Adaptive cutting method, system, header machine, electronic device, medium and chip

Abstract

An adaptive cutting method, and a system, header machine, electronic device, medium and chip based on said method. The method comprises: acquiring a working section image, and determining a first coal-rock hardness level according to the working section image; determining an initial cutting arm swing speed according to the first coal-rock hardness level and a first model library; acquiring a vibration spectrum of cutting the working section at the initial cutting arm swing speed, and determining a second coal-rock hardness level according to the vibration spectrum and a second model library; determining an optimized cutting arm swing speed according to the first coal-rock hardness level, the second coal-rock hardness level and the first model library. This method improves the accuracy of predicting a hardness level, thereby improving the accuracy of controlling a cutting arm swing speed.

Description

Adaptive cutting method, system, roadheader, electronic device, medium and chip

[0001] This application claims priority to the Chinese patent application filed with the State Intellectual Property Office of China on June 13, 2023, with application number "202310692269.X" and application name "Adaptive cutting method, system, tunneling machine, electronic device, medium and chip", all contents of which are incorporated by reference into this application. Technical Field

[0002] The present application relates to the technical field of autonomous control of coal mine comprehensive excavation equipment, and specifically to an adaptive cutting method, system, excavator, electronic equipment, medium and chip. Background Art

[0003] In related technologies, a roadheader (TBM) is equipped with a sensor module, an edge computer, and a data acquisition unit, and uses various parameters to adaptively control the swing speed of the cutting arm, thereby achieving adaptive cutting. Specifically, the sensor module collects cylinder pressure data, cylinder displacement data, and cutting arm vibration data during the cutting process. This data is then transmitted to the edge computer via the data acquisition unit. The edge computer processes this data, including cylinder pressure, displacement, cutting arm vibration, cutting current, and cutting voltage, and adaptively controls the swing speed of the TBM's cutting arm based on the processing results.

[0004] In the process of realizing the present application, the inventors found that there are at least the following problems in the related art: the method for adaptively controlling the swing speed of the cutting arm does not differentiate between working faces with different coal and rock working conditions, and the adaptive cutting efficiency is not high.

[0005] Summary of the Invention

[0006] In order to solve or improve the technical problem that the method for adaptive control of the swing speed of the cutting arm does not distinguish between working faces with different coal and rock working conditions and the adaptive cutting efficiency is low, one purpose of this application is to provide an adaptive cutting method for a tunneling machine based on coal and rock identification.

[0007] Another object of the present application is to provide an adaptive cutting system for a roadheader based on coal and rock identification.

[0008] Another object of the present application is to provide a tunnel boring machine.

[0009] Another object of the present application is to provide an electronic device.

[0010] Another object of the present application is to provide a computer-readable storage medium.

[0011] Another object of the present application is to provide a chip.

[0012] To achieve the above-mentioned objectives, the first aspect of the present application provides an adaptive cutting method for a tunnel boring machine based on coal and rock identification, including: obtaining a working section image in front of the tunnel boring machine, and determining a first coal and rock hardness grade based on the working section image; determining an initial cutting arm swing speed based on the first coal and rock hardness grade and a first model library; obtaining a vibration spectrum when the working section is cut at the initial cutting arm swing speed, and determining a second coal and rock hardness grade based on the vibration spectrum and a second model library; determining an optimized cutting arm swing speed based on the first coal and rock hardness grade, the second coal and rock hardness grade and the first model library.

[0013] According to the technical solution of the adaptive cutting method of a roadheader based on coal and rock identification provided in this application, an adaptive cutting method of a roadheader based on coal and rock identification is provided. During the cutting process of the roadheader, the swing speed of the cutting arm is continuously adjusted and optimized according to the coal and rock hardness grade, so as to achieve the purpose of adaptively adjusting the swing speed of the cutting arm for the working surface of different coal and rock working conditions. Specifically, the coal and rock classification is realized by combining a support vector machine algorithm based on vibration signal analysis with the image acquisition module to collect working section images. The average value of the first coal and rock hardness grade and the second coal and rock hardness grade are matched with the first model library, and the swing speed of the cutting arm is continuously adjusted and optimized. By continuously adjusting and optimizing the swing speed of the cutting arm, on the one hand, the optimized swing speed of the cutting arm will not be too small, ensuring that the roadheader has a sufficiently high adaptive cutting efficiency; on the other hand, the optimized swing speed of the cutting arm will not be too large, so as to avoid excessive load on the cutting arm, which is beneficial to reducing the degree of wear and increasing the service life of the cutting components.

[0014] The tunnel boring machine includes a machine body, a cutting arm, a cutting motor, a shovel, a walking crawler assembly and a transport device. The cutting arm and the shovel are arranged at the same end of the machine body. The cutting motor is arranged on the machine body, and the cutting motor is connected to the cutting arm. The cutting motor is used to drive the cutting arm to operate. The cutting arm is arranged above the shovel. The cutting arm can fracture and cut the coal and rock on the tunnel face, causing it to fall in the form of block materials. The tunnel face is a working face that continuously advances forward during tunnel excavation (in coal mining, mining or tunnel engineering). The shovel located below the cutting arm can accumulate and collect block materials that fall on the ground or directly fall on the shovel. Furthermore, the transport device is arranged on the machine body, and one end of the transport device is connected to the shovel. The transport device can transport the block materials accumulated and collected by the shovel from the front end of the tunnel boring machine (the end close to the tunnel face) to the rear end of the tunnel boring machine. Furthermore, the walking crawler assembly is arranged at the bottom of the machine body. By setting up a walking crawler group, the tunnel boring machine can move forward or backward in the tunnel to realize the walking function.

[0015] Specifically, the steps of the roadheader adaptive cutting method based on coal-rock identification include:

[0016] The first step is to acquire a working cross-sectional image in front of the roadheader and determine the first coal and rock hardness grade based on this image. This step occurs when the roadheader is in a static state, or, in other words, before cutting begins. Of course, the roadheader can also acquire working cross-sectional images during the cutting process and determine the first coal and rock hardness grade based on these images.

[0017] Specifically, an image acquisition module captures images of the tunnel face to obtain a working cross-sectional image in front of the roadheader. Optionally, the image acquisition module is located within the body of the roadheader. By placing the image acquisition module within the body of the roadheader, compared to designs in which the image acquisition module is located within the roadheader's blade or crawler assembly, the image acquisition module is of sufficient height, providing a wider viewing angle for capturing images. Furthermore, the image acquisition module operates stably regardless of whether the roadheader is in a static or cutting state, effectively preventing severe vibration of the image acquisition module during the cutting state, thereby improving the clarity of the working cross-sectional image. Compared to designs in which the image acquisition module is located within the roadheader's cutting arm or cutting motor, the image acquisition module does not experience severe vibration during the cutting state, thereby improving the clarity of the working cross-sectional image. Compared to designs in which the image acquisition module is located within the roadheader's transport equipment, the image acquisition module is closer to the tunnel face, providing a wider viewing angle. Optionally, the image acquisition module is a camera and / or a still camera.

[0018] Furthermore, the working section image is used as an image signal, and the information processing module performs coal and rock identification and classification based on the image texture. Optionally, the information processing module includes an image analysis module. The image analysis module performs image recognition based on the cross-sectional texture pattern on the working section image to obtain a first coal and rock hardness grade based on the image texture recognition.

[0019] The second step is to determine the initial cutting arm swing speed based on the first coal rock hardness grade and the first model library. This step occurs when the roadheader changes from a static state to a cutting state.

[0020] Specifically, a first model library is obtained that maps coal rock hardness grades to optimal cutting arm swing speeds. Optionally, the first model library is an optimal cutting model library. For working faces with different coal rock working conditions, multiple different coal rock hardness grades may exist. In the first model library, each coal rock hardness grade has a corresponding optimal cutting arm swing speed. Therefore, a matching cutting arm swing speed will also exist in the first model library for the first coal rock hardness grade, and this cutting arm swing speed is used as the initial cutting arm swing speed. It is worth noting that the first coal rock hardness grade is obtained by the information processing module through image texture analysis of the working section image. It is of great reference value for the initial cutting arm swing speed when the roadheader transitions from a static state to a cutting state. On the one hand, the initial cutting arm swing speed is not too low, ensuring that the roadheader has sufficiently high adaptive cutting efficiency. On the other hand, the initial cutting arm swing speed is not too high, avoiding excessive load on the cutting arm, which helps reduce wear and increase the service life of the cutting components (including the cutting arm and cutting teeth). In the subsequent steps, the support vector machine algorithm based on vibration signal analysis is combined with the image acquisition module to collect working section images to realize coal rock classification, so as to make the coal rock hardness grade more accurate.

[0021] The third step is to obtain the vibration spectrum when cutting the working section at the initial cutting arm swing speed, and determine the second coal and rock hardness grade based on the vibration spectrum and the second model library. This step occurs when the roadheader is cutting dynamically.

[0022] Specifically, while the roadheader is cutting the working section at the initial cutting arm swing speed, the sensor module collects bearing vibration signals. Optionally, the sensor module is a high-frequency vibration sensor. Optionally, the sensor module is installed in the roadheader's cutting motor. By installing the sensor module in the roadheader's cutting motor, bearing vibration signals can be acquired with greater sensitivity than designs in which the sensor module is installed in other roadheader components, thereby providing a more accurate second coal and rock hardness grade.

[0023] Furthermore, the vibration spectrum is determined based on the bearing vibration signal. A second model library is obtained that matches the vibration spectrum with the coal rock hardness grade. During the dynamic cutting of the tunnel boring machine, the vibration spectrum obtained by cutting coal rocks of different hardness is analyzed, and then the different vibration spectra are classified by the support vector machine algorithm. Finally, the classification results are matched with the coal rock hardness grade to obtain a second model library that matches the vibration spectrum with the coal rock hardness grade. In the second model library, each vibration spectrum will have a corresponding coal rock hardness grade, and this coal rock hardness grade is used as the second coal rock hardness grade. It is worth noting that the support vector machine (SVM) is a type of generalized linear classifier that performs binary classification on data in a supervised learning manner, and its decision boundary is the maximum margin hyperplane solved for the learning sample. The support vector machine uses the hinge loss function to calculate the empirical risk and adds a regularization term to the solution system to optimize the structural risk. It is a classifier with sparsity and robustness.

[0024] The fourth step is to determine the optimized cutting arm swing speed based on the first coal rock hardness grade, the second coal rock hardness grade, and the first model library. This step occurs when the roadheader is dynamically cutting. Coal rock classification is achieved by combining a support vector machine algorithm based on vibration signal analysis with the image acquisition module to collect working section images. Optionally, the average value of the first coal rock hardness grade and the second coal rock hardness grade is taken, and the optimized cutting arm swing speed is determined based on the average value and the first model library. In this case, the determined coal rock hardness grade is more accurate. Matching this coal rock hardness grade (i.e., the average value) with the first model library can correspond to a more appropriate optimized cutting arm swing speed. Optionally, the maximum value of the first coal rock hardness grade and the second coal rock hardness grade is taken, and the optimized cutting arm swing speed is determined based on the maximum value and the first model library. In this case, compared with the method of taking the average value, the determined coal rock hardness grade is slightly larger but the difference is not large, the calculation method is simple, and the interval for adjusting the optimized cutting arm swing speed is longer. The average value or maximum value of the first coal rock hardness grade and the second coal rock hardness grade are matched with the first model library, and the swing speed of the cutting arm is continuously adjusted and optimized.

[0025] The technical solution defined in the present application provides an adaptive cutting method for a tunnel boring machine based on coal and rock identification. During the cutting process of the tunnel boring machine, the swing speed of the cutting arm is continuously adjusted and optimized according to the coal and rock hardness grade, so as to achieve the purpose of adaptively adjusting the swing speed of the cutting arm for the working surface of different coal and rock working conditions. Specifically, the coal and rock classification is realized by combining a support vector machine algorithm based on vibration signal analysis with an image acquisition module to collect working section images. The average or maximum value of the first coal and rock hardness grade and the second coal and rock hardness grade are matched with the first model library, and the swing speed of the cutting arm is continuously adjusted and optimized. By continuously adjusting and optimizing the swing speed of the cutting arm, on the one hand, the optimized swing speed of the cutting arm will not be too small, ensuring that the tunnel boring machine has a sufficiently high adaptive cutting efficiency; on the other hand, the optimized swing speed of the cutting arm will not be too large, so as to avoid excessive load on the cutting arm, which is beneficial to reducing the degree of wear and increasing the service life of the cutting components.

[0026] In addition, the above technical solution provided by this application may also have the following additional technical features:

[0027] In some technical solutions, optionally, a vibration spectrum is obtained when the working section is cut at the initial cutting arm swing speed, and the second coal rock hardness grade is determined based on the vibration spectrum and the second model library, specifically including: obtaining a bearing vibration signal when the working section is cut at the initial cutting arm swing speed, and determining a first vibration spectrum based on the bearing vibration signal; obtaining a second model library; and determining the second coal rock hardness grade based on the first vibration spectrum and the second model library.

[0028] In this technical solution, while the roadheader is cutting the working section at the initial cutting arm swing speed, the sensor module collects the bearing vibration signal. The specific steps of determining the vibration spectrum based on the bearing vibration signal and determining the second coal rock hardness grade based on the vibration spectrum and the second model library include:

[0029] Acquire the bearing vibration signal when the working section is cut at the initial cutting arm swing speed, and determine the first vibration spectrum based on the bearing vibration signal. When the roadheader cuts the working section at the initial cutting arm swing speed, collect the bearing vibration signal through the sensor module. Optionally, the sensor module is a high-frequency vibration sensor. Optionally, the sensor module is arranged in the cutting motor of the roadheader. By arranging the sensor module in the cutting motor of the roadheader, compared with the design method of arranging the sensor module in other components of the roadheader, the bearing vibration signal can be obtained more sensitively, thereby making the second coal rock hardness grade more accurate. Furthermore, the multiple bearing vibration signals are sorted and analyzed to determine the first vibration spectrum.

[0030] Obtain a second model library. Obtain a second model library that matches the vibration spectrum with the coal rock hardness grade. During dynamic cutting by the tunnel boring machine, the vibration spectrum obtained by cutting coal rocks of different hardness is analyzed, and then the different vibration spectra are classified by the support vector machine algorithm. Finally, the classification results are matched with the coal rock hardness grade to obtain a second model library that matches the vibration spectrum with the coal rock hardness grade. It is worth noting that the support vector machine (SVM) is a type of generalized linear classifier that performs binary classification on data in a supervised learning manner. Its decision boundary is the maximum margin hyperplane solved for the learning samples. The support vector machine uses the hinge loss function to calculate the empirical risk and adds a regularization term to the solution system to optimize the structural risk. It is a classifier with sparsity and robustness.

[0031] The second coal rock hardness grade is determined based on the first vibration spectrum and the second model library. In the second model library, each vibration spectrum has a corresponding coal rock hardness grade. Therefore, the first vibration spectrum will also have a coal rock hardness grade matching it in the second model library, and this coal rock hardness grade is used as the second coal rock hardness grade. It is worth noting that the second coal rock hardness grade is derived using a support vector machine algorithm based on vibration signal analysis. This provides valuable insights for adaptively adjusting the cutting arm swing speed of the roadheader's working surface to accommodate different coal rock conditions during the cutting process.

[0032] In some technical solutions, optionally, obtaining a second model library specifically includes: obtaining a second vibration spectrum; classifying the second vibration spectrum through a support vector machine algorithm; matching the classified second vibration spectrum with the coal rock hardness grade to determine the second model library.

[0033] In this technical solution, the specific steps of obtaining a second model library that matches the vibration spectrum with the coal rock hardness grade include:

[0034] Acquire the second vibration spectrum. During dynamic cutting of the roadheader, the bearing vibration signal is collected by the sensor module, and the second vibration spectrum is determined based on the bearing vibration signal.

[0035] The second vibration spectrum is classified using a support vector machine algorithm. The second vibration spectrum obtained by analyzing and cutting coal rocks of different hardnesses is then classified using a support vector machine algorithm, and the classification results are finally matched to the coal rock hardness grade. A support vector machine (SVM) is a type of generalized linear classifier that performs binary classification on data using supervised learning. Its decision boundary is the maximum-margin hyperplane solved for the learning samples. The support vector machine uses a hinge loss function to calculate empirical risk and incorporates a regularization term into the solution system to optimize structural risk. It is a sparse and robust classifier.

[0036] The classified second vibration spectrum is matched to the coal rock hardness grade to determine the second model library. By analyzing the vibration spectra obtained by cutting coal rocks of different hardnesses, the different vibration spectra are classified using a support vector machine algorithm. Finally, the classification results are matched to the coal rock hardness grade to obtain a second model library that matches the vibration spectra to the coal rock hardness grade. In the second model library, each vibration spectrum has a corresponding coal rock hardness grade. Therefore, the first vibration spectrum will also have a coal rock hardness grade matching it in the second model library.

[0037] In some technical solutions, optionally, the optimized cutting arm swing speed is determined based on the first coal rock hardness grade, the second coal rock hardness grade and the first model library, specifically: taking the average value of the first coal rock hardness grade and the second coal rock hardness grade, and determining the optimized cutting arm swing speed based on the average value and the first model library; or taking the maximum value of the first coal rock hardness grade and the second coal rock hardness grade, and determining the optimized cutting arm swing speed based on the maximum value and the first model library.

[0038] In this technical solution, the optimized cutting arm swing speed is determined based on the average value of the first coal rock hardness grade and the second coal rock hardness grade and the first model library. In this case, the determined coal rock hardness grade is more accurate (not too large or too small). If the determined coal rock hardness grade is too large, the corresponding cutting arm swing speed will be too small, which will affect the cutting efficiency; if the determined coal rock hardness grade is too small, the corresponding cutting arm swing speed will be too large. Cutting according to this cutting arm swing speed may cause the cutting arm to be overloaded and aggravate wear. Therefore, matching the average value of the two coal rock hardness grades with the first model library can correspond to a more suitable optimized cutting arm swing speed.

[0039] Alternatively, the optimized cutter arm swing speed can be determined based on the maximum value of the first and second coal rock hardness grades and the first model library. In this case, compared to taking an average value, the determined coal rock hardness grade is slightly higher, but the difference is not significant. The calculation is simpler, and the interval for adjusting the optimized cutter arm swing speed is longer.

[0040] The purpose of this step is to match the average value or maximum value of the first coal rock hardness grade and the second coal rock hardness grade with the first model library, and continuously adjust and optimize the swing speed of the cutting arm.

[0041] In some technical solutions, optionally, the initial cutting arm swing speed is determined based on the first coal rock hardness grade and the first model library, specifically: obtaining the first model library that maps the coal rock hardness grade and the optimal cutting arm swing speed, and determining the initial cutting arm swing speed based on the first coal rock hardness grade and the first model library.

