frequency ultrasonic signals to the cutting surface through an ultrasonic transmitter. The ultrasonic receiving module is used to receive high-frequency ultrasonic signals reflected from the cutting surface via an ultrasonic receiver, and to transmit the received high-frequency ultrasonic signals to the signal processing module. Preferably, the ultrasonic receiving module includes multiple ultrasonic receivers, which are evenly placed on the identification base. The signal processing module amplifies, filters, and digitizes the received high-frequency ultrasonic signal, extracts useful feature information, and transmits the processed high-frequency ultrasonic signal to the data analysis module. Preferably, the feature information may be the time-domain features, frequency-domain features, energy features, waveform parameters, or peak-valley parameters of the received high-frequency ultrasonic signal. The data analysis module uses advanced data processing algorithms to analyze the processed high-frequency ultrasonic signal data, distinguishing between coal seams and rocks, and generating coal-rock distribution maps to provide a basis for staff to analyze coal mine quality. Preferably, the data analysis module may further include a user interface, which is used to intuitively display the coal and rock distribution map and related statistical data. Preferably, the data analysis module can use machine learning or pattern recognition technology to analyze the processed high-frequency ultrasonic signal data; Furthermore, the aforementioned coal and rock identification device based on hardness characteristics also includes a distance sensing system, which comprises a distance sensor, a signal converter, a data processor, and a controller. The distance sensor is placed on the inner bottom surface of the planetary slot. When the tunneling machine cutting head performs coal mining operations, the planetary column moves with the extension and contraction of the high-strength damper and the high-strength spring. The distance sensor can collect the distance from the planetary column to the inner bottom surface of the planetary slot. Preferably, the distance sensor is located in the middle of the inner bottom surface of the planetary slot. The signal converter is located on the inner bottom surface of the planetary slot, and the data processor is located on the inner bottom surface of the planetary slot. The signal converter is connected to the data processor via a data transmission line. The data processor is connected to the controller via a data transmission line. The tunneling machine cutting head is connected to the controller via a data cable. The controller and the tunneling machine control system establish signal interaction. The signal converter can convert the electrical signal of the distance data collected by the distance sensor into a digital signal. The controller can be implemented using one or more application-specific integrated circuits (ASICs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to execute instructions from a data processing device. The data processor and the signal converter interact with each other. The data processor stores a computer-readable storage medium, and when the computer-readable storage medium is executed, it performs the following steps: The digital signals of the distance data collected by the distance sensor are processed respectively. The difference in cutting depth between the coal seam and the rock is calculated by using a preset positive function between the distance data and the cutting depth. The cutting time of the rock layer is determined by using a preset negative function between the distance data and the cutting time. An execution command is sent to the controller. The controller controls the cutting head of the tunneling machine to tunnel and cut the rock layer according to the determined cutting time. When the cutting time is equal to the determined cutting time of the rock layer, the controller controls the cutting head of the tunneling machine to stop working, which can ensure the flatness of the cutting surface. Furthermore, a sealing detection hole is provided on the side of the identification base, and a threaded sealing plug is provided on the side of the identification base, the threaded sealing plug being embedded in the sealing detection hole; This invention discloses a method for identifying coal and rock at a cross-section based on hardness characteristics. The method comprises the following steps: using a coal and rock identification device based on hardness characteristics for coal and rock identification. Before coal mining begins, the ultrasonic transmitting module generates high-frequency ultrasonic signals according to preset frequency and amplitude parameters, and transmits the high-frequency ultrasonic signals to the cutting face through the ultrasonic transmitter. The ultrasonic receiving module receives the high-frequency ultrasonic signal reflected from the cutting surface and transmits the received ultrasonic signal to the signal processing module. The signal processing module amplifies, filters, and digitizes the received high-frequency ultrasonic signal, extracts useful feature information, and transmits the processed high-frequency ultrasonic signal to the data analysis module. The data analysis module uses advanced data processing algorithms to analyze the processed high-frequency ultrasonic signal data, enabling the differentiation between coal seams and rocks, and generating coal and rock distribution maps to provide a basis for staff to analyze coal mine quality. Based on the data analysis module's differentiation of coal seams and rocks, the tunneling machine controls the cutting head's depth using high-strength dampers and springs. When encountering coal seams, which are relatively soft, the cutting head can penetrate deeper and cut coal quickly thanks to the support of the high-strength dampers and springs. When encountering rocks, which are harder, the cutting head can penetrate less, and the high-strength dampers and springs retract, allowing for shallower tunneling. This reduces damage to the cutting head and ensures a smooth cutting surface. Beneficial effects

