Study on the prediction of gangue content rate in fully mechanized caving face based on DeepLab v3+
-
摘要: 针对综放工作面真实煤矸堆叠状态下的体积含矸率很难获取的问题，提出一种基于DeepLab v3+的综放工作面含矸率预测方法。构建了煤矸堆积体图像数据集，采用半自动的数据标注方法和限制对比度自适应直方图均衡化法对煤矸图像进行预处理。运用DeepLab v3+模型进行煤矸图像语义分割，进而计算煤矸图像的投影面积含矸率。利用PFC3D数值模拟软件，基于重建的三维煤矸块体建立数值模型，模拟顶煤放落和刮板输送机运煤过程，通过fish语言读取每个矸石或煤的体积，计算得到煤矸堆积体体积含矸率。通过分析不同顶煤厚度条件下刮板输送机上煤矸堆积体的投影面积含矸率与体积含矸率的量化关系，建立了煤流的体积含矸率预测模型。实验结果表明：DeepLab v3+模型的准确率、平均像素准确率和平均交并比分别为97.68%，97.72%，95.33%，均高于经典语义分割模型FCN8s和PSPNet，实现了煤矸堆积体投影面积含矸率的精准快速识别；体积含矸率预测模型的决定系数R2为0.982 8，预测效果较好。Abstract: To tackle the challenge of accurately determining the volumetric gangue content rate under actual stacking conditions of coal-gangue in fully mechanized caving faces, a prediction method based on the DeepLab v3+ model was proposed. A dataset consisting of images depicting coal-gangue accumulation was constructed, and a semi-automatic data labeling method, along with Contrast Limited Adaptive Histogram Equalization (CLAHE), was employed for image preprocessing. The DeepLab v3+ model was utilized for the semantic segmentation of coal-gangue images, which facilitated the calculation of the projected area gangue content rate. A numerical model was established using the PFC3D numerical simulation software based on the reconstructed three-dimensional coal-gangue block, simulating the top coal drop and the coal transport process via scraper conveyor. The volume of each gangue or coal particle was extracted using the FISH programming language, enabling the calculation of the volumetric gangue content rate of the coal-gangue accumulation. By analyzing the quantitative relationship between the projected area gangue content rate and the volumetric gangue content rate under varying top coal thickness conditions, a predictive model for the volumetric gangue content rate of coal flow was developed. Experimental results indicated that the accuracy, mean pixel accuracy, and mean intersection-over-union (IoU) of the DeepLab v3+ model were 97.68%, 97.72%, and 95.33%, respectively, all surpassing those of classical semantic segmentation models such as FCN8s and PSPNet. This enabled precise and rapid identification of the projected area gangue content rate of coal-gangue accumulations. The coefficient of determination (R2) for the volumetric gangue content rate prediction model was 0.9828, demonstrating robust predictive performance.
-
表 1 DeepLab v3+模型参数设置
Table 1. DeepLab v3+ model parameter setting
名称 参数 名称 参数 数据集大小 2 480 学习率下降调整策略 cos Batch size 6 backbone MobileNet 初始学习率 0.000 1 优化方法 Adam 迭代次数 80 
下载: 导出CSV
表 2 图像分割模型对比实验结果
Table 2. Comparison of image segmentation models experimental results
% 模型 准确率 平均交并比 MPA FCN8s 87.84 86.52 98.28 PSPNet 97.46 94.86 97.34 DeepLab v3+ 97.68 95.33 97.72
下载: 导出CSV
表 3 放煤模拟实验方案
Table 3. Coal caving simulation experiment plans
方案 顶煤块体直径/m 矸石块
体直径/m顶煤
厚度/m刮板
速度/（m·s−1）方案1 0.3 0.4～0.5 5 2 方案2 0.3 0.4～0.5 7.5 2 方案3 0.3 0.4～0.5 2.5 2
下载: 导出CSV
-
[1] 王国法,刘合,王丹丹,等. 新形势下我国能源高质量发展与能源安全[J]. 中国科学院院刊,2023,38(1):23-37.WANG Guofa,LIU He,WANG Dandan,et al. High-quality energy development and energy security under the new situation for China[J]. Bulletin of Chinese Academy of Sciences,2023,38(1):23-37. [2] 王国法,孟令宇. 煤矿智能化及其技术装备发展[J]. 中国煤炭,2023,49(7):1-13.WANG Guofa,MENG Lingyu. Development of coal mine intelligence and its technical equipment[J]. China Coal,2023,49(7):1-13. [3] 王国法,庞义辉,任怀伟,等. 智慧矿山系统工程及关键技术研究与实践[J]. 煤炭学报,2024,49(1):181-202.WANG Guofa,PANG Yihui,REN Huaiwei,et al. System engineering and key technologies research and practice of smart mine[J]. Journal of China Coal Society,2024,49(1):181-202. [4] 王家臣,刘云熹,李杨,等. 矿业系统工程60年发展与展望[J]. 煤炭学报,2024,49(1):261-279.WANG Jiachen,LIU Yunxi,LI Yang,et al. 60 years development and prospect of mining systems engineering[J]. Journal of China Coal Society,2024,49(1):261-279. [5] 王家臣,杨胜利,李良晖,等. 智能放煤理论与技术研究进展[J]. 工矿自动化,2024,50(9):1-12.WANG Jiachen,YANG Shengli,LI Lianghui,et al. Research progress on intelligent coal caving theory and technology[J]. Journal of Mine Automation,2024,50(9):1-12. [6] 王家臣. 我国放顶煤开采的工程实践与理论进展[J]. 