煤矿通风机轴承故障诊断方法研究.pdf
硕士学位论文 煤矿通风机轴承故障诊断方法研究 Research on Fault Diagnosis s of Coal Mine Ventilator Bearings 作 者刘迪 导 师郭星歌副教授 中国矿业大学 二〇二〇年六月 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 中图分类号 TP391.4 学校代码 10290 UDC 621.39 密 级 公开 中国矿业大学 硕士学位论文 煤矿通风机轴承故障诊断方法研究 Research on Fault Diagnosis s of Coal Mine Ventilator Bearings 作 者 刘迪 导 师 郭星歌 副教授 申请学位 工学硕士学位 培养单位 信息与控制工程学院 学科专业 信息与通信工程 研究方向 矿山物联网 答辩委员会主席 华钢 评 阅 人 二○二○年六月 万方数据 致谢致谢 时光飞逝, 转眼间已在彭城求学近三年, 自己的硕士学习生活即将画上句号, 回忆起自己初见矿大,画面仿佛在昨日。在“勤奋、求实、进取、奉献”的校风 影响下,让我在三年的学习生活中获益良多,正如警世贤文勤奋篇中说的, “宝剑锋从磨砺出,梅花香自苦寒来” 。 感谢中国矿业大学信息与控制工程学院给 与我的科研学习平台,正如观书有感中说的, “半亩方塘一鉴开,天光云影 共徘徊。问渠那得清如许为有源头活水来” 。 饮水思源,我要特别感谢我的导师郭星歌副教授三年的教导,郭老师严谨认 真的科研态度、乐观随和的生活理念,深深启发了我,为我今后的工作生活指明 了方向。从论文的选题、论文的框架安排、仿真验证到最后的定稿,郭老师都给 与了细致地指导,并提出了详尽地修改意见。再次向郭老师表达最真诚地感谢 感谢课题组的钱建生教授、 张剑英教授在硕士期间给与我学习上的指导和帮 助感谢程德强老师、蔡利梅老师、李雷达老师、张国鹏老师在论文选题中给与 的意见,帮我分析了论文在内容、结构上的不足,并提出了改进意见,非常感谢 老师们提出的宝贵意见,让我更加清晰地明白自己论文写作的重点。 感谢华洋通信科技有限公司的马平姐在煤矿水泵、通风机、皮带项目上的指 导和帮助,为我之后的论文写作提供了第一手资料和思路。感谢吴响博士在专利 写作和论文数据获取上的指导和帮助。 感谢宋玉龙、吕晓波、季鹏、周嘉男、张凯歌等师兄师姐们无私的分享和帮 助。 感谢喻振杰、 曾尚琦、 李哲、 张宝山等小伙伴们在学习生活中的帮助与支持。 聚不是开始,散也不是结束,临别之际,祝君前程似锦。 感谢父母在我求学道路上的无私奉献和付出,父母是我最温馨的港湾,有了 他们的陪伴和支持,使我在今后的道路上更加自信。 气有浩然,学无止境。在以后的人生道路上,我必将不忘初心,砥砺前行。 最后, 非常感谢评阅本文的专家老师, 感谢您在百忙之中抽出时间评阅本文, 期待您的批评与指正。 万方数据 I 摘摘 要要 目前正处于煤矿智能化建设的关键阶段, 而通风机作为煤矿的 “矿井之肺” , 负责将井下对矿工有害的气体排出并带来新鲜的空气。如果发生故障,将会给企 业造成巨大的经济损失,并严重威胁井下人员的生命安全,故针对煤矿通风机故 障诊断的研究具有重要意义。 本文以通风机轴承为切入点,分析了当前通风机轴承的主要故障形式,针对 故障诊断流程中的特征向量提取和故障类型识别两方面来改进现有的故障诊断 模型。 (1)针对经验模态分解中端点效应和模态混叠问题,分别使用改进后的极 值点对称延拓法、集合经验模态分解(EEMD)进行改善。针对 EEMD 中虚假分量 数目多的问题,对固有模态函数的筛选准则进行改进,并引入到自适应白噪声的 完备总体经验模态分解算法中。 (2)针对遗传算法(GA)收敛速度和收敛精度差的问题,对遗传算法的遗 传算子进行改进。针对支持向量机(SVM)参数不易确定的问题,使用改进后的 遗传算法(IGA)来改善 SVM 参数寻优过程,构建 IGA-SVM 模型。结果表明,模 型有更好地收敛速度和收敛精度,提高了故障识别准确率。 (3)针对 SVM 模型样本训练用时长的问题,使用极限学习机(ELM)来替代 SVM。针对粒子群算法(PSO)早熟收敛、局部最优的问题,对 PSO 的惯性因子进 行改进,构建了一个类 S 形递减的惯性因子变化曲线。使用改进后的粒子群算法 (IPSO)与 IGA 算法相融合,构建 IGA-IPSO-ELM 模型。结果表明,模型具有训 练用时短、故障识别准确率高、鲁棒性强等特点。 该论文有图 59 幅,表 16 个,参考文献 77 篇。 关键词关键词煤矿通风机轴承;故障诊断;经验模态分解;SVM;ELM 万方数据 II Abstract At present, it is in the key stage of intelligent construction of coal mine. As the “lung of coal mine“, the ventilator is responsible for exhausting the harmful gas and bringing fresh air. If the ventilator breaks down, it will cause huge economic loss to the enterprise, and seriously threaten the life safety of the underground personnel. So the research on the fault diagnosis of coal mine ventilator is of great significance. This article takes the ventilator bearing as breakthrough point, and analyzes the main fault s of the current ventilator bearing. Aiming at the two aspects of feature vector extraction and fault type identification in the fault diagnosis process, the existing fault diagnosis model is improved. 1 Aiming at the problems in empirical mode decomposition, the improved extreme point symmetric extension is used to improve the endpoint effect, and the ensemble empirical mode decomposition EEMD is used to improve the modal aliasing. Aiming at the problem of the large number of false components in the ensemble empirical mode decomposition, the screening criteria of the intrinsic mode function were improved and introduced into the complete ensemble empirical mode decomposition with adaptive noise. 2 Aiming at the problem of poor convergence speed and precision of genetic algorithm GA, the genetic operator of genetic algorithm is improved. Aiming at the problem that the support vector machine SVM parameters are not easy to determine, improved genetic algorithm IGA is used to improve the SVM parameter optimization process, and an IGA-SVM model is constructed. The results show that the model has better convergence speed and convergence accuracy, it improves the accuracy of fault identification. 3 Aiming at the problem that samples training time of SVM model is long, an extreme learning machine ELM is used instead of SVM. Aiming at the problem of premature convergence and local optimization of particle swarm optimization PSO, the inertia factor of the particle swarm optimization algorithm is improved, and a similar S-shaped decreasing inertial factor curve is constructed. The improved particle swarm algorithm IPSO and IGA algorithm are used to construct the IGA-IPSO-ELM model. The results show that the model has the characteristics of short training time, high accuracy of fault recognition, and strong robustness. There are 59 figures, 16 tables and 77 references in this paper. 