[0042] In this technical solution, there will be multiple different coal rock hardness levels for working faces with different coal rock working conditions. In the first model library, each coal rock hardness level will have a corresponding optimal cutting arm swing speed. Therefore, there will also be a cutting arm swing speed that matches the first coal rock hardness level in the first model library, and this cutting arm swing speed will be used as the initial cutting arm swing speed. It is worth noting that the first coal rock hardness level is obtained by the information processing module performing image texture analysis on the working section image, which has a very important reference value for the initial cutting arm swing speed when the tunnel boring machine changes from a static state to a cutting state. On the one hand, the initial cutting arm swing speed will not be too small, ensuring that the tunnel boring machine has a sufficiently high adaptive cutting efficiency; on the other hand, the initial cutting arm swing speed will not be too large to avoid excessive load on the cutting arm, which is beneficial to reducing the degree of wear and increasing the service life of the cutting components (including the cutting arm and cutting teeth). In the subsequent steps, the support vector machine algorithm based on vibration signal analysis is combined with the image acquisition module to collect the working section image to realize coal rock classification, so that the coal rock hardness level is more accurate.

[0043] In some technical solutions, optionally, a working section image in front of the tunnel boring machine is obtained, and the first coal rock hardness grade is determined based on the working section image. Specifically, a working section image in front of the tunnel boring machine is obtained, and the first coal rock hardness grade is determined by performing image texture recognition on the working section image.

[0044] In this technical solution, an image acquisition module captures images of the tunnel face to obtain a working cross-sectional image in front of the roadheader. Optionally, the image acquisition module is located within the body of the roadheader. By placing the image acquisition module within the body of the roadheader, compared to designs in which the image acquisition module is located within the roadheader's blade or crawler assembly, the image acquisition module is of sufficient height, providing a wider viewing angle for image capture. Furthermore, the image acquisition module operates stably regardless of whether the roadheader is in a static or cutting state, effectively preventing severe vibration of the image acquisition module during the cutting state, thereby improving the clarity of the working cross-sectional image. Compared to designs in which the image acquisition module is located within the roadheader's cutting arm or cutting motor, the image acquisition module does not experience severe vibration during the cutting state, thereby improving the clarity of the working cross-sectional image. Compared to designs in which the image acquisition module is located within the roadheader's transport equipment, the image acquisition module is closer to the tunnel face, providing a wider viewing angle. Optionally, the image acquisition module is a camera and / or a still camera.

[0045] Furthermore, the working section image is used as an image signal, and the information processing module performs coal and rock identification and classification based on the image texture. Optionally, the information processing module includes an image analysis module. The image analysis module performs image recognition based on the cross-sectional texture pattern on the working section image to obtain a first coal and rock hardness grade based on the image texture recognition.

[0046] The second aspect of the present application provides a roadheader adaptive cutting system based on coal-rock identification, comprising: an information processing module for executing the steps of the roadheader adaptive cutting method based on coal-rock identification in any of the above technical solutions.

[0047] According to the technical solution of the roadheader adaptive cutting system based on coal and rock recognition of this application, the roadheader adaptive cutting system based on coal and rock recognition includes an information processing module, which is configured to execute the steps of the roadheader adaptive cutting method based on coal and rock recognition described in any of the above technical solutions. The roadheader adaptive cutting system based on coal and rock recognition also includes an image acquisition module and a sensor module. The image acquisition module is configured to acquire a working cross-sectional image in front of the roadheader. The image acquisition module captures an image of the tunnel face to obtain a working cross-sectional image in front of the roadheader. Optionally, the image acquisition module is located within the body of the roadheader. By placing the image acquisition module on the body of the tunnel boring machine, compared to a design in which the image acquisition module is placed on the shovel or walking track assembly of the tunnel boring machine, the image acquisition module has sufficient height and a wider viewing angle for capturing images. Furthermore, the image acquisition module can operate stably regardless of whether the tunnel boring machine is in a static state or a cutting state, effectively preventing the image acquisition module from vibrating violently when the tunnel boring machine is in the cutting state, which is beneficial for improving the clarity of the working section image. Compared to a design in which the image acquisition module is placed on the cutting arm or cutting motor of the tunnel boring machine, the image acquisition module does not vibrate violently when the tunnel boring machine is in the cutting state, which is beneficial for improving the clarity of the working section image. Compared to a design in which the image acquisition module is placed on the transport equipment of the tunnel boring machine, the image acquisition module is closer to the tunnel face and has a wider viewing angle. Optionally, the image acquisition module is a camera and / or a camera.

[0048] Furthermore, the sensor module is used to acquire bearing vibration signals. When the roadheader cuts the working section, the sensor module collects bearing vibration signals. Optionally, the sensor module is a high-frequency vibration sensor. Optionally, the sensor module is installed in the cutting motor of the roadheader. By installing the sensor module in the cutting motor of the roadheader, bearing vibration signals can be acquired more sensitively than designs where the sensor module is installed in other components of the roadheader, thereby ensuring a more accurate second coal and rock hardness grade.

[0049] Furthermore, the information processing module is communicatively connected to the image acquisition module. The information processing module is configured to determine a first coal and rock hardness grade based on the working section image, and to determine an initial cutting arm swing speed based on the first coal and rock hardness grade and the first model library. Specifically, the working section image serves as the image signal, and the information processing module performs coal and rock identification and classification based on the image texture. Optionally, the information processing module includes an image analysis module. The image analysis module performs image recognition on the working section image based on the cross-sectional texture pattern to obtain a first coal and rock hardness grade based on the image texture recognition. Furthermore, the information processing module obtains a first model library that maps coal and rock hardness grades to optimal cutting arm swing speeds. Optionally, the first model library is an optimal cutting model library. For working faces with different coal and rock working conditions, multiple different coal and rock hardness grades may exist. In the first model library, each coal and rock hardness grade has a corresponding optimal cutting arm swing speed. Therefore, a cutting arm swing speed matching the first coal and rock hardness grade will also exist in the first model library, and this cutting arm swing speed is used as the initial cutting arm swing speed. It is worth noting that the first coal rock hardness grade is obtained by the information processing module through image texture analysis of the working section image, which has important reference value for the initial cutting arm swing speed when the tunnel boring machine changes from a static state to a cutting state. On the one hand, the initial cutting arm swing speed will not be too small, ensuring that the tunnel boring machine has a sufficiently high adaptive cutting efficiency; on the other hand, the initial cutting arm swing speed will not be too large to avoid excessive load on the cutting arm, which is beneficial to reduce the degree of wear and increase the service life of the cutting components (including the cutting arm and cutting teeth).

[0050] Furthermore, the information processing module is communicatively connected to the sensor module. The information processing module is also used to determine the vibration spectrum based on the bearing vibration signal, determine the second coal rock hardness level based on the vibration spectrum and the second model library, and determine the optimized cutting arm swing speed based on the first coal rock hardness level, the second coal rock hardness level and the first model library. Specifically, when the roadheader is dynamically cutting, the vibration spectrum obtained by cutting coal rocks of different hardness is analyzed, and then the different vibration spectra are classified by the support vector machine algorithm. Finally, the classification results are matched with the coal rock hardness level to obtain a second model library in which the vibration spectrum and the coal rock hardness level are matched. In the second model library, each vibration spectrum will have a corresponding coal rock hardness level, and this coal rock hardness level is used as the second coal rock hardness level. It is worth noting that the support vector machine (SVM) is a type of generalized linear classifier that performs binary classification on data in a supervised learning manner, and its decision boundary is the maximum margin hyperplane solved for the learning sample. The support vector machine (SVM) uses a hinge loss function to calculate empirical risk and incorporates a regularization term into the solution system to optimize structural risk. It is a classifier with both sparsity and robustness. Furthermore, the information processing module determines the optimal cutting arm swing speed based on the first and second coal rock hardness grades and the first model library. Coal rock classification is achieved by combining a support vector machine algorithm based on vibration signal analysis with images of the working section acquired by the image acquisition module. Alternatively, the average of the first and second coal rock hardness grades can be taken, and the optimized cutting arm swing speed determined based on this average and the first model library. This method provides a more accurate determination of the coal rock hardness grade. Matching this coal rock hardness grade (i.e., the average) with the first model library can yield a more appropriate optimized cutting arm swing speed. Alternatively, the maximum value of the first and second coal rock hardness grades can be taken, and the optimal cutting arm swing speed determined based on this maximum value and the first model library. Compared to the average method, this method results in a slightly higher determined coal rock hardness grade, but the difference is not significant. The calculation is simpler, and the interval for adjusting the optimized cutting arm swing speed is longer. The average value or maximum value of the first coal rock hardness grade and the second coal rock hardness grade are matched with the first model library, and the swing speed of the cutting arm is continuously adjusted and optimized.

[0051] In the technical solution defined in the present application, during the cutting process of the tunnel boring machine, the swing speed of the cutting arm is continuously adjusted and optimized according to the coal rock hardness grade, so as to achieve the purpose of adaptively adjusting the swing speed of the cutting arm for the working surface of different coal rock working conditions. Specifically, the coal rock classification is realized by combining the support vector machine algorithm based on vibration signal analysis with the image acquisition module to collect the working section image, and the average or maximum value of the first coal rock hardness grade and the second coal rock hardness grade is matched with the first model library, and the swing speed of the cutting arm is continuously adjusted and optimized. By continuously adjusting and optimizing the swing speed of the cutting arm, on the one hand, the optimized swing speed of the cutting arm will not be too small, ensuring that the tunnel boring machine has a sufficiently high adaptive cutting efficiency; on the other hand, the optimized swing speed of the cutting arm will not be too large, so as to avoid excessive load on the cutting arm, which is beneficial to reduce the degree of wear and increase the service life of the cutting components.

