摘要
随着高技术装备的发展及其在现代高技术条件下局部战争中的应用,对武器装备的故障诊断与维修保障提出了越来越高的要求。使高技术装备具备快速诊断与维修能力,是增强装备战场抢修能力,提高装备的战备完好率、二次出动率和战斗力再生能力,保障战斗任务,降低装备的维护和保障费用的 要而有效的途径。
本文在“十五”国防预研项目“基于信息融合的装备快速故障诊断技术”和总装维修改革项目“便携式二次电源智能测试系统”的支持下,充分利用贝叶斯网络的优点,针对装备故障诊断中的若干问题,将目前有关贝叶斯网络方面的相关理论研究应用到具体的设备维修实践中,开发了一套贝叶斯网络维修决策系统,并将该系统应用到二次电源设备的故障诊断与维修实践中,提高了对二次电源设备的维修能力。论文主要完成的工作包括:
(1)在分析目前故障诊断与维修决策面临的主要问题的基础上,引入了基于贝叶斯网络的故障诊断与维修决策方法;通过对故障诊断与维修决策问题的一般描述和对诊断贝叶斯网络的表达方式和数学描述进行的介绍,对贝叶斯网络维修决策系统进行了功能分析和方案设计。
(2)围绕目前贝叶斯网络在故障诊断领域进行应用的三个主要技术难点,即贝叶斯网络诊断模型的建造、贝叶斯网络的诊断模型推理与辅助维修决策、以及贝叶斯网络诊断模型自学习,设计了系统的实现方案,解决了以上技术难点,开发并完成了完整的辅助维修决策系统。
(3)将本文开发的贝叶斯网络维修决策系统作为“便携式二次电源智能测试系统在线故障诊断平台”部分,以直升机二次电源系统为维修对象,应用并检验了该维修决策系统的有效性。应用结果表明,该系统对提高装备尤其是二次电源设备的快速故障诊断与维修能力具有较高的应用价值。
综上所述,本文开发的贝叶斯网络维修决策系统,作为一个完整且相对独立的软件系统,实现了一个将贝叶斯网络从理论研究过渡到维修实践的成功应用案例。
With the development and application of high-tech weapons, their ability of fast fault diagnosis and maintenance support is becoming more and more important in modern war to enhance the behavior of weapon repair in battlefield, improve the rate of combat readiness and rebirth of battle effectiveness, and guarantee task success.This dissertation has been supported by two projects. One is the Research on Weapon's Fast Fault Diagnosis Technique Based on Data Fusion, and the other is the portable intelligent test system for secondary power supply. On the purpose of solving some problems in the weapon maintenance, a Bayesian network based fault diagnosis and maintenance decision software system has been developed, and applied in repairing of helicopter secondary power supply instrument.The main research work in this paper can be summarized as follows:(1) The key problems and popular description of fault diagnosis and maintenance decision behavior were analyzed first. Then, the expression method and mathematical description of the Bayesian network were described as well. After those, the function of Bayesian network based decision system was analyzed and its implementing scheme was given.(2) To solve the technical problems of the Bayesian network's usage in the fault diagnosis domain, including model construction, model inference and the model learning, respectively, the implementing scheme was realized and maintenance decision software was accomplished as a result.(3) With the integration with the portable intelligent test system for secondary power supply, the maintenance decision software has been developed as an online fault diagnosis platform. During the maintenance practice of helicopter, the maintenance decision system was tested and has been successfully improved its reliability.In a summary, this dissertation has developed a Bayesian network based maintenance decision system. With the integration of a test instrument, it realized a successful application case of transferring Bayesian network from theoretical research into maintenance practice.
