液压支架姿态智能感知系统及基于BP神经网络决策研究.pdf

工程硕士专业学位论文 液压支架姿态智能感知系统及基于 BP 神经 网络决策研究 Research on the Posture Intelligent Sensing System of the Hydraulic Support and the Decision-making Based on the BP Neural Network 作者谷超 导师陆菜平教授 中国矿业大学 二〇一九年五月 国家自然科学基金资助（51874276） 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 中图分类号TD326学校代码10290 UDC622密级公开 中国矿业大学 工程硕士专业学位论文 液压支架姿态智能感知系统及基于 BP 神经网络 决策研究 Research on the Posture Intelligent Sensing System of the Hydraulic Support and the Decision-making Based on the BP Neural Network 作者谷超导师陆菜平教授 申请学位 工程硕士专业学位培养单位矿业工程学院 学科专业矿业工程研究方向智能化开采 答辩委员会主席黄艳利评 阅 人盲审 二〇一九年五月 致致谢谢 本文是在陆菜平教授、 方新秋教授的悉心指导下完成的， 从论文的选题到整个撰写与修 改过程，都凝聚着导师辛勤的汗水。两位导师渊博的知识、深厚的学术造诣、敏锐的思维和 洞察力、严谨求实的治学态度、丰富的工作经验和诲人不倦的师者风范，时刻激励着我不断 向前努力。在科研上严格要求我们，教导我们要踏踏实实的做学问；生活上无微不至的关心 我们，帮助我们排忧解难，使我们能全身心的投入到科研当中。值此论文完成之际，谨向我 的二位导师致以衷心的感谢。 在论文撰写过程中，得到了薛广哲博士、梁敏富博士、吴刚博士、李虎威博士、刘洋博 士、张恒博士、马盟师兄、刘兴国师兄、陈宁宁师兄、宁耀圣师兄、冯裕堂师兄、卢海洋师 兄、魏涛、尹超超和张钰庚等实验室其他师兄弟们以及多年挚友曹海岗的诸多支持和帮助， 在此表示深深的感谢。 感谢我的校外导师郑建平高工对我的指导和教诲， 让我在专业知识水平和实践能力方面 获得了较大的提高， 并感谢中国华电隆德煤矿的领导们和工程技术人员对现场项目的实施给 予了大力的支持和密切的配合， 论文也包含他们努力的成果和智慧的结晶， 在此一并表示感 谢。 论文得到国家自然科学基金资助（51874276），在此表示感谢。 感谢我的母校中国矿业大学， 感谢图书馆的工作人员为我的学习提供丰富的资源， 感谢 每一位帮助和关心过我的老师和领导。 感谢家人、 同学和朋友在生活学习和论文撰写过程中 的关心和帮助。 最后，感谢各位专家、教授在百忙之中评审本文，由于时间仓促和作者水平有限，错误 和疏漏之处在所难免，恳请批评和指正。 I 摘摘要要 在煤矿生产中，由于工作面环境恶劣，回采条件艰苦，提高煤矿设备智能化 水平对安全高效生产有重要意义。在此背景下，本文以两柱掩护式液压支架作为 基础设备，构建了支架的光纤姿态智能感知系统，并对支架顶梁姿态决策问题进 行了深入研究。主要的研究内容如下 （1）分析了光纤光栅传感技术的结构、分类、感知原理以及温度、应力（应 变）的监测原理；结合支架姿态类型以及两柱掩护式液压支架结构特征，建立支 架姿态模型，并利用矢量闭环理论对其进行解算；最后，基于上述理论分析，完 成了支架姿态智能感知系统的构建。 （2）研发设计了感应梁式 FBG 倾角传感器。利用 Ansys Workbench 对其进 行数值仿真研究， 采用试验研究的方法对其性能以及与支架姿态的结合度进行测 试。研究结果表明在全量程范围内-2525），传感器灵敏度理论值为 51.78pm/，实测值为 51.25pm/，灵敏性较好，且其具有较高的稳定性，与支架 姿态匹配性良好，符合支架姿态感知要求。 （3）构建了基于 BP 神经网络的顶梁姿态决策模型。通过分析支架顶梁姿 态的影响因素及姿态智能感知系统的监测量，确定了顶梁的决策指标体系；结合 BP 神经网络的相关理论，给出了决策模型的相关参数，即输入层和输出层的神 经元个数分别为 17 个和 1 个，隐含层神经元个数范围为 415 个，学习速率为 0.5，期望误差设置为 0.00001。 （4） 在 MATLAB 平台中对基于 BP 神经网络顶梁姿态决策模型进行仿真与 分析。选取隆德 101 工作面进行液压支架姿态智能感知系统的安装与布置，对 81支架在推进 100m 范围内姿态信息进行数据采集，然后利用该数据对网络模 型在 MATLAB 中进行学习与测试。仿真结果表明trainlm 为最佳的训练函数， 隐含层神经元节点数最优值为 10 个；模型所产生的绝对误差范围 00.06，相对 误差的范围为 02.1，证明了模型的预测精度高，稳定性强；其平均绝对误 差为 0.021，平均相对误差为 0.70，均符合决策时要求，说明模型的有效性。 该论文有图 78 幅，表 10 个，参考文献 83 篇。 关键词关键词支架姿态；光纤传感技术；智能感知系统；BP 神经网络 II Abstract In coal mine production, it is of great significance to improve the intelligent level of coal mine equipment for safe and efficient production due to the harsh working face environment and difficult mining conditions. In this context, the optical fiber posture intelligent sensing system of the support is constructed by using the two-column shield hydraulic support as the basic equipment, and the attitude decision problem of the top beam of the support is deeply studied in this paper. The main contents of the study are as follows 1 First,analyzing the structure, classification, sensing principle and monitoring principle of temperature and stress（strain）of optical fiber sensing technology. Then, through the analysis of the type of support and the structure characteristics of the two-prop shield hydraulic support, the posture model of the support is established and solved by vector closed-loop theory. Finally, according to the above-mentioned theoretical analysis, the posture intelligent sensing system of the support are constructed . 2 The inducting beam FBG tilt sensor has been developed and designed. Numerical simulation was carried out by using Ansys workbench, and the perance and attitude of the support were tested by the of laboratory research. The results show that in the range of measurement, the sensitivity of the sensor is better, the theoretical value is 51.78pm/, the measured value is 51.25pm/, and it has high stability and adaptability to the posture of the support. 3 The posture decision model of top beam based on BP neural network is constructed. The decision index system of the top beam is determined by analyzing the influencing factors of the support top beam and the monitoring measurement of the attitude sensing system. Combined with the theory of BP neural network, the specific parameters of the decision model are determined, that is, the number of neurons in the layer and the output layer is 17 and 1 respectively, the number of neurons in the hidden layer is 4 15, and the learning rate is 0.5, Expected error set to 0.00001. 