[0006] First, the ultrasonic identification system can automatically identify and distinguish coal seams and rocks, forming a coal and rock distribution map of the cut surface, providing a basis for staff to analyze coal mine quality.

[0007] Second, the cutting depth of the tunneling machine's cutting head is controlled by high-strength dampers and high-strength damping springs. When encountering coal seams, which are relatively soft, the cutting head can cut deeper and cut coal quickly under the support of the high-strength dampers and high-strength damping springs. When encountering rocks, which are hard, the high-strength dampers and high-strength damping springs retract, resulting in a smaller cutting depth. This reduces damage to the cutting head and ensures a smooth cutting surface. Attached Figure Description

[0008] Figure 1 This is a three-dimensional structural diagram of a coal and rock identification device based on hardness characteristics for a cutting surface according to the present invention. Figure 2 This is a schematic diagram of the structure of a coal and rock identification device based on hardness characteristics at a cut surface according to the present invention. Figure 3 This is a three-dimensional structural diagram of a coal and rock identification device based on hardness characteristics of the cutting surface according to the present invention, which only shows the structure of the planetary groove, high-strength damper and high-strength spring. Figure 4 This is a schematic diagram of the structure of Embodiment 2 of the coal and rock identification device based on hardness characteristics of the present invention; Figure 5 This is a schematic diagram of embodiment 3 of the coal and rock identification device based on hardness characteristics of the present invention. Attached Figure

[0009] The components include: tunneling machine cutting head (1), planetary column (2), identification base (3), rotating rocker arm (4), planetary groove (5), cutting head mounting column (6), high-strength damper (7), high-strength spring (8), distance sensor (9), sealing detection hole (10), and threaded sealing plug (11). Detailed Implementation Example 1

[0010] The present invention discloses a method and device for identifying coal and rock at a cutting face based on hardness characteristics, which is implemented as follows: The coal and rock identification device at a cutting face based on hardness characteristics consists of a tunneling machine cutting head (1), a planetary column (2), an identification base (3), a rotating rocker arm (4), a planetary groove (5), a cutting head mounting column (6), a high-strength damper (7), and a high-strength spring (8). One end of the identification base (3) is placed on the rotating rocker arm (4). Preferably, the identification base (3) has a cylindrical structure, and the diameter of the identification base (3) is larger than the diameter of the rotating rocker arm (4). The other end of the identification base (3) has a planetary slot (5). One end of the high-strength damper (7) is placed on the inner bottom surface of the planetary slot (5). Preferably, there are multiple high-strength dampers (7), and the multiple high-strength dampers (7) are evenly distributed in the planetary slot (5). A high-strength spring (8) is fitted on the side of the high-strength damper (7), and the planetary column (2) is inserted into the planetary slot (5) and connected to the high-strength damper (7). The other end of the high-strength damper (7) is placed at one end of the planetary column (2). One end of the cutting head mounting post (6) is placed at the other end of the planetary post (2). Preferably, the cutting head mounting post (6) has a cylindrical structure, and the diameter of the cutting head mounting post (6) is smaller than the diameter of the planetary post (2). The other end of the cutting head mounting column (6) is placed on the bottom surface of the tunneling machine cutting head (1). Preferably, the bottom diameter of the tunneling machine cutting head (1) is larger than the outer diameter of the planetary column (2). The aforementioned coal and rock identification device based on hardness characteristics also includes an ultrasonic identification system, which comprises a monitoring backend, an ultrasonic transmitting module, an ultrasonic receiving module, a signal processing module, and a data analysis module. The ultrasonic transmitting module is placed on the identification base (3), the ultrasonic receiving module is placed on the identification base (3), and the signal processing module and the data analysis module are placed on the monitoring backend. The ultrasonic receiving module and the signal processing module establish signal interaction. The signal processing module and the data analysis module establish signal interaction. The ultrasonic transmitting module is used to generate high-frequency ultrasonic signals according to preset frequency and amplitude parameters, and transmit the high-frequency ultrasonic signals to the cutting surface through an ultrasonic transmitter. The ultrasonic receiving module is used to receive high-frequency ultrasonic signals reflected from the cutting surface via an ultrasonic receiver, and to transmit the received high-frequency ultrasonic signals to the signal processing module. Preferably, the ultrasonic receiving module includes multiple ultrasonic receivers, which are evenly placed on the identification base (3). The signal processing module amplifies, filters, and digitizes the received high-frequency ultrasonic signal, extracts useful feature information, and transmits the processed high-frequency ultrasonic signal to the data analysis module. Preferably, the feature information may be the time-domain features, frequency-domain features, energy features, waveform parameters, or peak-valley parameters of the received high-frequency ultrasonic signal. The data analysis module uses advanced data processing algorithms to analyze the processed high-frequency ultrasonic signal data, distinguishing between coal seams and rocks, and generating coal-rock distribution maps to provide a basis for staff to analyze coal mine quality. Preferably, the data analysis module may further include a user interface, which is used to intuitively display the coal and rock distribution map and related statistical data. Preferably, the data analysis module can use machine learning or pattern recognition technology to analyze the processed high-frequency ultrasonic signal data.