引文
[1] 吴今培,肖健华.智能故障诊断与专家系统.北京:科学出版社,1997
[2] 朱时银等.C++Builder 5编程实例与技巧.北京:机械工业出版社,2001
[3] 李凡.人工智能中的不确定性.北京:气象出版社,1992
[4] 张志涌等.精通MATLAB 6.5版.北京:北京航空航天大学出版社,2003
[5] Geiger D, Heckerman D. A Characterization of The Dirichlet Distribution with Applicable to learning Bayesian Networks. Proceedings of Eleventh Conference on Uncertainty in Artificial Intelligence, Montreal, QU, 1995: 196-207
[6] 张安华.设备故障诊断中的信息融合技术.机械科学与技术,1997,16(4):612-616
[7] 史忠植.知识发现.北京:清华大学出版社,2002
[8] Dasarathy B V. Sensor Fusion Potential Exploitation-Innovative Architecture and Illustrative Application. Proceedings of the IEEE, 1997, 85(1): 29-36
[9] 金星,洪延姬,武江涛,沈怀荣.基于故障树的智能型故障诊断系统.宇航学报,2001,22(3):111-114
[10] 李俭川.贝叶斯网络故障诊断与维修决策方法及应用研究:[博士学位论文].长沙:国防科技大学,2002
[11] C++ Builder与Matlab混合编程Http://cdf.51.net/software/softeng/development/c++ma.html
[12] 高文胜,钱政,严璋.基于决策树神经网络模型的电力变压器故障诊断方法.西安交通大学学报,1999,33(6):23-29
[13] 李国丽,王孝武.用马尔柯夫可靠性模型对测量仪表进行故障排序.合肥工业大学学报(自然科学版),1997,20(4):32-36
[14] 钱彦岭.测试性建模技术及其应用研究:[博士学位论文].长沙:国防科技大学,2002
[15] 赵不贿.一种基于模型模拟电路模糊故障诊断方法.电子测量技术,2001,(1):13-15
[16] 邱静.柔性加工设备状态监测与故障诊断及预警系统研究:[博士学位论文].长沙:国防科技大学,1998
[17] 陈长征,刘强.概率因果网络在汽轮机故障诊断中的应用.中国电机工程学报,2001,21(3):78-81
[18] 杨莉,尚勇,周跃峰,严璋.基于概率推理和模糊数学的变压器综合故障诊断模型.中国电机工程学报,2000,20(7):19-23
[19] 蔡自兴,徐光佑.人工智能及其应用.北京:清华大学出版社,1996
[20] Agre G. Diagnostic Bayesian Networks. Computers and Artificial Intelligence, 1996, 16(1): 41-56
[21] 轰炸6型飞机电气设备讲义,河南:空军第二航空学院,1994年12月翻印
[22] 严仰光主编,航空航天器供电系统,北京:航空工业出版社,1995
[23] 阮跃.案例推理在汽轮发电机组故障诊断中的应用.热能动力工程,2000,15(3):301-304
[24] 甘茂治等著,军用装备维修工程学,北京:国防工业出版社,1999
[25] 赵不贿.一种基于模型模拟电路模糊故障诊断方法.电子测量技术,2001,(1):13-15
[26] C++Builder调用Matlab的实现方法.Http://gbyang.4y.com.cn/matlabc.html
[27] Beiser J A, Rigdon S E. Bayes Prediction for the Number of Failures of A Repairable System. IEEE Transactions on Reliability, 1997, 46(2): 320-326
[28] Pearl J. Fusion, Propagation, and Structuring in Belief Networks. Artificial Intelligence, 1986, 29(9): 241-288
[29] 张晓莉,杨杰,吕永.诊断推理中人工神经网络与基于案例推理的结合.上海铁道大学学报,2000,21(6):6-11
[30] Kim J H, Pearl J. A Computation Model for Causal and Diagnostic Reasoning in Inference Systems. Proceedings of the 8th International Joint Conference on AI. Los Angeles, 1983. 190-193
[31] (美)Nils J. Nilsson著.郑扣根,庄越挺译.人工智能.机械工业出版社,2000
[32] Stephenson T A. An Introduction To Bayesian Network Theory And Usage. IDIAP-RR 00-03, Feb, 2000
[33] Jensen F V. Bayesian Network Basics. AISB Quarterly, 1996, 94: 9-22
[34] Shachter R D. Probabilistic Inference and Influence Diagrams. Operations Research, 1988, 36: 589-605
[35] Mahoney S M, and Laskey K B. Representing and Combining Partially Specified Conditional Probability Tables. Proc. of the 15th Conf. of Uncertainty in Artificial Intelligence, San Mateo, CA: Morgan Kaufmann, 1999: 327-339
[36] Jensen F V. An Introduction to Bayesian Networks. UCL Press Ltd., London, 1996
[37] Bresnick T A, Buede D M, Tatman J A. Introduction to Bayesian Networks: A Tutorial for the 66th MORS Symposium. Naval Postgraduate School Monterey, California, 23-25 June 1998
[38] 刘启元,张聪,沈一栋.信度网近似推理算法(下).计算机科学,2001,28(2):111-114
[39] Pearl J. Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference. Morgan Kaufmann, San Mateo, CA, 1988
[40] Pearl J. Graphical Models for Probabilistic and Causal Reasoning. The Computer Science and Engineering Handbook, Kluwer Academic Publishers, 1997: 697—714
[41] 詹原瑞,陈埏.影响图理论与方法.天津:天津大学出版社,1995
[42] 王军,周伟达.贝叶斯网络的研究与进展.电子科技,1999,(8):6-7
[43] Wolbrecht E, Ambrosio B D, Passch B, Kirby D. Monitoring and Diagnosis of A Multi-stage Manufacturing Process Using Bayesian Networks. Artificial Intelligence for Engineering, Design and Manufacturing, 2000, 14(2): 53-67
[44] 刘启元,张聪,沈一栋.信度网近似推理算法(上).计算机科学,2001,28(1):70-73
[45] Shachter R D., D'Ambrosio B, DelFabero B. Symbolic Probabilistic Inference in Belief Networks. Proceedings Eighth National Conference on AI, 1990, 126-131