[0052] The third aspect of the present application provides a roadheader, comprising: the roadheader adaptive cutting system based on coal and rock identification in the above technical solution; and a cutting arm connected to the information processing module of the roadheader adaptive cutting system based on coal and rock identification.

[0053] According to the technical solution of the tunnel boring machine of the present application, the tunnel boring machine includes the tunnel boring machine adaptive cutting system based on coal and rock identification and the cutting arm in the above technical solution. The information processing module of the tunnel boring machine adaptive cutting system based on coal and rock identification is connected to the cutting arm. The information processing module obtains a working section image in front of the tunnel boring machine and determines a first coal and rock hardness grade based on the working section image. The information processing module determines an initial cutting arm swing speed based on the first coal and rock hardness grade and the first model library. Furthermore, the information processing module obtains a vibration spectrum when the working section is cut at the initial cutting arm swing speed, and determines a second coal and rock hardness grade based on the vibration spectrum and the second model library. The information processing module determines an optimized cutting arm swing speed based on the first coal and rock hardness grade, the second coal and rock hardness grade, and the first model library.

[0054] Optionally, the information processing module includes an underground industrial computer and a PLC (Programmable Logic Controller). The underground industrial computer and the PLC are connected via a CAN-to-Ethernet module. CAN stands for Controller Area Network. The image acquisition module is connected to the underground industrial computer. The sensor module is connected to the PLC. Optionally, the roadheader also includes a cutting motor connected to the cutting arm to drive the cutting arm. The cutting motor is electrically connected to the PLC to adjust the swing speed of the cutting arm.

[0055] Optionally, the tunnel boring machine further includes a fuselage, a shovel, a walking crawler assembly and a transport device. The cutting arm and the shovel are arranged at the same end of the fuselage. The cutting motor is arranged on the fuselage, and the cutting motor is connected to the cutting arm. The cutting motor is used to drive the cutting arm to operate. The cutting arm is arranged above the shovel. The cutting arm can fracture and cut the coal and rock on the face of the tunnel, causing it to fall in the form of block materials. The face of the tunnel is a working face that continuously advances forward during tunnel excavation (in coal mining, mining or tunnel engineering). The shovel located below the cutting arm can stack and collect block materials that fall on the ground or directly fall on the shovel. Furthermore, the transport device is arranged on the fuselage, and one end of the transport device is connected to the shovel. The transport device can transport the block materials stacked and collected by the shovel from the front end of the tunnel boring machine (the end close to the face of the tunnel) to the tail end of the tunnel boring machine. Furthermore, the walking crawler assembly is arranged at the bottom of the fuselage. By setting up a walking crawler group, the tunnel boring machine can move forward or backward in the tunnel to realize the walking function.

[0056] Optionally, the image acquisition module of the roadheader's adaptive cutting system based on coal-rock identification is located on the roadheader's fuselage. By locating the image acquisition module on the roadheader's fuselage, compared to a design in which the image acquisition module is located on the roadheader's shovel or crawler assembly, the image acquisition module has sufficient height, a wider viewing angle for capturing images, and can operate stably regardless of whether the roadheader is in a static or cutting state, effectively preventing the image acquisition module from vigorous shaking when the roadheader is in the cutting state, thereby improving the clarity of the working section image. Compared to a design in which the image acquisition module is located on the roadheader's cutting arm or cutting motor, the image acquisition module does not vibrate violently when the roadheader is in the cutting state, thereby improving the clarity of the working section image. Compared to a design in which the image acquisition module is located on the roadheader's transport equipment, the image acquisition module is closer to the tunnel face and has a wider viewing angle.

[0057] Optionally, the sensor module of the roadheader's adaptive cutting system based on coal-rock identification is installed in the roadheader's cutting motor. This allows for more sensitive acquisition of bearing vibration signals, compared to designs where the sensor module is installed in other roadheader components, resulting in a more accurate second coal and rock hardness rating.

[0058] The fourth aspect of the present application provides an electronic device, including a processor, a memory, and a program or instruction stored in the memory and executable on the processor. When the program or instruction is executed by the processor, the steps of the adaptive cutting method of a tunnel boring machine based on coal and rock identification in any of the above-mentioned technical solutions are implemented.

[0059] In a fifth aspect, the present application provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, the steps of the adaptive cutting method of a roadheader based on coal and rock identification in any of the above technical solutions are implemented.

[0060] In the sixth aspect of the present application, a chip is provided, which includes a processor and a communication interface. The communication interface and the processor are coupled, and the processor is used to run programs or instructions to implement the steps of the adaptive cutting method of a tunnel boring machine based on coal and rock identification in any of the above technical solutions.

[0061] Additional aspects and advantages of the technical solution of the present application will become apparent in the following description or be understood through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] FIG1 shows one of the flow charts of a method for adaptive cutting of a roadheader based on coal and rock identification according to an embodiment of the present application;

[0063] FIG2 shows a second flow chart of a method for adaptive cutting of a roadheader based on coal and rock identification according to an embodiment of the present application;

[0064] FIG3 shows a third flow chart of a method for adaptive cutting of a roadheader based on coal and rock identification according to an embodiment of the present application;

[0065] FIG4 shows a schematic diagram of connections between modules of a roadheader adaptive cutting system based on coal and rock identification according to an embodiment of the present application;

[0066] FIG5 shows a schematic diagram of a roadheader according to an embodiment of the present application.

[0067] Among them, the correspondence between the figure marks and component names in Figures 4 and 5 is: 400: Adaptive cutting system of roadheader based on coal and rock recognition; 410: Image acquisition module; 420: Sensor module; 430: Information processing module; 500: Roadheader; 510: Fuselage; 520: Cutting arm; 530: Cutting motor; 540: Shovel board; 550: Walking track group; 560: Transportation equipment. DETAILED DESCRIPTION

[0068] In order to more clearly understand the above-mentioned purposes, features and advantages of the embodiments of the present application, the embodiments of the present application are further described in detail below in conjunction with the accompanying drawings and specific implementation methods. It should be noted that the embodiments of the present application and the features therein can be combined with each other in the absence of conflict.

[0069] In the following description, many specific details are set forth to facilitate a full understanding of the present application. However, the embodiments of the present application may also be implemented in other ways different from those described herein. Therefore, the scope of protection of the present application is not limited to the specific embodiments disclosed below.

[0070] 1 to 5 , the following describes an adaptive cutting method for a roadheader based on coal and rock identification, an adaptive cutting system 400 for a roadheader based on coal and rock identification, a roadheader 500, an electronic device, a computer-readable storage medium, and a chip according to some embodiments of the present application.

[0071] As shown in Figure 5, the tunnel boring machine 500 includes a body 510, a cutting arm 520, a cutting motor 530, a shovel 540, a walking crawler group 550 and a transport device 560. Among them, the cutting arm 520 and the shovel 540 are arranged at the same end of the body 510. The cutting motor 530 is arranged on the body 510, and the cutting motor 530 is connected to the cutting arm 520. The cutting motor 530 is used to drive the cutting arm 520 to operate. The cutting arm 520 is arranged above the shovel 540. The cutting arm 520 can fracture and cut the coal and rock on the tunnel face, causing it to fall in the form of block materials. The tunnel face is the working face that continuously advances forward during the excavation of a tunnel (in coal mining, mining or tunnel engineering). The shovel 540 located below the cutting arm 520 can accumulate and collect block materials that fall on the ground or directly fall on the shovel 540. Furthermore, a transport device 560 is mounted on the machine body 510, with one end of the transport device 560 connected to the shovel 540. The transport device 560 can transport bulk materials accumulated and collected by the shovel 540 from the front end (the end closest to the tunnel face) of the roadheader 500 to the rear end of the roadheader 500. Furthermore, a walking track assembly 550 is mounted on the bottom of the machine body 510. The walking track assembly 550 enables the roadheader 500 to move forward or backward within the tunnel, thus achieving its walking function.

[0072] In one embodiment of the present application, as shown in FIG1 , the steps of the first flow chart of the roadheader adaptive cutting method based on coal-rock identification include:

[0073] S102: Acquire a working cross-sectional image in front of the roadheader and determine a first coal and rock hardness grade based on the working cross-sectional image. This step occurs when the roadheader is in a static state, or, in other words, before cutting begins. Of course, the roadheader can also acquire a working cross-sectional image during the cutting process and determine the first coal and rock hardness grade based on the working cross-sectional image.

[0074] Specifically, an image acquisition module captures images of the tunnel face to obtain a working cross-sectional image in front of the roadheader. Optionally, the image acquisition module is located within the body of the roadheader. By placing the image acquisition module within the body of the roadheader, compared to designs in which the image acquisition module is located within the roadheader's blade or crawler assembly, the image acquisition module is of sufficient height, providing a wider viewing angle for capturing images. Furthermore, the image acquisition module operates stably regardless of whether the roadheader is in a static or cutting state, effectively preventing severe vibration of the image acquisition module during the cutting state, thereby improving the clarity of the working cross-sectional image. Compared to designs in which the image acquisition module is located within the roadheader's cutting arm or cutting motor, the image acquisition module does not experience severe vibration during the cutting state, thereby improving the clarity of the working cross-sectional image. Compared to designs in which the image acquisition module is located within the roadheader's transport equipment, the image acquisition module is closer to the tunnel face, providing a wider viewing angle. Optionally, the image acquisition module is a camera and / or a still camera.