煤炭学报,2018,43(1):43-51.WANG Jiachen. Engineering practice and theoretical progress of top-coal caving mining technology in China[J]. Journal of China Coal Society,2018,43(1):43-51. [7] 王家臣. 我国综放开采40年及展望[J]. 煤炭学报,2023,48(1):83-99.WANG Jiachen. 40 years development and prospect of longwall top coal caving in China[J]. Journal of China Coal Society,2023,48(1):83-99. [8] 王家臣,杨胜利,刘淑琴,等. 急倾斜煤层开采技术现状与流态化开采构想[J]. 煤炭科学技术,2022,50(1):48-59. doi: 10.3969/j.issn.0253-2336.2022.1.mtkxjs202201003WANG Jiachen,YANG Shengli,LIU Shuqin,et al. Technology status and fluidized mining conception for steeply inclined coal seams[J]. Coal Science and Technology,2022,50(1):48-59. doi: 10.3969/j.issn.0253-2336.2022.1.mtkxjs202201003 [9] 王家臣. 我国综放开采技术及其深层次发展问题的探讨[J]. 煤炭科学技术,2005,33(1):14-17.WANG Jiachen. Fully mechanized longwall top coal caving technology in China and discussion on issues of further development[J]. Coal Science and Technology,2005,33(1):14-17. [10] 张宁波,鲁岩,刘长友,等. 综放开采煤矸自动识别基础研究[J]. 采矿与安全工程学报,2014,31(4):532-536.ZHANG Ningbo,LU Yan,LIU Changyou,et al. Basic study on automatic detection of coal and gangue in the fully mechanized top coal caving mining[J]. Journal of Mining & Safety Engineering,2014,31(4):532-536. [11] 王增才,富强. 自然γ射线穿透煤层及支架顶梁衰减规律[J]. 辽宁工程技术大学学报,2006,25(6):804-807.WANG Zengcai,FU Qiang. Attenuation of natural γ-ray passing through coal seam and hydraulic support[J]. Journal of Liaoning Technical University,2006,25(6):804-807. [12] 袁源,汪嘉文,朱德昇,等. 顶煤放落过程煤矸声信号特征提取与分类方法[J]. 矿业科学学报,2021,6(6):711-720.YUAN Yuan,WANG Jiawen,ZHU Desheng,et al. Feature extraction and classification method of coal gangue acoustic signal during top coal caving[J]. Journal of Mining Science and Technology,2021,6(6):711-720. [13] 窦希杰,王世博,刘后广,等. 基于EMD特征提取与随机森林的煤矸识别方法[J]. 工矿自动化,2021,47(3):60-65.DOU Xijie,WANG Shibo,LIU Houguang,et al. Coal and gangue identification method based on EMD feature extraction and random forest[J]. Industry and Mine Automation,2021,47(3):60-65. [14] 王家臣,李良晖,杨胜利. 不同照度下煤矸图像灰度及纹理特征提取的实验研究[J]. 煤炭学报,2018,43(11):3051-3061.WANG Jiachen,LI Lianghui,YANG Shengli. Experimental study on gray and texture features extraction of coal and gangue image under different illuminance[J]. Journal of China Coal Society,2018,43(11):3051-3061. [15] 王家臣,潘卫东,张国英,等. 图像识别智能放煤技术原理与应用[J]. 煤炭学报,2022,47(1):87-101.WANG Jiachen,PAN Weidong,ZHANG Guoying,et al. Principles and applications of image-based recognition of withdrawn coal and intelligent control of draw opening in longwall top coal caving face[J]. Journal of China Coal Society,2022,47(1):87-101. [16] 贺海涛,王佳豪,张海峰,等. 基于U−Net的放煤状态控制关键技术研究[J]. 煤炭科学技术,2022,50(增刊2):237-243.HE Haitao,WANG Jiahao,ZHANG Haifeng,et al. Research on key technology of coal caving state control based on U-Net[J]. Coal Science and Technology,2022,50(S2):237-243. [17] SONG Qingjun,JIANG Haiyan,ZHAO Xieguang,et al. An automatic decision approach to coal-rock recognition in top coal caving based on MF-Score[J]. Pattern Analysis and Applications,2017,20(4):1307-1315. doi: 10.1007/s10044-017-0618-7 [18] 张国军,章振海,汪玉凤,等. 综放采煤自动化煤岩识别传感器的研究[J]. 传感器与微系统,2011,30(2):14-16.ZHANG Guojun,ZHANG Zhenhai,WANG Yufeng,et al. Research on fully mechanized caving mining automation technology for coal rock recognition[J]. Transducer and Microsystem Technologies,2011,30(2):14-16. [19] 朱世刚. 综放工作面煤岩性状识别方法研究[D]. 北京:中国矿业大学(北京),2014.ZHU Shigang. Study on identification method of coal and rock properties in fully mechanized top-coal caving face[D]. Beijing:China University of Mining & Technology-Beijing,2014. [20] 米彦军,潘卫东,杨克虎,等. 黄玉川煤矿无人干预自动化放煤研究[J]. 工矿自动化,2021,47(增刊2):29-31,42.MI Yanjun,PAN Weidong,YANG Kehu,et al. Research of automatic top-coal caving without human intervention in Huangyuchuan Coal Mine[J]. Industry and Mine Automation,2021,47(S2):29-31,42. [21] 张守祥,张学亮,刘帅,等. 智能化放顶煤开采的精确放煤控制技术[J]. 煤炭学报,2020,45(6):2008-2020.ZHANG Shouxiang,ZHANG Xueliang,LIU Shuai,et al. Intelligent precise control technology of fully mechanized top coal caving face[J]. Journal of China Coal Society,2020,45(6):2008-2020. -
点击查看大图
图(13) / 表(3)
计量
- 文章访问数: 40
- HTML全文浏览量: 20
- PDF下载量: 6
- 被引次数: 0
