基于EWMA-BN的冷水机组故障诊断策略
|
摘要
为提高冷水机组故障诊断的准确度,本文提出一种基于EWMA-BN的冷水机组故障诊断策略。EWMA-BN模型通过EWMA控制图进行故障检测,以其控制限为阈值将各性能指标的故障数据分为高、低、正常3种状态,通过概率统计获得条件概率表,将条件概率表和由专家知识获得的先验概率表输入BN进行故障诊断。利用实验数据从输入模型的证据节点数量、顺序及完整性等方面分析该模型的故障诊断特性。结果表明:EWMA-BN方法对冷水机组常见故障的诊断效果显著,后验概率值(故障诊断结果)均大于0.85,且输入模型的证据节点越多,故障诊断结果越准确,但证据节点输入模型的顺序对最终故障诊断结果无任何影响;对不确定、不完整信息的利用进一步提高了模型的故障诊断能力。采用ASHRAE Project提供的数据对EWMA-BN模型进行验证,故障诊断结果良好。
To improve the accuracy of fault diagnosis for chillers, a fault diagnosis strategy based on an exponentially weighted moving average(EWMA) and Bayesian network(BN) is proposed in this study. The EWMA-BN method used an EWMA control chart to detect faults, and its control limits classified the fault data into the three states of higher, lower, and normal. The conditional probability table was obtained through probability statistics, and the prior probabilities were obtained from expert knowledge. The conditional probabilities were input to BN for fault diagnosis. With respect to number, input order, and completeness of evidence nodes, experimental data were used to analyze the characteristics of the method for fault diagnosis. The results showed that the EWMA-BN method had a significant effect on fault diagnosis for chillers, and the posterior probability values(fault diagnosis results) were all higher than 85%. The results also showed that the increase of evidence nodes could improve the accuracy of fault diagnosis results, but the order of the input nodes had no effect on the final results. The use of uncertain and incomplete information further improved the fault diagnosis capability of the method. The EWMA-BN method was validated using the data provided by the ASHRAE Project, which revealed that this strategy is robust and effective.
To improve the accuracy of fault diagnosis for chillers, a fault diagnosis strategy based on an exponentially weighted moving average(EWMA) and Bayesian network(BN) is proposed in this study. The EWMA-BN method used an EWMA control chart to detect faults, and its control limits classified the fault data into the three states of higher, lower, and normal. The conditional probability table was obtained through probability statistics, and the prior probabilities were obtained from expert knowledge. The conditional probabilities were input to BN for fault diagnosis. With respect to number, input order, and completeness of evidence nodes, experimental data were used to analyze the characteristics of the method for fault diagnosis. The results showed that the EWMA-BN method had a significant effect on fault diagnosis for chillers, and the posterior probability values(fault diagnosis results) were all higher than 85%. The results also showed that the increase of evidence nodes could improve the accuracy of fault diagnosis results, but the order of the input nodes had no effect on the final results. The use of uncertain and incomplete information further improved the fault diagnosis capability of the method. The EWMA-BN method was validated using the data provided by the ASHRAE Project, which revealed that this strategy is robust and effective.
引文
[1]ZHOU Qiang,WANG Shenwei,XIAO Fu.A novel strategy for the fault detection and diagnosis of centrifugal chiller systems[J].HVAC&R Research,2009,15(1):57-75.
[2]胡云鹏,陈焕新,周诚,等.基于小波去噪的冷水机组传感器故障检测[J].华中科技大学学报(自然科学版),2013,41(3):16-19.(HU Yunpeng,CHEN Huanxin,CHOU Cheng,et al.Chiller sensor fault detection using wavelet de-noising[J].Huazhong University of Science&Technology(Natural Science Edition),2013,41(3):16-19.)
[3]CHEN Y M,LAN L L.A fault detection technique for airsource heat pump water chiller/heater[J].Energy and Buildings,2009,41(8):881-887.
[4]黄彬彬,谷波,任能.基于主元分析的制冷系统渐变故障检测[J].制冷学报,2009,30(1):56-62.(HUANG Binbin,GU Bo,REN Neng.Gradual faults detection of refrigeration system based on principal component analysis[J].Journal of Refrigeration,2009,30(1):56-62.)
[5]石书彪,陈焕新,李冠男,等.基于改进BP网络的冷水机组故障诊断[J].制冷学报,2015,36(6):34-39.(SHIShubiao,CHEN Huanxin,LI Guannan,et al.Research on fault diagnosis of chillers based on improved BP network[J].Journal of Refrigeration,2015,36(6):34-39.)
