不确定数据背景下基于DS-MM的设备健康预测研究
|
摘要
目前,设备健康预测问题的研究大都在样本数据准确下进行,而在样本数据不确定下的研究却很少.因此,针对不确定样本数据下设备健康预测问题,提出了集成Dempster-Shafe(DS)证据理论与马尔可夫模型(MM)的联合优化模型.首先,基于马尔可夫模型,利用DS证据理论建立状态识别框架.其次,用区间数表示不确定的数据,并利用区间数之间的距离和相似度作为产生基本概率赋值(BPA)的证据,为了使预测结果更加可靠,采用Pignistic概率转换将BPA转化为基础状态的概率分布.最后,通过案例分析对模型进行评价和验证.结果表明,提出的方法能够有效解决数据不确定下的设备健康预测问题.
At present,most of the researches on equipment health prognostic information executed under the certain sample data,but there are fewstudies under the uncertain sample data. Therefore,this paper develops a joint optimization model of Dempster-Shafe evidence theory and Markov model for the problem of equipment health prediction under the uncertain sample data. First,based on Markov model,DS evidence theory is used to build the state recognition structure. Secondly,the uncertain data is showed by interval number and basic probability assignments( BPA) are generated based on the distance and similarity between interval numbers. To make the results more reliable,BPA is transformed into the probability distribution of basic states by Pignistic probability transform.Finally,a case study is used evaluated the performance of the model. The results showthat the proposed method could effectively solve the problem of equipment health prognostic under the uncertain data.
At present,most of the researches on equipment health prognostic information executed under the certain sample data,but there are fewstudies under the uncertain sample data. Therefore,this paper develops a joint optimization model of Dempster-Shafe evidence theory and Markov model for the problem of equipment health prediction under the uncertain sample data. First,based on Markov model,DS evidence theory is used to build the state recognition structure. Secondly,the uncertain data is showed by interval number and basic probability assignments( BPA) are generated based on the distance and similarity between interval numbers. To make the results more reliable,BPA is transformed into the probability distribution of basic states by Pignistic probability transform.Finally,a case study is used evaluated the performance of the model. The results showthat the proposed method could effectively solve the problem of equipment health prognostic under the uncertain data.
引文
[1]Zhang J K,Wang J,Liu X X,et al. Health prognostic method based on the time series analysis for actuators[J]. Applied Mechanics&Materials,2013,(373-375):329-332.
[2]Dai G,Du Y,Liu L,et al. In-situ MEMS inertial sensor health prognostic method based on micro vibrator[C]. Reliability and Maintainability Symposium,IEEE,2017.
[3]Wang Y,Peng Y,Zi Y,et al. A two-stage data-driven-based prognostic approach for bearing degradation problem[J]. IEEE Transactions on Industrial Informatics,2016,12(3):924-932.
[4]Du Y. Parameter estimation and remaining useful life prediction of lubricating oil with HMM[C]. International Conference on Wear of Materials,Long Beach,California,USA,2017.
[5]Khaleghei A,Makis V. Model parameter estimation and residual life prediction for a partially observable failing system[J]. Naval Research Logistics,2015,62(3):190-205.
[6]Dong M,He D,Banerjee P,et al. Equipment health diagnosis and prognosis using hidden semi-Markov models[J]. The International Journal of Advanced Manufacturing Technology,2006,30(7):738-749.
[7]Dong M,He D. Hidden semi-Markov model-based methodology for multi-sensor equipment health diagnosis and prognosis[J]. European Journal of Operational Research,2007,178(3):858-878.
[8]Wang Ning,Sun Shu-dong,Li Shu-ming,et al. Equipment state recognition and fault prognostics methods based on DD-HSMMmodel[J]. Computer Integrated Manufacturing Systems,2012,18(8):1861-1848.
[9]Liu Qin-ming,Li Ya-qin,Lv Wen-yuan,et al. Equipment health diagnostics and prognostics method based on adaptive HSMM[J].Computer Integrated Manufacturing Systems, 2016, 22(9):2187-2194.
[10]Tan Yong-xue,Wang Hong-guang,Yang Ai-ling,et al. Numerical prediction of hydrodynamic noise for a centrifugal pump[J].Journal of University of Shanghai for Science and Technology,2011,33(1):89-94.
[11]Gui Lin,Wu Xiao-yue. Discrete hidden semi-Markov model based on prognosis model[J]. Application Research of Computers,2008,25(11):3320-3322.
[12]Li Yu-peng,Lu Xi. Preliminary study on fatigue damage line[J].Journal of University of Shanghai for Science and Technology,2010,32(5):453-456.
[13]Niu G,Zhao Y,Defoort M,et al. Fault diagnosis of locomotive electro-pneumatic brake through uncertain bond graph modeling and robust online monitoring[J]. Mechanical Systems&Signal Processing,2015,50-51:676-691.
[14]Tang H,Li D,Chen W,et al. Uncertainty quantification using evidence theory in concrete fatigue damage prognosis[C]. IEEE International Conference on Prognostics and Health Management.IEEE,2016:1-7.
[15] Wu Jian-fei,Liu Qin-ming,Lv Wen-yuan,et al. Equipment health prognosis based on grey EM-SHSMMunder missing data[J]. Application Research of Computers,2018,35(11):3255-3258.
[16]Schafer U,Schnurr M. A comparison of simple tests for accuracy of approximate solutions to nonlinear systems with uncertain data[J]. Journal of Industrial&Management Optimization,2017,2(4):425-434.
[17]He Yun-bin,Wang Xiao,Wan Jing,et al. Uncertain data clustering algorithm based on density in the obstacle space[J]. Journal of Chinese Computer Systems,2017,38(12):2772-2776.
