综采工作面煤壁片帮识别关键技术研究.pdf

硕士学位论文 综采工作面煤壁片帮识别关键技术研究 Research on Key Technologies of Rib Spalling Recognition on the Fully Mechanized Coal Mining Face 作 者徐荣鑫 导 师谭 超 副教授 中国矿业大学 二○一七年四月 万方数据 中图分类号 TD676 学校代码 10290 UDC 621 密 级 公开 中国矿业大学 硕士学位论文 综采工作面煤壁片帮识别关键技术研究 Research on Key Technologies of Rib Spalling Recognition on the Fully Mechanized Coal Mining Face 作 者 徐荣鑫 导 师 谭超 副教授 申请学位 工学硕士 培养单位 机电工程学院 学科专业 机械电子工程 研究方向 煤矿机电装备自动化 答辩委员会主席 韩正铜 教授 评 阅 人 二○一七年四月 万方数据 学位论文使用授权声明学位论文使用授权声明 本人完全了解中国矿业大学有关保留、使用学位论文的规定，同意本人所撰 写的学位论文的使用授权按照学校的管理规定处理 作为申请学位的条件之一， 学位论文著作权拥有者须授权所在学校拥有学位 论文的部分使用权， 即①学校档案馆和图书馆有权保留学位论文的纸质版和电 子版，可以使用影印、缩印或扫描等复制手段保存和汇编学位论文；②为教学和 科研目的，学校档案馆和图书馆可以将公开的学位论文作为资料在档案馆、图书 馆等场所或在校园网上供校内师生阅读、浏览。另外，根据有关法规，同意中国 国家图书馆保存研究生学位论文。 保密的学位论文在解密后适用本授权书。 作者签名 导师签名 年 月 日 年 月 日 万方数据 致谢致谢 时光荏苒， 转眼间三年的研究生生活即将结束。 回首走过的岁月， 感慨万千， 对那些引导我、帮助我、激励我的人，心中充满无限感激。 首先感谢我的导师谭超副教授，本论文是在谭超副教授的悉心指导下完成 的。三年来，导师敏锐的思维、严谨的治学态度、渊博的学识、诚挚谦虚的品格 和宽厚善良的处世方式， 永远值得我学习和效仿。导师在我的学业上尤其是在论 文的撰写过程中，倾注了大量的心血，给予了我许多教诲和指导，这将使我终生 受益。三年来，导师还在生活方面给予了我诸多慈父般的关怀和爱护，使我在感 激之余暗下决心，我将更加努力，不辜负恩师的期望。 感谢课题组王忠宾、刘新华、杨寅威、韩振铎、姚新港、闫海峰、司垒等老 师， 在课题研究和科研实践中给予的热忱鼓励和悉心指导。 他们脚踏实地的作风、 平和谦虚的为人、团结奋进的精神风貌为我树立了良好的榜样，这种潜移默化的 作用将对我今后的工作、 学习产生不可估量的影响。在这里同样对他们致以深深 的敬意 三年的时间里， 课题组的兄弟姐妹在我的学习生活和实践环节中给予了莫大 的帮助和鼓励，我们朝夕相处，共同进步，感谢你们给予我的所有关心和帮助。 同窗之谊，我将终生难忘 在此更要感谢我生活学习了七年的母校中国矿业大学， 母校给了我一个 宽阔的学习平台，让我不断吸取新知，充实自己。 需要特别感谢的是我的父母。 父母的养育之恩无以为报，他们是我多年求学 路上的坚强后盾，在我面临人生选择的迷茫之际，为我排忧解难，他们对我无私 的爱与照顾是我不断前进的动力。 最后，感谢各位专家和学者在百忙之中审阅我的论文，并给予宝贵的指导， 在此谨向各位专家学者表示深深的谢意 万方数据 I 摘摘 要要 煤壁片帮是综采工作面常见的危害之一， 它的发生会导致液压支架泄漏以及 支架结构件损坏， 片帮量过大会导致工作面刮板输送机负载突变， 损坏驱动电机， 威胁采区电网稳定性， 影响整个综采工作面的生产安全。本文以识别煤壁片帮为 目标，研究了基于机器视觉的综采工作面煤壁片帮识别关键技术，提出了综采工 作面监控图像增强方法与煤壁片帮特征分析方法，实现了煤壁片帮危害程度评 估。主要工作及研究内容如下 （1）针对综采工作面煤壁片帮监控图像质量差的问题，提出了基于双边滤 波和单尺度 Retinex 的混合图像增强算法。实验结果表明混合图像增强算法对 综采工作面监控图像的增强效果在主观效果、对比度与信息熵方面较同态滤波、 直方图均衡等常规方法更优，更适用于综采工作面监控图像增强。 （2）建立了煤壁片帮特征分析体系，选取了片帮时间、片帮面积、片帮区 域高度和片帮中心高度 4 个煤壁片帮特征指标，给出了煤壁片帮特征分析方法， 实现了基于背景差分法的煤壁片帮特征分析。仿真结果表明分析所得特征的误 差较小，可为下一步煤壁片帮危害程度评估提供依据。 （3）确定了安全、轻微、中等和严重四个煤壁片帮危害程度，研究了基于 支持向量机（SVM）的煤壁片帮危害程度评估方法，并与 BP 神经网络、人工免 疫算法进行对比。仿真结果表明在煤壁片帮样本较少的情况下，SVM 评估正 确率高于 BP 神经网络、人工免疫算法。 （4）搭建煤壁片帮识别模拟实验平台，对混合图像增强算法、煤壁片帮特 征分析方法和煤壁片帮危害程度评估方法进行了验证，结果表明在不同光照、 雾化、灰尘环境下，混合图像增强算法可改善煤壁片帮图像质量，降低煤壁片帮 特征平均误差，提升煤壁片帮危害程度评估正确率 13.3，算法耗时稍有增加。 该论文有图 48 幅，表 11 个，参考文献 121 篇。 关键词关键词综采工作面；煤壁片帮识别；机器视觉；支持向量机 万方数据 III Abstract On the fully mechanized coal mining face, the rib spalling may cause the leakage and the structural damage of roof supports. Large-scale rib spalling may lead to the load-mutation of scraper conveyer, which may damage the driving motors, threaten the stability of power in working field and worsen the security of the fully mechanized coal mining face. To recognize the rib spalling, the key technologies of recognizing the rib spalling based on machine vision have been studied in this thesis. In order to assess the hazard level of rib spalling, the mixed algorithm for enhancing the monitoring image and the feature analysis of rib spalling were proposed. The main researches are as follows 1 To solve the problem that the low-quality monitoring images had on fully mechanized coal mining face, the mixed algorithm based on single-scale Retinex and bilateral filtering was proposed. The experimental results showed that, the proposed was more suitable for enhancing the quality of rib spalling monitoring image in aspects of subjective effect, contrast and comentropy than common s. 2 The feature analysis structure of rib spalling was built, four features time, area, height of rib spalling and rib spalling center height were analyzed, the analysis was proposed too. Simulation results showed that, the error of analysed value was small enough to support the assessment of rib spalling hazard level. 3 Four hazard level of rib falling safe, slight, medium and heavy were chosen. The assessment of rib spalling hazard level based on support vector machine SVM was studied, and the BP neural network and artificial immunity algorithm were taken as the comparison. The simulation results showed that SVM was better than the other two s in the case that the feature samples are few. 4 The simulation experiment plat was built and experiments were cuted. The results showed that, the mixed image enhancement algorithm could improve the quality of interrupted rib spalling image, decrease the average error of feature analysis and increase the accuracy of rib spalling assessment 13.3, but consumed more time. There are 48 figures, 11 tables and 121 references in this thesis. Keywords fully mechanized coal mining face; rib spalling recognition; machine vision; support vector machine 万方数据 V 目目 录录 摘摘 要要 ........................................................................................................................... I 目目 录录 .......................................................................................................................... V 图清单图清单 ........................................................................................................................ IX 表清单表清单 ....................................................................................................................... XII 变量注释表变量注释表 ............................................................................................................. XIII 1 绪论绪论 ........................................................................................................................... 