[46] Software Packages for Graphical Models/Bayesian Networks. Http://www.cs.berkeley.edu/～murphyk/bayes/bnsoft.html
[47] 邢永康,沈一栋.信度网分类器.重庆大学学报(自然科学版),2001,23(5):49-52
[48] Cheng J, Greiner R. Comparing Bayesian Network Classifiers. In Proceedings of the 15th Conference on Uncertainty in Artificial Intelligence (UAI'99), Morgan Kaufmann Publishers, August 1999: 101—107
[49] 傅军,贺炜,阎建国,张洪才.贝叶斯网络在柴油机动力装置故障诊断中的 应用.上海海运学院学报,2001,22(3):68-72
[50] 孟宪尧,白广来,伞宝钢,韩新洁.贝叶斯数据融合技术在机舱故障智能诊断中的应用.大连海事大学学报,2002,28(3):10-13
[51] 华斌,周建中,喻菁.贝叶斯网络在水电机组故障诊断中的应用研究.华北电力大学学报,2004,9,31(5):33-36
[52] 王永强,律方成,李和明.基于贝叶斯网络和DGA的变压器故障诊断.高电压技术,2004,30(5):12-14
[53] 夏文汇,曾红.物流自动化系统故障诊断的贝叶斯决策判据.重庆工学院学报,2004.18(3):9-12
[54] Romessis C, Stamatis A, Mathioudakis K. Setting up a Belief Network for Turbofan Diagnosis With the Aid of an Engine Performance Model. ISABE 2001: 1032～1040
[55] Dechter R. Bucket Elimination: Aunifying Framework for Probabilistic Inference. Proc. 12th Conference on Uncertainty in Artificial Intelligence. Porland, OR, 1996: 211-219
[56] Przytula K, Hagen F, Yung K. Bayesian Networks for Satellite Payload Testing, Proceeding of the Forty-Fourth SPIE, Denver, July 1999
[57] Lepar V, Shenoy P P. A Comparison of Lauritzen and Spiegelhalter, Hugin and Shafer and Shenoy Architectures
[58] Leang S, Spanos C J. Ageneral Equipment Diagnostic System and Its Application on Photolithographic Sequences. IEEEE Transactions on Semiconductor Manufacturing, 1997, 10(3): 329-343
[59] Huard J F, Lazar A A. Fault Isolation Based on Decision-Theoretic Troubleshooting. Technical Report, Center for Telecommunications Research, Columbia University, New York, NY, 1996
[60] Madsen A L, Jensen F V. A Junction Tree Inference Based on Lazy Evaluation. The Proc. Of the Fourteenth Conf. On Uncertainty in Artificial Intelligence, Morgan Kaufmann Publishers, San Francisco, CA, 1998: 362-369
[61] Neal R M. Probabilistic Inference Using Markov Chain Monte Carlo Methods: [Technical Report CRGTR-93-1]. Department of Computer Science, University of Toronto, 1993
[62] Poole D. The Use of Conflicts in Searching Bayesian Networks: [Technical Report 93]. Department of Computer Science, University of Britis Columgia, March 1993
[63] 党明瑞,董宇翔.用Bayes网络对光纤接入网供电系统故障的监控.半导体光电,2000,21(4):286-290
[64] 胡振宇.贝叶斯学习的先验分布的研究:[硕士学位论文].广西:广西师范大学,2001
[65] Horvitz E, Barry M. Display of Information for Time-critical Decision Making. Proceedings of the 11th Conference on Uncertainty in Artificial Intelligence, 1995: 296-305
[66] 邢永康,沈一栋.学习信度网的结构.计算机科学,2000,27(10):83-87
[67] Skaanning C, Jensen F V, Kjaerulff U. Printer Troubleshooting Using Bayesian Networks. Industrial and Engineering Applications of Artificial Intelligence and Expert Systems (IEA/AIE) 2000, New Orleans, USA, June, 2000
[68] Cooper G, Herskovits E. A Bayesian Method for the Induction of Probabilistic Networks From Data. Machine Learning, 1992, 36(9): 141-153
[69] Chickering D. Learning Equivalence Classes of Bayesian Network Structures. Proc. 12th Conference on Uncertainty in Artificial Intelligence, Morgan Kaufmann, San Francisco, CA, 1996: 177-186
[70] Heckerman D. Learning Bayesian Network: The Combination of Knowledge and Statistical Data. Proceedings of the 10th Conference on Uncertainty in Artificial Intelligence, Morgan Kaufmann Publishers, San Francisco, CA., 1994: 293-301
[71] Hansen A F. Bayesian Networks as a Decision Support Tool in Marine Applications. PhD Thesis, Department of Naval Architecture and Offshore Engineering, Technical University of Denmark, December, 2000
[72] Nicholson A E, Brady J M. Sensor Validation Using Dynamic Belief Networks. Proceedings of the Eighth Conference on Uncertainty in Artificial Intelligence, 1992: 207～214
[73] Heckerman D, Breese J, Rommelse K. Sequential Troubleshooting Under Uncertainty. Proceedings of the Fifth International Workshop on Principles of Diagnosis, New Paltz, NY, October 1994: 121-130
