Method, device, equipment, medium and product for collecting point cloud data of fully mechanized coal mining face

Abstract

The invention relates to the technical field of point cloud data collection, in particular to a fully mechanized coal mining face point cloud data collection method, device, equipment, medium and product, and the method comprises the steps: obtaining a collection deployment scheme corresponding to collection task information based on the collection task information of a fully mechanized coal mining face of a target mine; according to a pre-trained acquisition parameter optimization model, optimizing parameter configuration information of the point cloud data acquisition device included in the acquisition deployment scheme; and acquiring point cloud data of the fully mechanized coal mining face of the target mine based on the optimized acquisition and deployment scheme. Through the pre-trained acquisition parameter optimization model, the parameter configuration information of the point cloud data acquisition equipment included in the acquisition deployment scheme is optimized, so that the performance of the point cloud data acquisition equipment can be improved, the accuracy of the acquired point cloud data is further improved, the real condition of the fully mechanized coal mining face of the underground coal mine can be reflected, and the accuracy of point cloud data acquisition is improved. And the operation safety and the production efficiency of the fully-mechanized coal mining face are guaranteed.

Description

Technical Field

[0001] The present disclosure relates to the technical field of point cloud data acquisition, and in particular to a method, device, equipment, medium and product for acquiring point cloud data of a fully mechanized mining working face. Background Art

[0002] A fully mechanized mining face is an underground coal mine area where a full suite of mechanized equipment is used to complete production processes such as coal breaking, loading, transporting, supporting, and goaf treatment. With the rapid development of the coal mining industry and the increasing automation of fully mechanized mining faces, real-time monitoring of equipment status and environmental information is required to ensure safety and improve efficiency.

[0003] Point cloud data, as a highly efficient and accurate three-dimensional information tool, is widely used in monitoring fully mechanized mining faces in underground coal mines. However, existing point cloud data acquisition technologies suffer from low accuracy, making it difficult to accurately reflect the true conditions of fully mechanized mining faces in underground coal mines. This hinders operational safety and production efficiency. Summary of the Invention

[0004] The present disclosure is proposed in view of the above problems, and provides a method, device, equipment, medium and product for collecting point cloud data of a fully mechanized mining working face.

[0005] According to one aspect of the present disclosure, a method for collecting point cloud data of a fully mechanized mining face is provided, comprising:

[0006] Based on the collection task information of the fully mechanized mining face of the target mine, obtaining a collection deployment plan corresponding to the collection task information;

[0007] Optimizing parameter configuration information of the point cloud data acquisition equipment included in the acquisition deployment plan according to a pre-trained acquisition parameter optimization model;

[0008] Based on the optimized acquisition deployment plan, point cloud data of the fully mechanized mining face of the target mine is obtained.

[0009] In addition, according to an aspect of the present disclosure, a method for collecting point cloud data of a fully-mechanized mining face is provided, wherein the point cloud data of the fully-mechanized mining face of the target mine is obtained based on the optimized collection deployment scheme, including:

[0010] Based on the optimized acquisition deployment plan, confirm the number of devices, device locations, device acquisition angles, and parameter configuration information of the point cloud data acquisition devices deployed on the fully mechanized mining working face;

[0011] Based on the deployed point cloud data acquisition equipment, point cloud data of the fully mechanized mining face of the target mine is obtained.

[0012] In addition, according to one aspect of the present disclosure, the method for collecting point cloud data of a fully mechanized mining face, after obtaining point cloud data of the fully mechanized mining face of the target mine based on the optimized collection deployment scheme, further includes:

[0013] Extracting global point cloud data features of the point cloud data using a pre-trained point cloud data processing model;

[0014] Segmenting the global point cloud data features to obtain real-time point cloud areas of each entity in the fully mechanized mining working face;

[0015] Based on the real-time point cloud area, point cloud data of a complete coal wall entity in the entity is obtained.

[0016] In addition, according to the point cloud data acquisition method of a fully-mechanized mining working face according to one aspect of the present disclosure, point cloud data of a complete coal wall entity in the entity is obtained based on the real-time point cloud area, including:

[0017] Extract local point cloud data features of the real-time point cloud area of ​​each entity;

[0018] Performing entity recognition on the local point cloud data features of each entity to obtain an entity recognition result;

[0019] Based on the entity recognition result, a real-time point cloud area of ​​a local coal wall entity in the fully mechanized mining working face is obtained;

[0020] Based on the real-time point cloud area of ​​the local coal wall entity, point cloud data of the complete coal wall entity in the entity is obtained.

[0021] In addition, according to an aspect of the present disclosure, a method for collecting point cloud data of a fully-mechanized mining face is provided, which comprises: obtaining a collection deployment plan corresponding to the collection task information based on the collection task information of the fully-mechanized mining face of the target mine; and

[0022] The acquisition task information of the fully mechanized mining face of the target mine is input into a pre-trained scheme prediction model to obtain the acquisition deployment scheme corresponding to the acquisition task information. The scheme prediction model is trained based on the historical acquisition task information and historical acquisition deployment schemes of the fully mechanized mining face.

[0023] In addition, the point cloud data acquisition method for a comprehensive mining working face according to one aspect of the present disclosure also includes: the parameter configuration information includes the scanning frequency, resolution, scanning angle, laser pulse duration, laser power and sampling interval of the point cloud data acquisition device.

[0024] According to another aspect of the present disclosure, a point cloud data acquisition device for a fully mechanized mining face is provided, comprising:

[0025] A scheme acquisition module is used to obtain a collection deployment scheme corresponding to the collection task information based on the collection task information of the fully mechanized mining working face of the target mine;

[0026] An optimization module, configured to optimize parameter configuration information of the point cloud data acquisition device included in the acquisition deployment plan based on a pre-trained acquisition parameter optimization model;

[0027] A data acquisition module is used to acquire point cloud data of the fully mechanized mining face of the target mine based on the optimized acquisition deployment plan.

[0028] According to another aspect of the present disclosure, a computer device is provided, including a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the method of the above aspect.

[0029] According to another aspect of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the method of the above aspect is implemented.

[0030] According to another aspect of the present disclosure, a computer program product is provided, including a computer program, which implements the method of the above aspect when executed by a processor.