万方数据 III Keywords Bearing of coal mine ventilator; Fault diagnosis; empirical mode decomposition; SVM; ELM 万方数据 IV 目目 录录 摘要摘要................................................................................................................................ I 目录目录............................................................................................................................. IV 图清单图清单...................................................................................................................... VIII 表清单表清单......................................................................................................................... XI 1 绪论绪论............................................................................................................................ 1 1.1 课题研究背景及意义 ............................................................................................. 1 1.2 通风机轴承故障诊断方法研究现状 ..................................................................... 2 1.3 论文主要研究内容 ................................................................................................. 6 1.4 论文的结构安排 ..................................................................................................... 7 2 煤矿通风机故障机理分析煤矿通风机故障机理分析 ....................................................................................... 9 2.1 煤矿主通风机工作原理分析 ................................................................................. 9 2.2 煤矿主通风机轴承故障机理分析 ....................................................................... 11 2.3 滚动轴承的信号特征频率分析 ........................................................................... 13 2.4 本章小结 ............................................................................................................... 14 3 通风机轴承故障特征值提取方法研究通风机轴承故障特征值提取方法研究 ................................................................. 15 3.1 传统的时频分析方法研究 ................................................................................... 15 3.2 小波变换 ............................................................................................................... 16 3.3 经验模态分解 ....................................................................................................... 18 3.4 改进 EMD 存在的不足 ........................................................................................ 24 3.5 轴承故障特征向量提取 ....................................................................................... 38 3.6 本章小结 ............................................................................................................... 44 4 基于基于 IGA-SVM 的轴承故障诊断研究的轴承故障诊断研究 .................................................................. 45 4.1 支持向量机理论研究 ........................................................................................... 45 4.2 IGA-SVM 模型建立 ............................................................................................. 48 4.3 基于 IGA-SVM 的轴承故障诊断分析 ............................................................... 52 4.4 本章小结 ............................................................................................................... 55 5 基于基于 IGA-IPSO-ELM 的轴承故障诊断研究的轴承故障诊断研究 ....................................................... 56 5.1 极限学习机理论研究 ........................................................................................... 56 5.2 IGA-IPSO 混合优化算法 ..................................................................................... 58 5.3 基于 IGA-IPSO-ELM 的故障诊断模型 .............................................................. 62 5.4 轴承故障诊断分析 ............................................................................................... 67 万方数据 V 5.5 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 ..................................................................................................................... 78 学位论文原创性声明学位论文原创性声明 ................................................................................................. 79 学位论文数据集学位论文数据集 ......................................................................................................... 80 万方数据 VI Contents Abstract ........................................................................................................................ II Contents ..................................................................................................................... VI List of Figures ......................................................................................................... VIII List of Tables .............................................................................................................. XI 1 Introduction ............................................................................................................... 