1 1.1 课题来源与背景 .................................................................................................... 1 1.2 课题研究现状 ........................................................................................................ 3 1.3 课题研究内容与方法 ............................................................................................ 5 1.4 课题研究意义 ........................................................................................................ 6 1.5 论文结构 ................................................................................................................ 6 2 基于混合算法的综采工作面监控图像增强方法研究基于混合算法的综采工作面监控图像增强方法研究 .......................................... 8 2.1 综采工作面监控图像特性分析 ............................................................................ 8 2.2 基于双边滤波与单尺度 Retinex 的混合图像增强算法 ...................................... 9 2.3 基于混合算法的综采工作面监控图像增强实验分析 ...................................... 14 2.4 本章小结 .............................................................................................................. 22 3 基于背景差分法的煤壁片帮特征分析方法研究基于背景差分法的煤壁片帮特征分析方法研究 ................................................ 23 3.1 背景差分算法 ...................................................................................................... 23 3.2 基于背景差分法的煤壁片帮特征分析体系构建 .............................................. 30 3.3 煤壁片帮特征分析方法仿真与结果分析 .......................................................... 34 3.4 本章小结 .............................................................................................................. 38 4 基于支持向量机的煤壁片帮危害程度评估方法研究基于支持向量机的煤壁片帮危害程度评估方法研究 ........................................ 39 4.1 煤壁片帮危害程度评估问题 .............................................................................. 39 4.2 支持向量机 .......................................................................................................... 40 4.3 基于支持向量机的煤壁片帮危害程度评估模型 .............................................. 48 4.4 煤壁片帮危害程度评估方法的仿真与结果分析 .............................................. 51 4.5 本章小结 .............................................................................................................. 56 5 实验研究实验研究 ................................................................................................................. 57 5.1 煤壁片帮识别模拟实验平台设计 ...................................................................... 57 万方数据 VI 5.2 煤壁片帮识别软件设计 ...................................................................................... 59 5.3 实验方案与结果分析 .......................................................................................... 65 5.4 本章小结 .............................................................................................................. 70 6 总结与展望总结与展望 ............................................................................................................. 71 6.1 总结 ................................................................................................................. 71 6.2 展望 ................................................................................................................. 72 参考文献参考文献 ..................................................................................................................... 73 作者简历作者简历 ..................................................................................................................... 81 学位论文原创性声明学位论文原创性声明 ................................................................................................. 83 学位论文数据集学位论文数据集 ......................................................................................................... 85 万方数据 VII Contents Abstract ...................................................................................................................... III Contents .................................................................................................................... VII List of Figures ............................................................................................................ IX List of Tables ............................................................................................................ XII List of Variables ..................................................................................................... XIII 1 Introduction ............................................................................................................. 