[0031] As will be described in detail below, according to a method, device, equipment, medium and product for collecting point cloud data of a comprehensive mining working face in an embodiment of the present disclosure, the parameter configuration information of the point cloud data collection equipment included in the collection deployment plan is optimized through a pre-trained collection parameter optimization model, which can improve the performance of the point cloud data collection equipment and thus improve the accuracy of the collected point cloud data, which is conducive to reflecting the actual situation of the comprehensive mining working face underground in a coal mine and ensuring the operation safety and production efficiency of the comprehensive mining working face.

[0032] It is to be understood that both the foregoing general description and the following detailed description are exemplary, and are intended to provide further explanation of the technology as claimed. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] The above and other purposes, features, and advantages of the present disclosure will become more apparent through a more detailed description of the embodiments of the present disclosure in conjunction with the accompanying drawings. The accompanying drawings are intended to provide a further understanding of the embodiments of the present disclosure and constitute a part of the specification. Together with the embodiments of the present disclosure, they are used to explain the present disclosure and are not intended to limit the present disclosure. In the drawings, the same reference numerals generally represent the same components or steps.

[0034] Figure 1 It is a flowchart illustrating the application of the method for collecting point cloud data of a fully mechanized mining working face according to an embodiment of the present disclosure.

[0035] Figure 2 It is another flow chart illustrating the application of the method for collecting point cloud data of a fully mechanized mining face according to an embodiment of the present disclosure.

[0036] Figure 3 It is a structural diagram illustrating the application of a comprehensive mining working face point cloud data acquisition system according to an embodiment of the present disclosure.

[0037] Figure 4 It is a structural diagram illustrating a point cloud data acquisition device for a fully mechanized mining working face according to an embodiment of the present disclosure.

[0038] Figure 5 FIG2 is a schematic diagram illustrating the structure of a computer device according to an embodiment of the present disclosure.

[0039] Figure 6 is a schematic diagram illustrating a computer program product according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0040] In order to make the purpose, technical solutions and advantages of the present disclosure more apparent, the following will describe in detail exemplary embodiments of the present disclosure with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present disclosure, rather than all the embodiments of the present disclosure, and it should be understood that the present disclosure is not limited to the exemplary embodiments described herein.

[0041] A fully mechanized coal mining face (full name: comprehensive mechanized coal mining face) refers to an underground coal mine operating area where a full set of mechanized equipment is used to complete production processes such as coal breaking, loading, transporting, supporting, and goaf treatment. With the rapid development of my country's coal mining industry and the increasing automation level of fully mechanized coal mining faces, real-time monitoring of equipment status and environmental information is required to ensure production safety and improve production efficiency during fully mechanized coal mining face operations.

[0042] Point cloud data, as a highly efficient and accurate three-dimensional information source, is widely used in monitoring fully mechanized mining faces in underground coal mines. However, existing technologies for collecting point cloud data for fully mechanized mining faces present the following challenges: The resulting point cloud data is inaccurate, failing to accurately reflect the true conditions within the face, hindering operational safety and productivity. Deploying and implementing point cloud data collection solutions requires manual analysis and setup, resulting in significant labor costs. The point cloud data collection speed is slow, failing to meet the high-speed requirements of real-time monitoring. Furthermore, due to the harsh environment of underground coal mines, the stability and reliability of point cloud data transmission needs to be improved.

[0043] Above, with reference to the accompanying drawings, a method, device, equipment, medium and product for collecting point cloud data of a comprehensive mining working face according to an embodiment of the present disclosure are described. Through a pre-trained collection parameter optimization model, the parameter configuration information of the point cloud data collection equipment included in the collection deployment plan is optimized, which can improve the performance of the point cloud data collection equipment, and thus improve the accuracy of the collected point cloud data, which is conducive to reflecting the actual situation of the comprehensive mining working face underground in a coal mine, but is not conducive to ensuring the operational safety and production efficiency of the comprehensive mining working face.

[0044] By generating a collection deployment plan corresponding to the collection task information through a pre-trained plan prediction model, human cost investment is reduced and it is beneficial to improve data collection efficiency.

[0045] By using a pre-trained point cloud data processing model to process the point cloud data of the fully mechanized mining working face, the coal wall morphology of the target mine can be accurately and completely presented, making it convenient for coal mine technicians and managers to quickly understand the situation of the fully mechanized mining working face in the coal mine in real time, and providing reliable data support for production command and dispatch and emergency plans.

[0046] The point cloud data of the fully mechanized mining working face is processed in a unified and real-time manner through the cloud data center, which strengthens the data interaction of the collected point cloud data of the fully mechanized mining working face and avoids the situation of information islands.

[0047] The point cloud data transmission network enables wireless transmission of point cloud data from fully mechanized mining faces, reducing hardware costs while increasing data acquisition speed. This makes it suitable for large-scale, wide-area data collection. The point cloud data transmission network, which utilizes serial communication, not only expands the range of wireless data transmission, but also improves data transmission reliability and stability, preventing data loss.

[0048] To facilitate understanding of this embodiment, a method for collecting point cloud data of a fully mechanized mining face disclosed in an embodiment of the present disclosure is first introduced in detail. The execution subject of the method for collecting point cloud data of a fully mechanized mining face provided in an embodiment of the present disclosure is generally a computer device with certain computing capabilities, such as a terminal device or a server or other processing device. The terminal device may be a user equipment (UE), a mobile device, a user terminal, a terminal, a cellular phone, a cordless phone, a personal digital assistant (PDA), a handheld device, a computing device, a vehicle-mounted device, a wearable device, etc. In some possible implementations, the method for collecting point cloud data of a fully mechanized mining face may be implemented by a processor calling computer-readable instructions stored in a memory.

[0049] like Figure 1 FIG. 1 is a flow chart of a method for collecting point cloud data of a fully mechanized mining face provided by an embodiment of the present disclosure, wherein the method includes S101 to S103:

[0050] S101: Based on the collection task information of the fully mechanized mining face of the target mine, a collection deployment plan corresponding to the collection task information is obtained.

[0051] Among them, the collection task information includes real-time scale information of the fully mechanized mining face, monitoring demand information, and working environment information underground in the coal mine; the collection deployment plan includes the real-time number of devices, setting location, collection angle, and parameter configuration information of each point cloud data collection device.

[0052] Optionally, in this embodiment, the collection deployment plan can be generated by a pre-trained plan prediction model. Specifically, the collection task information of the comprehensive mining working face of the target mine is input into the pre-trained plan prediction model to obtain the collection deployment plan corresponding to the collection task information.

