基于概率神经网络和线性判别分析的PEMFC水管理故障诊断方法研究
|
摘要
为了准确迅速判断质子交换膜燃料电池(proton exchange membrane fuel cell,PEMFC)水管理子系统故障,提出基于概率神经网络(probabilistic neural network,PNN)和线性判别分析(linear discriminant analysis,LDA)的PEMFC水管理故障诊断方法。该方法采用归一化消除原始数据参量之间的量纲影响,使用线性判别分析对归一化后的变量进行特征提取。不但可以将原始实验数据映射到同一区间内,而且能有效降低数据维度。利用概率神经网络对5维故障特征向量实现水管理故障诊断。17086组PEMFC水管理故障样本的诊断结果表明:所提方法能有效识别正常状态、水淹故障和膜干故障共3种水管理健康状态,训练集和测试集的诊断正确率分别为99.80%和93.48%,运算时间仅为14.04s。与BPNN和LDA-BPNN相比:新方法测试集的预测精度分别高出17.47%和2.75%,计算时间分别节省39.83s和28.37s。因此,新方法能快速准确地诊断PEMFC水管理故障。
In order to accurately and quickly identify the water management subsystem fault problem of proton exchange membrane fuel cell(PEMFC), a PEMFC water management fault diagnosis method based on probabilistic neural network(PNN) and linear discriminant analysis(LDA)was proposed. In this method, the dimensional effect between the original data parameters was eliminated by normalization,and the normalized variables were extracted by linear discriminant analysis. Not only can the original experimental data be mapped to the same interval, but also can effectively reduce the data dimension. The probabilistic neural network was used to implement water management fault diagnosis for 5-dimensional fault eigenvectors. The diagnostic results of 17086 sets of PEMFC water management failure samples show that the proposed method can effectively identify three health states of water management system: normal state, flooded fault,and membrane dry fault. The diagnostic accuracy of the training set and test set is 99.80% and 93.48% respectively, and the computing time is only 14.04 seconds. Compared with BPNN and LDA-BPNN, the prediction accuracy of the test set of the novel method is 17.47% and 2.75% higher than that of BPNN and LDA-BPNN, respectively, and the calculation time is saved by 39.83 seconds and 28.37 seconds, respectively.Therefore, the novel method can quickly and accurately diagnose PEMFC water management failure.
In order to accurately and quickly identify the water management subsystem fault problem of proton exchange membrane fuel cell(PEMFC), a PEMFC water management fault diagnosis method based on probabilistic neural network(PNN) and linear discriminant analysis(LDA)was proposed. In this method, the dimensional effect between the original data parameters was eliminated by normalization,and the normalized variables were extracted by linear discriminant analysis. Not only can the original experimental data be mapped to the same interval, but also can effectively reduce the data dimension. The probabilistic neural network was used to implement water management fault diagnosis for 5-dimensional fault eigenvectors. The diagnostic results of 17086 sets of PEMFC water management failure samples show that the proposed method can effectively identify three health states of water management system: normal state, flooded fault,and membrane dry fault. The diagnostic accuracy of the training set and test set is 99.80% and 93.48% respectively, and the computing time is only 14.04 seconds. Compared with BPNN and LDA-BPNN, the prediction accuracy of the test set of the novel method is 17.47% and 2.75% higher than that of BPNN and LDA-BPNN, respectively, and the calculation time is saved by 39.83 seconds and 28.37 seconds, respectively.Therefore, the novel method can quickly and accurately diagnose PEMFC water management failure.
引文
[1]陈维荣,刘嘉蔚,李奇,等.质子交换膜燃料电池故障诊断方法综述及展望[J].中国电机工程学报,2017,37(16):4712-4721.Chen Weirong,Liu Jiawei,Li Qi,et al.Review and prospect of fault diagnosis methods for proton exchange membrane fuel cell[J].Proceedings of the CSEE,2017,37(16):4712-4721(in Chinese).
[2]赵思臣,王奔,谢玉洪,等.无外增湿质子交换膜燃料电池线性温度扫描实验[J].中国电机工程学报,2014,34(26):4528-4533.Zhao Sichen,Wang Ben,Xie Yuhong,et al.Linear temperature sweep experimental study on proton exchange membrane fuel cell without external humidification[J].Proceedings of the CSEE,2014,34(26):4528-4533(in Chinese).
[3]李曦,曹广益,朱新坚.质子交换膜燃料电池电堆温度特性的模糊建模[J].上海交通大学学报,2005,39(S1):187-188.Li Xi,Cao Guangyi,Zhu Xinjian.Fuzzy modeling for PEMFC stack temperature characteristic[J].Journal of Shanghai Jiaotong University,2005,39(S1):187-188(in Chinese).