4 The posture decision model of top beam based on BP neural network is simulated and analyzed in MATLAB plat. The Longde 101 working face was selected to install and arrange the hydraulic support attitude sensing system. The 81 support was collected for data acquisition in the range of 100, and then the data was used to learn and test the network model in MATLAB.The simulation results show III that trainlm is the best training function and the optimal number of neurons in the hidden layer is 10; The absolute error range of the model is 00.06and the relative error range is 02.1. It is proved that the model has high prediction precision and strong stability. The average absolute error is 0.021and the average relative error is 0.70, which accords with the requirements of decision-making, which shows the validity of the model. This thesis has78 figures, 10 tables and 83 references. Keywords posture of supports; optical fiber sensing technology; intelligent sensing system; BP neural network IV 目目录录 摘摘要要............................................................................................................................ I 目目录录..........................................................................................................................IV 图清单图清单...................................................................................................................... VIII 表清单表清单...................................................................................................................... XIII 变量注释表变量注释表...............................................................................................................XIV 1 绪论绪论............................................................................................................................1 1.1 问题的提出及研究意义.........................................................................................1 1.2 国内外研究现状.....................................................................................................2 1.3 研究内容、方法和技术路线.................................................................................5 2 液压液压支架姿态感知系统的构建与实现支架姿态感知系统的构建与实现....................................................................8 2.1 光纤光栅传感技术基本理论及其特性.................................................................8 2.2 液压支架姿态模型的构建...................................................................................12 2.3 支架的姿态智能感知系统的构建.......................................................................17 2.4 本章小结...............................................................................................................23 3 光纤光栅光纤光栅倾角传感器测量原理及其测试倾角传感器测量原理及其测试..............................................................24 3.1 光纤光栅倾角传感器基本结构...........................................................................24 3.2 光纤光栅倾角传感器的力学分析.......................................................................27 3.3 光纤光栅倾角传感器的仿真研究.......................................................................30 3.4 光纤光栅倾角传感器性能测试...........................................................................34 3.5 光纤光栅倾角传感器与支架姿态的匹配性能测试...........................................38 3.6 本章小结...............................................................................................................41 4 基于基于 BP 神经网络的支架顶梁姿态决策模型研究神经网络的支架顶梁姿态决策模型研究...............................................43 4.1 智能支架顶梁姿态决策指标体系.......................................................................43 4.2 BP 神经网络的基本理论......................................................................................48 4.3 基于 BP 神经网络的顶梁姿态决策模型............................................................53 4.4 本章小结...............................................................................................................56 5 基于基于 BP 神经网络顶梁决策实例仿真与分析神经网络顶梁决策实例仿真与分析.......................................................57 V 5.1 工程地质概况.......................................................................................................57 5.2 液压支架姿态感知系统布置...............................................................................58 5.3 顶梁姿态决策模型仿真与分析...........................................................................60 5.4 本章小结...............................................................................................................73 6 结论结论..........................................................................................................................74 参考文献参考文献......................................................................................................................76 作者简历作者简历......................................................................................................................81 学位论文原创声明学位论文原创声明......................................................................................................82 学位论文数据集学位论文数据集..........................................................................................................83 VI Contents Abstract.......................................................................................................................ⅡⅡ Contents......................................................................................................................VI List of Figures..........................................................................................................VIII List of Tables............................................................................................................XIII List of Variables......................................................................................................XIV 1 Introduction............................................................................................................... 