Fault Detection of Hoisting Wireope with SVM Optimized by PSO
-
摘要: 为了加强多绳摩擦提升系统的提升钢丝绳故障与提升钢丝绳张力之间的联系,提出了基于支持向量机(SVM)以及最小二乘支持向量机(LSSVM)的诊断模型。在MATLAB中应用粒子群优化算法(PSO)对模型参数进行优化,得到具有最优参数的支持向量机诊断模型;在某矿的提升系统进行三种故障及正常状态试验,利用东方所INV3060S采集仪获得的钢丝绳故障及正常状态数据对PSO-SVM以及PSO-LSSVM进行训练以及预测,结果显示PSO-SVM的运算结果的误差及均方误差较小,PSO-LSSVM的运算速度较快,且两种算法都能有较好的故障诊断能力。
-
关键词:
- 故障诊断 /
- 钢丝绳 /
- 多绳摩擦提升系统 /
- 支持向量机(SVM) /
- 最小二乘支持向量机(LSSVM) /
- 粒子群优化算法(PSO) /
- MATLAB /
Abstract: To strengthen the relationship between the hoisting wirerope fault and the hoisting wirerope tension of multi-rope friction lifting system, a fault detection model based on support vector machine(SVM) and least squares support vector machine(LSSVM) was proposed. The particle swarm optimization algorithm (PSO) was used to optimize the model parameters to obtain the support vector machine diagnostic model with optimal parameters in MATLAB. Three kinds of faults and normal state tests were carried out in the lifting system of a mine. The PSO-SVM and PSO-LSSVM were trained and predicted by the wirerope fault data. The results showed the error and the mean square error of the PSO-SVM is smaller, and the PSO-LSSVM is faster, and both algorithms have good detection capabilities. -
表 1 张力差数据库
数据序号 钢丝绳序号 故障类别 1 2 3 4 1 0.439 0.453 0.155 0.201 1 2 0.804 0.437 0.418 0.182 2 3 0.749 0.510 0.342 0.234 3 4 0.973 0.518 0.627 0.227 4 5 0.430 0.435 0.153 0.191 1 6 0.742 0.453 0.421 0.192 2 7 0.801 0.404 0.309 0.186 3 8 0.942 0.421 0.583 0.169 4 9 0.460 0.464 0.168 0.202 1 10 0.739 0.453 0.411 0.192 2 11 0.807 0.554 0.364 0.251 3 12 0.946 0.604 0.531 0.115 4 13 0.450 0.438 0.152 0.192 1 14 0.741 0.352 0.382 0.146 2 15 0.929 0.541 0.354 0.247 3 16 0.930 0.588 0.591 0.133 4 17 0.466 0.463 0.161 0.202 1 18 0.731 0.445 0.427 0.183 2 19 0.810 0.527 0.382 0.217 3 20 0.965 0.609 0.644 0.311 4 21 0.523 0.489 0.281 0.221 1 22 0.809 0.455 0.389 0.256 2 23 0.859 0.632 0.399 0.302 3 24 0.998 0.686 0.596 0.299 4 注:故障类别1、2、3、4分别代表了钢丝绳的正常、卡罐、过卷以及打滑状态。 表 2 运行结果比较
算法 最大预测误差绝对值 均方误差 运行时间/s PSO-SVM 0.031 55 6.904 0×10-4 3.420 404 PSO-LSSVM 0.414 574 0.022 0 0.246 795 -
[1] 刘义, 陈国定, 李济顺.主轴弹性对摩擦提升系统纵向振动特性影响的研究[J].机械科学与技术, 2017, 36(4):547-552 doi: 10.13433/j.cnki.1003-8728.2017.0409Liu Y, Chen G D, Li J S. Study on friction hoist longitudinal vibration characteristics considering elastic effect of main axle[J]. Mechanical Science and Technology for Aerospace Engineering, 2017, 36(4):547-552(in Chinese) doi: 10.13433/j.cnki.1003-8728.2017.0409 [2] 袁方, 胡斌梁, 周知进.在役钢丝绳缺陷检测方法的研究现状与展望[J].机械设计与制造, 2010, (2):260-262 doi: 10.3969/j.issn.1001-3997.2010.02.103Yuan F, Hu B L, Zhou Z J. An analysis on the research status quo and prospects of defect detection methods of wire ropes[J]. Machinery Design & Manufacture, 2010, (2):260-262(in Chinese) doi: 10.3969/j.issn.1001-3997.2010.02.103 [3] 寇少凯, 寇子明.深井提升钢丝绳故障分析及其可靠度仿真[J].煤炭工程, 2018, 50(3):112-115, 121 doi: 10.3969/j.issn.1008-4495.2018.03.025Kou S K, Kou Z M. Fault analysis and reliability simulation of deep mine hoisting wire rope[J]. Coal Engineering, 2018, 50(3):112-115, 121(in Chinese) doi: 10.3969/j.issn.1008-4495.2018.03.025 [4] Xu G Y, Da J P, Zhang X G, et al. A novel tension monitoring device of multi-rope friction hoister by using acoustic filtering sensor[J]. Journal of Vibroengineering, 2016, 18(8):5537-5552 [5] Zhang D L, Zhao M, Zhou Z H, et al. Characterization of wire rope defects with gray level co-occurrence matrix of magnetic flux leakage images[J]. Journal of Nondestructive Evaluation, 2013, 32(1):37-43 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=a7a7f0828cb4798835729e9a39c98eab [6] Zhao Z K, Zhang X G. Theory and numerical analysis of extreme learning machine and its application for different degrees of defect recognition of hoisting wire rope[J]. Shock and Vibration, 2018(8):1-13 [7] 徐乐, 邢邦圣, 郎超男, 等.LMD能量熵和SVM相结合的滚动轴承故障诊断[J].机械科学与技术, 2017, 36(6), 915-918 doi: 10.13433/j.cnki.1003-8728.2017.0615Xu L, Xing, B S, Lang C N, et al. Fault diagnosis of rolling bearing combined LMD energy entropy and SVM[J]. Mechanical Science and Technology for Aerospace Engineering, 2017, 36(6), 915-918(in Chinese) doi: 10.13433/j.cnki.1003-8728.2017.0615 [8] 钱庆, 方叶祥, 王洪冬.基于支持向量机的拉弯工件弯曲质量检测研究[J].制造技术与机床, 2018, (11), 141-144 http://d.old.wanfangdata.com.cn/Periodical/zzjsyjc201811038Qian Q, Fang Y X, Wang H D. Research on bending quality detection of bending parts based on support vector machine[J]. Manufacturing Technology & Machine Tool, 2018, (11), 141-144(in Chinese) http://d.old.wanfangdata.com.cn/Periodical/zzjsyjc201811038 [9] 胡良谋.支持向量机故障诊断及控制技术[M].北京:国防工业出版社, 2011Hu L M. Support vector machine fault diagnosis and control technology[M]. Beijing:National Defense Industry Press, 2011(in Chinese) [10] 陈法法, 杨晶晶, 肖文荣, 等.Adaboost-SVM集成模型的滚动轴承早期故障诊断[J].机械科学与技术, 2018, 37(2):237-243 doi: 10.13433/j.cnki.1003-8728.2018.0212Chen F F, Yang J J, Xiao W R, et al. Early fault diagnosis of rolling bearing based on ensemble model of Adaboost SVM[J]. Mechanical Science and Technology for Aerospace Engineering, 2018, 37(2):237-243(in Chinese) doi: 10.13433/j.cnki.1003-8728.2018.0212 [11] Gu X D, Deng F, Gao X, et al. An improved sensor fault diagnosis scheme based on TA-LSSVM and ECOC-SVM[J]. Journal Of Systems Science and Complexity, 2018, 31(2):372-384 http://d.old.wanfangdata.com.cn/Periodical/xtkxysx201802002 [12] Vapnik V N. The nature of statistical learning theory[M]. 2nd ed. New York: Springer, 1999 [13] Burges C J C. A tutorial on support vector machines for pattern recognition[J]. Data Mining and Knowledge Discovery, 1998, 2(2):121-167 doi: 10.1023-A-1009715923555/ [14] 杨英杰.粒子群算法及其应用研究[M].北京:北京理工大学出版社, 2017Yang Y J. Particle swarm optimization algorithm and its application[M]. Beijing:Beijing Institute of Technology Press, 2017(in Chinese) [15] 单剑锋, 杨雨.粒子群优化的流形SVM模拟电路故障诊断[J].机械科学与技术, 2019, 38(2):260-264 doi: 10.13433/j.cnki.1003-8728.20180157Shan J F, Yang Y. Fault diagnosis of manifold SVM analog circuit based on particle swarm optimization[J]. Mechanical Science and Technology for Aerospace Engineering, 2019, 38(2):260-264(in Chinese) doi: 10.13433/j.cnki.1003-8728.20180157