[0053] Regarding the scenario prediction model, specifically, based on the historical data collection tasks and historical data collection deployment plans of several fully mechanized mining faces, a deep learning algorithm is used to build and train the scenario prediction model. Refer to steps 1.1 to 1.7 below:

[0054] Step 1.1: Preprocess several historical collection task information and historical collection deployment plans of the fully mechanized mining face. The preprocessing includes operations such as denoising and filtering to improve data quality.

[0055] Step 1.2: According to the pre-processed historical collection deployment plan, set the real collection deployment plan label for the corresponding pre-processed historical collection task information to obtain the corresponding collection deployment plan prediction sample;

[0056] Step 1.3: Divide the several collected deployment plan prediction samples into the first model training sample set and the first model test sample set in a ratio of 7:3;

[0057] Step 1.4: Use a deep learning algorithm, such as the Bi-directional Long Short-Term Memory (BiLSTM) algorithm, to build an initial solution prediction model. Input the first model training sample set for optimization training to obtain an optimized solution prediction model.

[0058] Step 1.5: Input the first model test sample set to perform model testing on the optimized solution prediction model to obtain corresponding prediction labels for several acquisition and deployment solutions;

[0059] Step 1.6: Compare and count the predicted labels of several collection and deployment plans with the corresponding real labels of the collection and deployment plans to obtain the corresponding first model prediction accuracy;

[0060] Step 1.7: If the prediction accuracy of the first model is greater than the preset accuracy threshold, the optimal solution prediction model is output; otherwise, training optimization is continued until the optimal solution prediction model is obtained.

[0061] S102: Optimizing parameter configuration information of the point cloud data acquisition equipment included in the acquisition deployment plan according to a pre-trained acquisition parameter optimization model.

[0062] The parameter configuration information includes the scanning frequency, resolution, scanning angle, laser pulse duration, laser power and sampling interval of the point cloud data acquisition device.

[0063] Specifically, S102 includes the following steps:

[0064] S102.1: Use the acquisition parameter optimization model to encode the parameter configuration information in the acquisition deployment plan into IFWA individuals in the IFWA population;

[0065] S102.2: Use the Circle chaotic map sequence to initialize the IFWA population and obtain the initialized IFWA population. The formula is:

[0066]

[0067] Among them, q r is the initial IFWA individual of the Circle chaos map, is the randomly generated initial IFWA individual.

[0068] S102.3: Iteratively update the initialized IFWA population according to the preset algorithm parameters of the IFWA optimization algorithm to obtain an updated IFWA population;

[0069] The formula for the explosion radius and number of sparks of IFWA individuals in the updated IFWA population is:

[0070]

[0071] Among them, S r For updated IFWA individual q r The number of sparks, M ′ is a constant, f max is the maximum fitness value in the updated IFWA population, f(q r ) is the IFWA individual q before updating r The fitness value of , τ is an infinitesimal constant.

[0072]

[0073] Among them, R r For updated IFWA individual q r The explosion radius, is the explosion radius adjustment constant, f min is the minimum fitness value in the updated IFWA population.

[0074] q′ r =q r +S r ×rand(-1,1)

[0075] Among them, q′ r is the updated IFWA individual, rand(-1,1) is a random number between -1 and 1, q r is the initial IFWA individual of the Circle chaos map.

[0076] S102.4: Use the Gaussian mutation algorithm to perform Gaussian mutation on the initialized IFWA population to generate a Gaussian mutated IFWA population. The formula is:

[0077] q″ r =q r +S r ×G(1,1)

[0078] Among them, q r is a Gaussian variant IFWA individual, and G(1,1) is a random number with a Gaussian distribution and a mean and variance of 1.

[0079] S102.5: Use the dynamic reverse learning algorithm to perform dynamic reverse learning on the initialized IFWA population to generate a dynamic reverse IFWA population. The formula is:

[0080] q″′ r =γ(L max +L min )-q r

[0081] Among them, q″′ r is the dynamic reverse IFWA individual, γ is the decreasing inertia coefficient, γ=0.9-0.5d / T, d is the current iteration number, T is the maximum iteration number, L max is the maximum value of the vector space, L min is the minimum value in the vector space.

[0082] S102.6: Use the fitness function to calculate the fitness values ​​of all IFWA individuals in the updated IFWA population, the Gaussian-mutated IFWA population, and the dynamically reversed IFWA population, and take the IFWA individual with the smallest fitness value as the optimal individual;

[0083] S102.7: If the number of iterations reaches the threshold or the fitness value of the optimal individual meets the requirements, the optimal solution corresponding to the current optimal individual is output to obtain the optimized parameter configuration information.

[0084] Optionally, refer to steps 2.1 to 2.8 below for the construction and training of the acquisition parameter optimization model:

[0085] Step 2.1: Preprocess several historical collection deployment plans and historical point cloud data of the fully mechanized mining face. The preprocessing includes denoising, filtering and other operations in sequence to improve data quality.

[0086] Step 2.2: According to the pre-processed historical acquisition deployment plan, set the optimal acquisition parameter configuration information label for each corresponding pre-processed historical point cloud data to obtain the corresponding acquisition parameter optimization sample;

[0087] Step 2.3: Divide the collected parameter optimization samples into a third model training sample set and a third model test sample set in a ratio of 7:3;

[0088] Step 2.4: Determine the optimization objective and acquisition parameter variables. Based on the optimization objective, set the fitness function of the Improved Fireworks Algorithm (IFWA) algorithm and encode the acquisition parameter variables into IFWA individuals of the IFWA optimization algorithm.

[0089] The formula of the fitness function is:

[0090] f(q r )=A1·F total (q r )+A2·F com (q r )+A3·F noise (q r )+A4·F cover (q r )

[0091] Among them, q r is the IFWA individual, f(q r ) is q r The fitness value, F total (q r ) is the point cloud density function, F com (qr ) is the point cloud integrity function, F noise (q r ) is the noise level function, F cover (q r ) is the scan coverage function, and A1, A2, A3, and A4 are all fitness weights.