[8]王宁,孙树栋,李淑敏,等.基于DD-HSMM的设备运行状态识别与故障预测方法[J].计算机集成制造系统,2012,18(8):1861-1868.
[9]刘勤明,李亚琴,吕文元,等.基于自适应隐式半马尔可夫模型的设备健康诊断与寿命预测方法[J].计算机集成制造系统,2016,22(9):2187-2194.
[10]谭永学,王宏光,杨爱玲,等.离心泵水动力噪声预测[J].上海理工大学学报,2011,33(1):89-94.
[11]桂林,武小悦.基于离散HSMM的故障预测模型[J].计算机应用研究,2008,25(11):3320-3322.
[12]李玉鹏,卢曦.疲劳损伤线的初步研究[J].上海理工大学学报,2010,32(5):453-456.
[15]吴健飞,刘勤明,吕文元,等.基于灰色EM-SHSMM的缺失数据下设备健康预测研究[J].计算机应用研究,2018,35(11):3255-3258.
[17]何云斌,王霄,万静,等.障碍空间中基于密度的不确定数据聚类算法[J].小型微型计算机系统,2017,38(12):2772-2776.
[2]Dai G,Du Y,Liu L,et al. In-situ MEMS inertial sensor health prognostic method based on micro vibrator[C]. Reliability and Maintainability Symposium,IEEE,2017.
[3]Wang Y,Peng Y,Zi Y,et al. A two-stage data-driven-based prognostic approach for bearing degradation problem[J]. IEEE Transactions on Industrial Informatics,2016,12(3):924-932.
[4]Du Y. Parameter estimation and remaining useful life prediction of lubricating oil with HMM[C]. International Conference on Wear of Materials,Long Beach,California,USA,2017.
[5]Khaleghei A,Makis V. Model parameter estimation and residual life prediction for a partially observable failing system[J]. Naval Research Logistics,2015,62(3):190-205.
[6]Dong M,He D,Banerjee P,et al. Equipment health diagnosis and prognosis using hidden semi-Markov models[J]. The International Journal of Advanced Manufacturing Technology,2006,30(7):738-749.
[7]Dong M,He D. Hidden semi-Markov model-based methodology for multi-sensor equipment health diagnosis and prognosis[J]. European Journal of Operational Research,2007,178(3):858-878.
[8]Wang Ning,Sun Shu-dong,Li Shu-ming,et al. Equipment state recognition and fault prognostics methods based on DD-HSMMmodel[J]. Computer Integrated Manufacturing Systems,2012,18(8):1861-1848.
[9]Liu Qin-ming,Li Ya-qin,Lv Wen-yuan,et al. Equipment health diagnostics and prognostics method based on adaptive HSMM[J].Computer Integrated Manufacturing Systems, 2016, 22(9):2187-2194.
[10]Tan Yong-xue,Wang Hong-guang,Yang Ai-ling,et al. Numerical prediction of hydrodynamic noise for a centrifugal pump[J].Journal of University of Shanghai for Science and Technology,2011,33(1):89-94.
[11]Gui Lin,Wu Xiao-yue. Discrete hidden semi-Markov model based on prognosis model[J]. Application Research of Computers,2008,25(11):3320-3322.
[12]Li Yu-peng,Lu Xi. Preliminary study on fatigue damage line[J].Journal of University of Shanghai for Science and Technology,2010,32(5):453-456.
[13]Niu G,Zhao Y,Defoort M,et al. Fault diagnosis of locomotive electro-pneumatic brake through uncertain bond graph modeling and robust online monitoring[J]. Mechanical Systems&Signal Processing,2015,50-51:676-691.
[14]Tang H,Li D,Chen W,et al. Uncertainty quantification using evidence theory in concrete fatigue damage prognosis[C]. IEEE International Conference on Prognostics and Health Management.IEEE,2016:1-7.
[15] Wu Jian-fei,Liu Qin-ming,Lv Wen-yuan,et al. Equipment health prognosis based on grey EM-SHSMMunder missing data[J]. Application Research of Computers,2018,35(11):3255-3258.
[16]Schafer U,Schnurr M. A comparison of simple tests for accuracy of approximate solutions to nonlinear systems with uncertain data[J]. Journal of Industrial&Management Optimization,2017,2(4):425-434.
[17]He Yun-bin,Wang Xiao,Wan Jing,et al. Uncertain data clustering algorithm based on density in the obstacle space[J]. Journal of Chinese Computer Systems,2017,38(12):2772-2776.
[8]王宁,孙树栋,李淑敏,等.基于DD-HSMM的设备运行状态识别与故障预测方法[J].计算机集成制造系统,2012,18(8):1861-1868.
[9]刘勤明,李亚琴,吕文元,等.基于自适应隐式半马尔可夫模型的设备健康诊断与寿命预测方法[J].计算机集成制造系统,2016,22(9):2187-2194.
[10]谭永学,王宏光,杨爱玲,等.离心泵水动力噪声预测[J].上海理工大学学报,2011,33(1):89-94.
[11]桂林,武小悦.基于离散HSMM的故障预测模型[J].计算机应用研究,2008,25(11):3320-3322.
[12]李玉鹏,卢曦.疲劳损伤线的初步研究[J].上海理工大学学报,2010,32(5):453-456.
[15]吴健飞,刘勤明,吕文元,等.基于灰色EM-SHSMM的缺失数据下设备健康预测研究[J].计算机应用研究,2018,35(11):3255-3258.
[17]何云斌,王霄,万静,等.障碍空间中基于密度的不确定数据聚类算法[J].小型微型计算机系统,2017,38(12):2772-2776.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |