Remaining useful life prediction of PEMFC based on long short-term memory recurrent neural networks

Abstract To solve the prediction problem of proton exchange membrane fuel cell (PEMFC) remaining useful life (RUL), a novel RUL prediction approach of PEMFC based on long short-term memory (LSTM) recurrent neural networks (RNN) has been developed. The method uses regular interval sampling and locally weighted scatterplot smoothing (LOESS) to realize data reconstruction and data smoothing. Not only the primary trend of the original data can be preserved, but noise and spikes can be effectively removed. The LSTM RNN is adopted to estimate the remaining life of test data. 1154-hour experimental aging analysis of PEMFC shows that the prediction accuracy of the novel method is 99.23%, the root mean square error (RMSE) and mean absolute error (MAE) is 0.003 and 0.0026 respectively. The comparison analysis shows that the prediction accuracy of the novel method is 28.46% higher than that of back propagation neural network (BPNN). Root mean square error, relative error (RE) and mean absolute error are all much smaller than that of BPNN. Therefore, the novel method can quickly and accurately forecast the residual service life of the fuel cell.

[1]  R. Gouriveau,et al.  Fuel Cells Remaining Useful Lifetime Forecasting Using Echo State Network , 2014, 2014 IEEE Vehicle Power and Propulsion Conference (VPPC).

[2]  Belkacem Ould Bouamama,et al.  Fuel cells remaining useful life estimation using an extended Kalman Filter , 2015, IECON 2015 - 41st Annual Conference of the IEEE Industrial Electronics Society.

[3]  Suleyman Serdar Kozat,et al.  Efficient Online Learning Algorithms Based on LSTM Neural Networks , 2018, IEEE Transactions on Neural Networks and Learning Systems.

[4]  P. Pei,et al.  Approaches to avoid flooding in association with pressure drop in proton exchange membrane fuel cells , 2018, Applied Energy.

[5]  Abdellatif Miraoui,et al.  Prediction of PEMFC stack aging based on Relevance Vector Machine , 2015, 2015 IEEE Transportation Electrification Conference and Expo (ITEC).

[6]  Damien Paire,et al.  Nonlinear Performance Degradation Prediction of Proton Exchange Membrane Fuel Cells Using Relevance Vector Machine , 2016, IEEE Transactions on Energy Conversion.

[7]  Noureddine Zerhouni,et al.  Improving accuracy of long-term prognostics of PEMFC stack to estimate remaining useful life , 2015, 2015 IEEE International Conference on Industrial Technology (ICIT).

[8]  Hongwen He,et al.  Long Short-Term Memory Recurrent Neural Network for Remaining Useful Life Prediction of Lithium-Ion Batteries , 2018, IEEE Transactions on Vehicular Technology.

[9]  Chuan Lyu,et al.  A novel health indicator for PEMFC state of health estimation and remaining useful life prediction , 2017 .

[10]  Belkacem Ould Bouamama,et al.  Remaining Useful Life Prediction and Uncertainty Quantification of Proton Exchange Membrane Fuel Cell Under Variable Load , 2016, IEEE Transactions on Industrial Electronics.

[11]  Lisa M. Jackson,et al.  Effect of Sensor Set Size on Polymer Electrolyte Membrane Fuel Cell Fault Diagnosis , 2018, Sensors.

[12]  Ali Emadi,et al.  Long Short-Term Memory Networks for Accurate State-of-Charge Estimation of Li-ion Batteries , 2018, IEEE Transactions on Industrial Electronics.

[13]  Li Lin,et al.  Remaining useful life estimation of engineered systems using vanilla LSTM neural networks , 2018, Neurocomputing.

[14]  R. Gouriveau,et al.  Fuel Cells prognostics using echo state network , 2013, IECON 2013 - 39th Annual Conference of the IEEE Industrial Electronics Society.

[15]  Lei Mao,et al.  Fault Diagnosis of Practical Polymer Electrolyte Membrane (PEM) Fuel Cell System with Data‐driven Approaches , 2017 .

[16]  Werner Lehnert,et al.  Design of durability test protocol for vehicular fuel cell systems operated in power-follow mode based on statistical results of on-road data , 2018 .

[17]  Hongye Su,et al.  Optimal Oxygen Excess Ratio Control for PEM Fuel Cells , 2018, IEEE Transactions on Control Systems Technology.

[18]  Pierluigi Pisu,et al.  Prognostic-oriented Fuel Cell Catalyst Aging Modeling and Its Application to Health-Monitoring and Prognostics of a PEM Fuel Cell , 2020 .

[19]  Xiaozhan Yang,et al.  Robust Model-Based Fault Diagnosis for PEM Fuel Cell Air-Feed System , 2016, IEEE Transactions on Industrial Electronics.

[20]  Noureddine Zerhouni,et al.  Prognostics of PEM fuel cell in a particle filtering framework , 2014 .

[21]  Ruiqing Niu,et al.  Displacement prediction of Baijiabao landslide based on empirical mode decomposition and long short-term memory neural network in Three Gorges area, China , 2018, Comput. Geosci..

[22]  Noureddine Zerhouni,et al.  A hybrid remaining useful life prognostic method for proton exchange membrane fuel cell , 2018, International Journal of Hydrogen Energy.