[0092] Step 2.5: Use the IFWA optimization algorithm to build an initial acquisition parameter optimization model, and input the third model training sample set for optimization training to obtain the optimized acquisition parameter optimization model;

[0093] Step 2.6: Input the third model test sample set to perform model testing on the optimized acquisition parameter optimization model, and obtain corresponding optimized acquisition parameter configuration information labels;

[0094] Step 2.7: Compare and count the several optimized acquisition parameter configuration information labels and the corresponding optimal acquisition parameter configuration information labels to obtain the corresponding third model prediction accuracy;

[0095] Step 2.8: If the prediction accuracy of the third model is greater than the third model prediction accuracy threshold, the optimal acquisition parameter optimization model is output; otherwise, the training optimization is continued until the optimal acquisition parameter optimization model is output.

[0096] S103: Based on the optimized acquisition deployment plan, obtain point cloud data of the fully mechanized mining face of the target mine.

[0097] The optimized acquisition deployment plan includes the real-time number of laser point cloud acquisition devices, as well as the real-time location, acquisition angle, and optimized parameter configuration information for each laser point cloud acquisition device. This optimized parameter configuration includes the scanning frequency, resolution, scanning angle, laser pulse duration, laser power, and sampling interval of the optimized point cloud data acquisition device. Optimizing this parameter configuration information enables automated optimization of point cloud data acquisition for the laser point cloud acquisition device group, improving the quality of the collected point cloud data and providing stronger support for subsequent data processing and application.

[0098] The specific steps of S103 are: 1) based on the optimized acquisition deployment plan, confirm the number of devices, device locations, device acquisition angles, and parameter configuration information of the point cloud data acquisition devices deployed on the fully-mechanized mining working face, and deploy corresponding laser point cloud data acquisition devices at corresponding locations on the fully-mechanized mining working face in the coal mine;

[0099] 2) Based on the deployed laser point cloud data acquisition equipment, obtain the point cloud data of the fully mechanized mining face of the target mine.

[0100] The laser point cloud data acquisition equipment transmits the collected point cloud data to a cloud data center via a point cloud data transmission network. Based in the cloud data center, unified, real-time point cloud data processing is performed on the fully mechanized mining face, enhancing data interaction within the collected point cloud data and avoiding information silos.

[0101] Optionally, this embodiment further includes, after S103:

[0102] S104: Using the pre-trained point cloud data processing model to process the collected point cloud data. Specifically, the following steps are included:

[0103] S104.1: Extract global point cloud data features from point cloud data using a pre-trained point cloud data processing model;

[0104] S104.2: Segment the global point cloud data features to obtain the real-time point cloud area of ​​each entity in the fully mechanized mining face;

[0105] S104.3: Based on the real-time point cloud area, obtain point cloud data of the complete coal wall entity in the entity.

[0106] Specifically:

[0107] Extract the local point cloud data features of the real-time point cloud area of ​​each entity; perform entity recognition on the local point cloud data features of each entity to obtain entity recognition results; based on the entity recognition results, obtain the real-time point cloud area of ​​the local coal wall entity in the fully mechanized mining working face; based on the real-time point cloud area of ​​the local coal wall entity, obtain the point cloud data of the complete coal wall entity in the entity.

[0108] The point cloud data processed by the point cloud data processing model can fully present the coal wall morphology of the target mine, making it convenient for coal mine technicians and managers to quickly understand the situation of the underground fully mechanized mining working face in the coal mine in real time, and provide reliable data support for production command and dispatch and emergency plans.

[0109] For the construction and training process of the point cloud data processing model, refer to the following steps 4.1 to 4.7:

[0110] Step 4.1: Preprocess the historical point cloud data of the fully mechanized mining face. The preprocessing includes denoising, filtering and other operations in sequence to improve the data quality.

[0111] Step 4.2: Set corresponding entity real labels for different point cloud regions in each pre-processed historical point cloud data to obtain corresponding point cloud data processing samples;

[0112] Step 4.3: Divide the point cloud data processing samples into a second model training sample set and a second model test sample set in a ratio of 7:3;

[0113] Step 4.4: Use the PointNet-GNN-SVM algorithm to build an initial point cloud data processing model, and input the second model training sample set for optimization training to obtain the optimized point cloud data processing model;

[0114] The point cloud data processing model includes a global feature extraction module based on the PointNet++ algorithm, a point cloud segmentation module based on the Graph Neural Network (GNN) algorithm, and an entity recognition module based on the Support Vector Machine (SVM) algorithm.

[0115] The global feature extraction module is used to directly process point cloud data without converting it into voxel representation, extracting global point cloud data features of real-time fully mechanized mining working face point cloud data for subsequent segmentation tasks;

[0116] Point cloud segmentation module, which is used to segment the global point cloud data features according to the global point cloud data features to obtain the real-time point cloud areas of different entities;

[0117] The entity recognition module is used to extract local point cloud data features of the real-time point cloud area of ​​different entities, and perform entity recognition based on the local point cloud data features to obtain real-time point cloud entity recognition results;

[0118] By segmenting and identifying point cloud data, various entities in the fully-mechanized mining face of the target mine, such as machinery and equipment, obstacles, work locations, and coal walls, can be detected and classified, which helps to understand the specific layout and environmental conditions of the fully-mechanized mining face.

[0119] Step 4.5: Input the second model test sample set to perform model testing on the optimized point cloud data processing model to obtain corresponding entity prediction labels;

[0120] Step 4.6: Compare and count the predicted labels of several entities with the corresponding real labels of the entities to obtain the corresponding prediction accuracy of the second model;

[0121] Step 4.7: If the second model prediction accuracy is greater than the second model prediction accuracy threshold, the optimal point cloud data processing model is output; otherwise, training optimization is continued until the optimal point cloud data processing model is output.

[0122] like Figure 2 As shown, it is another flow chart of the method for collecting point cloud data of a fully mechanized mining face provided by the embodiment of the present disclosure, combined with Figure 3 The structure diagram of the point cloud data acquisition system for a fully mechanized mining working face is shown, and the method includes S201-S206:

[0123] S201: Based on the cloud data center, build a solution prediction model, acquisition parameter optimization model and point cloud data processing model.

[0124] The construction of the scenario prediction model includes the following steps:

[0125] Step 1.1: Preprocess several historical collection task information and historical collection deployment plans of the fully mechanized mining face. The preprocessing includes operations such as denoising and filtering to improve data quality.