[0011] This invention provides a method for identifying coal and rock at a cut surface based on hardness characteristics, comprising the following steps: Before coal mining begins, the ultrasonic transmitting module generates high-frequency ultrasonic signals according to preset frequency and amplitude parameters, and transmits these signals to the cutting face via the ultrasonic transmitter. The ultrasonic receiving module receives the high-frequency ultrasonic signal reflected from the cutting surface and transmits the received ultrasonic signal to the signal processing module. The signal processing module amplifies, filters, and digitizes the received high-frequency ultrasonic signal, extracts useful feature information, and transmits the processed high-frequency ultrasonic signal and the extracted useful feature information to the data analysis module. Preferably, the signal processing module can extract the time-domain features from the digitized high-frequency ultrasonic signal, including the following steps: Segmented processing divides the processed high-frequency ultrasonic signal into segments, each containing a certain number of sampling points. Amplitude feature extraction, calculating the root mean square value of each signal segment to reflect the vibration intensity of the signal, identifying and calculating the peak value and frequency of the signal to reflect the sharpness of the signal waveform; Statistical feature extraction involves calculating the average value of each signal segment to reflect the overall signal level, measure signal volatility, and describe the asymmetry and peaks in the signal distribution. Time interval feature extraction calculates the time interval or delay between adjacent segments to reflect the rate of signal change; Frequency domain feature extraction: The time domain signal is converted into a frequency domain signal through Fourier transform, and the frequency domain features of the signal are obtained by analyzing the spectrum of the frequency domain signal; Feature selection involves comprehensively extracting feature parameters from various features and using a feature selection algorithm based on analysis of variance to select the feature information that best distinguishes the hardness characteristics of coal seams and rocks. The data analysis module uses advanced data processing algorithms to analyze the processed high-frequency ultrasonic signal data, enabling the differentiation between coal seams and rocks, and generating coal and rock distribution maps to provide a basis for staff to analyze coal mine quality. Preferably, the data analysis module can employ a random forest algorithm, pre-trained on a large number of high-frequency ultrasonic signal data samples, and establish a classification model by constructing multiple decision trees. The feature information extracted by the signal processing module is input into the established classification model to obtain the recognition result of each classification model. Specific steps include: Open a local terminal window, ensure that Python is installed, and use the command in Python to install the NumPy library; Import the NumPy library using commands in Python; The collected high-frequency ultrasonic signal samples are stored on the local terminal and loaded using the Numpy library; The large number of high-frequency ultrasonic signal samples collected are amplified, filtered and digitized. Feature information that has a greater impact on the recognition results is selected from the processed high-frequency ultrasonic signals to form a feature set. The processed high-frequency ultrasonic signal samples are divided into training set and test set. The training set and test set are independent, and the training set is large enough and the test set is small enough. The ratio of training set to test set can be 7:3 or 8:2. Creating a random forest model involves building multiple decision trees, each trained using a different subset of the training set and different subsets of features. The specific steps for creating a random forest model include: Randomly select a subset of training data from the training set; Randomly select a subset of features from the feature set; The specific steps for training a decision tree T_i (i from 1 to N) using the extracted training subset and feature subset include: Randomly draw n samples with replacement from the training subset D to form a training subset D_i; If the number of features in D_i is greater than 1, then m features are randomly selected from all features to partition the data; Based on the selected features and partitioning criteria, D_i is divided into k subsets; Recursively repeat step ac for each subset D_j (j from 1 to k) until each subset contains only one sample or the stopping condition is met; Calculate the recognition result of decision tree T_i; Repeat step AC until a sufficient number of decision trees are trained; Combine all decision trees into a random forest model; The performance of a random forest model is evaluated using a test set. Common evaluation metrics include accuracy, recall, mean squared error, and mean absolute error. For the input feature information, calculate the recognition result y_i (i from 1 to N) of all decision trees T_i (i from 1 to N), and average or vote on y_i (i from 1 to N) to obtain the final recognition result of the random forest algorithm; (5) Based on the coal seam and rock identified by the data analysis module, the tunneling machine controls the depth of the tunneling machine cutting head (1) through the high-strength damper (7) and the high-strength damping spring. When encountering a coal seam, the coal seam is relatively soft. Under the support of the high-strength damper (7) and the high-strength damping spring, the tunneling machine cutting head (1) has a larger depth and cuts coal quickly. When encountering a rock, the rock is hard and the tunneling machine cutting head (1) has a smaller depth. The high-strength damper (7) and the high-strength damping spring retract, which can reduce the damage to the tunneling machine cutting head (1) and ensure the flatness of the cutting surface. Example 2

