基于脆弱性的制造设备故障智能诊断与维护

doi:10.3901/JME.2020.23.141

摘要/Abstract

摘要： 制造设备故障智能诊断与维护是保障制造系统安全运行的重要手段。为准确地诊断制造设备的健康状态、识别设备故障的关键因素，建立高效的健康维护系统，提出了基于脆弱性的设备故障智能诊断与维护方法。该方法将考虑脆弱性的设备故障智能诊断与维修决策模块嵌入到设备的过程控制系统（Process control system，PCS）中，它基于系统脆弱性的定义和性能劣化理论建立了设备脆弱性评估模型实时判断设备的脆弱状态，利用非线性核映射方法实时监测制造设备的运行参数是否超出预设边界，建立设备参数的高斯核函数模型准确识别故障的关键因素，将设备的脆弱性状态与维护模式相结合建立维修决策模型避免维修过度和维修不足。以某机器人的伺服系统为例，证实了所提方法能有效提高故障诊断效率、智能化诊断故障因素，优化设备维修决策。

关键词: 制造设备, 脆弱性, 故障诊断, 维护

Abstract: Intelligent fault diagnosis and maintenance are the important tools to guarantee the healthy operation of the manufacturing system. In order to accurately diagnose the health status of manufacturing systems,identify key factors of equipment failures, and establish an efficient health maintenance system, a vulnerability-based method is proposed for the intelligent diagnosis and maintenance of equipment failures. In this method,the module of intelligent diagnosis and maintenance decision optimization,which the vulnerability of the manufacturing equipment is considered,is embedded into the Process control system(PCS) of the equipment. In order to judge the vulnerability state of the equipment timely, the definition of vulnerability and degradation theory are combined to establish a vulnerability assessment model. The Non-linear kernel mapping method is used to implement real-time monitoring of the operating parameters of manufacturing equipment,a Gaussian kernel function model of equipment parameters is established to accurately identify the key factors of failure. To avoid over-repair and under-maintenance,the equipment vulnerability status and maintenance mode are combined together to establish maintenance decision model. The results for a robot servo system indicate that the proposed method can improve the efficiency of fault diagnosis effectively,identify fault factors accurately, and optimize maintenance decision.

Key words: manufacturing equipment, vulnerability, fault diagnosis, maintenance

中图分类号:

TG156

高贵兵, 王俊深, 岳文辉, 彭建华. 基于脆弱性的制造设备故障智能诊断与维护[J]. 机械工程学报, 2020, 56(23): 141-149.

GAO Guibing, WANG Junshen, YUE Wenhui, PENG Jianhua. Fault Diagnosis and Maintain of Manufacturing Equipment Based on Vulnerability[J]. Journal of Mechanical Engineering, 2020, 56(23): 141-149.

参考文献

[1] 石瑞敏,杨兆建.基于复杂网络优化的DAG-SVM在滚动轴承故障诊断中的应用[J].振动与冲击,2015,34(12):1-6,34. SHI Ruimin,YANG Zhaojian. Application of optimized directed acyclic graph support vector machine based on complex network in fault diagnosis of rolling bearing[J]. Journal of Vibration& Shock,2015,34(12):1-6,34.
[2] 张明,江志农.基于多源信息融合的往复式压缩机故障诊断方法[J].机械工程学报,2017,53(23):46-52. ZHANG Ming,JIANG Zhinong. Reciprocating compressor fault diagnosis technology based on multi-source information fusion[J]. Journal of Mechanical Engineering,2017,53(23):46-52.
[3] RATNAYAKE R M C. KBE development for criticality classification of mechanical equipment:a fuzzy expert system[J]. International Journal of Disaster Risk Reduction,2014,9:84-98.
[4] 时培明,梁凯,赵娜,等.基于深度学习特征提取和粒子群支持向量机状态识别的齿轮智能故障诊断[J].中国机械工程,2017,28(9):1056-1061. SHI Peiming,LIANG Kai,ZHAO Na,et al. Intelligent fault diagnosis for gears based on deep learning feature extraction and particle swarm optimization SVM state identification[J]. China Mechanical Engineering,2017,28(9):1056-1061.
[5] SHEN Y,ZHU X. Intelligent particle filter and its application to fault detection of nonlinear system[J]. IEEE Transactions on Industrial Electronics,2015,62(6):3852-3861.
[6] LUO S,CHENG J,MING Z,et al. An intelligent fault diagnosis model for rotating machinery based on multi-scale higher order singular spectrum analysis and GA-VPMCD[J]. Measurement,2016,87:38-50.
[7] LUGHOFER E. On-line active learning:A new paradigm to improve practical use ability of data stream modeling methods[J]. Information Sciences,2017,415:356-376.
[8] WANG D,QIAO H,ZHANG B,et al. Online support vector machine based on convex hull vertices selection[J]. IEEE Transactions on Neural Networks& Learning Systems,2013,24(4):593-609.
[9] ORABONA F,CASTELLINI C,CAPUTO B,et al. On-line independent support vector machines[J]. Pattern Recognition,2010,43(4):1402-1412.
[10] LAU K W,WU Q H. Online training of support vector classifier[J]. Pattern Recognition,2003,36(8):1913-1920.
[11] MENG J,LUO G,FEI G. Lithium polymer battery state-of-charge estimation based on adaptive unscented kalman filter and support vector machine[J]. IEEE Transactions on Power Electronics,2015,31(3):2226-2238.
[12] MARTÍNEZ-MORALES J D,PALACIOS-HERNÁNDEZ E R,CAMPOS-DELGADO D U. Multiple-fault diagnosis in induction motors through support vector machine classification at variable operating conditions[J]. Electrical Engineering,2016:1-15.
[13] 朱大业,丁晓红,王神龙,等.基于支持向量机模型的复杂非线性系统试验不确定度评定方法[J].机械工程学报,2018,54(8):177-184. ZHU Daye,DING Xiaohong,WANG Shenlong,et al. Uncertainty evaluation method of complex nonlinear system test based on support vector machine model[J]. Journal of Mechanical Engineering,2018,54(8):177-184.
[14] TAO D,LI X,HU W,et al. Supervised tensor learning[J]. Knowledge& Information Systems,2007,13(1):1-42.
[15] 雷亚国,贾峰,孔德同,等.大数据下机械智能故障诊断的机遇与挑战[J].机械工程学报,2018,54(5):94-104. LEI Yaguo,JIANG Feng,KONG Detong,et al. Opportunities and challenges of machinery intelligent fault diagnosis in big data era[J]. Journal of Mechanical Engineering,2018,54(5):94-104.
[16] 高贵兵,岳文辉,张人龙.基于状态熵的制造系统结构脆弱性评估方法[J].计算机集成制造系统,2017,23(10):2211-2220. GAO Guibing,YUE Wenhui,ZHANG Renlong. Structural vulnerability assessment method of manufacturing systems based on state entropy[J]. Computer Integrated Manufacturing System,2017,23(10):2211-2220.
[17] NA D,HAENGGI M. The benefits of hybrid caching in Gauss-Poisson D2D networks[J]. IEEE Journal on Selected Areas in Communications,2018,36(6):1217-1230.
[18] HAO X,SUN J,ZETTL A. Canonical forms of self-adjoint boundary conditions for differential operators of order four[J]. Journal of Mathematical Analysis& Applications,2012,387(2):1176-1187.
[19] 高贵兵,岳文辉,王峰.基于CPS方法与脆弱性评估的制造系统健康状态智能诊断[J].中国机械工程,2019,30(2):212-219. GAO Guibing,YUE Wenhui,WANG Feng. Intelligent diagnosis on health status of manufacturing systems based on embedded CPS method and vulnerability assessment[J]. China Mechanical Engineering,2019,30(2):212-219.
[20] LAST M. Kernel methods for pattern analysis[J]. Publications of the American Statistical Association,2004,101(476):1730-1730.
[21] SUN Q,ZHOU J,ZHONG Z,et al. Gauss-Poisson joint distribution model for degradation failure[J]. Plasma Science IEEE Transactions on,2004,32(5):1864-1868.
[22] TRAN V T,HONG T P,YANG B S,et al. Machine performance degradation assessment and remaining useful life prediction using proportional hazard model and support vector machine[J]. Mechanical Systems& Signal Processing,2012,32(4):320-330.
[23] 胡姚刚,李辉,刘海涛,等.基于多类证据体方法的风电机组健康状态评估[J].太阳能学报,2018,39(2):331-341. HU Yaogang,LI Hui,LIU Haitao,et al. Evaluation of health status of wind turbine based on multiple evidence method[J]. Acta Energiae Solaris Sinica,2018,39(2):331-341.