Prognostics of Proton Exchange Membrane Fuel Cells stack using an ensemble of constraints based connectionist networks
作者： Kamran Javed , Rafael Gouriveau , Noureddine Zerhouni , Daniel Hissel
DOI: 10.1016/J.JPOWSOUR.2016.05.092
关键词:
摘要: Proton Exchange Membrane Fuel Cell (PEMFC) is considered the most versatile among available fuel cell technologies, which qualify for diverse applications. However, large-scale industrial deployment of PEMFCs limited due to their short life span and high exploitation costs. Therefore, ensuring service a long duration vital importance, has led Prognostics Health Management cells. More precisely, prognostics PEMFC major area focus nowadays, aims at identifying degradation stack early stages estimating its Remaining Useful Life (RUL) cycle management. This paper presents data-driven approach using an ensemble constraint based Summation Wavelet- Extreme Learning Machine (SW-ELM) models. development aim improving robustness applicability online application, with learning data. The proposed applied real data from two different stacks compared ensembles well known connectionist algorithms. results comparison on long-term both validates our proposition.
harvard.edu
archives-ouvertes.fr
sci-hub.se 参考文章(31)
Michael Knowles, David Baglee, Adrian Morris, Qinglian Ren, None, The State of the Art in Fuel Cell Condition Monitoring and Maintenance World Electric Vehicle Journal. ,vol. 4, pp. 487- 494 ,(2010) , 10.3390/WEVJ4030487
R.E. Silva, R. Gouriveau, S. Jemeï, D. Hissel, L. Boulon, K. Agbossou, N. Yousfi Steiner, Proton exchange membrane fuel cell degradation prediction based on Adaptive Neuro-Fuzzy Inference Systems . International Journal of Hydrogen Energy. ,vol. 39, pp. 11128- 11144 ,(2014) , 10.1016/J.IJHYDENE.2014.05.005
R. Gouriveau, N. Zerhouni, Connexionist-Systems-Based Long Term Prediction Approaches for Prognostics IEEE Transactions on Reliability. ,vol. 61, pp. 909- 920 ,(2012) , 10.1109/TR.2012.2220700
Herbert Jaeger, Mantas Lukoševičius, Dan Popovici, Udo Siewert, 2007 Special Issue: Optimization and applications of echo state networks with leaky- integrator neurons Neural Networks. ,vol. 20, pp. 335- 352 ,(2007) , 10.1016/J.NEUNET.2007.04.016
D. Nguyen, B. Widrow, Improving the learning speed of 2-layer neural networks by choosing initial values of the adaptive weights 1990 IJCNN International Joint Conference on Neural Networks. ,vol. 1990, pp. 21- 26 ,(1990) , 10.1109/IJCNN.1990.137819
Kamran Javed, Rafael Gouriveau, Noureddine Zerhouni, Patrick Nectoux, Enabling Health Monitoring Approach Based on Vibration Data for Accurate Prognostics. IEEE Transactions on Industrial Electronics. ,vol. 62, pp. 647- 656 ,(2015) , 10.1109/TIE.2014.2327917
Shu-Xian Lun, Xian-Shuang Yao, Hong-Yun Qi, Hai-Feng Hu, A novel model of leaky integrator echo state network for time-series prediction Neurocomputing. ,vol. 159, pp. 58- 66 ,(2015) , 10.1016/J.NEUCOM.2015.02.029
Jian Guo, Zhaojun Li, Michael Pecht, A Bayesian approach for Li-Ion battery capacity fade modeling and cycles to failure prognostics Journal of Power Sources. ,vol. 281, pp. 173- 184 ,(2015) , 10.1016/J.JPOWSOUR.2015.01.164
Linxia Liao, Discovering Prognostic Features Using Genetic Programming in Remaining Useful Life Prediction IEEE Transactions on Industrial Electronics. ,vol. 61, pp. 2464- 2472 ,(2014) , 10.1109/TIE.2013.2270212
Kamran Javed, Rafael Gouriveau, Noureddine Zerhouni, A New Multivariate Approach for Prognostics Based on Extreme Learning Machine and Fuzzy Clustering IEEE Transactions on Cybernetics. ,vol. 45, pp. 2626- 2639 ,(2015) , 10.1109/TCYB.2014.2378056