基于MRU-Net++的极薄煤层综采面煤岩界面图像识别  

Coal-rock interface image recognition based on MRU-Net++for extremely thin coal seam fully-mechanized mining face

作　　者：张传伟[1,2] 何正伟 路正雄 李林岳 龚凌霄 张刚强 潘巧娜 ZHANG Chuanwei;HE Zhengwei;LU Zhengxiong;LI Linyue;GONG Lingxiao;ZHANG Gangqiang;PAN Qiaona(School of Mechanical Engineering,Xi’an University of Science and Technology,Xi’an 710054,China;Shaanxi College of Communications Technology,Xi’an 710018,China;School of Safety Science and Engineering,Xi’an University of Science and Technology,Xi’an 710054,China)

机构地区：[1]西安科技大学机械工程学院,陕西西安710054 [2]陕西交通职业技术学院,陕西西安710018 [3]西安科技大学安全科学与工程学院,陕西西安710054

出　　处：《煤炭科学技术》2024年第11期103-116,共14页Coal Science and Technology

基　　金：陕西省重点研发计划资助项目(2022GD-TSLD-63,2022GD-TSLD-64);陕西省教育厅资助项目(23JP100)。

摘　　要：煤岩识别是极薄煤层综采工作面实现智能化开采的核心技术之一。针对极薄煤层开采时煤岩分界线自然裸露在外的特殊情况,提出了一种基于MRU-Net++网络的极薄煤层煤岩图像识别方法。该网络以U-Net++为基础,通过“剪枝”技术对U-Net++结构进行优化,在U-Net++网络性能损失最小的同时减少其复杂度,以提高运算速度;采用MobileNetV2轻量化网络,构建一个基于MobileNetV2的核心骨干网络,替代U-Net++原有的网络架构,显著降低了模型的参数数量,提高了模型分割效率;同时引入含有通道注意力机制的ResNeSt模块来增强对煤岩图像边缘细节特征的提取能力,提高分割精度。利用液压支架上的防爆摄像仪采集极薄煤层综采工作面煤岩图像,获取具有煤岩分布信息的高清煤岩图像并对图像进行预处理,创建含有2 536个样本的极薄煤层综采面煤岩图像数据集。设置消融试验,验证改进部分对网络性能的影响,并将该模型与经典FCN、U-Net、U-Net++网络模型进行对比,利用自适应学习算法训练各网络模型,选择像素准确度(Pixel Accuracy, P_(A))、交并比(Intersection over Union, IOU)及测试时间等关键指标评估模型分割效果。结果显示,MRU-Net++网络模型的平均像素准确度P_(AM)和交并比I_(OUM)分别为97.15%和94.16%,模型占用内存25.71 M,每张图像的平均测试时间28.61 ms,充分证明了该方法在极薄煤层特殊环境下进行煤岩识别任务的可行性与有效性。Coal rock recognition is one of the core technologies to realize intelligent mining in the integrated mining face of extremely thin coal seam.Aiming at the special situation that the coal-rock boundary is naturally exposed during the mining of extremely thin coal seams,an image recognition method based on MRU-Net++network was proposed for coal-rock image recognition of extremely thin coal seams.The network is based on U-Net++,and the structure of U-Net++was optimized by the method of“pruning”,which reduces the complexity of U-Net++network while minimizing the loss of its performance in order to improve the computing speed.MobileNetV2 lightweight net-work was used to construct a core backbone network based on MobileNetV2,replacing the original network architecture of U-Net++,which significantly reduces the number of parameters of the model and improves the efficiency of the model segmentation.At the same time,the ResNeSt module,which contains the channel attention mechanism,was introduced to enhance the ability of extracting the detailed features of the edges of the coal and rock images,and to increase the segmentation accuracy.The explosion-proof camera on the hydraulic support was used to collect the coal rock images of the comprehensive mining face in the extremely thin coal seam,and the high-definition coal rock images with coal rock distribution information were acquired and preprocessed to create a coal rock image dataset of the comprehensive mining face of the extremely thin coal seam containing 2536 samples.The ablation test was set up to verify the effect of the improved part on the network performance.The model was compared with the classical FCN,U-Net,and U-Net++network models and the network models were trained using adaptive learning algorithms.Key indexes such as Pixel Accuracy(P_(A)),Intersection over Uni-on(I_(OU))and test time were selected to evaluate the model segmentation effect.The results show that the Mean Pixel Ascuracy(P_(AM))and Mean Intersection over Union(IOUM)of the MRU-Net++networ

关 键 词：极薄煤层 煤岩识别 语义分割 U-Net++网络模型 深度学习 

分 类 号：TD67[矿业工程—矿山机电]