Coal rock identification method and apparatus, readable storage medium, and roadheader
By integrating image acquisition and data acquisition devices on the boring machine, combining point cloud data and motor operation data, accurate identification of coal rock distribution is achieved, and the problems of low cutting efficiency of intelligent boring machine and fatigue in the cutting part are solved, and the boring machine is improved work efficiency and equipment life.
Patent Information
- Application Number
- PCT/CN2024/077685
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2023-05-16
- Filing Date
- 2024-02-20
- Publication Date
- 2024-11-21
AI Technical Summary
During the automatic cutting process, the intelligent boring machine cannot judge the distribution of coal rock in the tunnel, resulting in low efficiency and easy fatigue damage.
The cutting efficiency of the boring machine is improved, fatigue damage of the cutting part is avoided, and the accuracy of coal rock distribution identification is ensured.
Smart Images

Figure CN2024077685_21112024_PF_FP_ABST
Abstract
Description
Coal rock identification method, device, readable storage medium and tunneling machine
[0001] This application claims priority to the Chinese patent application filed with the State Intellectual Property Office of China on May 16, 2023, with application number "202310545383.X" and application name "Coal and Rock Identification Method, Device, Readable Storage Medium and Tunneling Machine", the entire contents of which are incorporated by reference into this application. Technical Field
[0002] The present application relates to the technical field of coal rock identification, and in particular to a coal rock identification method, device, readable storage medium and tunnel boring machine. Background Art
[0003] At present, the intelligent roadheader is unable to judge the distribution of coal and rock in the tunnel during the automatic cutting process, resulting in the cutting part of the intelligent roadheader being unable to make adaptive adjustments during the cutting process, causing the roadheader to be overloaded and cutting. This not only reduces the cutting efficiency of the intelligent roadheader, but also causes fatigue damage to the cutting part.
[0004] Summary of the Invention
[0005] The present application aims to at least solve the technical problems existing in the prior art or related art, such as the low cutting efficiency of the intelligent tunnel boring machine and the easy fatigue damage to the cutting part.
[0006] To this end, the first aspect of this application is to propose a coal rock identification method.
[0007] The second aspect of this application is to propose a coal rock identification device.
[0008] The third aspect of this application is to propose another coal rock identification device.
[0009] A fourth aspect of the present application is to provide a readable storage medium.
[0010] A fifth aspect of the present application is to provide a tunnel boring machine.
[0011] In view of this, according to the first aspect of the present application, a coal and rock identification method is proposed for a tunneling machine. The tunneling machine is provided with an image acquisition device and a data acquisition device. The coal and rock identification method includes: obtaining a point cloud data set corresponding to the working area of the tunneling machine through the image acquisition device; determining the cutting area in the working area based on the point cloud data set; performing image recognition on the regional image corresponding to the cutting area to obtain first coal and rock distribution information corresponding to the cutting area; in the process of controlling the cutting part of the tunneling machine to perform cutting work, obtaining the motor operation data corresponding to the cutting part through the data acquisition device; determining the second coal and rock distribution information corresponding to the cutting area based on the motor operation data; and determining the target coal and rock distribution information of the cutting area based on the first coal and rock distribution information and the second coal and rock distribution information.
[0012] The coal and rock identification method in this technical solution collects a point cloud data set of the working area of the tunnel boring machine through an image acquisition device, performs data processing on the point cloud data set, extracts a cutting area in the working area, and performs image recognition on the regional image to determine the first coal and rock distribution information corresponding to the cutting area. Then, the motor operation data corresponding to the cutting part is collected through a data acquisition device, and data recognition is performed on the motor operation data to obtain the second coal and rock distribution information corresponding to the cutting area. Then, based on the first coal and rock distribution information and the second coal and rock distribution information, the target coal and rock distribution information of the cutting area is determined, thereby ensuring the accuracy of the recognition of the coal and rock distribution in the cutting area, thereby improving the cutting efficiency of the tunnel boring machine, and avoiding fatigue damage to the cutting part of the tunnel boring machine.
[0013] According to the second aspect of the present application, a coal and rock identification device is proposed for use in a roadheader. The roadheader is provided with an image acquisition device and a data acquisition device. The coal and rock identification device includes: an acquisition module for acquiring a point cloud data set corresponding to the working area of the roadheader through the image acquisition device; a processing module for determining a cutting area in the working area based on the point cloud data set; the processing module is also used to perform image recognition on the regional image corresponding to the cutting area to obtain first coal and rock distribution information corresponding to the cutting area; the acquisition module is also used to acquire motor operation data corresponding to the cutting part through the data acquisition device during the process of controlling the cutting part of the roadheader to perform cutting work; the processing module is also used to determine second coal and rock distribution information corresponding to the cutting area based on the motor operation data; the processing module is also used to determine target coal and rock distribution information of the cutting area based on the first coal and rock distribution information and the second coal and rock distribution information.
[0014] The coal and rock identification device in this technical solution collects a point cloud data set of the working area of the tunnel boring machine through an image acquisition device, performs data processing on the point cloud data set, extracts a cutting area in the working area, and performs image recognition on the regional image to determine the first coal and rock distribution information corresponding to the cutting area, and then collects the motor operation data corresponding to the cutting part through a data acquisition device, performs data recognition on the motor operation data to obtain the second coal and rock distribution information corresponding to the cutting area, and then determines the target coal and rock distribution information of the cutting area based on the first coal and rock distribution information and the second coal and rock distribution information, thereby ensuring the accuracy of the recognition of the coal and rock distribution in the cutting area, thereby improving the cutting efficiency of the tunnel boring machine and avoiding fatigue damage to the cutting part of the tunnel boring machine.