1 1.1 Origin and Background ........................................................................................... 1 1.2 Research Status ....................................................................................................... 3 1.3 Research Contents and s ............................................................................. 5 1.4 Research Significance ............................................................................................. 6 1.5 Structure of Thesis .................................................................................................. 6 2 Study on Monitoring Image Enhancement of Fully Mechanized Coal Mining Face Based on Mixed Algorithm ............................................................................ 8 2.1 Peculiarity Analysis of Monitoring Image of Fully Mechanized Coal Mining Face ................................................................................................................... 8 2.2 Mixed Algorithm for Image Enhancement Based on Single-scale Retinex Algorithm and Bilateral Filter ................................................................................. 9 2.3 Experimental Analysis of Image Enhancement of Fully Mechanized Coal Mining Face Based on Mixed Algorithm .......................................................................... 14 2.4 Summary ............................................................................................................... 21 3 Study on Feature Analysis of Rib Spalling Based on Background Subtraction ............................................................................................................ 23 3.1 Background Subtraction Algorithm ...................................................................... 23 3.2 Building of Feature Analysis System for Rib Spalling Based on Background Subtraction ............................................................................................................ 30 3.3 Simulation and Analysis of Feature Analysis of Rib Spalling ................ 34 3.4 Summary ............................................................................................................... 38 4 Study on the Assessment of Rib Spalling Hazard Level Based on Support Vector Machine ..................................................................................................... 39 4.1 Problem of Assessment of Rib Spalling Hazard Level ......................................... 39 万方数据 VIII 4.2 Support Vector Machine ....................................................................................... 40 4.3 Assessment Model of Rib Spalling Hazard Level Based on Support Vector Machine ................................................................................................................ 48 4.4 Simulation and Analysis of Rib Spalling Hazard Level Assessment ...... 51 4.5 Summary ............................................................................................................... 56 5 Experimental Study .............................................................................................. 57 5.1 Designing of Rib Spalling Recognition Experimental Plat .......................... 57 5.2 Software Design of Rib Spalling Recognition System ......................................... 59 5.3 Experimental Scheme and Result Analysis .......................................................... 65 5.4 Summary ............................................................................................................... 70 6 Summary and Forecast ......................................................................................... 71 6.1 Summary ............................................................................................................... 71 6.2 Forecast ................................................................................................................. 72 References ................................................................................................................... 73 Author’s Resume ........................................................................................................ 81 Declaration of Thesis Originality ............................................................................. 83 Thesis Data Collection ............................................................................................... 85 万方数据 IX 图清单图清单 图序号 图名称 页码 图 1-1 综采工作面“三机” 2 Figure 1-1 Three main machines on the fully mechanized coal mining face 2 图 1-2 综采工作面煤壁片帮冒顶 3 Figure 1-2 Rib spalling and roof fall on the fully mechanized coal mining face 3 图 2-1 综采工作面的“三机配套” 8 Figure 2-1 Three fully mechanized machines 8 图 2-2 Retinex 理论基本原理 9 Figure 2-2 Basic principle of Retinex 9 图 2-3 单尺度 Retinex 算法原理框图 10 Figure 2-3 Block diagram of the SSR a