[0075] Furthermore, the working section image is used as an image signal, and the information processing module performs coal and rock identification and classification based on the image texture. Optionally, the information processing module includes an image analysis module. The image analysis module performs image recognition based on the cross-sectional texture pattern on the working section image to obtain a first coal and rock hardness grade based on the image texture recognition.

[0076] S104: Determine an initial cutting arm swing speed based on the first coal rock hardness grade and the first model library. This step occurs when the roadheader transitions from a static state to a cutting state.

[0077] Specifically, a first model library is obtained that maps coal rock hardness grades to optimal cutting arm swing speeds. Optionally, the first model library is an optimal cutting model library. For working faces with different coal rock working conditions, multiple different coal rock hardness grades may exist. In the first model library, each coal rock hardness grade has a corresponding optimal cutting arm swing speed. Therefore, a matching cutting arm swing speed will also exist in the first model library for the first coal rock hardness grade, and this cutting arm swing speed is used as the initial cutting arm swing speed. It is worth noting that the first coal rock hardness grade is obtained by the information processing module through image texture analysis of the working section image. It is of great reference value for the initial cutting arm swing speed when the roadheader transitions from a static state to a cutting state. On the one hand, the initial cutting arm swing speed is not too low, ensuring that the roadheader has sufficiently high adaptive cutting efficiency. On the other hand, the initial cutting arm swing speed is not too high, avoiding excessive load on the cutting arm, which helps reduce wear and increase the service life of the cutting components (including the cutting arm and cutting teeth). In the subsequent steps, the support vector machine algorithm based on vibration signal analysis is combined with the image acquisition module to collect working section images to realize coal rock classification, so as to make the coal rock hardness grade more accurate.

[0078] S106: Obtain the vibration spectrum when the working section is cut at the initial cutting arm swing speed, and determine the second coal rock hardness grade based on the vibration spectrum and the second model library. This step occurs when the roadheader is cutting dynamically.

[0079] Specifically, while the roadheader is cutting the working section at the initial cutting arm swing speed, the sensor module collects bearing vibration signals. Optionally, the sensor module is a high-frequency vibration sensor. Optionally, the sensor module is installed in the roadheader's cutting motor. By installing the sensor module in the roadheader's cutting motor, bearing vibration signals can be acquired with greater sensitivity than designs in which the sensor module is installed in other roadheader components, thereby providing a more accurate second coal and rock hardness grade.

[0080] Furthermore, the vibration spectrum is determined based on the bearing vibration signal. A second model library is obtained that matches the vibration spectrum with the coal rock hardness grade. During the dynamic cutting of the tunnel boring machine, the vibration spectrum obtained by cutting coal rocks of different hardness is analyzed, and then the different vibration spectra are classified by the support vector machine algorithm. Finally, the classification results are matched with the coal rock hardness grade to obtain a second model library that matches the vibration spectrum with the coal rock hardness grade. In the second model library, each vibration spectrum will have a corresponding coal rock hardness grade, and this coal rock hardness grade is used as the second coal rock hardness grade. It is worth noting that the support vector machine (SVM) is a type of generalized linear classifier that performs binary classification on data in a supervised learning manner, and its decision boundary is the maximum margin hyperplane solved for the learning sample. The support vector machine uses the hinge loss function to calculate the empirical risk and adds a regularization term to the solution system to optimize the structural risk. It is a classifier with sparsity and robustness.

[0081] S108: Determine the optimized cutting arm swing speed based on the first coal rock hardness grade, the second coal rock hardness grade, and the first model library. This step occurs during dynamic cutting by the roadheader. Coal rock classification is achieved by combining a support vector machine algorithm based on vibration signal analysis with working section images collected by an image acquisition module. Optionally, the average of the first coal rock hardness grade and the second coal rock hardness grade is taken, and the optimized cutting arm swing speed is determined based on the average and the first model library. In this case, the determined coal rock hardness grade is more accurate. Matching this coal rock hardness grade (i.e., the average) with the first model library can correspond to a more appropriate optimized cutting arm swing speed. Optionally, the maximum value of the first coal rock hardness grade and the second coal rock hardness grade is taken, and the optimized cutting arm swing speed is determined based on the maximum value and the first model library. In this case, compared to taking the average value, the determined coal rock hardness grade is slightly higher, but the difference is not significant. The calculation method is simpler, and the interval for adjusting the optimized cutting arm swing speed is longer. The average value or maximum value of the first coal rock hardness grade and the second coal rock hardness grade are matched with the first model library, and the swing speed of the cutting arm is continuously adjusted and optimized.

[0082] The technical solution defined in the present application provides an adaptive cutting method for a tunnel boring machine based on coal and rock identification. During the cutting process of the tunnel boring machine, the swing speed of the cutting arm is continuously adjusted and optimized according to the coal and rock hardness grade, so as to achieve the purpose of adaptively adjusting the swing speed of the cutting arm for the working surface of different coal and rock working conditions. Specifically, the coal and rock classification is realized by combining a support vector machine algorithm based on vibration signal analysis with an image acquisition module to collect working section images. The average or maximum value of the first coal and rock hardness grade and the second coal and rock hardness grade are matched with the first model library, and the swing speed of the cutting arm is continuously adjusted and optimized. By continuously adjusting and optimizing the swing speed of the cutting arm, on the one hand, the optimized swing speed of the cutting arm will not be too small, ensuring that the tunnel boring machine has a sufficiently high adaptive cutting efficiency; on the other hand, the optimized swing speed of the cutting arm will not be too large, so as to avoid excessive load on the cutting arm, which is beneficial to reducing the degree of wear and increasing the service life of the cutting components.

[0083] In one embodiment of the present application, as shown in FIG2 , the steps of the second flow chart of the roadheader adaptive cutting method based on coal-rock identification include:

[0084] S202: Acquire a working cross-sectional image in front of the roadheader and determine a first coal and rock hardness grade by performing image texture recognition on the working cross-sectional image. This step occurs when the roadheader is in a static state, or, in other words, before cutting. Of course, the roadheader can also acquire working cross-sectional images during the cutting process and determine the first coal and rock hardness grade based on the working cross-sectional images.

[0085] Specifically, an image acquisition module captures images of the tunnel face to obtain a working cross-sectional image in front of the roadheader. Optionally, the image acquisition module is located within the body of the roadheader. By placing the image acquisition module within the body of the roadheader, compared to designs in which the image acquisition module is located within the roadheader's blade or crawler assembly, the image acquisition module is of sufficient height, providing a wider viewing angle for capturing images. Furthermore, the image acquisition module operates stably regardless of whether the roadheader is in a static or cutting state, effectively preventing severe vibration of the image acquisition module during the cutting state, thereby improving the clarity of the working cross-sectional image. Compared to designs in which the image acquisition module is located within the roadheader's cutting arm or cutting motor, the image acquisition module does not experience severe vibration during the cutting state, thereby improving the clarity of the working cross-sectional image. Compared to designs in which the image acquisition module is located within the roadheader's transport equipment, the image acquisition module is closer to the tunnel face, providing a wider viewing angle. Optionally, the image acquisition module is a camera and / or a still camera.

[0086] Furthermore, the working section image is used as an image signal, and the information processing module performs coal and rock identification and classification based on the image texture. Optionally, the information processing module includes an image analysis module. The image analysis module performs image recognition based on the cross-sectional texture pattern on the working section image to obtain a first coal and rock hardness grade based on the image texture recognition.

[0087] S204: Obtain a first model library mapping coal rock hardness grades and optimal cutting arm swing speeds, and determine an initial cutting arm swing speed based on the first coal rock hardness grades and the first model library. This step occurs when the roadheader transitions from a static state to a cutting state.

[0088] Specifically, a first model library is obtained that maps coal rock hardness grades to optimal cutting arm swing speeds. Optionally, the first model library is an optimal cutting model library. For working faces with different coal rock working conditions, multiple different coal rock hardness grades may exist. In the first model library, each coal rock hardness grade has a corresponding optimal cutting arm swing speed. Therefore, a matching cutting arm swing speed will also exist in the first model library for the first coal rock hardness grade, and this cutting arm swing speed is used as the initial cutting arm swing speed. It is worth noting that the first coal rock hardness grade is obtained by the information processing module through image texture analysis of the working section image. It is of great reference value for the initial cutting arm swing speed when the roadheader transitions from a static state to a cutting state. On the one hand, the initial cutting arm swing speed is not too low, ensuring that the roadheader has sufficiently high adaptive cutting efficiency. On the other hand, the initial cutting arm swing speed is not too high, avoiding excessive load on the cutting arm, which helps reduce wear and increase the service life of the cutting components (including the cutting arm and cutting teeth). In the subsequent steps, the support vector machine algorithm based on vibration signal analysis is combined with the image acquisition module to collect working section images to realize coal rock classification, so as to make the coal rock hardness grade more accurate.

[0089] S206, obtain the bearing vibration signal when the working section is cut at the initial cutting arm swing speed, and determine the first vibration spectrum based on the bearing vibration signal. This step occurs when the tunnel boring machine is dynamically cutting. When the tunnel boring machine cuts the working section at the initial cutting arm swing speed, the bearing vibration signal is collected by the sensor module. Optionally, the sensor module is a high-frequency vibration sensor. Optionally, the sensor module is provided in the cutting motor of the tunnel boring machine. By arranging the sensor module in the cutting motor of the tunnel boring machine, compared with the design method of arranging the sensor module in other components of the tunnel boring machine, the bearing vibration signal can be obtained more sensitively, so that the second coal rock hardness grade is more accurate. Furthermore, multiple bearing vibration signals are sorted and analyzed to determine the first vibration spectrum.