[0126] Step 1.2: According to the pre-processed historical collection deployment plan, set the real collection deployment plan label for the corresponding pre-processed historical collection task information to obtain the corresponding collection deployment plan prediction sample;

[0127] Step 1.3: Divide the several collected deployment plan prediction samples into the first model training sample set and the first model test sample set in a ratio of 7:3;

[0128] Step 1.4: Use a deep learning algorithm, such as the Bi-directional Long Short-Term Memory (BiLSTM) algorithm, to build an initial solution prediction model. Input the first model training sample set for optimization training to obtain an optimized solution prediction model.

[0129] Step 1.5: Input the first model test sample set to perform model testing on the optimized solution prediction model to obtain corresponding prediction labels for several acquisition and deployment solutions;

[0130] Step 1.6: Compare and count the predicted labels of several collection and deployment plans with the corresponding real labels of the collection and deployment plans to obtain the corresponding first model prediction accuracy;

[0131] Step 1.7: If the prediction accuracy of the first model is greater than the preset accuracy threshold, the optimal solution prediction model is output; otherwise, training optimization is continued until the optimal solution prediction model is obtained.

[0132] The construction of the acquisition parameter optimization model includes the following steps:

[0133] Step 2.1: Preprocess several historical collection deployment plans and historical point cloud data of the fully mechanized mining face. The preprocessing includes denoising, filtering and other operations in sequence to improve data quality.

[0134] Step 2.2: According to the pre-processed historical acquisition deployment plan, set the optimal acquisition parameter configuration information label for each corresponding pre-processed historical point cloud data to obtain the corresponding acquisition parameter optimization sample;

[0135] Step 2.3: Divide the collected parameter optimization samples into a third model training sample set and a third model test sample set in a ratio of 7:3;

[0136] Step 2.4: Determine the optimization objective and acquisition parameter variables. Based on the optimization objective, set the fitness function of the Improved Fireworks Algorithm (IFWA) algorithm and encode the acquisition parameter variables into IFWA individuals of the IFWA optimization algorithm.

[0137] The formula of the fitness function is:

[0138] f(q r )=A1·F total (q r )+A2·F com (q r )+A3·F noise (q r )+A4·F cover (q r )

[0139] Among them, q r is the IFWA individual, f(q r ) is q r The fitness value, F total (q r ) is the point cloud density function, F com (q r ) is the point cloud integrity function, F noise (q r ) is the noise level function, F cover (q r ) is the scan coverage function, and A1, A2, A3, and A4 are all fitness weights.

[0140] Step 2.5: Use the IFWA optimization algorithm to build an initial acquisition parameter optimization model, and input the third model training sample set for optimization training to obtain the optimized acquisition parameter optimization model;

[0141] Step 2.6: Input the third model test sample set to perform model testing on the optimized acquisition parameter optimization model, and obtain corresponding optimized acquisition parameter configuration information labels;

[0142] Step 2.7: Compare and count the several optimized acquisition parameter configuration information labels and the corresponding optimal acquisition parameter configuration information labels to obtain the corresponding third model prediction accuracy;

[0143] Step 2.8: If the prediction accuracy of the third model is greater than the third model prediction accuracy threshold, the optimal acquisition parameter optimization model is output; otherwise, the training optimization is continued until the optimal acquisition parameter optimization model is output.

[0144] The construction of the point cloud data processing model includes the following steps:

[0145] Step 4.1: Preprocess the historical point cloud data of the fully mechanized mining face. The preprocessing includes denoising, filtering and other operations in sequence to improve the data quality.

[0146] Step 4.2: Set corresponding entity real labels for different point cloud regions in each pre-processed historical point cloud data to obtain corresponding point cloud data processing samples;

[0147] Step 4.3: Divide the point cloud data processing samples into a second model training sample set and a second model test sample set in a ratio of 7:3;

[0148] Step 4.4: Use the PointNet-GNN-SVM algorithm to build an initial point cloud data processing model, and input the second model training sample set for optimization training to obtain the optimized point cloud data processing model;

[0149] The point cloud data processing model includes a global feature extraction module based on the PointNet++ algorithm, a point cloud segmentation module based on the Graph Neural Network (GNN) algorithm, and an entity recognition module based on the Support Vector Machine (SVM) algorithm.

[0150] The global feature extraction module is used to directly process point cloud data without converting it into voxel representation, extracting global point cloud data features of real-time fully mechanized mining working face point cloud data for subsequent segmentation tasks;

[0151] Point cloud segmentation module, which is used to segment the global point cloud data features according to the global point cloud data features to obtain the real-time point cloud areas of different entities;

[0152] The entity recognition module is used to extract local point cloud data features of the real-time point cloud area of ​​different entities, and perform entity recognition based on the local point cloud data features to obtain real-time point cloud entity recognition results;

[0153] By segmenting and identifying point cloud data, various entities in the fully-mechanized mining face of the target mine, such as machinery and equipment, obstacles, work locations, and coal walls, can be detected and classified, which helps to understand the specific layout and environmental conditions of the fully-mechanized mining face.

[0154] Step 4.5: Input the second model test sample set to perform model testing on the optimized point cloud data processing model to obtain corresponding entity prediction labels;

[0155] Step 4.6: Compare and count the predicted labels of several entities with the corresponding real labels of the entities to obtain the corresponding prediction accuracy of the second model;

[0156] Step 4.7: If the second model prediction accuracy is greater than the second model prediction accuracy threshold, the optimal point cloud data processing model is output; otherwise, training optimization is continued until the optimal point cloud data processing model is output.

[0157] S202: Based on the collection task information of the fully mechanized mining face of the target mine, a corresponding collection deployment plan is generated using a plan prediction model.

[0158] The collected task information includes real-time fully mechanized mining face scale information, real-time monitoring demand information, and real-time coal mine underground working environment information;

[0159] The collection deployment plan includes the real-time number of laser point cloud data collection devices in the laser point cloud data collection device group, as well as the real-time setting position, collection angle and parameter configuration information of each laser point cloud data collection device;

[0160] The parameter configuration information includes the real-time initial scanning frequency, initial resolution, initial scanning angle, initial laser pulse duration, initial laser power, and initial sampling interval of each laser point cloud data acquisition device.

[0161] S203: Using the acquisition parameter optimization model, optimize the parameter configuration information in the acquisition deployment plan to obtain an optimized acquisition deployment plan containing the optimized parameter configuration information. This includes the following steps:

[0162] S203.1: Use the acquisition parameter optimization model to encode the parameter configuration information in the acquisition deployment plan into IFWA individuals in the IFWA population;

[0163] S203.2: Use the Circle chaotic map sequence to initialize the IFWA population and obtain the initialized IFWA population. The formula is:

[0164]

[0165] Among them, q r is the initial IFWA individual of the Circle chaos map, is the randomly generated initial IFWA individual.

