摘要
针对液压动力单元中元件数量繁多、联系复杂,以及难以精确进行故障诊断的问题,提出了融合多源信息的贝叶斯网络故障诊断新方法,建立了液压动力单元单一故障失效模式的贝叶斯网络拓扑结构,开发了融合多源信息的故障诊断网络。利用Noisy-OR/MAX计算了故障诊断网络的条件概率参数;针对两故障并发模式,将观测信息节点加入已建立的单一故障模式诊断网络,辅助诊断液压动力单元的两故障并发失效。实例诊断结果表明:对单一失效的诊断,观测节点对诊断结果的影响不大,正确率均接近100%;对于两失效同时发生的情况,未考虑观测信息的模型出现了漏诊和误诊的问题,正确率不到50%,而考虑观测信息的模型能够正确诊断出所有两失效并发的情况,正确率达到100%。研究结果可为水下生产系统的故障诊断奠定基础。
To address the problem of large number of components and complicated connection in the hydraulic power unit which makes it difficult to accurately diagnose the fault,a new Bayesian network fault diagnosis method based on multi-source information is proposed. A Bayesian network topology of single fault failure mode of the hydraulic power unit is established. A fault diagnosis network integrating multi-source information is developed. The conditional probability parameters of the fault diagnosis network are calculated using Noisy-OR/MAX. For the two simultaneous faults modes,the observation information nodes are added to the established single fault mode diagnosis network to assist diagnosing the two simultaneous faults of the hydraulic power unit. The case diagnosis results show that,for the diagnosis of single fault,the observation node has little effect on the diagnosis result,and the correct rate is close to 100%. For the case of two simultaneous faults,the model without the observation information has the problem of missed diagnosis and misdiagnosis,of which the correct rate is less than 50%. However,the model considering the observation information can correctly diagnose two simultaneous faults,and the correct rate reaches 100%. The study can lay the foundation for fault diagnosis of subsea production system.
引文
[1]FUDGE D,DONOVAN J F.Multiplex control system the heart to the operability of subsea development[R].AU-TOE-V22-023,1990.
[2]ISO.Petroleum and natural gas industries design and operation of subsea production system-Part 6:Subsea production control system:ISO 13628-6:2006[S].Geneva:International Organization for Standards,2006.
[3]范亚民.水下生产控制系统的发展[J].石油机械,2012,40(7):45-49.FAN Y M.Development of underwater production control system[J].China Petroleum Machinery,2012,40(7):45-49.
[4]张宪阵,王晓敏,张凡,等.水下生产系统液压动力单元液压系统原理研究[J].液压与气动,2014(10):33-37.ZHANG X Z,WANG X M,ZHANG F,et al.Hydraulic theory study for hydraulic power unit of subsea production control system[J].Chinese Hydraulics&Pneumatics,2014(10):33-37.
[5]王鑫,左信,马恬然,等.水下采油树液压系统高压回油压力分析[J].海洋工程装备与技术,2016,3(5):298-304.WANG X,ZUO X,MA T R,et al.Study on the high pressure oil return of subsea christmas tree hydraulic control system[J].Ocean Engineering Equipment and Technology,2016,3(5):298-304.
[6]胡飚,朱宏武,丁矿,等.水下跨接管的外部扰流及振动分析[J].石油机械,2016,44(4):42-45.HU B,ZHU H W,DING K,et al.Analysis on exterior circumferential flow and vibration of subsea jumper[J].China Petroleum Machinery,2016,44(4):42-45.
[7]余建星,刘春辉,何宁,等.深水跨接管热应力计算及敏感性分析[J].天津理工大学学报,2015,31(1):1-6.YU J X,LIU C H,HE N,et al.Calculation and sensitivity analysis of the thermal stress in a deepwater jumper[J].Journal of Tianjin University of Technology,2015,31(1):1-6.
[8]马增骥,唐文勇,薛鸿祥.水下生产系统跨接管结构极限承载能力分析[J].海洋工程,2013,31(1):9-15.MA Z J,TANG W Y,XUE H X.Ultimate strength analysis of a jumper in subsea production facility[J].The Ocean Engineering,2013,31(1):9-15.
[9]赖文龙,唐文勇,薛鸿祥.水下生产系统跨接管结构在地震作用下动力响应分析[J].振动与冲击,2013,32(4):48-53.LAI W L,TANG W Y,YUE H X.Dynamic responses of a jumper in a subsea production facility under earthquake[J].Journal of Vibration and Shock,2013,32(4):48-53.
[10]CAI B P,HUANG L,XIE M.Bayesian networks in fault diagnosis[J].IEEE Transactions on Industrial Informatics,2017(13):2227-2240.
[11]张玉龙,段梦兰,段礼祥,等.基于SAX的往复压缩机气阀故障诊断[J].石油机械,2018,46(3):78-83.ZHANG Y L,DUAN M L,DUAN L X,et al.SAX-based fault diagnosis of air valve on reciprocating compressor[J].China Petroleum Machinery,2018,46(3):78-83.
[12]白堂博,张来斌,王旭铎,等.基于SAX的关联规则挖掘方法在故障诊断中的应用[J].石油机械,2017,45(1):70-74.BAI T B,ZHANG L B,WANG X D,et al.Application of sax-based association rule mining on fault diagnosis[J].China Petroleum Machinery,2017,45(1):70-74.
[13]姜民政,段天玉,张迪,等.基于RS-LVQ的同井注采系统故障诊断研究[J].石油机械,2018,46(3):95-99.JIANG M Z,DUAN T Y,ZHANG D,et al.RS-LVQ-based fault diagnosis of the injection-produetion system[J].China Petroleum Machinery,2018,46(3):95-99.
[14]CAI B P,LIU Y H,FAN Q.Multi-source information fusion based fault diagnosis of ground-source heat pump using Bayesian network[J].Applied Energy,2014(114):1-9.
[15]YODO N,WANG P.Resilience modeling and quantification for engineered systems using Bayesian networks[J].Journal of Mechanical Design,2016(3):031404.
[16]LI W,POUPART P,BEEK P.Exploiting structure in weighted model counting approaches to probabilistic inference[J].Journal of Artificial Intelligence Research,2011,40:729-765.