[0012] The difference between this embodiment and Embodiment 1 is that the coal and rock identification device based on hardness characteristics of the cutting face further includes a distance sensing system. The distance sensing system includes a distance sensor (9), a signal converter, a data processor, and a controller. The distance sensor (9) is placed on the inner bottom surface of the planetary slot (5). When the tunneling machine cutting head (1) performs coal mining operations, the planetary column (2) will move with the extension and retraction of the high-strength damper (7) and the high-strength spring (8). The distance sensor (9) can collect the distance from the planetary column (2) to the inner bottom surface of the planetary slot (5). The signal converter is located on the inner bottom surface of the planetary slot (5), and the data processor is located on the inner bottom surface of the planetary slot (5). The signal converter is connected to the data processor via a data transmission line, and the data processor is connected to the controller via a data transmission line. The tunneling machine cutting head (1) is connected to the controller via a data line. The signal converter can convert the electrical signal of the distance data collected by the distance sensor (9) into a digital signal. The controller can be implemented by one or more application-specific integrated circuits (ASIC), programmable logic devices (PLD), field-programmable gate arrays (FPGA), controllers, microcontrollers, microprocessors, or other electronic components to execute instructions of the data processing device. The data processor and the signal converter interact with each other. The data processor stores a computer-readable storage medium. When the computer-readable storage medium is executed, it performs the following steps: processing the digital signal of the distance data collected by the distance sensor (9) respectively, calculating the cutting depth difference between the coal seam and the rock through a preset positive function between the distance data and the cutting depth, and calculating the cutting depth difference between the coal seam and the rock through a preset distance data and the cutting time. The inverse function between them determines the cutting time of the rock layer and sends an execution command to the controller. The controller controls the tunneling machine cutting head (1) to tunnel and cut the rock layer according to the determined cutting time of the rock layer. When the cutting time is equal to the determined cutting time of the rock layer, the controller controls the tunneling machine cutting head (1) to stop working, which can ensure the flatness of the cutting surface. When in use, when encountering a coal seam, the coal seam is relatively soft. Under the support of the high-strength damper (7) and the high-strength damping spring, the tunneling machine cutting head (1) has a large depth and the distance from the planetary column (2) to the bottom of the planetary groove (5) is large.When encountering rock, the rock is hard, the cutting head (1) of the tunneling machine has a small depth, the high-strength damper (7) and the high-strength damping spring retract, the distance from the planetary column (2) to the bottom of the planetary slot (5) is small, there is a positive function between the distance data and the cutting depth, the distance sensor (9) transmits the electrical signal of the collected distance data to the signal converter, the signal converter converts the received distance data electrical signal into a digital signal and transmits it to the data processor, the data processor processes the received distance data digital signal, and calculates the cutting depth when the tunneling machine cutting head (1) encounters coal seam and rock layer based on the processed distance data digital signal and the preset positive function. The cutting depth difference is due to the small distance data when encountering rock layers, resulting in a small cutting depth. A longer cutting time is required to ensure the flatness of the cutting surface. There is an inverse function between the distance data and the cutting time. The data processor can determine the cutting time of the rock layer based on the digital signal of the processed distance data and the preset inverse function, and send an execution command to the controller. The controller controls the tunneling machine cutting head (1) to tunnel and cut the rock layer according to the determined cutting time. When the cutting time is equal to the determined cutting time of the rock layer, the controller controls the tunneling machine cutting head (1) to stop working, which can reduce the damage to the tunneling machine cutting head (1) and ensure the flatness of the cutting surface. Example 3