[0090] S208, obtain a second model library. Obtain a second model library that matches the vibration spectrum with the coal rock hardness grade. During the dynamic cutting of the tunnel boring machine, the vibration spectrum obtained by cutting coal rocks of different hardness is analyzed, and then the different vibration spectra are classified by the support vector machine algorithm. Finally, the classification results are matched with the coal rock hardness grade to obtain a second model library that matches the vibration spectrum with the coal rock hardness grade. It is worth noting that the support vector machine (SVM) is a type of generalized linear classifier that performs binary classification on data in a supervised learning manner, and its decision boundary is the maximum margin hyperplane solved for the learning samples. The support vector machine uses the hinge loss function to calculate the empirical risk and adds a regularization term to the solution system to optimize the structural risk. It is a classifier with sparsity and robustness.

[0091] S210: Determine a second coal rock hardness level based on the first vibration spectrum and the second model library. In the second model library, each vibration spectrum corresponds to a corresponding coal rock hardness level. Therefore, a matching coal rock hardness level will also exist in the second model library for the first vibration spectrum, and this coal rock hardness level is used as the second coal rock hardness level. It is worth noting that the second coal rock hardness level is derived using a support vector machine algorithm based on vibration signal analysis, which is of great value in enabling adaptive adjustment of the cutting arm swing speed of the roadheader's working surface to different coal rock working conditions during the cutting process.

[0092] S212: Calculate the average of the first and second coal rock hardness grades and determine the optimal cutting arm swing speed based on the average and the first model library. Alternatively, calculate the maximum of the first and second coal rock hardness grades and determine the optimal cutting arm swing speed based on the maximum and the first model library. This step occurs during dynamic cutting by the roadheader. Coal rock classification is achieved by combining a support vector machine algorithm based on vibration signal analysis with cross-section images collected by an image acquisition module.

[0093] Optionally, the optimized cutting arm swing speed is determined based on the average value of the first coal rock hardness grade and the second coal rock hardness grade and the first model library. In this case, the determined coal rock hardness grade is more accurate (not too large or too small). If the determined coal rock hardness grade is too large, the corresponding cutting arm swing speed will be too small, which will affect the cutting efficiency; if the determined coal rock hardness grade is too small, the corresponding cutting arm swing speed will be too large. Cutting according to this cutting arm swing speed may cause the cutting arm to be overloaded and aggravate wear. Therefore, matching the average value of the two coal rock hardness grades with the first model library can correspond to a more appropriate optimized cutting arm swing speed.

[0094] Alternatively, the optimized cutting arm swing speed is determined based on the maximum value of the first and second coal hardness grades and the first model library. In this case, compared to taking an average value, the determined coal hardness grade is slightly higher, but the difference is not significant. The calculation is simpler, and the interval for adjusting the optimized cutting arm swing speed is longer.

[0095] The purpose of this step is to match the average value or maximum value of the first coal rock hardness grade and the second coal rock hardness grade with the first model library, and continuously adjust and optimize the swing speed of the cutting arm.

[0096] In one embodiment of the present application, as shown in FIG3 , the steps of the third flow chart of the roadheader adaptive cutting method based on coal-rock identification include:

[0097] S302: Acquire a working cross-sectional image in front of the roadheader and determine a first coal and rock hardness grade by performing texture recognition on the working cross-sectional image. This step occurs when the roadheader is in a static state, or, in other words, before cutting. Of course, the roadheader can also acquire working cross-sectional images during the cutting process and determine the first coal and rock hardness grade based on the working cross-sectional images.

[0098] Specifically, an image acquisition module captures images of the tunnel face to obtain a working cross-sectional image in front of the roadheader. Optionally, the image acquisition module is located within the body of the roadheader. By placing the image acquisition module within the body of the roadheader, compared to designs in which the image acquisition module is located within the roadheader's blade or crawler assembly, the image acquisition module is of sufficient height, providing a wider viewing angle for capturing images. Furthermore, the image acquisition module operates stably regardless of whether the roadheader is in a static or cutting state, effectively preventing severe vibration of the image acquisition module during the cutting state, thereby improving the clarity of the working cross-sectional image. Compared to designs in which the image acquisition module is located within the roadheader's cutting arm or cutting motor, the image acquisition module does not experience severe vibration during the cutting state, thereby improving the clarity of the working cross-sectional image. Compared to designs in which the image acquisition module is located within the roadheader's transport equipment, the image acquisition module is closer to the tunnel face, providing a wider viewing angle. Optionally, the image acquisition module is a camera and / or a still camera.

[0099] Furthermore, the working section image is used as an image signal, and the information processing module performs coal and rock identification and classification based on the image texture. Optionally, the information processing module includes an image analysis module. The image analysis module performs image recognition based on the cross-sectional texture pattern on the working section image to obtain a first coal and rock hardness grade based on the image texture recognition.

[0100] S304: Obtain a first model library mapping coal rock hardness grades and optimal cutting arm swing speeds, and determine an initial cutting arm swing speed based on the first coal rock hardness grades and the first model library. This step occurs when the roadheader transitions from a static state to a cutting state.

[0101] Specifically, a first model library is obtained that maps coal rock hardness grades to optimal cutting arm swing speeds. Optionally, the first model library is an optimal cutting model library. For working faces with different coal rock working conditions, multiple different coal rock hardness grades may exist. In the first model library, each coal rock hardness grade has a corresponding optimal cutting arm swing speed. Therefore, a matching cutting arm swing speed will also exist in the first model library for the first coal rock hardness grade, and this cutting arm swing speed is used as the initial cutting arm swing speed. It is worth noting that the first coal rock hardness grade is obtained by the information processing module through image texture analysis of the working section image. It is of great reference value for the initial cutting arm swing speed when the roadheader transitions from a static state to a cutting state. On the one hand, the initial cutting arm swing speed is not too low, ensuring that the roadheader has sufficiently high adaptive cutting efficiency. On the other hand, the initial cutting arm swing speed is not too high, avoiding excessive load on the cutting arm, which helps reduce wear and increase the service life of the cutting components (including the cutting arm and cutting teeth). In the subsequent steps, the support vector machine algorithm based on vibration signal analysis is combined with the image acquisition module to collect working section images to realize coal rock classification, so as to make the coal rock hardness grade more accurate.

[0102] S306, obtain the bearing vibration signal when the working section is cut at the initial cutting arm swing speed, and determine the first vibration spectrum based on the bearing vibration signal. This step occurs when the tunnel boring machine is dynamically cutting. When the tunnel boring machine cuts the working section at the initial cutting arm swing speed, the bearing vibration signal is collected by the sensor module. Optionally, the sensor module is a high-frequency vibration sensor. Optionally, the sensor module is provided in the cutting motor of the tunnel boring machine. By arranging the sensor module in the cutting motor of the tunnel boring machine, compared with the design method of arranging the sensor module in other components of the tunnel boring machine, the bearing vibration signal can be obtained more sensitively, so that the second coal rock hardness grade is more accurate. Furthermore, multiple bearing vibration signals are sorted and analyzed to determine the first vibration spectrum.

[0103] S308, obtaining a second vibration spectrum. When the roadheader is dynamically cutting, the bearing vibration signal is collected by the sensor module, and the second vibration spectrum is determined based on the bearing vibration signal.

[0104] S310, classify the second vibration spectrum using the support vector machine algorithm. The second vibration spectrum obtained by cutting coal rocks of different hardness is analyzed, and then the different second vibration spectra are classified using the support vector machine algorithm. Finally, the classification results are matched to the coal rock hardness grade. Support Vector Machine (SVM) is a type of generalized linear classifier that performs binary classification on data using supervised learning. Its decision boundary is the maximum margin hyperplane solved for the learning samples. The support vector machine uses a hinge loss function to calculate empirical risk and adds a regularization term to the solution system to optimize structural risk. It is a classifier with sparsity and robustness.

[0105] S312: Match the classified second vibration spectrum with the coal rock hardness grade to determine a second model library. This is done by analyzing the vibration spectra obtained by cutting coal rocks of varying hardness, classifying the different vibration spectra using a support vector machine algorithm, and finally matching the classification results with the coal rock hardness grades. This creates a second model library that matches vibration spectra with coal rock hardness grades. In the second model library, each vibration spectrum has a corresponding coal rock hardness grade. Therefore, the first vibration spectrum will also have a matching coal rock hardness grade in the second model library.

[0106] S314: Determine a second coal rock hardness level based on the first vibration spectrum and the second model library. In the second model library, each vibration spectrum corresponds to a corresponding coal rock hardness level. Therefore, a matching coal rock hardness level will also exist in the second model library for the first vibration spectrum, and this coal rock hardness level is used as the second coal rock hardness level. It is worth noting that the second coal rock hardness level is derived using a support vector machine algorithm based on vibration signal analysis, which is of great value in enabling adaptive adjustment of the cutting arm swing speed of the roadheader's working surface to different coal rock working conditions during the cutting process.

[0107] S316: Calculate the average of the first and second coal rock hardness grades and determine the optimal cutting arm swing speed based on the average and the first model library. Alternatively, calculate the maximum of the first and second coal rock hardness grades and determine the optimal cutting arm swing speed based on the maximum and the first model library. This step occurs during dynamic cutting by the roadheader. Coal rock classification is achieved by combining a support vector machine algorithm based on vibration signal analysis with cross-section images collected by an image acquisition module.