[0015] According to a third aspect of the present application, another coal-rock identification device is provided, comprising a processor and a memory. The memory stores a program or instructions that, when executed by the processor, implement the steps of the coal-rock identification method described in any of the above-mentioned technical solutions. Therefore, this coal-rock identification device possesses all the beneficial effects of the coal-rock identification method described in any of the above-mentioned technical solutions, and will not be further elaborated here.
[0016] According to a fourth aspect of the present application, a readable storage medium is provided, on which a program or instruction is stored. When executed by a processor, the program or instruction implements the coal-rock identification method described in any of the above-mentioned technical solutions. Therefore, the readable storage medium has all the beneficial effects of the coal-rock identification method described in any of the above-mentioned technical solutions, and no further description is given here.
[0017] According to the fifth aspect of the present application, a roadheader is proposed, comprising: a coal and rock identification device as defined in the above-mentioned second aspect, or the coal and rock identification device defined in the above-mentioned third aspect, and / or the readable storage medium defined in the above-mentioned fourth aspect, and thus having all the beneficial technical effects of the coal and rock identification device defined in the above-mentioned second aspect, or the coal and rock identification device defined in the above-mentioned third aspect, and / or the readable storage medium defined in the above-mentioned fourth aspect, and no further details will be given here.
[0018] Additional aspects and advantages of the present application will become apparent in the following description or may be learned through practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS
[0019] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the description of the embodiments in conjunction with the following drawings, in which:
[0020] FIG1 shows a schematic diagram of a process of a coal-rock identification method according to an embodiment of the present application;
[0021] FIG2 shows a second flow chart of a coal-rock identification method according to an embodiment of the present application;
[0022] FIG3 shows a third flow chart of a coal rock identification method according to an embodiment of the present application;
[0023] FIG4 shows a fourth flow chart of a coal rock identification method according to an embodiment of the present application;
[0024] FIG5 shows a fifth flow chart of a coal-rock identification method according to an embodiment of the present application;
[0025] FIG6 shows a sixth flow chart of a coal-rock identification method according to an embodiment of the present application;
[0026] FIG7 shows a seventh flow chart of a coal-rock identification method according to an embodiment of the present application;
[0027] FIG8 shows one structural block diagram of a coal-rock identification device according to an embodiment of the present application;
[0028] FIG9 shows a schematic diagram of a coal rock identification device according to an embodiment of the present application;
[0029] FIG10 shows a second structural block diagram of a coal rock identification device according to an embodiment of the present application. DETAILED DESCRIPTION
[0030] In order to more clearly understand the above-mentioned objects, features and advantages of the present application, the present application is further described in detail below in conjunction with the accompanying drawings and specific embodiments. 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.
[0031] In the following description, many specific details are set forth to facilitate a full understanding of the present application. However, 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.
[0032] 1 to 10 , the coal and rock identification method, device, readable storage medium, and roadheader provided in the embodiments of the present application are described in detail through specific embodiments and their application scenarios.
[0033] The technical solution of the coal rock identification method provided in this application can be implemented by a coal rock identification device, which can also be determined based on actual usage requirements and is not specifically limited here. In order to more clearly describe the coal rock identification method provided in this application, the following description uses the coal rock identification device as the implementation body.
[0034] In one embodiment provided in the present application, as shown in FIG1 , a coal-rock identification method is proposed for a roadheader. The roadheader is provided with an image acquisition device and a data acquisition device. The coal-rock identification method includes:
[0035] Step 102: Acquire a point cloud data set corresponding to the working area of the roadheader through an image acquisition device;
[0036] Step 104, determining a cutting area in the working area based on the point cloud data set;
[0037] Step 106: performing image recognition on the regional image corresponding to the cutting area to obtain first coal and rock distribution information corresponding to the cutting area;
[0038] Step 108, while controlling the cutting part of the roadheader to perform cutting work, obtaining motor operation data corresponding to the cutting part through a data acquisition device;
[0039] Step 110: determining second coal and rock distribution information corresponding to the cutting area based on the motor operation data;
[0040] Step 112: Determine target coal and rock distribution information of the cutting area based on the first coal and rock distribution information and the second coal and rock distribution information.
[0041] In this embodiment, a coal rock identification method is provided, which is applied to a roadheader. The roadheader is a machine used to excavate tunnels on flat ground. An image acquisition device and a data acquisition device are provided on the roadheader, wherein the image acquisition device is used to acquire image data of the working area of the roadheader, and the data acquisition device is used to acquire motor data of the cutting part of the roadheader.
[0042] It should be noted that coal rock is a mixture of coal and rock. Coal rock identification is to identify the distribution of coal and rock on the cutting surface. The working area is the area where the tunnel boring machine performs cutting, and the cutting part is the component on the tunnel boring machine that performs cutting work.
[0043] Exemplarily, the image acquisition device may include multiple binocular cameras.
[0044] For example, the data acquisition device may acquire current data or vibration data of the cutting part motor.
[0045] For example, the working area may be specifically an underground coal mining tunnel.
[0046] For example, the tunnel boring machine may be specifically an automatic tunnel boring machine that can perform automatic cutting work.
[0047] Exemplarily, the cutting part may be a drum-type cutting part.
[0048] The coal and rock identification device collects a point cloud data set of the working area of the roadheader through an image acquisition device, wherein the point cloud data set is a point cloud data set corresponding to the working area of the roadheader.
[0049] The coal and rock identification device processes the point cloud data set and extracts a cutting area within the working area, wherein the cutting area is a cutting surface where the roadheader performs cutting work.
[0050] Exemplarily, the cutting area may be specifically a rectangular cutting surface.
[0051] The coal-rock identification device captures the regional image corresponding to the cutting area through the image acquisition device, and performs image recognition on the regional image to determine the first coal-rock distribution information corresponding to the cutting area, wherein the regional image is the image corresponding to the cutting area, and the first coal-rock distribution information is the coal-rock distribution information obtained through image recognition.