[0013] The difference between this embodiment and embodiment 1 is that: the side of the identification base (3) has a sealing detection hole (10), and the side of the identification base (3) has a threaded sealing plug (11), which is embedded in the sealing detection hole (10); when the tunneling machine is mining coal, a large amount of dust will be generated. The identification base (3) needs to be sealed to prevent the dust from entering the identification base (3) and causing wear when the concentration is high, which will affect the normal operation of the tunneling machine. Therefore, it is necessary to pull out the threaded sealing plug (11) every once in a while, clean the dust in the sealing detection hole (10), and test the sealing of the identification base (3) to determine whether its sealing meets the requirements and ensure the normal coal mining operation of the tunneling machine; There are multiple high-strength dampers (7), and the multiple high-strength dampers (7) are evenly distributed in the planetary slot (5). The multiple high-strength dampers and high-strength springs (8) can provide better support and retraction force to the tunneling machine cutting head (1), which is more conducive to the tunneling machine cutting head (1) cutting coal seams and rocks with different hardness characteristics. The design of the bottom diameter of the tunneling machine cutter head (1) being larger than the outer diameter of the planetary column (2) can prevent the high-strength damper and high-strength spring (8) from retracting when encountering rocks, and the tunneling machine cutter head (1) enters the planetary slot (5) as the planetary column (2) retracts. The ultrasonic receiving module includes multiple ultrasonic receivers. The design of the multiple ultrasonic receivers being evenly placed on the identification base (3) means that when the ultrasonic signal encounters the coal seam and rock, a portion of the signal will be reflected back. The multiple ultrasonic receivers can simultaneously receive high-frequency ultrasonic signals from multiple directions and angles, which can improve the receiving efficiency, reduce signal loss, and help to comprehensively detect the hardness characteristics of coal and rock at the cutting surface. The data analysis module may also include a user interface, which is designed to intuitively display the coal and rock distribution map and related statistical data. This allows staff to analyze the distribution of coal seams and rocks based on the coal and rock distribution map and related statistical data, providing a basis for analyzing coal mine quality. It can also control the extension of the cutting time of the tunneling machine cutting head (1) based on the rock distribution, thereby reducing damage to the tunneling machine cutting head (1).

[0014] The goal is to achieve the ability to automatically identify and distinguish coal seams and rocks through an ultrasonic identification system, and to control the depth of the tunneling machine cutting head (1) through a high-strength damper (7) and a high-strength damping spring, thereby reducing the damage to the tunneling machine cutting head (1).