[4]刘嘉蔚,李奇,陈维荣,等.基于多分类相关向量机和模糊C均值聚类的有轨电车用燃料电池系统故障诊断方法[J].中国电机工程学报,2018,38(20):6045-6052.Liu Jiawei,Li Qi,Chen Weirong,et al.A fault diagnosis method of fuel cell systems for tramways based on the multi-class relevance vector machine and fuzzy C means clustering[J].Proceedings of the CSEE,2018,38(20):6045-6052(in Chinese).
[5]Liu Jianxing,Luo Wensheng,Yang Xiaozhan,et al.Robust model-based fault diagnosis for PEM fuel cell air-feed system[J].IEEE Transactions on Industrial Electronics,2016,63(5):3261-3270.
[6]Xie Changjun,Xu Xinyi,Bujlo P,et al.Fuel cell and lithium iron phosphate battery hybrid powertrain with an ultracapacitor bank using direct parallel structure[J].Journal of Power Sources,2015,279:487-494.
[7]Liu Jiawei,Li Qi,Chen Weirong,et al.A discrete hidden Markov model fault diagnosis strategy based on K-means clustering dedicated to PEM fuel cell systems of tramways[J].International Journal of Hydrogen Energy,2018,43(27):12428-12441.
[8]Mao Lei,Jackson L.Effect of sensor set size on polymer electrolyte membrane fuel cell fault diagnosis[J].Sensors,2018,18(9):2777.
[9]Mao Lei,Davies B,Jackson L.Application of the sensor selection approach in polymer electrolyte membrane fuel cell prognostics and health management[J].Energies,2017,10(10):1511.
[10]Mao L,Jackson L,Davies B.Investigation of PEMFCfault diagnosis with consideration of sensor reliability[J].International Journal of Hydrogen Energy,2018,43(35):16941-16948.
[11]Mao Lei,Jackson L,Davies B.Effectiveness of a novel sensor selection algorithm in PEM fuel cell on-line diagnosis[J].IEEE Transactions on Industrial Electronics,2018,65(9):7301-7310.
[12]Mao L,Jackson L,Dunnett S.Fault diagnosis of practical polymer electrolyte membrane(PEM)fuel cell system with data-driven approaches[J].Fuel Cells,2017,17(2):247-258.
[13]Li Zhongliang,Outbib R,Giurgea S,et al.Fault diagnosis for PEMFC systems in consideration of dynamic behaviors and spatial inhomogeneity[J].IEEETransactions on Energy Conversion,2019,34(1):3-11.
[14]Li Zhongliang,Cadet C,Outbib R.Diagnosis for PEMFCbased on magnetic measurements and data-driven approach[J].IEEE Transactions on Energy Conversion,2019,34(2):964-972.
[15]Li Zhongliang,Outbib R,Giurgea S,et al.Fault diagnosis for fuel cell systems:a data-driven approach using high-precise voltage sensors[J].Renewable Energy,2019,135:1435-1444.
[16]杨忠君,刘精一,宗学军.质子交换膜燃料电池故障检测研究[J].可再生能源,2015,33(1):128-133.Yang Zhongjun,Liu Jingyi,Zong Xuejun.Fault detection research based on proton exchange membrane fuel cell[J].Renewable Energy Resources,2015,33(1):128-133(in Chinese).
[17]周苏,任宏伟,裴冯来.基于诊断用COMSOL模型的PEMFC故障诊断方法研究[J].化学工业与工程,2015,32(4):56-62.Zhou Su,Ren Hongwei,Pei Fenglai.Faults diagnosis method study of PEMFC based on a diagnostic COMSOLmodel[J].Chemical Industry and Engineering,2015,32(4):56-62(in Chinese).
[18]Li Dan,Hu Guoqiang,Spanos C J.A data-driven strategy for detection and diagnosis of building chiller faults using linear discriminant analysis[J].Energy and Buildings,2016,128:519-529.
[19]Jiang Quansheng,Shen Yehu,Li Hua,et al.New fault recognition method for rotary machinery based on information entropy and a probabilistic neural network[J].Sensors,2018,18(2):337.
[2]赵思臣,王奔,谢玉洪,等.无外增湿质子交换膜燃料电池线性温度扫描实验[J].中国电机工程学报,2014,34(26):4528-4533.Zhao Sichen,Wang Ben,Xie Yuhong,et al.Linear temperature sweep experimental study on proton exchange membrane fuel cell without external humidification[J].Proceedings of the CSEE,2014,34(26):4528-4533(in Chinese).
