矿压监测系统中传感器故障检测与分离算法研究.pdf

万方数据 论文题目论文题目 矿压监测系统中传感器故障检测与分离 算法研究 作者姓名作者姓名 滕滕 薇薇 入学时间入学时间2015 年年 9 月月 专业名称专业名称 控制工程控制工程 研究方向研究方向自动自动检测和检测和诊断诊断技术技术 指导教师指导教师 刘刘 传传 玺玺 职职 称称教教 授授 论文提交日期论文提交日期2018 年年 4 月月 11 日日 论文答辩日期论文答辩日期2018 年年 6 月月 03 日日 授予学位日期授予学位日期 万方数据 RESEARCH ON SENSOR FAULT DETECTION AND SEPARATION ALGORITHM IN MINE PRESSURE MONITORING A Thesis ted in fulfillment of the requirements for the degree of MASTER OF ENGINEERING from Shandong University of Science and Technology by Teng Wei Supervisor Professor Liu Chuanxi College of Electrical Engineering and Automation April 2018 万方数据 万方数据 万方数据 万方数据 山东科技大学硕士学位论文 摘要 I 摘摘 要要 随着科技的进步与发展，故障诊断技术在各个领域都得到了普遍应用，本 文以矿压监测系统的传感器故障为研究背景，研究了矿压监测系统中传感器在 产生偏差、失效、漂移、精度下降这四种故障时故障检测与故障分离的方法， 本文的主要工作和成果如下。 第一，分别描述偏差、失效、漂移、精度下降四种故障，基于 MATLAB 仿真平台利用主元分析对数据进行处理并仿真，仿真结果表明，传统的主元分 析在检测矿压系统的传感器故障时，没有准确检测出数据中的故障数据，并且 贡献图无法判断单一变量的故障。第二，加入核函数对检测方法进行改进，分 析不同的参数对不同故障模型的统计量的影响，统计不同参数的故障准确率， 寻找最适合的参数。仿真结果表明，与传统的主元分析相比，基于核函数的主 元分析方法使故障检测率大大提高。第三，利用格兰杰因果关系检验的方法进 行故障分离。经核主元提取检测到的故障样本数，检验每个变量的稳定性，在 变量稳定的前提下，依次利用其中一个变量对其他变量进行格兰杰因果关系检 验，通过对比完成故障分离。仿真结果表明，核函数与格兰杰因果关系检验相 结合的方法可以检测故障数据并能分离出故障的变量。 利用汝箕沟煤矿 32213 工作面的实际故障数据对以上方法进行检验，结果 成功检测出故障数据并分离故障变量，表明本文方法的有效性。 关键词关键词主元分析，核函数，格兰杰因果，故障诊断 万方数据 山东科技大学硕士学位论文 Abstract II Abstract With the advancement and development of science and technology, fault diagnosis has been applied universally in both military and civilian applications. This thesis takes the sensor fault of the mine pressure monitoring system as the research background. The fault detection and fault separation s of sensors in mine pressure detection system are studied in the following four kinds of failures, such as deviation, failure, drift and accuracy decrease. The main work and achievements of this thesis are as follows Firstly, four kinds of faults, deviation, failure, drift and accuracy, are described respectively. Principal component analysis is used to process and simulate the data based on MATLAB simulation plat. The simulation results show that the traditional principal component analysis does not accurately detect the fault data in the data when detecting the sensor fault of the mine pressure system. However, the contribution plot cannot determine the single variable fault. Secondly, the kernel function is added to improve the detection . Analyze the influence of different parameters on the statistics of different fault models, and calculate the accuracy of the fault data generated by different parameters, and find the most suitable parameters. The simulation results show that compared with the traditional principal component analysis, the principal component analysis based on kernel function greatly improves the probability of detecting fault data. Principal component analysis based on kernel function can well solve the shortcomings of failure of nonlinear data failure in traditional principal component analysis. Thirdly, a fault detection based on Granger causality test is proposed. The number of failures detected by the kernel principal component is extracted. The stability of each variable is tested. Under the premise of variable stability, variable is used to per Granger causality tests with another variable. Fault separation is completed by comparison. The simulation results show that the combination of kernel function and Granger causality test can detect the fault data and can isolate the fault variables. The above is tested by the actual fault data of the 32213 working face of the Ru Ji Gou coal mine. The results are successfully detected and the fault variable is separated, which shows the effectiveness of the . 万方数据 山东科技大学硕士学位论文 Abstract III Keywords Principal component analysis, kernel function, grainger causality, fault diagnosis 万方数据 山东科技大学硕士学位论文 目录 IV 目目 录录 1 绪 论 ...........................................................................................................1 1.1 研究背景与意义 .................................................................................................................... 1 1.2 国内外研究现状 .................................................................................................................... 2 1.3 本文的主要研究内容 ............................................................................................................ 6 2 矿压监测传感器故障描述 ............................................................................8 2.1 引言 ......................................................................................................................................... 8 2.2 矿压传感器 ............................................................................................................................ 9 2.3 故障描述 .............................................................................................................................. 12 2.4 本章小结 .............................................................................................................................. 14 3 基于主元分析的故障检测研究 ..................................................................15 3.1 引言 ....................................................................................................................................... 15 3.2 主元的选取 .......................................................................................................................... 16 3.3 故障的统计量 ...................................................................................................................... 18 3.4 故障的贡献图 ...................................................................................................................... 20 3.5 仿真验证 .............................................................................................................................. 22 3.6 本章小结 .............................................................................................................................. 26 4 基于核主元分析的故障检测研究 ..............................................................27 4.1 引言 ....................................................................................................................................... 27 4.2 核主元原理 .......................................................................................................................... 27 4.3 核函数分类 .......................................................................................................................... 30 4.4 仿真验证 .............................................................................................................................. 32 4.5 本章小结 .............................................................................................................................. 45 5 基于格兰杰因果分析的故障分离研究 ......................................................46 5.1 引言 .......................................................................................................................................................... 46 5.2 格兰杰因果关系原理 .......................................................................................................... 46 5.3 平稳性检验 .......................................................................................................................... 48 5.4 格兰杰因果检验 .................................................................................................................. 