[0166] S203.3: Iteratively update the initialized IFWA population according to the preset algorithm parameters of the IFWA optimization algorithm to obtain an updated IFWA population;

[0167] The formula for the explosion radius and number of sparks of IFWA individuals in the updated IFWA population is:

[0168]

[0169] Among them, S r For updated IFWA individual q r The number of sparks, M ′ is a constant, f max is the maximum fitness value in the updated IFWA population, f(q r ) is the IFWA individual q before updating r The fitness value of , τ is an infinitesimal constant.

[0170]

[0171] Among them, R r For updated IFWA individual q r The explosion radius, is the explosion radius adjustment constant, f min is the minimum fitness value in the updated IFWA population.

[0172] q′ r =q r +S r ×rand(-1,1)

[0173] Among them, q′ r is the updated IFWA individual, rand(-1,1) is a random number between -1 and 1, q r is the initial IFWA individual of the Circle chaos map.

[0174] S203.4: Use the Gaussian mutation algorithm to perform Gaussian mutation on the initialized IFWA population to generate a Gaussian mutated IFWA population. The formula is:

[0175] q″ r =q r +S r ×G(1,1)

[0176] Among them, q r is a Gaussian variant IFWA individual, and G(1,1) is a random number with a Gaussian distribution and a mean and variance of 1.

[0177] S203.5: Use the dynamic reverse learning algorithm to perform dynamic reverse learning on the initialized IFWA population to generate a dynamic reverse IFWA population. The formula is:

[0178] q″′ r =γ(L max +L min )-q r

[0179] Among them, q″′ r is the dynamic reverse IFWA individual, γ is the decreasing inertia coefficient, γ=0.9-0.5d / T, d is the current iteration number, T is the maximum iteration number, L max is the maximum value of the vector space, L min is the minimum value in the vector space.

[0180] S203.6: Using the fitness function, calculate the fitness values ​​of all IFWA individuals in the updated IFWA population, the Gaussian-mutated IFWA population, and the dynamically reversed IFWA population, and take the IFWA individual with the smallest fitness value as the optimal individual;

[0181] S203.7: If the number of iterations reaches the threshold or the fitness value of the optimal individual meets the requirements, the optimal solution corresponding to the current optimal individual is output to obtain the optimized parameter configuration information;

[0182] S203.8: Generate a corresponding optimized collection deployment plan based on the optimized parameter configuration information.

[0183] S204: According to the optimized acquisition deployment plan, a corresponding laser point cloud data acquisition equipment group is deployed at a corresponding position of the fully mechanized mining working face in the coal mine.

[0184] S205: Collecting point cloud data of the corresponding fully mechanized mining working face based on the laser point cloud data acquisition device group, and sending the collected point cloud data of the fully mechanized mining working face to the cloud data center through the point cloud data transmission network;

[0185] S206: Based on the cloud data center, use the point cloud data processing model to process the point cloud data of the fully mechanized mining working face to obtain processed point cloud data. This specifically includes the following steps:

[0186] S206.1: Based on the cloud data center, the point cloud data of the fully mechanized mining face is input into the point cloud data processing model;

[0187] S206.2: Extract global point cloud data features from the point cloud data using a pre-trained point cloud data processing model;

[0188] S206.3: Segment the global point cloud data features to obtain the real-time point cloud area of ​​each entity in the fully mechanized mining face;

[0189] S206.4: Extract local point cloud data features of the real-time point cloud area of ​​each entity, perform entity recognition on the local point cloud data features of each entity, and obtain entity recognition results;

[0190] S206.5: Integrate and trim the real-time point cloud area where the entity recognition result is a local coal wall entity to obtain point cloud data of the complete coal wall entity of the fully mechanized mining working face.

[0191] The processed point cloud data of the fully mechanized mining working face can fully present the coal wall shape underground in the coal mine, making it convenient for coal mine technicians and managers to quickly understand the situation of the fully mechanized mining working face underground in the coal mine in real time, and provide reliable data support for production command and dispatch and emergency plans.

[0192] According to another aspect of the embodiment of the present disclosure, a point cloud data acquisition system for a fully mechanized mining working face is provided. Figure 3 As shown, it includes a cloud data center, a point cloud data transmission network and several laser point cloud data acquisition devices. The cloud data center is communicated with the laser point cloud data acquisition devices through the point cloud data transmission network.

[0193] The cloud data center is used to build a solution prediction model, an acquisition parameter optimization model, and a point cloud data processing model. Based on the acquisition task information, the solution prediction model is used to generate the corresponding acquisition deployment plan. The acquisition parameter optimization model is used to optimize the parameter configuration information in the acquisition deployment plan to obtain the optimized configuration information.

[0194] The point cloud data transmission network is used to transmit the point cloud data of the fully mechanized mining face sent by the laser point cloud data acquisition equipment to the cloud data center.

[0195] Laser point cloud data acquisition equipment is used to collect point cloud data of the fully mechanized mining working face in the target mine.

[0196] Optionally, the point cloud data transmission network includes a plurality of point cloud data transmission links, each point cloud data transmission link includes a plurality of point cloud data transmission devices communicatively connected in series, each point cloud data transmission device is communicatively connected to a laser point cloud data acquisition device at a corresponding position, and the point cloud data transmission device located at the head end of the point cloud data transmission link is communicatively connected to a cloud data center;

[0197] The point cloud data transmission device receives the point cloud data collected by the corresponding laser point cloud data acquisition equipment group and sends it to the previous point cloud data transmission device in the corresponding point cloud data transmission link. Data backup is performed between adjacent point cloud data transmission devices, avoiding the risk of data loss in direct transmission to the cloud data center. It is suitable for signal unstable scenarios in coal mines, and at the same time avoids the limitations of large hardware cost investment in cable transmission.

[0198] The cloud data center includes a model construction unit, a solution generation unit, an acquisition parameter optimization unit, a parallel data communication unit and a point cloud data processing unit connected in sequence. The parallel data communication unit is respectively communicated with several point cloud data transmission devices located at the head end of the point cloud data transmission link.