[23]  Björn W. Schuller,et al.  Combining Long Short-Term Memory and Dynamic Bayesian Networks for Incremental Emotion-Sensitive Artificial Listening , 2010, IEEE Journal of Selected Topics in Signal Processing.

[24]  Yanyan Hu,et al.  Remaining useful life estimation for proton exchange membrane fuel cell based on extreme learning machine , 2016, 2016 31st Youth Academic Annual Conference of Chinese Association of Automation (YAC).

[25]  Hoang Huu Son.  Toward a proposed framework for mood recognition using LSTM Recurrent Neuron Network , 2017, ANT/SEIT.

[26]  Noureddine Zerhouni,et al.  A Prognostic Framework for PEMFC Based on Least Squares Support Vector Regression-Particle Filter , 2017, 2017 IEEE Vehicle Power and Propulsion Conference (VPPC).

[27]  Liangfei Xu,et al.  A reconstructed fuel cell life-prediction model for a fuel cell hybrid city bus , 2018 .

[28]  Ahmed Nait Aicha,et al.  Deep Learning to Predict Falls in Older Adults Based on Daily-Life Trunk Accelerometry , 2018, Sensors.

[29]  Shuhai Quan,et al.  Fuel cell and lithium iron phosphate battery hybrid powertrain with an ultracapacitor bank using direct parallel structure , 2015 .

[30]  Zuomin Dong,et al.  Load profile based empirical model for the lifetime prediction of an automotive PEM fuel cell , 2017 .

[31]  Daniel Hissel,et al.  Fault Diagnosis for PEMFC Systems in Consideration of Dynamic Behaviors and Spatial Inhomogeneity , 2019, IEEE Transactions on Energy Conversion.

[32]  Qi Li,et al.  Power Management Strategy Based on Adaptive Droop Control for a Fuel Cell-Battery-Supercapacitor Hybrid Tramway , 2018, IEEE Transactions on Vehicular Technology.

[33]  Laurent Larger,et al.  Brain-inspired computational paradigm dedicated to fault diagnosis of PEM fuel cell stack , 2017 .

[34]  Junghui Chen,et al.  Prognostics of PEM fuel cells based on Gaussian process state space models , 2018 .

[35]  Belkacem Ould Bouamama,et al.  Extended Kalman Filter for prognostic of Proton Exchange Membrane Fuel Cell , 2016 .

[36]  Daniel Hissel,et al.  Proton exchange membrane fuel cell degradation prediction based on Adaptive Neuro-Fuzzy Inference Systems . , 2014 .

[37]  R. Gouriveau,et al.  Data-driven Prognostics of Proton Exchange Membrane Fuel Cell Stack with constraint based Summation-Wavelet Extreme Learning Machine. , 2015 .

[38]  Ling Hong,et al.  A nonlinear control strategy for fuel delivery in PEM fuel cells considering nitrogen permeation , 2017 .

[39]  Maxime Wack,et al.  PEM fuel cell air-feed system observer design for automotive applications: An adaptive numerical differentiation approach , 2014 .

[40]  Bumshik Lee,et al.  Combining LSTM Network Ensemble via Adaptive Weighting for Improved Time Series Forecasting , 2018, Mathematical Problems in Engineering.

[41]  Noureddine Zerhouni,et al.  PEM fuel cell prognostics under variable load: A data-driven ensemble with new incremental learning , 2016, 2016 International Conference on Control, Decision and Information Technologies (CoDIT).

[42]  Lei Mao,et al.  Effectiveness of a Novel Sensor Selection Algorithm in PEM Fuel Cell On-Line Diagnosis , 2018, IEEE Transactions on Industrial Electronics.

[43]  Mohamed Tkiouat,et al.  Rolling element bearing remaining useful life estimation based on a convolutional long-short-term memory network , 2018 .

[44]  Abdellatif Miraoui,et al.  A Modified Relevance Vector Machine for PEM Fuel-Cell Stack Aging Prediction , 2016 .

[45]  Ruqiang Yan,et al.  Learning to Monitor Machine Health with Convolutional Bi-Directional LSTM Networks , 2017, Sensors.

[46]  Zheng Huang,et al.  Deep Recurrent Model for Server Load and Performance Prediction in Data Center , 2017, Complex..

[47]  Abdellatif Miraoui,et al.  Degradation prediction of PEM fuel cell using a moving window based hybrid prognostic approach , 2017 .

[48]  Huicui Chen,et al.  Lifetime prediction and the economic lifetime of Proton Exchange Membrane fuel cells , 2015 .

[49]  Noureddine Zerhouni,et al.  Prognostics of Proton Exchange Membrane Fuel Cells stack using an ensemble of constraints based connectionist networks , 2016 .

[50]  L. Mao,et al.  Investigation of PEMFC fault diagnosis with consideration of sensor reliability , 2017, International Journal of Hydrogen Energy.

[51]  Noureddine Zerhouni,et al.  Proton exchange membrane fuel cell ageing forecasting algorithm based on Echo State Network , 2017 .

[52]  Abdellatif Miraoui,et al.  Dynamic Phenomena Coupling Analysis and Modeling of Proton Exchange Membrane Fuel Cells , 2016, IEEE Transactions on Energy Conversion.

[53]  Hongye Su,et al.  Data-based short-term prognostics for proton exchange membrane fuel cells , 2017 .