[0052] Exemplarily, the first coal-rock distribution information may specifically be the coal-rock distribution information obtained after the regional image is identified through a deep learning model.
[0053] In the process of controlling the cutting part of the roadheader to perform cutting work, the coal and rock identification device collects the motor operation data corresponding to the cutting part through the data acquisition device, wherein the motor operation data is the operation data of the motor corresponding to the cutting part.
[0054] Exemplarily, the motor operation data may specifically include current data and vibration data of the motor.
[0055] The coal-rock identification device performs data identification on the motor operation data to obtain second coal-rock distribution information corresponding to the cutting area, wherein the second coal-rock distribution information is coal-rock distribution information determined based on the motor operation data.
[0056] For example, the second coal-rock distribution information may specifically be coal-rock distribution information obtained by identifying motor operation data through a neural network.
[0057] The coal rock identification device performs data fusion on the first coal rock distribution information and the second coal rock distribution information to obtain target coal rock distribution information of the cutting area, wherein the target coal rock distribution information is coal rock distribution information determined based on the first coal rock distribution information and the second coal rock distribution information.
[0058] For example, the target coal-rock distribution information may be specifically coal-rock distribution information obtained by performing data matching on the first coal-rock distribution information and the second coal-rock distribution information.
[0059] The coal and rock identification method in this embodiment collects a point cloud data set of the working area of the tunnel boring machine through an image acquisition device, performs data processing on the point cloud data set, extracts a cutting area in the working area, and performs image recognition on the regional image to determine the first coal and rock distribution information corresponding to the cutting area. Then, the motor operation data corresponding to the cutting part is collected through the data acquisition device, and data recognition is performed on the motor operation data to obtain the second coal and rock distribution information corresponding to the cutting area. Then, based on the first coal and rock distribution information and the second coal and rock distribution information, the target coal and rock distribution information of the cutting area is determined, thereby ensuring the accuracy of the recognition of the coal and rock distribution in the cutting area, thereby improving the cutting efficiency of the tunnel boring machine, and avoiding fatigue damage to the cutting part of the tunnel boring machine.
[0060] In one embodiment provided in this application, as shown in FIG2 , a coal-rock identification method is proposed. The coal-rock identification method includes:
[0061] Step 202: Acquire a point cloud data set corresponding to the working area of the roadheader through an image acquisition device;
[0062] Step 204: performing data operations on the point cloud data set to obtain a depth variance corresponding to the point cloud data set;
[0063] Step 206: extracting target point cloud data from the point cloud data set based on the depth variance;
[0064] Step 208: performing data projection processing on the target point cloud data to obtain a cutting area;
[0065] Step 210: performing image recognition on a regional image corresponding to the cutting area to obtain first coal and rock distribution information corresponding to the cutting area;
[0066] Step 212, while controlling the cutting part of the roadheader to perform cutting work, obtaining motor operation data corresponding to the cutting part through a data acquisition device;
[0067] Step 214: determining second coal and rock distribution information corresponding to the cutting area based on the motor operation data;
[0068] Step 216: Determine target coal and rock distribution information of the cutting area based on the first coal and rock distribution information and the second coal and rock distribution information.
[0069] In this embodiment, the coal and rock identification device performs data calculation on the point cloud data set to determine the depth variance corresponding to the point cloud data set, wherein the depth variance is the variance of the depth data of each point cloud in the point cloud data set.
[0070] Exemplarily, the depth variance may be specifically the depth variance of each neighborhood point cloud in the point cloud data set.
[0071] The coal and rock identification device performs data extraction processing on the point cloud data set according to the depth variance to obtain target point cloud data, and performs data projection processing on the target point cloud data to determine the cutting area, wherein the target point cloud data is the point cloud data corresponding to the cutting area in the point cloud data set.
[0072] Exemplarily, the coal rock identification device projects the target point cloud data into the left view pixel space, and finally obtains the cutting surface pixel area in the left view.
[0073] The coal and rock identification method in this embodiment performs data calculation on the point cloud data set, determines the depth variance corresponding to the point cloud data set, performs data extraction processing on the point cloud data set based on the depth variance, obtains the target point cloud data, and performs data projection processing on the target point cloud data to determine the cutting area, thereby ensuring the accuracy of the identification of the cutting area, and further ensuring the accuracy of the identification of the coal and rock distribution in the cutting area, thereby improving the cutting efficiency of the tunnel boring machine.
[0074] In one embodiment provided in this application, as shown in FIG3 , a coal-rock identification method is proposed. The coal-rock identification method includes:
[0075] Step 302: Acquire a point cloud data set corresponding to the working area of the roadheader through an image acquisition device;
[0076] Step 304: determining a cutting area in the working area based on the point cloud data set;
[0077] Step 306: Obtain a coal-rock recognition model corresponding to the cut area, and divide the area image into multiple sub-images;
[0078] Step 308: Using the coal-rock recognition model, texture recognition is performed on the multiple sub-images to obtain multiple pieces of coal-rock texture information.
[0079] Step 310: determining first coal rock distribution information based on multiple coal rock texture information;
[0080] Step 312, while controlling the cutting part of the roadheader to perform cutting work, obtaining motor operation data corresponding to the cutting part through a data acquisition device;
[0081] Step 314: determining second coal and rock distribution information corresponding to the cutting area based on the motor operation data;
[0082] Step 316: Determine target coal and rock distribution information of the cutting area based on the first coal and rock distribution information and the second coal and rock distribution information.