[0108] Optionally, the optimized cutting arm swing speed is determined based on the average value of the first coal rock hardness grade and the second coal rock hardness grade and the first model library. In this case, the determined coal rock hardness grade is more accurate (not too large or too small). If the determined coal rock hardness grade is too large, the corresponding cutting arm swing speed will be too small, which will affect the cutting efficiency; if the determined coal rock hardness grade is too small, the corresponding cutting arm swing speed will be too large. Cutting according to this cutting arm swing speed may cause the cutting arm to be overloaded and aggravate wear. Therefore, matching the average value of the two coal rock hardness grades with the first model library can correspond to a more appropriate optimized cutting arm swing speed.

[0109] Alternatively, the optimized cutting arm swing speed is determined based on the maximum value of the first and second coal hardness grades and the first model library. In this case, compared to taking an average value, the determined coal hardness grade is slightly higher, but the difference is not significant. The calculation is simpler, and the interval for adjusting the optimized cutting arm swing speed is longer.

[0110] The purpose of this step is to match the average value or maximum value of the first coal rock hardness grade and the second coal rock hardness grade with the first model library, and continuously adjust and optimize the swing speed of the cutting arm.

[0111] In one embodiment of the present application, as shown in Figure 4 , a roadheader adaptive cutting system 400 based on coal and rock recognition includes an information processing module 430, which is configured to execute the steps of the roadheader adaptive cutting method based on coal and rock recognition described in any of the above-described technical solutions. The roadheader adaptive cutting system 400 based on coal and rock recognition also includes an image acquisition module 410 and a sensor module 420. The image acquisition module 410 is configured to acquire a working cross-sectional image in front of the roadheader 500. The image acquisition module 410 acquires images of the tunnel face to obtain a working cross-sectional image in front of the roadheader 500. Optionally, the image acquisition module 410 is located on the body 510 of the roadheader 500. By arranging the image acquisition module 410 on the body 510 of the roadheader 500, compared with a design method in which the image acquisition module 410 is arranged on the shovel 540 or the walking track assembly 550 of the roadheader 500, the image acquisition module 410 has a sufficient height and a wider viewing angle for capturing images. In addition, the image acquisition module 410 can operate stably regardless of whether the roadheader 500 is in a static state or a cutting state, effectively preventing the image acquisition module 410 from vigorous shaking when the roadheader 500 is in the cutting state, which is beneficial to improving the clarity of the working section image; compared with a design method in which the image acquisition module 410 is arranged on the cutting arm 520 or the cutting motor 530 of the roadheader 500, the image acquisition module 410 will not vibrate violently when the roadheader 500 is in the cutting state, which is beneficial to improving the clarity of the working section image; compared with a design method in which the image acquisition module 410 is arranged on the transportation equipment 560 of the roadheader 500, the image acquisition module 410 is closer to the tunnel face and has a wider viewing angle. Optionally, the image acquisition module 410 is a camera and / or a still camera.

[0112] Furthermore, the sensor module 420 is used to acquire bearing vibration signals. When the roadheader 500 cuts the working section, the sensor module 420 collects bearing vibration signals. Optionally, the sensor module 420 is a high-frequency vibration sensor. Optionally, the sensor module 420 is installed in the cutting motor 530 of the roadheader 500. By installing the sensor module 420 in the cutting motor 530 of the roadheader 500, compared to designs where the sensor module 420 is installed in other components of the roadheader 500, bearing vibration signals can be acquired more sensitively, thereby ensuring a more accurate second coal and rock hardness grade.

[0113] Furthermore, the information processing module 430 is communicatively connected to the image acquisition module 410. The information processing module 430 is used to determine a first coal rock hardness grade based on the working section image, and to determine an initial cutting arm swing speed based on the first coal rock hardness grade and the first model library. Specifically, the working section image serves as an image signal, and the information processing module 430 performs coal rock identification and classification on the working section image based on the image texture. Optionally, the information processing module 430 includes an image analysis module. The image analysis module performs image recognition on the working section image based on the cross-sectional texture pattern to obtain a first coal rock hardness grade based on image texture recognition. Furthermore, the information processing module 430 obtains a first model library that maps coal rock hardness grades to optimal cutting arm swing speeds. Optionally, the first model library is an optimal cutting model library. For working faces with different coal rock working conditions, there may be multiple different coal rock hardness grades. In the first model library, each coal rock hardness grade has a corresponding optimal cutting arm swing speed. Therefore, a matching cutting arm swing speed exists in the first model library for the first coal rock hardness grade, and this cutting arm swing speed is used as the initial cutting arm swing speed. It is worth noting that the first coal rock hardness grade, obtained by the information processing module 430 through image texture analysis of the working section image, is of great reference value for the initial cutting arm swing speed when the roadheader 500 transitions from a static state to a cutting state. On the one hand, the initial cutting arm swing speed is not too slow, ensuring that the roadheader 500 has sufficiently high adaptive cutting efficiency. On the other hand, the initial cutting arm swing speed is not too fast, preventing excessive load on the cutting arm 520, thereby reducing wear and increasing the service life of the cutting components (including the cutting arm 520 and cutting teeth).

[0114] Furthermore, the information processing module 430 is in communication connection with the sensor module 420. The information processing module 430 is also used to determine the vibration spectrum based on the bearing vibration signal, determine the second coal rock hardness level based on the vibration spectrum and the second model library, and determine the optimized cutting arm swing speed based on the first coal rock hardness level, the second coal rock hardness level and the first model library. Specifically, when the roadheader 500 is dynamically cutting, the vibration spectrum obtained by cutting coal rocks of different hardness is analyzed, and then the different vibration spectra are classified by the support vector machine algorithm. Finally, the classification results are matched with the coal rock hardness level to obtain a second model library in which the vibration spectrum and the coal rock hardness level are matched. In the second model library, each vibration spectrum will have a corresponding coal rock hardness level, and this coal rock hardness level is used as the second coal rock hardness level. It is worth noting that the support vector machine (SVM) is a type of generalized linear classifier that performs binary classification on data in a supervised learning manner, and its decision boundary is the maximum margin hyperplane solved for the learning sample. The support vector machine uses the hinge loss function to calculate the empirical risk and adds a regularization term to the solution system to optimize the structural risk. It is a classifier with sparsity and robustness.

[0115] Furthermore, the information processing module 430 determines the optimized cutting arm swing speed based on the first and second coal rock hardness grades and the first model library. Coal rock classification is achieved by combining a support vector machine algorithm based on vibration signal analysis with cross-sectional images collected by the image acquisition module 410. Alternatively, the average of the first and second coal rock hardness grades is taken, and the optimized cutting arm swing speed is determined based on this average and the first model library. In this case, the determined coal rock hardness grade is more accurate. By matching this coal rock hardness grade (i.e., the average) with the first model library, a more appropriate optimized cutting arm swing speed can be obtained. Alternatively, the maximum of the first and second coal rock hardness grades is taken, and the optimized cutting arm swing speed is determined based on this maximum and the first model library. In this case, compared to taking the average, the determined coal rock hardness grade is slightly higher, but the difference is not significant. The calculation is simpler, and the interval for adjusting the optimized cutting arm swing speed is longer. The average or maximum of the first and second coal rock hardness grades is matched with the first model library to continuously adjust the optimized cutting arm swing speed.

[0116] In the technical solution defined in the present application, during the cutting process of the roadheader 500, the swing speed of the cutting arm is continuously adjusted and optimized according to the coal rock hardness grade, so as to achieve the purpose of adaptively adjusting the swing speed of the cutting arm for the working surface of different coal rock working conditions. Specifically, the coal rock classification is realized by combining the support vector machine algorithm based on vibration signal analysis with the image acquisition module 410 to collect the working section image, and the average or maximum value of the first coal rock hardness grade and the second coal rock hardness grade is matched with the first model library, and the swing speed of the cutting arm is continuously adjusted and optimized. By continuously adjusting and optimizing the swing speed of the cutting arm, on the one hand, the optimized swing speed of the cutting arm will not be too small, ensuring that the roadheader 500 has a sufficiently high adaptive cutting efficiency; on the other hand, the optimized swing speed of the cutting arm will not be too large, so as to avoid excessive load on the cutting arm 520, which is beneficial to reduce the degree of wear and increase the service life of the cutting components.

[0117] In one embodiment of the present application, as shown in Figure 5, a roadheader 500 includes the roadheader adaptive cutting system 400 based on coal and rock identification and a cutting arm 520 according to the above-described embodiment. The information processing module 430 of the roadheader adaptive cutting system 400 based on coal and rock identification is connected to the cutting arm 520. The information processing module 430 obtains an image of the working section in front of the roadheader 500 and determines a first coal and rock hardness grade based on the image. The information processing module 430 determines an initial cutting arm swing speed based on the first coal and rock hardness grade and a first model library. Furthermore, the information processing module 430 obtains a vibration spectrum when cutting the working section at the initial cutting arm swing speed and determines a second coal and rock hardness grade based on the vibration spectrum and a second model library. The information processing module 430 determines an optimized cutting arm swing speed based on the first and second coal and rock hardness grades and the first model library.

[0118] Optionally, the information processing module 430 includes an underground industrial computer and a PLC (Programmable Logic Controller). The underground industrial computer and the PLC are connected via a CAN-to-Ethernet module. CAN stands for Controller Area Network. The image acquisition module 410 is connected to the underground industrial computer. The sensor module 420 is connected to the PLC. Optionally, the roadheader 500 also includes a cutting motor 530, which is connected to the cutting arm 520 and is used to drive the cutting arm 520. The cutting motor 530 is electrically connected to the PLC to adjust the swing speed of the cutting arm.

[0119] Optionally, the tunnel boring machine 500 further includes a body 510, a shovel plate 540, a walking crawler group 550 and a transport device 560. Among them, the cutting arm 520 and the shovel plate 540 are arranged at the same end of the body 510. The cutting motor 530 is arranged on the body 510, and the cutting motor 530 is connected to the cutting arm 520. The cutting motor 530 is used to drive the cutting arm 520 to operate. The cutting arm 520 is arranged above the shovel plate 540. The cutting arm 520 can fracture and cut the coal and rock on the face of the tunnel so that it falls in the form of block materials. The face of the tunnel is a working face that is constantly moving forward in the excavation of a tunnel (in coal mining, mining or tunnel engineering). The shovel plate 540 located below the cutting arm 520 can stack and collect block materials that fall on the ground or directly fall on the shovel plate 540. Furthermore, a transport device 560 is mounted on the machine body 510, with one end of the transport device 560 connected to the shovel 540. The transport device 560 can transport bulk materials accumulated and collected by the shovel 540 from the front end (the end closest to the tunnel face) of the roadheader 500 to the rear end of the roadheader 500. Furthermore, a walking track assembly 550 is mounted on the bottom of the machine body 510. The walking track assembly 550 enables the roadheader 500 to move forward or backward within the tunnel, thus achieving its walking function.

[0120] Optionally, the image acquisition module 410 of the roadheader adaptive cutting system 400 based on coal-rock recognition is provided on the body 510 of the roadheader 500 . By arranging the image acquisition module 410 on the body 510 of the roadheader 500, compared with a design method in which the image acquisition module 410 is arranged on the shovel 540 or the walking track assembly 550 of the roadheader 500, the image acquisition module 410 has a sufficient height and a wider viewing angle for capturing images. In addition, the image acquisition module 410 can operate stably regardless of whether the roadheader 500 is in a static state or a cutting state, effectively preventing the image acquisition module 410 from vigorous shaking when the roadheader 500 is in the cutting state, which is beneficial to improving the clarity of the working section image; compared with a design method in which the image acquisition module 410 is arranged on the cutting arm 520 or the cutting motor 530 of the roadheader 500, the image acquisition module 410 will not vibrate violently when the roadheader 500 is in the cutting state, which is beneficial to improving the clarity of the working section image; compared with a design method in which the image acquisition module 410 is arranged on the transportation equipment 560 of the roadheader 500, the image acquisition module 410 is closer to the tunnel face and has a wider viewing angle.

[0121] Optionally, the sensor module 420 of the roadheader adaptive cutting system 400 based on coal-rock identification is installed in the cutting motor 530 of the roadheader 500. By installing the sensor module 420 in the cutting motor 530 of the roadheader 500, compared to a design in which the sensor module 420 is installed in other components of the roadheader 500, the bearing vibration signal can be acquired more sensitively, thereby making the second coal and rock hardness grade more accurate.

[0122] In one embodiment of the present application, the electronic device includes a processor, a memory, and a program or instruction stored in the memory and executable on the processor. When the program or instruction is executed by the processor, the steps of the adaptive cutting method of a tunnel boring machine based on coal and rock identification in any of the above-mentioned embodiments are implemented.

[0123] In one embodiment of the present application, a computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the adaptive cutting method for a roadheader based on coal and rock identification in any of the above embodiments are implemented.

[0124] Those skilled in the art will appreciate that all or part of the steps in the above-described embodiment can be implemented by instructing related hardware through a program. The program can be stored in a computer-readable storage medium. When executed, the program includes the following parts: obtaining a working section image in front of the roadheader and determining a first coal rock hardness grade based on the working section image; determining an initial cutting arm swing speed based on the first coal rock hardness grade and a first model library; obtaining a vibration spectrum when cutting the working section at the initial cutting arm swing speed, and determining a second coal rock hardness grade based on the vibration spectrum and a second model library; and determining an optimized cutting arm swing speed based on the first coal rock hardness grade, the second coal rock hardness grade, and the first model library. The storage medium may be a computer read-only memory (ROM), random access memory (RAM), a disk, or an optical disk.

[0125] In one embodiment of the present application, the chip includes a processor and a communication interface, the communication interface and the processor are coupled, and the processor is used to run programs or instructions to implement the steps of the adaptive cutting method of the roadheader based on coal and rock identification in any of the above embodiments.

[0126] It should be understood that the chip mentioned in the embodiments of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.

[0127] In this application, the terms "first," "second," and "third" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance. The term "plurality" refers to two or more, unless expressly limited otherwise. Terms such as "installed," "connected," "connected," and "fixed" should be understood in a broad sense. For example, "connected" can mean a fixed connection, a detachable connection, or an integral connection; "connected" can mean a direct connection or an indirect connection through an intermediary. Those skilled in the art can understand the specific meanings of the above terms in this application based on the specific circumstances.

[0128] In the description of this application, it should be understood that the terms "up", "down", "left", "right", "front", "back", etc., indicating directions or positional relationships, are based on the directions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing this application and simplifying the description, rather than indicating or implying that the device or unit referred to must have a specific direction, be constructed and operated in a specific direction. Therefore, they should not be understood as limitations on this application.

[0129] Throughout this specification, terms such as "one embodiment," "some embodiments," and "specific embodiments" mean that the specific features, structures, materials, or characteristics described in conjunction with that embodiment or example are included in at least one embodiment or example of the present application. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

[0130] The above are merely preferred embodiments of the present application and are not intended to limit the present application. Those skilled in the art will readily appreciate that various modifications and variations are possible. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present application shall be included within the scope of protection of the present application.

Claims

1. An adaptive cutting method for a roadheader based on coal-rock identification, wherein: include: Acquire a working section image in front of the tunnel boring machine, and determine a first coal rock hardness grade according to the working section image; Determining an initial cutting arm swing speed according to the first coal rock hardness grade and the first model library; Acquire a vibration spectrum when the working section is cut at the initial cutting arm swing speed, and determine a second coal rock hardness grade according to the vibration spectrum and a second model library; The optimized cutting arm swing speed is determined according to the first coal rock hardness grade, the second coal rock hardness grade and the first model library.

2. The method for adaptive cutting of a roadheader based on coal-rock identification according to claim 1, wherein: The obtaining of the vibration spectrum when the working section is cut at the initial cutting arm swing speed, and determining the second coal rock hardness grade according to the vibration spectrum and the second model library specifically includes: Acquire a bearing vibration signal when the working section is cut at the initial cutting arm swing speed, and determine a first vibration spectrum according to the bearing vibration signal; Acquire the second model library; The second coal rock hardness grade is determined according to the first vibration spectrum and the second model library.

3. The method for adaptive cutting of a roadheader based on coal-rock identification according to claim 2, wherein: The obtaining of the second model library specifically includes: acquiring a second vibration spectrum; classifying the second vibration spectrum by a support vector machine algorithm; The second vibration spectrum after classification is matched with the coal rock hardness grade to determine the second model library.

4. The method for adaptive cutting of a roadheader based on coal-rock identification according to any one of claims 1 to 3, wherein: The step of determining the optimized cutting arm swing speed according to the first coal rock hardness grade, the second coal rock hardness grade and the first model library is specifically as follows: Take the average value of the first coal rock hardness grade and the second coal rock hardness grade, and determine the optimized cutting arm swing speed according to the average value and the first model library; or take the maximum value of the first coal rock hardness grade and the second coal rock hardness grade, and determine the optimized cutting arm swing speed according to the maximum value and the first model library. The model library determines the optimized cutting arm swing speed.

5. The adaptive cutting method for a roadheader based on coal-rock identification according to any one of claims 1 to 3, wherein: The initial cutting arm swing speed is determined according to the first coal rock hardness grade and the first model library, specifically: The first model library mapping coal rock hardness grade and optimal cutting arm swing speed is obtained, and the initial cutting arm swing speed is determined according to the first coal rock hardness grade and the first model library.

6. The adaptive cutting method for a roadheader based on coal-rock identification according to any one of claims 1 to 3, wherein: The obtaining of the working section image in front of the roadheader and determining the first coal rock hardness grade according to the working section image is specifically as follows: The working section image in front of the tunnel boring machine is acquired, and the first coal rock hardness grade is determined by performing image texture recognition on the working section image.

7. An adaptive cutting system for a roadheader based on coal-rock identification, wherein: include: An information processing module (430) is used to execute the steps of the roadheader adaptive cutting method based on coal-rock identification as described in any one of claims 1 to 6.

8. A tunnel boring machine, wherein: include: The adaptive cutting system for roadheaders based on coal-rock identification as claimed in claim 7; The cutting arm (520) is connected to the information processing module (430) of the roadheader adaptive cutting system based on coal-rock identification.

9. An electronic device, wherein: It includes a processor, a memory, and a program or instruction stored in the memory and executable on the processor. When the program or instruction is executed by the processor, the steps of the adaptive cutting method of a roadheader based on coal and rock identification as described in any one of claims 1 to 6 are implemented.

10. A computer-readable storage medium, wherein: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the adaptive cutting method for a roadheader based on coal-rock identification as described in any one of claims 1 to 6 are implemented.

11. A chip, wherein: The chip includes a processor and a communication interface, the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the steps of the adaptive cutting method for a roadheader based on coal and rock identification as described in any one of claims 1 to 6.

Images