51 万方数据 山东科技大学硕士学位论文 目录 V 5.5 仿真验证 .............................................................................................................................. 55 5.6 本章小结 .............................................................................................................................. 58 6 总结与展望 .................................................................................................59 6.1 总结 ....................................................................................................................................... 59 6.2 展望 ....................................................................................................................................... 59 参考文献 ...........................................................................................................60 致谢 ..................................................................................................................64 攻读硕士期间主要成果 ...................................................................................65 万方数据 山东科技大学硕士学位论文 Contents VI Contents 1 Introduction .............................................................................................................................. 1 1.1 Background and significance of research ..................................................................................................... 1 1.2 Research Actuality ......................................................................................................................................... 2 1.3 Main research contents .................................................................................................................................. 6 2 Mine pressure monitoring sensor fault description ............................................................ 8 2.1 Introduction .................................................................................................................................................... 8 2.2 Mineral pressure sensor ................................................................................................................................. 9 2.3 Fault description ........................................................................................................................................... 12 2.4 Chapter summary ......................................................................................................................................... 14 3 Research on fault detection based on principal component analysis ............................ 15 3.1 Introduction .................................................................................................................................................. 15 3.2 Select principal component ......................................................................................................................... 16 3.3 Fault statistics ............................................................................................................................................... 18 3.4 Fault contribution plots ................................................................................................................................ 20 3.5 Numerical results.......................................................................................................................................... 22 3.6 Chapter summary ......................................................................................................................................... 26 4 Research on fault detection based on kernel principle component................................ 27 4.1 Introduction .................................................................................................................................................. 27 4.2 Principle of kernel principle component..................................................................................................... 27 4.3 Classification of kernel principle component ............................................................................................. 30 4.4 Numerical results.......................................................................................................................................... 32 4.5 Chapter summary ......................................................................................................................................... 45 5 Research on fault separation based on granger ................................................................ 46 5.1 Introduction .................................................................................................................................................. 46 5.2 Granger causality principle .......................................................................................................................... 46 5.3 Test of stability ............................................................................................................................................. 48 5.4 Granger causality test ................................................................................................................................... 51 5.5 Numerical results.......................................................................................................................................... 55 万方数据 山东科技大学硕士学位论文 Contents VII 5.6 Chapter summary ......................................................................................................................................... 58 6 Conclusion and prospect ....................................................................................................... 59 6.1 Conclusion .................................................................................................................................................... 59 6.2 Prospect ......................................................................................................................................................... 59 References...................................................................................................................................... 60 Acknowledgement ........................................................................................................................ 64 Main Work Achievement of the Author during Working on Master Paper ...................... 65 万方数据 山东科技大学硕士学位论文 绪论 1 1 绪 论 1.1 研究背景与意义 随着自动化技术在生产、生活中的普及，如何保障自动化设备运行安全的 问题成为一大难点。针对这一问题，监测系统开始应用于各个领域。通过监测 系统对采集信息进行分析， 最后判断设备的运行是否正常。 在工业生产过程中， 监测系统的可靠性尤为重要， 需要实时监测当前设备运行情况， 一旦发现故障， 应及时进行维护和修理，采用合理的方法对故障进行排除，避免或减小设备故 障在生产中造成的产品质量下降、浪费大量时间和资源等问题。如在煤矿开采 过程中，通常使用矿压监测系统对支架所承受的压力进行采集并分析[1]，以便 监测井下安全情况。由于开采技术的迅速发展，矿压监测系统进行监测时所考 虑的因素也变的越来越复杂[2]。在采集到的信息中，不仅要分析支架受到的压 力情况，还要对自身可能产生的问题进行分析。 计算机科学技术的快速发展，使信息技术融入在日常生活的各个方面，从 而使人们的生活越来越方便，但享受这种方便的同时存在着许多隐患。如在复 杂的信息传输过程中，如果结果出现了问题，很难确定在传输过程中哪部分出 现了故障。信息技术包括信息传递的各个方面，如信息的产生、信息的收集、 设备间信息的交换、对信息的存储等。信息的采集作为信息传输中最基本的部 分，保障信息采集设备的正常工作是保障采集信息准确性的前提。使用传感器 进行信息采集的方法在各个领域应用广泛，传感器作为在信息传输过程中最先 接触信息的设备， 它的稳定性与可靠性直接影响信息在后续传递的转换、 运算、 观察，最终导致结果不准确甚至得到错误结果[3-7]。当分析矿压监测系统的传感 器采集到的信息时，应考虑到采集设备，即传感器的工作状态。当传感器本身 产生了故障，那么所采集的支架压力信息就不准确，从而导致无法正确分析井 下的安全情况。因此，对监测系统中的信息采集设备即传感器的