[6]SALSBURY T I,DIAMOND R C.Fault detection in HVACsystems using model-based feed forward control[J].Energy&Buildings,2001,33(4):403-415.
[7]李冠男,胡云鹏,陈焕新,等.基于SVDD的冷水机组传感器故障检测及效率分析[J].化工学报,2015,66(5):1815-1820.(LI Guannan,HU Yunpeng,CHENHuanxin,et al.SVDD-based chiller sensor fault detection method and its detection efficiency[J].CIESC Journal,2015,66(5):1815-1820.)
[8]赵阳,徐田华,周玉平,等.基于贝叶斯网络的高铁信号系统车载设备故障诊断方法的研究[J].铁道学报,2014,36(11):48-53.(ZHAO Yang,XU Tianhua,ZHOUYuping,et al.Bayesian network based fault diagnosis system for vehicleon-boad equipment of high-speed railway[J].Journal of the China Railway Society,2014,36(11):48-53.)
[9]朱坚民,张雷,翟东婷,等.基于声音多特征贝叶斯网络融合的话者识别研究[J].仪器仪表学报,2013,34(9):2058-2067.(ZHU Jianmin,ZHANG Lei,ZHAI Dongting,et al.Speaker recognition research based on voice multifeature Bayesian network fusion[J].Chinese Journal of Scientific Instrument,2013,34(9):2058-2067.)
[10]何曙光,何桢,齐二石,等.基于马尔可夫链模型的EW-MA控制图性能分析与优化[J].系统工程与电子技术,2008,30(6):1127-1130.(HE Shuguang,HE Zhen,QIErshi,et al.Performance analysis and chart based on optimization of EWMA control Markov chain model[J].Systems Engineering and Electronics,2008,30(6):1127-1130.)
[11]白双梅,杜福洲.基于马尔可夫链的EWMA控制图参数优化及其实现[J].制造业自动化,2010,32(6):64-67.(BAI Shuangmei,DU Fuzhou.Parameter optimization and implementation for ewma control chart based on markov chain[J].Manufacturing Automation,2010,32(6):64-67.)
[12]王永强,律方成,李和明,等.基于粗糙集理论和贝叶斯网络的电力变压器故障诊断方法[J].中国电机工程学报,2006,26(8):137-141.(WANG Yongqiang,LYUfangcheng,LI Heming,et al.Synthetic fault diagnosis method of power transformer based on rough set theory and bayesian network[J].Proceedings of the CSEE,2006,26(8):137-141.)
[13]ZHAO Yang,WANG Shengwei,XIAO Fu.A statistical fault detection and diagnosis method for centrifugal chillers based on exponentially-weighted moving average control charts and support vector regression[J].Applied Thermal Engineering,2013,51(1/2):560-572.
[14]卢文喜,罗建男,鲍新华,等.贝叶斯网络在水资源管理中的应用.吉林大学学报(地球科学版),2011,41(1):153-158.(LU Wenxi,LUO Jiannan,BAO Xinhua,et al.Application of Bayesian network in water resource management[J].Journal of Jilin University(Earth Science Edition),2011,41(1):153-158.)
[15]ZHAO Yang,XIAO Fu,WANG Shengwei.An intelligent chiller fault detection and diagnosis methodology using Bayesian belief network[J].Energy and Buildings,2013,57:278-288.
[16]ZHAO Yang,WEN Jin,XIAO Fu,et al.Diagnostic Bayesian networks for diagnosing air handling units faultspart I:faults in dampers,fans,filters and sensors[J].Applied Thermal Engineering,2017,111:1272-1286.
[17]WANG Zhanwei,WANG Zhiwei,GU Xiaowei,et al.Feature selection based on Bayesian network for chiller fault diagnosis from the perspective of field applications[J].Applied Thermal Engineering,2018,129:674-683.
[2]胡云鹏,陈焕新,周诚,等.基于小波去噪的冷水机组传感器故障检测[J].华中科技大学学报(自然科学版),2013,41(3):16-19.(HU Yunpeng,CHEN Huanxin,CHOU Cheng,et al.Chiller sensor fault detection using wavelet de-noising[J].Huazhong University of Science&Technology(Natural Science Edition),2013,41(3):16-19.)
[3]CHEN Y M,LAN L L.A fault detection technique for airsource heat pump water chiller/heater[J].Energy and Buildings,2009,41(8):881-887.
