基于光学图像的煤矸石识别方法以其设备稳定、安全系数高、成本低、易于实现成为现代煤矸识别方法关注和研究的热点，其中提取目标图像和特征提取是有效识别煤矸石的前提。目前，煤矸识别研究中，在提取目标图像上存在分割准确度和时间效率上不能很好兼顾的问题，对煤矸特征存在研究不全面不深入的问题，基于此，本文提出以下改进方法。

针对传统二维熵法计算量大、耗时长的问题，引入灰狼优化算法，提出一种基于改进非线性控制因子的灰狼优化二维熵阈值分割算法。该方法利用三次函数正半轴单调性改进灰狼优化算法中的控制因子，使其由线性迭代转换为非线性迭代，使得算法的全局搜索寻优能力与局部搜索寻优能力达到更好的平衡；通过标准测试函数验证了改进灰狼优化算法在寻优能力和迭代速度上的有效性。本文算法在煤和矸石分割准确度上比二维熵法分别提高13.95%、9.26%，分割时间分别快2.21倍、1.77倍。

在煤和矸石传统灰度统计特征及灰度共生矩阵统计特征（Gray-level Co-occurrence Matrix，GLCM）基础上，进一步研究了局部二值模式（Local Binary Pattern，LBP）特征、方向梯度直方图（Histogram of Oriented Gradient, HOG）特征，并引入表征信号复杂度的样本熵、近似熵、排列熵特征。

分别选取单特征和组合特征与支持向量机结合进行煤与矸石识别。实验结果表明在灰度特征与GLCM特征基础上，引入HOG特征、LBP特征、样本熵特征后平均识别率分别提升了13.79%、16.99%、1.12%。将多种图像特征组合识别的平均识别率为92.85%，提升了17.9%。

The method of coal and gangue identification based on optical image has become the focus of modern coal and gangue identification due to its stable equipment, high safety factor, low cost and easy implementation. Among them, target image extraction and feature extraction are the premise of effective identification of gangue. At present, in the research on coal and gangue identification, the segmentation accuracy and time efficiency of extracting target images cannot be well considered, and the research on coal and gangue characteristics is not comprehensive and in-depth, So, the following improvements methods are proposed in this thesis.

In order to solve the problem of large amount of calculation and longtime-consuming of tradition two-dimensional entropy method, gray wolf optimization algorithm is introduced,and a gray wolf optimization two-dimensional entropy segmentation algorithm based on improved nonlinear control factor is proposed. This method uses the monotonicity of the positive semi-axis of the cubic function to improve the control factor in the gray wolf optimization algorithm, which is transformed from linear iteration to nonlinear iteration, so that the global search optimization ability and local search optimization ability of the algorithm can achieve a better balance. The effectiveness of the improved gray wolf optimization algorithm in search ability and iteration speed is verified by the standard test function. The accuracy of this algorithm in coal and gangue segmentation is 13.95% and 9.26% higher than that of two-dimensional entropy method, and the segmentation time is 2.21 times and 1.17 times faster respectively.

In addition to the traditional gray level statistical features and gray level co-occurrence matrix (GLCM), the characteristics of local binary pattern (LBP) and histogram of oriented gradient (HOG) are further studied. Moreover, sample entropy, approximate entropy and permutation entropy are introduced to characterize signal complexity.

The signal feature and combined feature are combined with support vector machine to recognize coal and gangue. The experimental results show that the average recognize rate is improved by 13.79%, 16.99%, and 1.12% after introducing HOG feature, LBP feature and sample entropy feature, respectively. The average recognize rate of combing multiple image features is 92.85%, which is increased by 17.9%.

[1]Ji Feng Li,Zhong Yu Ma,Ya Xiong Zhang,et al. Analysis on energy demand and C-O2 emissions in China following the Energy Production and Consumption Revolut-ion Strategy and China Dream target[J]. Advances in Climate Change Research,2018,9(1).16-26.

[2]谢和平,王金华,王国法,等.煤炭革命新理念与煤炭科技发展构想[J].煤炭学报,2018,43(05):1187-1197.

[3]杨富强,陈怡心.“十四五”推动能源转型实现碳排放达峰[J].阅江学刊,2021,13(04):73-85+124.

[4]曹现刚,李莹,王鹏,等.煤矸石识别方法研究现状与展望[J].工矿自动化,2020,46(01):38-43.

[5]廖阳阳.基于BP网络和图像处理的煤矸石的动态识别[J].工业控制计算机,2015,28(07):119-120+122.

[6]米强,徐岩,刘斌,等.煤与矸石图像纹理特征提取方法[J].工矿自动化,2017,43(05):26-30.

[7]Su L,Cao X,Ma H,et al. Research on Coal Gangue Identification by Using Convol-utional Neural Network[C].2018 2nd IEEE Advanced Information Management,Communicates,Electronic and Automation Control Conference (IMCEC).IEEE,2018:810-814.

[8]薛光辉,李秀莹,钱孝玲,等.基于随机森林的综放工作面煤矸图像识别[J].工矿自动化,2020,46(05):57-62.

[9]张永超,于智伟,丁丽林.基于机器视觉的煤矸石检测研究[J].煤矿机械,2021,42(04):32-34.

[10]苏宝金,陈波,贺靖峰,等.煤与矸石灰度直方图的差异研究[J].洁净煤技术,2011,17(06):96-98.

[11]伍云霞,田一民.基于字典学习的煤岩图像特征提取与识别方法[J].煤炭学报,2016,41(12):3190-3196.

[12]余乐.一种煤和煤矸石图像识别的新方法[J].现代计算机(专业版),2017,(17):66-70.

[13]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.

[14]陈立,杜文华,曾志强,等.基于小波变换的煤矸石自动分选方法[J].工矿自动化,2018,44(12):60-64.

[15]沈宁,窦东阳,杨程,等.基于机器视觉的煤矸石多工况识别研究[J].煤炭工程,2019,51(01):120-125.

[16]李曼,段雍,曹现刚,等.煤矸分选机器人图像识别方法和系统[J].煤炭学报,2020,45(10):3636-3644.

[17]王鹏,曹现刚,夏晶等.基于机器视觉的多机械臂煤矸石分拣机器人系统研究[J].工矿自动化,2019,45(09):47-53.

[18]何克焓.基于卷积神经网络的煤矸石图像识别研究[J].河南科技,2020,(04):66-68.

[19]赵明辉.一种煤矸石优化识别方法[J].工矿自动化,2020,46(07):113-116.

[20]徐志强,吕子奇,王卫东,等.煤矸智能分选的机器视觉识别方法与优化[J].煤炭学报,2020,45(06):2207-2216.

[21]曹珍贯,吕旻姝,张宗唐.基于热成像技术和深度学习的煤矸石识别方法[J].湖南工程学院学报(自然科学版),2021,31(01):48-52.

[22]李曼,杨茂林,刘长岳,等.基于图像的煤矸分选中图像照度调节方法研究[J].煤炭学报,2021,07(04):1-8.

[23]曹现刚,刘思颖,王鹏,等.面向煤矸分拣机器人的煤矸识别定位系统研究[J].煤炭科学技术,2021:1-11

[24]郭永存,王希,何磊,等.基于TW-RN优化CNN的煤矸识别方法研究[J/OL].煤炭科学技术,2021:1-9.

[25]Hou,Wei. Identification of Coal and Gangue by Feed-forward Neural Network Base-d on Data Analysis[J]. International Journal of Coal Preparation & Utilization, 2017:1-11.

[26]Lei S,Xiao X,Zhang M, et al. Visual classification method based on CNN for coalgangue sorting robots[C].2020 5th International Conference on Automation, Control and Robotics Engineering (CACRE).2020:543-547.

[27]庞尚钟,李博,王学文,等.基于机器视觉的煤矸识别系统设计及试验研究[J].煤炭工程,2021,53(02):141-146.

[28]雷世威,肖兴美,张明.基于改进YOLOv3的煤矸识别方法研究[J].矿业安全与环保,2021,48(03):50-55.

[29]谭春超,杨洁明.煤与矸石图像灰度信息和纹理特征的提取研究[J].工矿自动化,2017,43(04):27-31.

[30]陈雪梅,张晞,徐莉莉,等.煤与矸石分形维数的差异研究[J].煤炭科学技术,2017,45(07):196-199.

[31]饶中钰,吴景涛,李明.煤矸石图像分类方法[J].工矿自动化,2020,46(03):69-73.

[32]郜亚松,张步勤,郎利影.基于深度学习的煤和矸石识别技术研究与实现[J].煤炭科学技术,2021:1-8.

[33]Li W,Wang Y,Fu B,et al. Coal and Coal Gangue Separation Based on Computer Vi-sion[C].2010 Fifth International Conference on Frontier of Computer Science and Technology.IEEE,2010:467-472.

[34]兰添才,郑汉垣.基于纹理特征融合的煤矸石分选技术研究[J].龙岩学院学报,2008,26(06):56-59.

[35]PU Y,APELD B,SZMIGIEL A,et al.Image Recognition of Coal and Coal Gangue U-sing a Convolutional Neural Network and Transfer Learning[J].Energies,2019,12(9):1735.

[36]Ma X.Coal Gangue Image Identification and Classification with Wavelet Transform[C].International Conference on Intelligent Computation Technology & Automation.IEEE,2009(1):562-565.

[37]Liang H,Cheng H,Ma T,et al. Identification of Coal and Gangue by Self-Organizin-g Competitive Neural Network and SVM[C].2010 Second International Conference on Intelligent Human-Machine Systems and Cybernetics.IEEE,2010(2):41-45.

[38]HARALICK R M,SHANMUGAM K,DINSTEIN I. Textural Features for Image Classification[J].IEEE Transactions on Systems,Man,and Cybernetics,1973,SMC-3(6):610-621.

[39]马岩.煤矸图像识别的深度学习算法及其关键技术研究[D].中国矿业大学(北京),2019.

[40]雷世威,肖兴美,张明.基于改进YOLOv3的煤矸识别方法研究[J].矿业安全与环保,2021,48(03):50-55.

[41]ABUTALEB A S. Automatic thresholding of gray-level pictures using two-dimensio-nal entropy[J].Computer Vision Graphics and Image Processing,1989,47(1):22-32.

[42]何敏,王培培,蒋慧慧.基于SVM和纹理的煤和煤矸石自动识别[J].计算机工程与设计,2012,33(03):1117-1121.

[43]陈雪梅,张晞,徐莉莉,等.煤与矸石分形维数的差异研究[J].煤炭科学技术,2017,45(07):196-199.

[44]董炯威. 基于多特征融合的图像复杂度评价及应用[D].西安科技大学,2020.

[45]JITKONGCHUEN D，PHAIDANG P. Grey wolf algorithm with borda count for feature selection in classification[C]//2018 3rd International Conference on Control and Robotics Engineering,IEEE, 2018:238-242.

[46]SUN Z,LU W,XUAN P,et al.Separation of gangue from coal based on supplementa-ry texture by morphology[J].International Journal of Coal Preparation and Utilization,2019,0(0):1-17.

[47]Seyedali Mirjalili, Seyed Mohammad Mirjalili, Andrew Lewis. Grey Wolf Optimizer[J].Advances in Engineering Software,2014(69): 1-4.

[48]Gai W,Qu C,Liu J,et al. An improved gray wolf algorithm for global optimization[C]. 2018 Chinese Control And Decision Conference (CCDC),2018:2494-2498.

[49]LUO K. Enhanced gray wolf optimizer with a model for dynamically estimating th-e location of the prey[J], Applied Soft Computing, 2019, 77:225-235.

[50]栗方.多目标优化算法标准测试函数寻优研究[J].电脑知识与技术,2020,16(23):203-206.

[51]CHEN X, SOLOMON I, CHON K. Comparison of the use of approximate entropy and sample entropy: Applications to neural respiratory signal[C]. International Conference of the Engineering in Medicine ＆ Biology Society. IEEE, 2006:4212-4215．

[52]MENAYO R, ENCARNACION. Sample entropy-based analysis of differential and traditional training effects on dynamic balance in healthy people[J] .Journal of Motor Behavior,2014, 46(2):73-82.

[53]王娇,罗燕,李德玉,林江莉,汪天富,彭玉兰.B超图像复杂性特征分析方法诊断脂肪肝[J].中国医学影像技术,2006(01):135-138.

[54]韦海成,王生营,许亚杰,赵静,肖明霞.样本熵融合聚类算法的森林火灾图像识别研究[J].电子测量与仪器学报,2020,34(01):171-177.