1 1.1 Research Background and Significance ................................................................... 1 1.2 Research Status of Ventilator Bearing Fault Diagnosis s ............................ 2 1.3 Main Research Content of this Paper ....................................................................... 6 1.4 Structure of the Dissertation .................................................................................... 7 2 Failure Mechanism Analysis of Coal Mine Ventilator ........................................... 9 2.1 Analysis of Working Principle of Coal Mine Main Ventilator ................................. 9 2.2 Analysis of Bearing Failure Mechanism of Coal Mine Main Ventilator ............... 11 2.3 Analysis of Signal Characteristic Frequency of Rolling Bearing .......................... 13 2.4 Chapter Summary .................................................................................................. 14 3 Research on Extraction of Eigenvalue of Ventilator Bearing Fault ..... 15 3.1 Research on Traditional Time-Frequency Analysis s ................................ 15 3.2 Wavelet Trans ................................................................................................. 16 3.3 Empirical Mode Decomposition ............................................................................ 18 3.4 Deficiencies in Improving EMD ............................................................................ 24 3.5 Bearing Fault Feature Vector Extraction ................................................................ 38 3.6 Chapter Summary .................................................................................................. 44 4 Research on Bearing Fault Diagnosis Based on IGA-SVM ................................ 45 4.1 Research on Support Vector Machine Theory ....................................................... 45 4.2 Establishment of IGA-SVM Model ....................................................................... 48 4.3 Analysis of Bearing Fault Diagnosis Based on IGA-SVM .................................... 52 4.4 Chapter Summary .................................................................................................. 55 5 Research on Bearing Fault Diagnosis Based on IGA-IPSO-ELM ..................... 56 5.1 Research on Extreme Learning Machine Theory .................................................. 56 5.2IGA-IPSO Fusion Optimization Algorithm ............................................................ 58 5.3 Fault Diagnosis Model Based on IGA-IPSO-ELM ............................................... 62 5.4 Analysis of Bearing Fault Diagnosis ...................................................................... 67 万方数据 VII 5.5 Chapter Summary .................................................................................................. 70 6 Conclusions and Prospects ..................................................................................... 71 6.1 Conclusions ............................................................................................................ 71 6.2 Prospects ................................................................................................................ 72 References ................................................................................................................... 73 Author’s Resume ........................................................................................................ 78 Declaration of Thesis Originality.............................................................................. 79 Thesis Data Collection ............................................................................................... 80 万方数据 VIII 图清单图清单 图序号 图名称 页码 图 1-1 近 10 年能源消费量 1 Figure 1-1 Energy consumption in recent 10 years 1 图 1-2 能源消费占比示意图 1 Figure 1-2 Energy consumption proportion 1 图 1-3 通风机轴承故障诊断过程 2 Figure 1-3 Ventilator bearing fault diagnosis process 2 图 1-4 时域分析法 4 Figure 1-4 Time domain analysis 4 图 1-5 频域分析法 4 Figure 1-5 Frequency domain analysis 4 图 1-6 时频分析法 5 Figure 1-6 Time-frequency analysis 5 图 2-1 抽出式通风 10 Figure 2-1 Withdrawable ventilation 10 图 2-2 压入式通风 10 Figure 2-2 Press-in ventilation 10 图 2-3 抽压混合式通风 11 Figure 2-3 Extraction and press-in hybrid ventilation 11 图 2-4 滚动轴承部件图 12 Figure 2-4 Rolling bearing parts drawing 12 图 2-5 滚动轴承结构 13 Figure 2-5 Rolling bearing structure 13 图 3-1 窗函数宽度选取示意图 16 Figure 3-1 Window function width selection diagram 16 图 3-2 变换示意图 19 Figure 3-2 Transation diagram 19 图 3-3 经验模态分解流程图 21 Figure 3-3 Empiri