1 1.1 Introduction of the Problem and the Meaning of the Research................................1 1.2 Research Status at Home and Abroad...................................................................... 2 1.3 Research Contents, and Technical Route....................................................5 2 Establishment and Realization of Posture Sensing System for Hydraulic support...........................................................................................................................8 2.1 Basic Theory and Characteristics of Fiber Optic Sensing Technology....................8 2.2 Posture Model Establishment of Hydraulic Support..............................................12 2.3 The Construction of posture sensing system based on Intelligent support............ 17 2.4 Brief Summary.......................................................................................................23 3 Test for Measurement Mechanism of FBG Tilt Sensor........................................24 3.1 Structure of Fiber Bragg Grating Tilt Sensor.........................................................24 3.2 Mechanical Analysis of Fiber Bragg Grating Tilt Sensor...................................... 27 3.3 Numerical Analysis of FBG Tilt Sensor.................................................................30 3.4 Perance Test of Fiber Bragg Grating Tilt Sensor............................................34 3.5 Tests of Coupling Capability Between Support Posture and Fiber Bragg Grating Tilt Sensor.....................................................................................................................38 3.6 Brief Summary.......................................................................................................41 4 Study on Posture Decision-making Model of support Top Beam based on BP Neural Network.......................................................................................................... 43 4.1 Decision-making Index System For Intelligent Support Top Beam Posture..........43 4.2 The Basic Theory of BP Neural Network...............................................................48 4.3 Posture Decision-making Model of Top Beam based on BP Neural Network.......53 4.4 Brief Summary.......................................................................................................56 5 Simulation andAnalysis of Top Beam Decision-making Based on BP Neural VII Network.......................................................................................................................57 5.1 General Geological Situation of Engineering.........................................................57 5.2Arrangement of Posture Sensing System for Hydraulic Support...........................58 5.3 Simulation and Analysis of Top Beam Posture Decision-making Model..............60 5.4 Brief Summary.......................................................................................................73 6 Conclusions.............................................................................................................. 74 References................................................................................................................... 76 Authors Resume........................................................................................................ 81 Declaration of Thesis Originality..............................................................................82 Thiesis Data Collection.............................................................................................. 83 VIII 图清单图清单 图序号图名称页码 图 1-1技术路线图6 Figure 1-1The diagram of technology route6 图 2-1光纤光栅结构示意图8 Figure 2-1Schematic diagram of FBG structure8 图 2-2光纤光栅感知示意图9 Figure 2-2Fiber Schematic diagram of FBG sensing9 图 2-3光谱图9 Figure 2-3Spectrogram9 图 2-4光纤光栅轴向均匀受力结构图10 Figure 2-4Axial uni force structure diagram of FBG10 图 2-5液压支架顶梁姿态12 Figure 2-5Roof posture of hydraulic supports12 图 2-6液压支架底座姿态12 Figure 2-6Base posture of hydraulic supports12 图 2-7液压支架支护高度13 Figure 2-7Support height of hydraulic supports13 图 2-8两柱式掩护液压支架实物图13 Figure 2-8Physical drawing of two-prop shield hydraulic support13 图 2-9液压支架姿态模型图15 Figure 2-9Model diagram of hydraulic support posture15 图 2-10支架姿态解算流程图17 Figure 2-10Flow chart for posture calculation of support17 图 2-11智能液压支架结构图18 Figure 2-11Structure diagram of intelligent hydraulic support18 图 2-12光纤光栅倾角传感器18 Figure 2-12Fiber bragg grating tilt sensor18 图 2-13光纤光栅压力传感器19 Figure 2-13Fiber bragg grating pressure sensor19 图 2-14光纤光栅压力传感器结构图19 Figure 2-14Structure diagram of fiber bragg grating pressure sensor19 图 2-15隔爆外壳以及光纤传感分析仪实物图20 Figure 2-15Ph