[0083] In this embodiment, the coal and rock identification device creates a coal and rock identification model corresponding to the cut area, and divides the regional image into blocks to obtain multiple sub-images, wherein the coal and rock identification model is a data model that can identify the distribution of coal and rock, and the sub-image is a partial image in the regional image.
[0084] The coal rock identification device performs texture recognition processing on multiple sub-images through a coal rock identification model to determine multiple coal rock texture information, wherein the coal rock texture information is texture classification information of the coal rock in the sub-image.
[0085] For example, the coal-rock recognition device can collect images of the underground working face, extract the pixel area of the cutting surface, manually mark the labels of the coal and rock areas, and then train the coal-rock recognition model. The coal-rock recognition model can be specifically a U-net (a speech segmentation network) semantic segmentation model.
[0086] The coal rock identification device determines first coal rock distribution information of the cutting area based on multiple coal rock texture information, wherein the coal rock identification model is a data model that can identify the coal rock distribution situation.
[0087] For example, the coal-rock identification device may classify the texture of the cutting area according to the coal-rock texture information, determine the coal-rock distribution in the cutting area, and further determine the first coal-rock distribution information.
[0088] The coal and rock identification method in this embodiment creates a coal and rock identification model corresponding to the cutting area, and uses the coal and rock identification model to identify and process the regional image to determine the first coal and rock distribution information of the cutting area, thereby ensuring the accuracy of the first coal and rock distribution information, and then ensuring the accuracy of the target coal and rock distribution information, while ensuring the accuracy of the identification of the coal and rock distribution situation in the cutting area.
[0089] In one embodiment provided in this application, as shown in FIG4 , a coal-rock identification method is proposed. The coal-rock identification method includes:
[0090] Step 402: Acquire a point cloud data set corresponding to the working area of the roadheader through an image acquisition device;
[0091] Step 404: determining a cutting area in the working area based on the point cloud data set;
[0092] Step 406: performing image recognition on the regional image corresponding to the cutting area to obtain first coal and rock distribution information corresponding to the cutting area;
[0093] Step 408, while controlling the cutting part of the roadheader to perform cutting work, obtaining motor operation data corresponding to the cutting part through the data acquisition device;
[0094] Step 410 , determining a plurality of classification confidences corresponding to a plurality of sub-regions based on the motor operation data;
[0095] Step 412: determining second coal-rock distribution information based on the multiple classification confidences;
[0096] Step 414: Determine target coal and rock distribution information of the cutting area based on the first coal and rock distribution information and the second coal and rock distribution information.
[0097] In this embodiment, during the cutting process, the roadheader divides the cutting area into a plurality of sub-areas, wherein the sub-areas are cutting block areas obtained by dividing the cutting area.
[0098] For example, the roadheader may divide the cutting area into multiple sub-areas according to the cutting trajectory.
[0099] The coal-rock identification device operates on the motor operation data to obtain multiple classification confidences corresponding to multiple sub-regions, wherein the classification confidence is the confidence of the coal-rock classification in the sub-region.
[0100] For example, the motor operation data may include an average value of the motor current and an average value of the motor vibration amplitude (vibration acceleration amplitude) in the sub-region.
[0101] The coal and rock identification device determines the second coal and rock distribution information of the cutting area according to multiple classification confidences.
[0102] Exemplarily, the coal rock identification device can train a CNN (Convolutional Neural Networks) neural network to identify coal rock areas through current and vibration values. The input dimension of the neural network is m×n×2 (the first two dimensions m and n correspond to the number of rows and columns of the sub-area, and the third dimension 2 corresponds to the two features of current and vibration values), and the output is m×n×2 (the first two dimensions m and n correspond to the number of rows and columns of the sub-area, and the third dimension 2 corresponds to the classification confidence of the coal rock).
[0103] The coal and rock identification method in this embodiment operates on the motor operation data to obtain multiple classification confidences corresponding to multiple sub-areas, and then determines the second coal and rock distribution information of the cutting area based on the multiple classification confidences, thereby ensuring the accuracy of the second coal and rock distribution information, and then ensuring the accuracy of the target coal and rock distribution information, while ensuring the accuracy of the identification of the coal and rock distribution situation in the cutting area.
[0104] In one embodiment provided in this application, as shown in FIG5 , a coal-rock identification method is proposed. The coal-rock identification method includes:
[0105] Step 502: Using an image acquisition device, a target image set corresponding to the working area of the roadheader is acquired;
[0106] Step 504: performing image matching processing on the target image set to obtain a disparity map corresponding to the target image set;
[0107] Step 506, determining a point cloud data set according to the disparity map;
[0108] Step 508, determining a cutting area in the working area based on the point cloud data set;
[0109] Step 510: performing image recognition on a regional image corresponding to the cutting area to obtain first coal and rock distribution information corresponding to the cutting area;
[0110] Step 512, while controlling the cutting part of the roadheader to perform cutting work, obtain motor operation data corresponding to the cutting part through the data acquisition device;
[0111] Step 514: determining second coal and rock distribution information corresponding to the cutting area based on the motor operation data;
[0112] Step 516: Determine target coal and rock distribution information of the cutting area based on the first coal and rock distribution information and the second coal and rock distribution information.
[0113] In this embodiment, the coal and rock identification device uses the image acquisition device to acquire images of the working area of the roadheader to obtain a target image set, wherein the target image set is a data set of images corresponding to the working area.
[0114] Exemplarily, the target image set may specifically be an image set captured by multiple binocular cameras.
[0115] The coal and rock identification device performs data operations on the target image set through a matching algorithm to determine a disparity map corresponding to the target image set, wherein the disparity map is a two-dimensional image including pixel disparity values in the target image set.
[0116] Exemplarily, the coal rock identification device may calculate the disparity map by using an SGM (semi-global matching algorithm) algorithm.
[0117] The coal and rock identification device calculates a point cloud data set based on the disparity map.