[0015] It should be noted that, unless otherwise explicitly specified and limited, the terms "placed," "connected," and "linked" should be interpreted broadly. For example, they can refer to fixed connections such as folded edges, rivets, pins, adhesives, and welds; detachable connections such as threaded connections, snap-fit ​​connections, and hinges; integral connections; electrical connections; direct connections; or indirect connections via an intermediate medium; or internal connections between two components. Those skilled in the art can understand the specific meaning of these terms in this invention based on the specific circumstances.

[0016] It should be further noted that, in order to keep the description simple and clear, the above specific embodiments only describe the differences between them and other embodiments. However, those skilled in the art should know that the above specific embodiments are also independent technical solutions.

Claims

1. A method for identifying coal and rock at a cut surface based on hardness characteristics, characterized in that: Coal and rock identification is performed using a cutting face coal and rock identification device based on hardness characteristics. The specific steps include: (1) Before the start of coal mining, the ultrasonic transmitting module generates a high-frequency ultrasonic signal according to the preset frequency and amplitude parameters, and transmits the high-frequency ultrasonic signal to the cutting face through the ultrasonic transmitter; (2) The ultrasonic receiving module receives the high-frequency ultrasonic signal reflected from the cutting face and transmits the received ultrasonic signal to the signal processing module; (3) The signal processing module amplifies, filters and digitizes the received high-frequency ultrasonic signal, extracts useful feature information, and transmits the processed high-frequency ultrasonic signal and the extracted useful feature information to the data analysis module; (4) The data analysis module uses advanced data... The high-frequency ultrasonic signal data after processing by the processing algorithm is used to distinguish between coal seams and rocks and generate a coal and rock distribution map to provide a basis for staff to analyze coal mine quality; (5) The tunneling machine controls the depth of the tunneling machine cutting head by using a high-strength damper and a high-strength damping spring to distinguish between coal seams and rocks according to the data analysis module. When encountering coal seams, the coal seams are relatively soft. Under the support of the high-strength damper and the high-strength damping spring, the tunneling machine cutting head has a larger depth and cuts coal quickly. When encountering rocks, the rocks are hard and the tunneling machine cutting head has a smaller depth. The high-strength damper and the high-strength damping spring retract, which can reduce the damage to the tunneling machine cutting head; The cutting face coal and rock identification device based on hardness characteristics consists of a tunneling machine cutting head, a planetary column, an identification base, and a rotary column. The device comprises a rocker arm, a planetary slot, a cutting head mounting column, a high-strength damper, and a high-strength spring. The coal and rock identification device for the cutting face based on hardness characteristics also includes a distance sensing system. This system includes a distance sensor, a signal converter, a data processor, and a controller. The distance sensor is located on the inner bottom surface of the planetary slot. When the tunneling machine's cutting head performs coal mining operations, the planetary column moves with the extension and retraction of the high-strength damper and the high-strength spring. The distance sensor can collect the distance from the planetary column to the inner bottom surface of the planetary slot. The distance sensor is located in the middle of the inner bottom surface of the planetary slot. The signal converter is located on the inner bottom surface of the planetary slot, and the data processor is located at the inner bottom of the planetary slot. The data processor stores a computer-readable storage medium, which, when executed, performs the following steps: processing the digital signals of the distance data collected by the distance sensor; calculating the difference in cutting depth between the coal seam and the rock using a preset positive function between the distance data and the cutting depth; determining the cutting time of the rock layer using a preset negative function between the distance data and the cutting time; sending an execution command to the controller; the controller controlling the tunneling machine cutting head to tunnel and cut the rock layer according to the determined cutting time; and when the cutting time equals the determined cutting time, the controller controlling the tunneling machine cutting head to stop working, thus ensuring the flatness of the cutting surface.