[4]黄彬彬,谷波,任能.基于主元分析的制冷系统渐变故障检测[J].制冷学报,2009,30(1):56-62.(HUANG Binbin,GU Bo,REN Neng.Gradual faults detection of refrigeration system based on principal component analysis[J].Journal of Refrigeration,2009,30(1):56-62.)
[5]石书彪,陈焕新,李冠男,等.基于改进BP网络的冷水机组故障诊断[J].制冷学报,2015,36(6):34-39.(SHIShubiao,CHEN Huanxin,LI Guannan,et al.Research on fault diagnosis of chillers based on improved BP network[J].Journal of Refrigeration,2015,36(6):34-39.)
[6]SALSBURY T I,DIAMOND R C.Fault detection in HVACsystems using model-based feed forward control[J].Energy&Buildings,2001,33(4):403-415.
[7]李冠男,胡云鹏,陈焕新,等.基于SVDD的冷水机组传感器故障检测及效率分析[J].化工学报,2015,66(5):1815-1820.(LI Guannan,HU Yunpeng,CHENHuanxin,et al.SVDD-based chiller sensor fault detection method and its detection efficiency[J].CIESC Journal,2015,66(5):1815-1820.)
[8]赵阳,徐田华,周玉平,等.基于贝叶斯网络的高铁信号系统车载设备故障诊断方法的研究[J].铁道学报,2014,36(11):48-53.(ZHAO Yang,XU Tianhua,ZHOUYuping,et al.Bayesian network based fault diagnosis system for vehicleon-boad equipment of high-speed railway[J].Journal of the China Railway Society,2014,36(11):48-53.)
[9]朱坚民,张雷,翟东婷,等.基于声音多特征贝叶斯网络融合的话者识别研究[J].仪器仪表学报,2013,34(9):2058-2067.(ZHU Jianmin,ZHANG Lei,ZHAI Dongting,et al.Speaker recognition research based on voice multifeature Bayesian network fusion[J].Chinese Journal of Scientific Instrument,2013,34(9):2058-2067.)
[10]何曙光,何桢,齐二石,等.基于马尔可夫链模型的EW-MA控制图性能分析与优化[J].系统工程与电子技术,2008,30(6):1127-1130.(HE Shuguang,HE Zhen,QIErshi,et al.Performance analysis and chart based on optimization of EWMA control Markov chain model[J].Systems Engineering and Electronics,2008,30(6):1127-1130.)
[11]白双梅,杜福洲.基于马尔可夫链的EWMA控制图参数优化及其实现[J].制造业自动化,2010,32(6):64-67.(BAI Shuangmei,DU Fuzhou.Parameter optimization and implementation for ewma control chart based on markov chain[J].Manufacturing Automation,2010,32(6):64-67.)
[12]王永强,律方成,李和明,等.基于粗糙集理论和贝叶斯网络的电力变压器故障诊断方法[J].中国电机工程学报,2006,26(8):137-141.(WANG Yongqiang,LYUfangcheng,LI Heming,et al.Synthetic fault diagnosis method of power transformer based on rough set theory and bayesian network[J].Proceedings of the CSEE,2006,26(8):137-141.)
[13]ZHAO Yang,WANG Shengwei,XIAO Fu.A statistical fault detection and diagnosis method for centrifugal chillers based on exponentially-weighted moving average control charts and support vector regression[J].Applied Thermal Engineering,2013,51(1/2):560-572.
[14]卢文喜,罗建男,鲍新华,等.贝叶斯网络在水资源管理中的应用.吉林大学学报(地球科学版),2011,41(1):153-158.(LU Wenxi,LUO Jiannan,BAO Xinhua,et al.Application of Bayesian network in water resource management[J].Journal of Jilin University(Earth Science Edition),2011,41(1):153-158.)
[15]ZHAO Yang,XIAO Fu,WANG Shengwei.An intelligent chiller fault detection and diagnosis methodology using Bayesian belief network[J].Energy and Buildings,2013,57:278-288.
[16]ZHAO Yang,WEN Jin,XIAO Fu,et al.Diagnostic Bayesian networks for diagnosing air handling units faultspart I:faults in dampers,fans,filters and sensors[J].Applied Thermal Engineering,2017,111:1272-1286.
[17]WANG Zhanwei,WANG Zhiwei,GU Xiaowei,et al.Feature selection based on Bayesian network for chiller fault diagnosis from the perspective of field applications[J].Applied Thermal Engineering,2018,129:674-683.