[0118] For example, the calculation formula of the point cloud data set can be specifically as follows:
[0119] Among them, x, y, z are the coordinate data of the point cloud in the point cloud data set, l is the baseline distance, disp is the disparity value in the disparity map, and f x and f y is the pixel focal length in the disparity map, x p and y pis the pixel coordinate in the disparity map.
[0120] For example, the spatial coordinates of the point cloud in the point cloud data set can be specifically {x k ,y k ,z k}k=1,2,…,K, where k is the point cloud number and K is a constant.
[0121] The coal and rock identification method in this embodiment uses an image acquisition device to capture images of the working area of the tunnel boring machine to obtain a target image set, performs data operations on the target image set through a matching algorithm, determines the disparity map corresponding to the target image set, and then calculates the point cloud data set based on the disparity map, thereby ensuring the data accuracy of the point cloud data set and further ensuring the information accuracy of the first coal and rock distribution information.
[0122] In one embodiment provided in this application, as shown in FIG6 , a coal-rock identification method is proposed. The coal-rock identification method includes:
[0123] Step 602: Acquire a point cloud data set corresponding to the working area of the roadheader through an image acquisition device;
[0124] Step 604, determining a cutting area in the working area based on the point cloud data set;
[0125] Step 606: performing image recognition on the regional image corresponding to the cutting area to obtain first coal and rock distribution information corresponding to the cutting area;
[0126] Step 608 , while controlling the cutting part of the roadheader to perform cutting work, obtain multiple real-time motor data corresponding to the multiple sub-areas through the data acquisition device;
[0127] Step 610 , integrating multiple real-time motor data to obtain motor operation data;
[0128] Step 612: Determine second coal and rock distribution information corresponding to the cutting area based on the motor operation data;
[0129] Step 614: Determine target coal and rock distribution information of the cutting area based on the first coal and rock distribution information and the second coal and rock distribution information.
[0130] In this embodiment, during the cutting process, the roadheader divides the cutting area into a plurality of sub-areas, wherein the sub-areas are cutting block areas obtained by dividing the cutting area.
[0131] For example, the roadheader may divide the cutting area into multiple sub-areas according to the cutting trajectory.
[0132] The coal and rock identification device obtains multiple real-time motor data corresponding to multiple sub-areas through the data acquisition device, wherein the real-time motor data is the real-time operation data of the cutting part motor.
[0133] For example, the real-time motor data may include an average value of the motor current and an average value of the motor vibration amplitude (vibration acceleration amplitude).
[0134] The coal and rock identification device integrates multiple real-time motor data to obtain motor operation data.
[0135] Exemplarily, the coal rock identification device combines multiple real-time motor data into motor operation data.
[0136] The coal rock identification method in this embodiment obtains multiple real-time motor data corresponding to multiple sub-areas through a data acquisition device, and integrates the multiple real-time motor data to obtain motor operation data, thereby ensuring the data integrity of the motor operation data and the data accuracy of the motor operation data, thereby ensuring the information accuracy of the second coal rock distribution information.
[0137] In one embodiment provided in this application, as shown in FIG7 , a coal-rock identification method is proposed. The coal-rock identification method includes:
[0138] Step 702: Acquire a point cloud data set corresponding to the working area of the roadheader through an image acquisition device;
[0139] Step 704: determining a cutting area in the working area based on the point cloud data set;
[0140] Step 706: performing image recognition on the regional image corresponding to the cutting area to obtain first coal and rock distribution information corresponding to the cutting area;
[0141] Step 708: While controlling the cutting part of the roadheader to perform cutting work, obtain motor operation data corresponding to the cutting part through the data acquisition device;
[0142] Step 710: Determine second coal and rock distribution information corresponding to the cutting area based on the motor operation data;
[0143] Step 712: Perform data fusion processing on the first coal-rock distribution information and the second coal-rock distribution information to obtain target coal-rock distribution information.
[0144] In this embodiment, the coal rock identification device fuses the first coal rock distribution information and the second coal rock distribution information to determine the target coal rock distribution information of the cutting area.
[0145] Exemplarily, the coal rock identification device may perform data matching on the first coal rock distribution information and the second coal rock distribution information to obtain target coal rock distribution information.
[0146] The coal and rock identification method in this embodiment integrates the first coal and rock distribution information and the second coal and rock distribution information to determine the target coal and rock distribution information of the cutting area, thereby ensuring the information integrity and accuracy of the target coal and rock distribution information, and thereby improving the cutting efficiency of the roadheader.
[0147] In one embodiment provided in the present application, as shown in FIG8 , a coal-rock identification device 800 is proposed for use in a roadheader. The roadheader is provided with an image acquisition device and a data acquisition device. The coal-rock identification device 800 includes:
[0148] An acquisition module 802 is configured to acquire a point cloud data set corresponding to a working area of the roadheader through an image acquisition device;
[0149] The processing module 804 is used to determine a cutting area in the working area based on the point cloud data set;
[0150] The processing module 804 is further configured to perform image recognition on the regional image corresponding to the cutting area to obtain first coal and rock distribution information corresponding to the cutting area;
[0151] The acquisition module 802 is further used to acquire motor operation data corresponding to the cutting part through the data acquisition device during the process of controlling the cutting part of the roadheader to perform cutting work;
[0152] The processing module 804 is further configured to determine second coal and rock distribution information corresponding to the cutting area based on the motor operation data;
[0153] The processing module 804 is further configured to determine target coal and rock distribution information of the cutting area according to the first coal and rock distribution information and the second coal and rock distribution information.