[0199] Model building unit, used to build solution prediction model, acquisition parameter optimization model and point cloud data processing model;

[0200] A plan generation unit is used to generate a corresponding collection deployment plan based on the collection task information using a plan prediction model;

[0201] A collection parameter optimization unit, configured to optimize parameter configuration information in a collection deployment plan using a collection parameter optimization model;

[0202] A parallel data communication unit is used to receive point cloud data of the fully mechanized mining working face collected by the laser point cloud data collection equipment and transmitted through the point cloud data transmission network;

[0203] The point cloud data processing unit is used to process the point cloud data of the fully mechanized mining working face using a point cloud data processing model to obtain corresponding processed point cloud data.

[0204] According to another aspect of the embodiment of the present disclosure, a point cloud data acquisition device for a fully mechanized mining working face is provided. Figure 4 As shown, the device includes:

[0205] A plan acquisition module 401 is used to obtain a collection deployment plan corresponding to the collection task information based on the collection task information of the fully mechanized mining face of the target mine;

[0206] An optimization module 402 is configured to optimize parameter configuration information of the point cloud data acquisition device included in the acquisition deployment plan based on a pre-trained acquisition parameter optimization model;

[0207] The data acquisition module 403 is used to acquire point cloud data of the fully mechanized mining face of the target mine based on the optimized acquisition deployment plan.

[0208] In one or more embodiments, the data acquisition module 403 is used to:

[0209] Based on the optimized acquisition deployment plan, confirm the number of devices, device locations, device acquisition angles, and parameter configuration information of the point cloud data acquisition devices deployed on the fully mechanized mining working face;

[0210] Based on the deployed point cloud data acquisition equipment, point cloud data of the fully mechanized mining face of the target mine is obtained.

[0211] The fully mechanized mining face point cloud data acquisition device is further configured to: after acquiring the point cloud data of the fully mechanized mining face of the target mine based on the optimized acquisition deployment plan, extract global point cloud data features of the point cloud data using a pre-trained point cloud data processing model;

[0212] Segmenting the global point cloud data features to obtain real-time point cloud areas of each entity in the fully mechanized mining working face;

[0213] Based on the real-time point cloud area, point cloud data of a complete coal wall entity in the entity is obtained.

[0214] In one or more embodiments, the fully mechanized mining working face point cloud data acquisition device is further used to: extract local point cloud data features of the real-time point cloud area of ​​each entity;

[0215] Performing entity recognition on the local point cloud data features of each entity to obtain an entity recognition result;

[0216] Based on the entity recognition result, a real-time point cloud area of ​​a local coal wall entity in the fully mechanized mining working face is obtained;

[0217] Based on the real-time point cloud area of ​​the local coal wall entity, point cloud data of the complete coal wall entity in the entity is obtained.

[0218] In one or more embodiments, the solution acquisition module 401 is used to:

[0219] The acquisition task information of the fully mechanized mining face of the target mine is input into a pre-trained scheme prediction model to obtain the acquisition deployment scheme corresponding to the acquisition task information. The scheme prediction model is trained based on the historical acquisition task information and historical acquisition deployment schemes of the fully mechanized mining face.

[0220] The comprehensive mining working face point cloud data acquisition device provided by the embodiment of the present disclosure and the comprehensive mining working face point cloud data acquisition method provided by the embodiment of the present disclosure are based on the same inventive concept and have the same beneficial effects as the methods adopted, operated or implemented by them.

[0221] The present disclosure also provides a computer device to execute the above-mentioned method for collecting point cloud data of a fully mechanized mining working face. Figure 5It shows a schematic diagram of a computer device provided by some embodiments of the present disclosure. Figure 5 As shown, the computer device 50 includes: a processor 500, a memory 501, a bus 502 and a communication interface 503, and the processor 500, the communication interface 503 and the memory 501 are connected via the bus 502; the memory 501 stores a computer program that can be run on the processor 500, and when the processor 500 runs the computer program, it executes the comprehensive mining working face point cloud data acquisition method provided by any of the aforementioned embodiments of the present disclosure.

[0222] The memory 501 may include high-speed random access memory (RAM) and may also include non-volatile memory, such as at least one disk storage. The communication connection between the device network element and at least one other network element is achieved through at least one communication interface 503 (which may be wired or wireless), and the Internet, wide area network, local area network, metropolitan area network, etc. may be used.

[0223] Bus 502 can be an ISA bus, a PCI bus, or an EISA bus. Such buses can be classified as address buses, data buses, and control buses. Memory 501 is used to store programs, and processor 500 executes the programs upon receiving execution instructions. The method for collecting point cloud data from a fully mechanized mining face disclosed in any of the aforementioned embodiments of the present disclosure can be applied to or implemented by processor 500.

[0224] The processor 500 may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method may be completed by hardware integrated logic circuits or software instructions in the processor 500. The processor 500 may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPTA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It may implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present disclosure. The general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in conjunction with the embodiments of the present disclosure may be directly implemented and executed by a hardware decoding processor, or by a combination of hardware and software modules in the decoding processor. The software module may be located in a storage medium mature in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, etc. The storage medium is located in the memory 501 , and the processor 500 reads the information in the memory 501 and completes the steps of the above method in combination with its hardware.

[0225] The computer device provided in the embodiment of the present disclosure and the method for collecting point cloud data of the comprehensive mining working face provided in the embodiment of the present disclosure are based on the same inventive concept and have the same beneficial effects as the methods adopted, operated or implemented by them.

[0226] The embodiments of the present disclosure also provide a computer-readable storage medium corresponding to the method for collecting point cloud data of a comprehensive mining working face provided in the aforementioned embodiments. The computer-readable storage medium is a CD on which a computer program (i.e., a computer program product) is stored. When the computer program is run by the processor, it will execute the method for collecting point cloud data of a comprehensive mining working face provided in any of the aforementioned embodiments.

[0227] It should be noted that examples of the computer-readable storage medium may also include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other optical or magnetic storage media, which are not listed here one by one.

[0228] The computer-readable storage medium provided by the above-mentioned embodiments of the present disclosure and the method for collecting point cloud data of a comprehensive mining working face provided by the embodiments of the present disclosure are based on the same inventive concept and have the same beneficial effects as the methods adopted, run or implemented by the application programs stored therein.

