面向装备RUL预测的平行仿真框架

doi:10.16182/j.issn1004731x.joss.201806027

摘要/Abstract

摘要： 由于装备状态具有复杂多变、不确定性强、信息量大的特点,造成根据装备状态研究具有自更新能力的剩余寿命预测模型成为当前的难点,仿真为解决剩余寿命预测问题提供了有效途径。基于平行系统理论,提出面向装备剩余寿命预测的平行仿真概念及技术框架,讨论了平行仿真的概念、特点、能力需求和功能组成,并重点介绍了面向装备剩余寿命预测平行仿真的主要建模技术,包括装备退化状态感知、装备退化状态空间模型构建、装备退化状态空间模型演化,为建立面向装备剩余寿命预测的平行仿真系统提供了借鉴。

关键词: 平行仿真, 模型演化, 剩余寿命, 状态感知, 状态空间模型, 数据同化, 参数估计

Abstract: As the equipment states are complicated with uncertainty, predicting remaining useful life with self-updating ability has become a hard task. Simulation provides an effective way to solve the problem. The concept and technology framework of equipment remaining useful life prediction oriented parallel simulation are proposed based on parallel system theory and the concept, characteristics, capacity demands and functional compositions of parallel simulation are introduced. The main modeling technologies of equipment remaining useful life prediction oriented parallel simulation are discussed, which include awareness of equipment degradation state, construction of equipment degradation state space model and evolution of equipment degradation state space model. It provides references for building equipment remaining useful life prediction oriented parallel simulation system.

Key words: parallel simulation, model evolution, remaining useful life, state awareness, state space model, data assimilation, parameter estimation

中图分类号:

TP391.9

葛承垄, 朱元昌, 邸彦强, 胡志伟, 董志华. 面向装备RUL预测的平行仿真框架[J]. 系统仿真学报, 2018, 30(6): 2216-2224.

Ge Chenglong, Zhu Yuanchang, Di Yanqiang, Hu Zhiwei, Dong Zhihua. Equipment RUL Prediction Oriented Parallel Simulation Framework[J]. Journal of System Simulation, 2018, 30(6): 2216-2224.