[0154] In this embodiment, a coal and rock identification device 800 is provided, which is applied to a roadheader. The roadheader is a machine used to excavate tunnels on flat ground. An image acquisition device and a data acquisition device are provided on the roadheader, wherein the image acquisition device is used to acquire image data of the working area of the roadheader, and the data acquisition device is used to acquire motor data of the cutting part of the roadheader.
[0155] It should be noted that coal rock is a mixture of coal and rock. Coal rock identification is to identify the distribution of coal and rock on the cutting surface. The working area is the area where the tunnel boring machine performs cutting, and the cutting part is the component on the tunnel boring machine that performs cutting work.
[0156] Exemplarily, the image acquisition device may include multiple binocular cameras.
[0157] For example, the data acquisition device may acquire current data or vibration data of the cutting part motor.
[0158] For example, the working area may be specifically an underground coal mining tunnel.
[0159] For example, the tunnel boring machine may be specifically an automatic tunnel boring machine that can perform automatic cutting work.
[0160] Exemplarily, the cutting part may be a drum-type cutting part.
[0161] The acquisition module 802 acquires a point cloud data set of the working area of the roadheader through an image acquisition device, wherein the point cloud data set is a point cloud data set corresponding to the working area of the roadheader.
[0162] The processing module 804 performs data processing on the point cloud data set, and extracts a cutting area in the working area, wherein the cutting area is a cutting surface where the roadheader performs cutting work.
[0163] Exemplarily, the cutting area may be specifically a rectangular cutting surface.
[0164] The processing module 804 captures the regional image corresponding to the cutting area through the image acquisition device, and performs image recognition on the regional image to determine the first coal-rock distribution information corresponding to the cutting area, wherein the regional image is the image corresponding to the cutting area, and the first coal-rock distribution information is the coal-rock distribution information obtained through image recognition.
[0165] Exemplarily, the first coal-rock distribution information may specifically be the coal-rock distribution information obtained after the regional image is identified through a deep learning model.
[0166] In the process of controlling the cutting part of the roadheader to perform cutting work, the acquisition module 802 collects the motor operation data corresponding to the cutting part through the data acquisition device, wherein the motor operation data is the operation data of the motor corresponding to the cutting part.
[0167] Exemplarily, the motor operation data may specifically include current data and vibration data of the motor.
[0168] The processing module 804 performs data recognition on the motor operation data to obtain second coal-rock distribution information corresponding to the cutting area, wherein the second coal-rock distribution information is coal-rock distribution information determined according to the motor operation data.
[0169] For example, the second coal-rock distribution information may specifically be coal-rock distribution information obtained by identifying motor operation data through a neural network.
[0170] The processing module 804 performs data fusion on the first coal-rock distribution information and the second coal-rock distribution information to obtain target coal-rock distribution information of the cutting area, wherein the target coal-rock distribution information is coal-rock distribution information determined based on the first coal-rock distribution information and the second coal-rock distribution information.
[0171] For example, the target coal-rock distribution information may be specifically coal-rock distribution information obtained by performing data matching on the first coal-rock distribution information and the second coal-rock distribution information.
[0172] The coal and rock identification device 800 in this embodiment collects a point cloud data set of the working area of the tunnel boring machine through an image acquisition device, performs data processing on the point cloud data set, extracts a cutting area in the working area, and performs image recognition on the regional image to determine the first coal and rock distribution information corresponding to the cutting area, and then collects the motor operation data corresponding to the cutting part through a data acquisition device, performs data recognition on the motor operation data to obtain the second coal and rock distribution information corresponding to the cutting area, and then determines the target coal and rock distribution information of the cutting area based on the first coal and rock distribution information and the second coal and rock distribution information, thereby ensuring the accuracy of the recognition of the coal and rock distribution in the cutting area, thereby improving the cutting efficiency of the tunnel boring machine, and avoiding fatigue damage to the cutting part of the tunnel boring machine.
[0173] In one embodiment provided in this application, the coal rock identification device 800 further includes:
[0174] The processing module 804 is further configured to perform data operations on the point cloud data set to obtain a depth variance corresponding to the point cloud data set;
[0175] The processing module 804 is further configured to extract target point cloud data from the point cloud data set based on the depth variance;
[0176] The processing module 804 is further configured to perform data projection processing on the target point cloud data to obtain a segmentation area.
[0177] The coal and rock identification device 800 in this embodiment performs data calculation on the point cloud data set, determines the depth variance corresponding to the point cloud data set, performs data extraction processing on the point cloud data set based on the depth variance, obtains the target point cloud data, and performs data projection processing on the target point cloud data, thereby determining the cutting area, ensuring the accuracy of the identification of the cutting area, and further ensuring the accuracy of the identification of the coal and rock distribution in the cutting area, thereby improving the cutting efficiency of the tunnel boring machine.
[0178] In one embodiment provided in this application, the coal rock identification device 800 further includes:
[0179] The processing module 804 is further used to obtain a coal-rock identification model corresponding to the cutting area and divide the area image into multiple sub-images;
[0180] The processing module 804 is further configured to perform texture recognition on the plurality of sub-images using a coal-rock recognition model to obtain a plurality of coal-rock texture information;
[0181] The processing module 804 is further configured to determine first coal rock distribution information based on the plurality of coal rock texture information.
[0182] The coal and rock identification device 800 in this embodiment creates a coal and rock identification model corresponding to the cutting area, and uses the coal and rock identification model to identify and process the regional image to determine the first coal and rock distribution information of the cutting area, thereby ensuring the accuracy of the first coal and rock distribution information, and then ensuring the accuracy of the target coal and rock distribution information, while ensuring the accuracy of the identification of the coal and rock distribution situation in the cutting area.
[0183] In one embodiment provided in this application, the coal rock identification device 800 further includes:
[0184] The processing module 804 is further configured to determine a plurality of classification confidences corresponding to the plurality of sub-regions based on the motor operation data;
[0185] The processing module 804 is further configured to determine the second coal rock distribution information according to multiple classification confidences.