2. The method for identifying coal and rock at a cut surface based on hardness characteristics according to claim 1, characterized in that... The signal processing module can extract time-domain features from the digitized high-frequency ultrasonic signal, including the following steps: 1) Segmentation: The processed high-frequency ultrasonic signal is segmented, with each segment containing a certain number of sampling points; 2) Amplitude feature extraction: The root mean square value of each segment is calculated to reflect the vibration intensity of the signal, and the peak value and frequency of the signal are identified and calculated to reflect the sharpness of the signal waveform; 3) Statistical feature extraction: The average value of each segment is calculated to reflect the overall level of the signal, measure the fluctuation of the signal, and describe the asymmetry and peaks of the signal distribution; 4) Time interval feature extraction: The time interval or delay between adjacent segments is calculated to reflect the rate of change of the signal; 5) Frequency domain feature extraction: The time-domain signal is converted into a frequency-domain signal through Fourier transform, and the frequency domain features of the signal are obtained by analyzing the spectrum of the frequency-domain signal. Feature selection involves comprehensively extracting feature parameters from various features and using a feature selection algorithm based on analysis of variance to select the feature information that best distinguishes the hardness characteristics of coal seams and rocks.

3. The method for identifying coal and rock at a cut surface based on hardness characteristics according to claim 1, characterized in that... The data analysis module can employ a random forest algorithm to pre-train on a large number of high-frequency ultrasonic signal data samples. It establishes a classification model by constructing multiple decision trees, inputting the feature information extracted by the signal processing module into the established classification model to obtain the recognition result of each model. Specific steps include: 1) Opening a local terminal window, ensuring Python is installed, and using commands to install the NumPy library within Python; 2) Importing the NumPy library using commands within Python; 3) Saving the collected large number of high-frequency ultrasonic signal samples to the local terminal and loading them using the NumPy library; 4) ... 5) The collected high-frequency ultrasonic signal samples are amplified, filtered, and digitized. Feature information that significantly impacts the recognition results is selected from the processed high-frequency ultrasonic signals to form a feature set; 6) The processed high-frequency ultrasonic signal samples are divided into training and testing sets, which are independent and have a sufficiently large training set and a sufficiently small testing set, with a ratio of 7:3 or 8:2; 7) A random forest model is created by constructing multiple decision trees. Each decision tree is trained using different subsets of the training set and different feature subsets. The specific steps include: A. Randomly selecting a training subset from the training set; B. Randomly selecting a feature subset from the feature set; C. Training a decision tree T_i using the selected training subset and feature subset, where i ranges from 1 to N. The specific steps for training a decision tree T_i include: a. Randomly selecting n samples with replacement from the training subset D to form a training subset D_i; b. If the number of features in D_i is greater than 1, then randomly selecting m features from all features to partition the data; c. Dividing D_i into k subsets according to the selected features and partitioning criteria; d. Recursively repeating steps for each subset D_j, where j ranges from 1 to k. Step AC, until each subset contains only one sample or the stopping condition is met; e. Calculate the recognition result of decision tree T_i; D. Repeat steps AC until a sufficient number of decision trees are trained; E. Combine all decision trees into a random forest model; 7) Use the test set to evaluate the performance of the random forest model. Common evaluation metrics include accuracy, recall, mean squared error, and mean absolute error; 8) For the input feature information, calculate the recognition results y_i, i from 1 to N of all decision trees T_i, i from 1 to N, and average or vote on y_i, i from 1 to N to obtain the final recognition result of the random forest algorithm.