[0229] The present disclosure also provides a computer program product. Figure 6 The computer program product 600 carries a program code, namely a computer program 601. The instructions included in the computer program 601 can be used to execute the steps of the comprehensive mining working face point cloud data collection method described in the above method embodiment. For details, please refer to the above method embodiment and will not be repeated here.

[0230] The computer program product may be implemented in hardware, software, or a combination thereof. In one embodiment, the computer program product is implemented as a computer storage medium. In another embodiment, the computer program product is implemented as a software product, such as a software development kit (SDK).

[0231] The basic principles of the present disclosure have been described above in conjunction with specific embodiments. However, it should be noted that the advantages, strengths, and effects mentioned in this disclosure are merely illustrative and not restrictive, and should not be construed as necessarily possessed by each embodiment of the present disclosure. Furthermore, the specific details disclosed above are provided for illustrative purposes and to facilitate understanding, rather than as limitations. These details do not limit the present disclosure to necessarily being implemented using these specific details.

[0232] The block diagrams of the devices, devices, equipment, and systems involved in this disclosure are merely illustrative examples and are not intended to require or imply that they must be connected, arranged, or configured in the manner shown in the block diagrams. As will be appreciated by those skilled in the art, these devices, devices, equipment, and systems can be connected, arranged, or configured in any manner. Words such as "include," "comprise," "have," and the like are open-ended words, meaning "including but not limited to," and can be used interchangeably therewith. The words "or" and "and" used herein refer to the words "and / or" and can be used interchangeably therewith, unless the context clearly indicates otherwise. The word "such as" used herein refers to the phrase "such as but not limited to," and can be used interchangeably therewith.

[0233] Additionally, as used herein, "or" used in a list of items beginning with "at least one" indicates a separate list, so that, for example, a list of "at least one of A, B, or C" means A or B or C, or AB or AC or BC, or ABC (i.e., A and B and C). Furthermore, the word "exemplary" does not mean that the example described is preferred or better than other examples.

[0234] It should also be noted that in the system and method of the present disclosure, each component or each step can be decomposed and / or recombined. Such decomposition and / or recombination should be regarded as equivalent solutions of the present disclosure.

[0235] Various changes, substitutions, and modifications may be made to the technology described herein without departing from the teachings defined by the appended claims. Moreover, the scope of the claims of this disclosure is not limited to the specific aspects of the processes, machines, manufactures, compositions of things, means, methods, and actions described above. Currently existing or later developed processes, machines, manufactures, compositions of things, means, methods, or actions that perform substantially the same function or achieve substantially the same results as the corresponding aspects described herein may be utilized. Accordingly, the appended claims include within their scope such processes, machines, manufactures, compositions of things, means, methods, or actions.

[0236] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present disclosure. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects without departing from the scope of the present disclosure. Therefore, the present disclosure is not intended to be limited to the aspects shown herein, but rather to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0237] The above description has been provided for the purpose of illustration and description. In addition, this description is not intended to limit the embodiments of the present disclosure to the forms disclosed herein. Although a number of example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, alterations, additions, and sub-combinations thereof.

Claims

1. A method for collecting point cloud data of a fully mechanized mining working face, characterized in that: include: Based on the collection task information of the fully mechanized mining face of the target mine, obtaining a collection deployment plan corresponding to the collection task information; Optimizing parameter configuration information of the point cloud data acquisition equipment included in the acquisition deployment plan according to a pre-trained acquisition parameter optimization model; Based on the optimized acquisition deployment plan, point cloud data of the fully mechanized mining face of the target mine is obtained.

2. The method for collecting point cloud data of a fully mechanized mining face according to claim 1, wherein: Based on the optimized acquisition deployment plan, point cloud data of the fully mechanized mining face of the target mine is obtained, including: Based on the optimized acquisition deployment plan, confirm the number of devices, device locations, device acquisition angles, and parameter configuration information of the point cloud data acquisition devices deployed on the fully mechanized mining working face; Based on the deployed point cloud data acquisition equipment, point cloud data of the fully mechanized mining face of the target mine is obtained.

3. The method for collecting point cloud data of a fully mechanized mining face according to claim 1, wherein: After acquiring the point cloud data of the fully mechanized mining face of the target mine based on the optimized acquisition deployment plan, the method further includes: Extracting global point cloud data features of the point cloud data using a pre-trained point cloud data processing model; Segmenting the global point cloud data features to obtain real-time point cloud areas of each entity in the fully mechanized mining working face; Based on the real-time point cloud area, point cloud data of a complete coal wall entity in the entity is obtained.

4. The method for collecting point cloud data of a fully mechanized mining face according to claim 3, wherein: Based on the real-time point cloud area, point cloud data of a complete coal wall entity in the entity is obtained, including: Extract local point cloud data features of the real-time point cloud area of ​​each entity; Performing entity recognition on the local point cloud data features of each entity to obtain an entity recognition result; Based on the entity recognition result, a real-time point cloud area of ​​a local coal wall entity in the fully mechanized mining working face is obtained; Based on the real-time point cloud area of ​​the local coal wall entity, point cloud data of the complete coal wall entity in the entity is obtained.

5. The method for collecting point cloud data of a fully mechanized mining face according to claim 1, wherein: Based on the collection task information of the fully mechanized mining face of the target mine, a collection deployment plan corresponding to the collection task information is obtained, including: The acquisition task information of the fully mechanized mining face of the target mine is input into a pre-trained scheme prediction model to obtain the acquisition deployment scheme corresponding to the acquisition task information. The scheme prediction model is trained based on the historical acquisition task information and historical acquisition deployment schemes of the fully mechanized mining face.

6. The method for collecting point cloud data of a fully mechanized mining face according to claim 1, wherein: The parameter configuration information includes the scanning frequency, resolution, scanning angle, laser pulse duration, laser power and sampling interval of the point cloud data acquisition device.

7. A point cloud data acquisition device for a fully mechanized mining working face, characterized in that: include: A scheme acquisition module is used to obtain a collection deployment scheme corresponding to the collection task information based on the collection task information of the fully mechanized mining working face of the target mine; An optimization module, configured to optimize parameter configuration information of the point cloud data acquisition device included in the acquisition deployment plan based on a pre-trained acquisition parameter optimization model; A data acquisition module is used to acquire point cloud data of the fully mechanized mining face of the target mine based on the optimized acquisition deployment plan.

8. A computer embedded device comprising a memory, a processor, and a computer program stored in the memory, characterized in that: The processor executes the computer program to implement the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images