[0186] The coal rock identification device 800 in this embodiment calculates the motor operation data to obtain multiple classification confidences corresponding to multiple sub-areas, and then determines the second coal rock distribution information of the cutting area based on the multiple classification confidences, thereby ensuring the accuracy of the second coal rock distribution information, and then ensuring the accuracy of the target coal rock distribution information, while ensuring the accuracy of the identification of the coal rock distribution situation in the cutting area.
[0187] In one embodiment provided in this application, the coal rock identification device 800 further includes:
[0188] The acquisition module 802 is further configured to acquire a target image set corresponding to the working area of the roadheader through an image acquisition device;
[0189] The acquisition module 802 is further configured to perform image matching processing on the target image set to obtain a disparity map corresponding to the target image set;
[0190] The acquisition module 802 is further configured to determine a point cloud data set according to the disparity map.
[0191] The coal and rock identification device 800 in this embodiment uses an image acquisition device to acquire images of the working area of the tunnel boring machine to obtain a target image set, performs data operations on the target image set through a matching algorithm, determines the disparity map corresponding to the target image set, and then calculates the point cloud data set based on the disparity map, thereby ensuring the data accuracy of the point cloud data set and further ensuring the information accuracy of the first coal and rock distribution information.
[0192] In one embodiment provided in this application, the coal rock identification device 800 further includes:
[0193] The acquisition module 802 is further configured to acquire a plurality of real-time motor data corresponding to the plurality of sub-regions through a data acquisition device, wherein the real-time motor data is the motor data when the cutting part performs cutting work in the sub-regions;
[0194] The acquisition module 802 is further configured to integrate multiple real-time motor data to obtain motor operation data.
[0195] The coal rock identification device 800 in this embodiment obtains multiple real-time motor data corresponding to multiple sub-areas through a data acquisition device, and integrates the multiple real-time motor data to obtain motor operation data, thereby ensuring the data integrity of the motor operation data and the data accuracy of the motor operation data, thereby ensuring the information accuracy of the second coal rock distribution information.
[0196] In one embodiment provided in this application, the coal rock identification device 800 further includes:
[0197] The processing module 804 is further configured to perform data fusion processing on the first coal-rock distribution information and the second coal-rock distribution information to obtain target coal-rock distribution information.
[0198] Exemplarily, as shown in FIG9 , a target image set is collected by an image acquisition device, and the image acquisition device may specifically be a binocular camera in FIG9 .
[0199] The point cloud data set is determined according to the target image set, and then the first coal rock distribution information is determined. As shown in Figure 9, the point cloud can be reconstructed, the depth variance in the point cloud field can be calculated, the cutting area can be quickly located according to the depth variance, the cutting area in the image can be extracted, and speech segmentation can be performed through the U-net neural network to achieve one-time recognition of the coal rock area.
[0200] The tunnel boring machine automatically cuts according to the preset trajectory and collects motor operation data. As shown in Figure 9, the motor current and vibration data at each point can be recorded.
[0201] The processing module 804 performs data recognition on the motor operation data to obtain the second coal rock distribution information. As shown in Figure 9, the cutting surface can be divided into multiple block areas according to the cutting trajectory. The average current and average vibration amplitude of each block area during the cutting process are stored in each block area. Then, the CNN neural network is used to realize the precise recognition of coal rocks, and the confidence of the coal rocks in each block area is output to realize the secondary recognition of the coal rock area.
[0202] The processing module 804 determines the target coal-rock distribution information based on the first coal-rock distribution information and the second coal-rock distribution information. As shown in FIG9 , the first recognition result and the second recognition result can be combined to obtain the final coal-rock area recognition result.
[0203] The coal and rock identification device 800 in this embodiment integrates the first coal and rock distribution information and the second coal and rock distribution information to determine the target coal and rock distribution information of the cutting area, thereby ensuring the information integrity and accuracy of the target coal and rock distribution information, and thereby improving the cutting efficiency of the tunnel boring machine.
[0204] In one embodiment provided herein, as shown in FIG10 , another coal rock identification device 1000 is provided. The coal rock identification device 1000 includes a processor 1002 and a memory 1004. The memory 1004 stores a program or instruction that, when executed by the processor 1002, implements the steps of the coal rock identification method described in any of the aforementioned technical solutions. Therefore, the coal rock identification device 1000 possesses all the beneficial effects of the coal rock identification method described in any of the aforementioned technical solutions, and will not be further elaborated upon here.
[0205] In one embodiment provided in the present application, a readable storage medium is provided. A person skilled in the art can understand that all or part of the steps in the method of the above embodiment can be implemented by instructing the relevant hardware to complete through a program. The program can be stored in a readable storage medium of any computer. When the program is executed, it implements the coal rock identification method in any of the above embodiments, the readable storage medium, such as read-only memory (ROM), random access memory (RAM), a disk or an optical disk, etc.
[0206] In one embodiment provided in the present application, a tunnel boring machine is proposed, comprising: a coal and rock identification device as in any of the above embodiments, and / or a readable storage medium as in any of the above embodiments, and thus having all the beneficial technical effects of the coal and rock identification device as in any of the above embodiments, and / or the readable storage medium as in any of the above embodiments, which will not be elaborated upon here.
