垮落煤岩性状识别研究  

Reseaech on identification of caving coal and rock traits

作　　者：李一鸣[1] 符世琛 李瑞[1] 吴淼[1] 

机构地区：[1]中国矿业大学(北京)机电与信息工程学院,北京100083

出　　处：《工矿自动化》2017年第2期24-28,共5页Journal Of Mine Automation

基　　金：国家重点基础研究发展计划(973计划)资助项目(2014CB046300;2014CB046306)

摘　　要：针对综放工作面垮落煤岩性状识别的技术问题,提出了一种基于连续小波变换和改进奇异值分解的识别方法。采用基于单边Jacobi的奇异值分解(SVD)方法对小波系数矩阵进行分解,得到与小波系数矩阵列向量位置对应的奇异值向量,并将奇异值向量作为神经网络的输入向量来识别落煤和落岩2种工况。现场试验结果表明,基于连续小波变换与SVD得到的奇异值向量可用于识别垮落煤岩,但基于连续小波变换与改进SVD得到的奇异值向量具有更高的识别率。In order to recognize caving coal and rock traits in fully mechanized caving face, an identification method based on continuous wavelet transform and improved singular value decomposition （SVD） was proposed. The SVD method based on unilateral Jacobi is used to decompose wavelet coefficient matrix, so as to get singular value vectors corresponding to the column vector position of the wavelet coefficient matrix. The singular value vectors are used as input vector of neural network to identify two conditions of falling coal and falling rock. Field test results show that the singular value vectors acquired by the method based on continuous wavelet transform and SVD can be used to identify coal and rock, but the singular value vectors acquired by the method based on continuous wavelet transform and improved SVD has higher identification rate.

关 键 词：煤炭开采 综放工作面 垮落煤岩 煤岩性状识别 连续小波变换 奇异值分解 神经网络 SVD 

分 类 号：TD67[矿业工程—矿山机电]