4. The method for identifying coal and rock at a cut surface based on hardness characteristics according to claim 1, characterized in that... One end of the identification base is placed on a rotating rocker arm, and the other end of the identification base has a planetary slot. One end of the high-strength damper is placed on the inner bottom surface of the planetary slot, and a high-strength spring is fitted on the side of the high-strength damper. The planetary column is inserted into the planetary slot and connected to the high-strength damper. The other end of the high-strength damper is placed on one end of the planetary column. One end of the cutting head mounting column is placed on the other end of the planetary column, and the other end of the cutting head mounting column is placed on the bottom surface of the tunneling machine cutting head. The coal and rock identification device based on hardness characteristics also includes an ultrasonic identification system. The ultrasonic identification system includes a monitoring backend, an ultrasonic transmitting module, an ultrasonic receiving module, a signal processing module, and a data analysis module. The ultrasonic transmitting module is placed on the identification base, the ultrasonic receiving module is placed on the identification base, and the signal processing module and the data analysis module are placed on the monitoring backend. The ultrasonic receiving module and the signal processing module establish signal interaction. The signal processing module and the data analysis module establish signal interaction. The ultrasonic transmitting module generates high-frequency ultrasonic signals according to preset frequency and amplitude parameters and transmits the high-frequency ultrasonic signals to the cutting surface through an ultrasonic transmitter. The ultrasonic receiving module receives the high-frequency ultrasonic signals reflected from the cutting surface through an ultrasonic receiver and transmits the received high-frequency ultrasonic signals to the signal processing module. The signal processing module amplifies, filters, and digitizes the received high-frequency ultrasonic signals to extract useful feature information and transmits the processed high-frequency ultrasonic signals to the data analysis module. The feature information includes the time-domain features, frequency-domain features, energy features, waveform parameters, or peak-valley parameters of the received high-frequency ultrasonic signals. The data analysis module uses advanced data processing algorithms to analyze the processed high-frequency ultrasonic signal data, distinguish between coal seams and rocks, and generate coal-rock distribution maps to provide a basis for workers to analyze coal mine quality.

5. The method for identifying coal and rock at a cut surface based on hardness characteristics according to claim 1, characterized in that... The signal converter is connected to the data processor via a data transmission line, the data processor is connected to the controller via a data transmission line, and the tunneling machine cutting head is connected to the controller via a data line. The controller and the tunneling machine control system establish signal interaction. The signal converter can convert the electrical signal of the distance data collected by the distance sensor into a digital signal. The controller is implemented by one or more application-specific integrated circuits (ASICs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to execute instructions of the data processing device. The data processor and the signal converter interact with each other.

6. The method for identifying coal and rock at a cut surface based on hardness characteristics according to claim 1, characterized in that... The identification base has a sealing test hole on its side, and a threaded sealing plug is placed on the side of the identification base. The threaded sealing plug is embedded in the sealing test hole. When the tunneling machine is mining coal, it will generate a lot of dust. The identification base needs to be sealed to prevent wear caused by high dust concentration inside the identification base, which would affect the normal operation of the tunneling machine. Therefore, it is necessary to pull out the threaded sealing plug every once in a while, clean the dust in the sealing test hole, and test the sealing of the identification base to determine whether its sealing meets the requirements and ensure the normal coal mining operation of the tunneling machine.

7. The method for identifying coal and rock at a cut surface based on hardness characteristics according to claim 1, characterized in that... The identification base has a cylindrical structure, and the diameter of the identification base is larger than the diameter of the rotating rocker arm; There are multiple high-strength dampers, which are evenly distributed in the planetary slots. The multiple high-strength dampers and high-strength springs can provide better support and retraction force for the tunneling machine cutting head, which is more conducive to the tunneling machine cutting head cutting coal seams and rocks with different hardness characteristics.

8. The method for identifying coal and rock at a cut surface based on hardness characteristics according to claim 1, characterized in that... The cutting head mounting column is a cylindrical structure. The diameter of the cutting head mounting column is smaller than the diameter of the planetary column. The bottom diameter of the tunneling machine cutting head is larger than the outer diameter of the planetary column. This can prevent the high-strength damper and high-strength spring from retracting when encountering rocks. The tunneling machine cutting head enters the planetary slot along with the retraction of the planetary column.

9. The method for identifying coal and rock at a cut surface based on hardness characteristics according to claim 4, characterized in that... The ultrasonic receiving module includes multiple ultrasonic receivers, which are evenly placed on the identification base. When the ultrasonic signal encounters the coal seam and rock, a portion of the signal is reflected back. The multiple ultrasonic receivers can simultaneously receive high-frequency ultrasonic signals from multiple directions and angles, which can improve the receiving efficiency, reduce signal loss, and help to comprehensively detect the hardness characteristics of coal and rock at the cut surface.

10. The method for identifying coal and rock at a cut surface based on hardness characteristics according to claim 1, characterized in that... The data analysis module also includes a user interface, which is used to intuitively display the coal and rock distribution map and related statistical data. The data analysis module uses machine learning or pattern recognition technology to analyze the processed high-frequency ultrasonic signal data.

Images