[0207] It should be clarified that in the claims, specification and drawings of this application, the term "plurality" refers to two or more. Unless otherwise clearly defined, the orientation or positional relationship indicated by the terms "upper" and "lower" is based on the orientation or positional relationship shown in the drawings. It is only for the purpose of more conveniently describing this application and making the description process simpler, and is not intended to indicate or imply that the device or element referred to must have the specific orientation described, be constructed and operated in a specific orientation. Therefore, these descriptions cannot be understood as limitations on this application. The terms "connect", "install", "fix" and the like should be understood in a broad sense. For example, "connection" can be a fixed connection between multiple objects, or a detachable connection between multiple objects, or an integral connection; it can be a direct connection between multiple objects, or an indirect connection between multiple objects through an intermediate medium. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood based on the specific circumstances of the above data.
[0208] In the claims, specification, and drawings of this application, the terms "one embodiment," "some embodiments," "a specific embodiment," and the like 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 this application. In the claims, specification, and drawings of this application, schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
[0209] 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. A method for identifying coal and rock, wherein: For a tunneling machine, the tunneling machine is provided with an image acquisition device and a data acquisition device, and the coal-rock identification method comprises: Acquire a point cloud data set corresponding to the working area of the roadheader through the image acquisition device; Determining a cutting area in the working area according to the point cloud data set; Performing image recognition on a regional image corresponding to the cutting area to obtain first coal-rock distribution information corresponding to the cutting area; In the process of controlling the cutting part of the tunnel boring machine to perform cutting work, the motor operation data corresponding to the cutting part is obtained through the data acquisition device; Determining second coal-rock distribution information corresponding to the cutting area according to the motor operation data; The target coal-rock distribution information of the cutting area is determined according to the first coal-rock distribution information and the second coal-rock distribution information.
2. The coal-rock identification method according to claim 1, wherein: Determining the cutting area in the working area according to the point cloud data set specifically includes: Performing data calculation on the point cloud data set to obtain a depth variance corresponding to the point cloud data set; Extracting target point cloud data from the point cloud data set according to the depth variance; The target point cloud data is subjected to data projection processing to obtain the cutting area.
3. The coal-rock identification method according to claim 1, wherein: The performing image recognition on the regional image corresponding to the cutting area to obtain the first coal-rock distribution information corresponding to the cutting area specifically includes: Obtaining a coal-rock recognition model corresponding to the cutting area, and dividing the area image into a plurality of sub-images; Using the coal-rock recognition model, texture recognition is performed on the multiple sub-images to obtain multiple coal-rock texture information; The first coal rock distribution information is determined based on the multiple coal rock texture information.
4. The coal-rock identification method according to claim 1, wherein: The cutting area includes a plurality of sub-areas, and determining the second coal-rock distribution information corresponding to the cutting area according to the motor operation data specifically includes: Determining, according to the motor operation data, a plurality of classification confidences corresponding to the plurality of sub-regions; The second coal rock distribution information is determined based on the multiple classification confidences.
5. The coal-rock identification method according to any one of claims 1 to 4, wherein: The coal-rock identification method further includes: By means of the image acquisition device, a target image set corresponding to the working area of the roadheader is acquired; Performing image matching processing on the target image set to obtain a disparity map corresponding to the target image set; The point cloud data set is determined according to the disparity map.
6. The coal-rock identification method according to any one of claims 1 to 4, wherein: The cutting area includes a plurality of sub-areas, and the coal-rock identification method further includes: Acquire a plurality of real-time motor data corresponding to the plurality of sub-areas through the data acquisition device, wherein the real-time motor data is the motor data when the cutting part performs cutting work in the sub-areas; The multiple real-time motor data are integrated to obtain the motor operation data.
7. The coal-rock identification method according to any one of claims 1 to 4, wherein: The determining the target coal-rock distribution information of the cutting area according to the first coal-rock distribution information and the second coal-rock distribution information specifically includes: Data fusion processing is performed on the first coal-rock distribution information and the second coal-rock distribution information to obtain the target coal-rock distribution information.
8. A coal-rock identification device, wherein: The coal-rock identification device can implement the steps of the coal-rock identification method according to any one of claims 1 to 7, and is used for a roadheader, wherein the roadheader is provided with an image acquisition device and a data acquisition device, and the coal-rock identification device comprises: An acquisition module, used to acquire a point cloud data set corresponding to the working area of the tunnel boring machine through the image acquisition device; A processing module, configured to determine a cutting area in the working area according to the point cloud data set; The processing module is further used to perform image recognition on the regional image corresponding to the cutting area to obtain the first coal-rock distribution information corresponding to the cutting area; The acquisition module is further used to acquire the motor operation data corresponding to the cutting part through the data acquisition device during the process of controlling the cutting part of the roadheader to perform cutting work; The processing module is further used to determine the second coal-rock distribution information corresponding to the cutting area according to the motor operation data; The processing module is further used to determine target coal-rock distribution information of the cutting area according to the first coal-rock distribution information and the second coal-rock distribution information.
9. A coal-rock identification device, wherein: include: processor; A memory, wherein a program or instruction is stored in the memory, and the processor implements the steps of the coal rock identification method as described in any one of claims 1 to 7 when executing the program or instruction in the memory.
10. A readable storage medium, wherein: The readable storage medium stores programs or instructions, and when the programs or instructions are executed by the processor, the steps of the coal-rock identification method according to any one of claims 1 to 7 are implemented.
11. A tunnel boring machine, wherein: include: The coal-rock identification device according to claim 8 or 9; and / or The readable storage medium as claimed in claim 10.
Citation Information
Patent Citations
Tactile-based coal rock recognition method
CN110847907A
Coal rock intelligent recognition system based on deep learning
CN113406296A
Coal face coal rock recognition method based on laser scanning
CN113486817A
Coal rock identification method based on acoustoelectric signal fusion
CN113569664A
Method and device for recognizing and controlling working face of heading machine based on binocular vision
CN114893198A
Cited By
Coal rock cutting state detection method
CN119961699A
Method and device for evaluating cutting effect of lower roller of coal mining machine based on image
CN121437503A