[3]李曦,曹广益,朱新坚.质子交换膜燃料电池电堆温度特性的模糊建模[J].上海交通大学学报,2005,39(S1):187-188.Li Xi,Cao Guangyi,Zhu Xinjian.Fuzzy modeling for PEMFC stack temperature characteristic[J].Journal of Shanghai Jiaotong University,2005,39(S1):187-188(in Chinese).
[4]刘嘉蔚,李奇,陈维荣,等.基于多分类相关向量机和模糊C均值聚类的有轨电车用燃料电池系统故障诊断方法[J].中国电机工程学报,2018,38(20):6045-6052.Liu Jiawei,Li Qi,Chen Weirong,et al.A fault diagnosis method of fuel cell systems for tramways based on the multi-class relevance vector machine and fuzzy C means clustering[J].Proceedings of the CSEE,2018,38(20):6045-6052(in Chinese).
[5]Liu Jianxing,Luo Wensheng,Yang Xiaozhan,et al.Robust model-based fault diagnosis for PEM fuel cell air-feed system[J].IEEE Transactions on Industrial Electronics,2016,63(5):3261-3270.
[6]Xie Changjun,Xu Xinyi,Bujlo P,et al.Fuel cell and lithium iron phosphate battery hybrid powertrain with an ultracapacitor bank using direct parallel structure[J].Journal of Power Sources,2015,279:487-494.
[7]Liu Jiawei,Li Qi,Chen Weirong,et al.A discrete hidden Markov model fault diagnosis strategy based on K-means clustering dedicated to PEM fuel cell systems of tramways[J].International Journal of Hydrogen Energy,2018,43(27):12428-12441.
[8]Mao Lei,Jackson L.Effect of sensor set size on polymer electrolyte membrane fuel cell fault diagnosis[J].Sensors,2018,18(9):2777.
[9]Mao Lei,Davies B,Jackson L.Application of the sensor selection approach in polymer electrolyte membrane fuel cell prognostics and health management[J].Energies,2017,10(10):1511.
[10]Mao L,Jackson L,Davies B.Investigation of PEMFCfault diagnosis with consideration of sensor reliability[J].International Journal of Hydrogen Energy,2018,43(35):16941-16948.
[11]Mao Lei,Jackson L,Davies B.Effectiveness of a novel sensor selection algorithm in PEM fuel cell on-line diagnosis[J].IEEE Transactions on Industrial Electronics,2018,65(9):7301-7310.
[12]Mao L,Jackson L,Dunnett S.Fault diagnosis of practical polymer electrolyte membrane(PEM)fuel cell system with data-driven approaches[J].Fuel Cells,2017,17(2):247-258.
[13]Li Zhongliang,Outbib R,Giurgea S,et al.Fault diagnosis for PEMFC systems in consideration of dynamic behaviors and spatial inhomogeneity[J].IEEETransactions on Energy Conversion,2019,34(1):3-11.
[14]Li Zhongliang,Cadet C,Outbib R.Diagnosis for PEMFCbased on magnetic measurements and data-driven approach[J].IEEE Transactions on Energy Conversion,2019,34(2):964-972.
[15]Li Zhongliang,Outbib R,Giurgea S,et al.Fault diagnosis for fuel cell systems:a data-driven approach using high-precise voltage sensors[J].Renewable Energy,2019,135:1435-1444.
[16]杨忠君,刘精一,宗学军.质子交换膜燃料电池故障检测研究[J].可再生能源,2015,33(1):128-133.Yang Zhongjun,Liu Jingyi,Zong Xuejun.Fault detection research based on proton exchange membrane fuel cell[J].Renewable Energy Resources,2015,33(1):128-133(in Chinese).
[17]周苏,任宏伟,裴冯来.基于诊断用COMSOL模型的PEMFC故障诊断方法研究[J].化学工业与工程,2015,32(4):56-62.Zhou Su,Ren Hongwei,Pei Fenglai.Faults diagnosis method study of PEMFC based on a diagnostic COMSOLmodel[J].Chemical Industry and Engineering,2015,32(4):56-62(in Chinese).
[18]Li Dan,Hu Guoqiang,Spanos C J.A data-driven strategy for detection and diagnosis of building chiller faults using linear discriminant analysis[J].Energy and Buildings,2016,128:519-529.
[19]Jiang Quansheng,Shen Yehu,Li Hua,et al.New fault recognition method for rotary machinery based on information entropy and a probabilistic neural network[J].Sensors,2018,18(2):337.