参考文献

[1] Compare M, Martini F, Zio E.Genetic Algorithms for Condition-based Maintenance Optimization under Uncertainty[J]. European Journal of Operational Research (S0377-2217), 2015, 244(2): 611-623.
[2] Parikshit Mehta, Andrew Werner, Laine Mears.Condition based Maintenance Systems Integration and Intelligence Using Bayesian Classification and Sensor Fusion[J]. Journal of Intelligent Manufacture (S0956-5515), 2015, 26(2): 331-346.
[3] 王兆强, 胡昌华, 王文彬, 等. 基于Wiener过程的钢厂风机剩余使用寿命实时预测[J]. 北京科技大学学报, 2014, 36(10): 1361-1368.
Wang Zhaoqiang, Hu Changhua, Wang Wenbin, et al.Wiener process-based online prediction method of remaining useful life for draught fans in steel mills[J]. Journal of University of Science and Technology Beijing, 2014, 36(10): 1361-1368.
[4] Si Xiaosheng, Wang Wenbin, Hu Changhua, et al.Remaining Useful Life Estimation Based on Nonlinear Diffusion Degradation Process[J]. IEEE Transactions on Reliability (S0018-9529), 2012, 61(1): 50-67.
[5] 张会会, 张伟, 胡昌华. 基于参数递归更新的惯性器件寿命预测[J]. 系统仿真学报, 2013, 25(5): 1036-1040.
Zhang Huihui, Zhang Wei, Hu Changhua.Inertia device lifetime prediction based on REM method[J]. Journal of System Simulation, 2013, 25(5): 1036-1040.
[6] 石慧, 曾建潮. 考虑非完美维修的实时剩余寿命预测及维修决策模型[J]. 计算机集成制造系统, 2014, 20(9): 2259-2266.
Shi Hui, Zeng Jianchao.Prediction of real-time remaining useful life and maintenance decision model considering imperfect preventive maintenance[J]. Computer Integrated Manufacturing Systems, 2014, 20(9): 2259-2266.
[7] 张建勋. 基于随机退化建模的寿命预测方法及应用研究[D]. 西安: 第二炮兵工程大学, 2013: 2-8.
Zhang Jianxun.Lifetime prediction method and its application based on stochastic degradation method[D]. Xi'an: Second Artillery Engineering University, 2013: 2-8.
[8] 张仕新, 昝翔, 李浩, 等. 状态维修理论及剩余寿命预测的研究现状与展望[J]. 兵工自动化, 2014, 33(9): 15-20.
Zhang Shixin, Zan Xiang, Li Hao, et al.Condition-Based Maintenance theory and research status and prospect about prediction of residual useful life[J]. Ordnance Industry Automation, 2014, 33(9): 15-20.
[9] 张昭. 基于贝叶斯统计推断的陀螺仪剩余寿命预测方法研究[D]. 西安: 第二炮兵工程大学, 2013: 13-25
Zhang Zhao.Remaining useful life prediction of gyroscope based on Bayesian statistical inference[D]. Xi'an: Second Artillery Engineering University, 2013: 13-25.
[10] 王飞跃. 平行系统方法与复杂系统的管理和控制[J]. 控制与决策, 2004, 19(5): 485-489.
Wang Feiyue.Parallel system methods for management and control of complex systems[J]. Control and Decision, 2004, 19(5): 485-489.
[11] 周云. 面向实时作战决策支持的动态数据驱动仿真理论和方法研究[D]. 长沙:国防科学技术大学, 2010: 20-40.
Zhou Yun.Research on the theory and methods of dynamic data driven simulation for real-time combat decision support[D]. Changsha: National University of Defense Technology, 2010: 20-40.
[12] 王飞跃. 面向赛博空间的战争组织与行动:关于平行军事体系的讨论[J]. 军事运筹与系统工程, 2012, 26(3): 5-10.
Wang Feiyue.War organizations and actions for Cyberspace: discussions on parallel military systems[J]. Military Operations Research and System Engineering, 2012, 26(3): 5-10.
[13] Chen B.KD-ACP: A Software Framework for Social Computing in Emergency Management[J]. Mathematical Problems in Engineering (S1024-123X), 2014, 21(3): 35-38.
[14] Wang F Y.Parallel Control and Management for Intelligent Transportation Systems: Concepts, Architectures, and Applications[J]. IEEE Transactions on Intelligent Transportation Systems (S1524-9050), 2010, 11(3): 630-638.
[15] 张育林. 平行试验—武器装备体系试验的理论与方法[R]. 第428次香山科学会议主题报告, 北京, 2012.
Zhang Yulin.Parallel experiment-a discussion concepts and methods of weapon equipment system-of-systems experiment[R]. The 428th Xiangshan Science Conference Thematic Report, Beijing, 2012.
[16] 王飞跃, 李晓晨, 毛文吉, 等. 社会计算的基本方法与应用[M]. 杭州: 浙江大学出版社, 2013: 7-10.
Wang Feiyue, Li Xiaochen, Mao Wenji, et al.Social computing methods and applications[M]. Hangzhou: Zhejiang University Press, 2013: 7-10.
[17] Darema Frederica. Dynamic Data Driven Application Systems, NSF Workshop Report[R/OL]. (2006-02) [2016-07]. http://www.cise.nsf.gov/dddas.
[18] Surdu J R, Kittka K.The Deep Green Concept[C]// Spring Multiconference 2008, Military Modeling and Simulation Symposium (MMS). Ottawa, Canada: DARPA, 2008: 103-107.
[19] Surdu J R, Kittka K.Deep Green: Commander's Tool for COA's Concept[C]// Computing, Communications and Control Technologies, Orlando, Florida, USA: CCCT, 2008: 56-62.
[20] Darema Frederica, Douglas Craig, Patra Abani. InfoSymbiotics /DDDAS: The Power of Dynamic Data Driven Applications Systems, NSF and AFOSR Workshop Report[R/OL].(2010-08) [2016-07]. http:// www.cise.nsf.gov/dddas.
[21] Fujimoto Richard, Lunceford Dell, Page Ernest, et al. Grand Challenges for Modeling and Simulation [R/OL].(2002-08) [2016-07]. http://www.dangstuhl.de/ Reports/02/02351.pdf.
[22] Aydt Heiko, Turner Stephen John, Cai Wentong, et al.Research Issues in Symbiotic Simulation[C]// Proceedings of the 2009 Winter Simulation Conference, Austin, Texas. USA: IEEE, 2009: 1213-1222.
[23] 胡晓峰. 大数据时代对建模仿真的挑战与思考[J]. 军事运筹与系统工程, 2013, 27(4): 5-12.
Hu Xiaofeng.Challenges and thoughts of modeling & simulation in big data era[J]. Military Operations Research and System Engineering, 2013, 27(4): 5-12.
[24] 毕长剑. 建模与仿真技术的三个前沿领域[R]. 第十届中国系统建模与仿真技术高层论坛, 北京, 2015.
Bi Changjian.Three frontiers of modeling and simulation technology[R]. The 10th China System Modeling and Simulation Technology Forum, Beijing, 2015.
[25] 王飞跃. 指控5.0: 平行时代的智能指挥与控制体系[J]. 指挥与控制学报, 2015, 1(1): 107-120.
Wang Feiyue.CC 5.0: intelligent command and control systems in the parallel age[J]. Journal of Command and Control, 2015, 1(1): 107-120.
[26] Scholkopf B, Smola A, Muller K R.Nonlinear Component Analysis as a Kernel Eigenvalue Problem[J]. Neural Computation (S0899-7667), 1998, 10(1): 1299-1319.
[27] Reichle R H, Walker J P, Koster R D, et al.Extended Versus Ensemble Kalman Filtering for Land Data Assimilation[J]. Journal of Hydrometeorology (S1525- 755X), 2002, 3(6): 728-740.
[28] Moradkhani H, Hsu K L, Gupta H, et al.Uncertainty Assessment of Hydrologic Model States and Parameters: Sequential Data Assimilation Using the Particle Filter[J]. Water Resources Research (S0043-1397), 2005, 41(5): 1-17.
[29] Vrugt J A, ter Braak C J F, Disks C G H, et al. Hydrologic Data Assimilation Using Particle Markov Chain Monte Carlo Simulation: Theory, Concepts and Application[J]. Advances in Water Resources (S0309-1708), 2013, 51: 457-478.
[30] 司小胜, 胡昌华, 李娟, 等. Bayesian更新与EM算法协作下退化数据驱动的剩余寿命估计方法[J]. 模式识别与人工智能, 2013, 26(4): 357-365.
Si Xiaosheng, Hu Changhua, Li Juan, et al.Degradation data-driven remaining useful life estimation approach under collaboration between Bayesian updating and EM algorithm[J]. Pattern Recognition and Artificial Intelligence, 2013, 26(4): 357-365.