{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T08:12:59Z","timestamp":1780906379478,"version":"3.54.1"},"reference-count":44,"publisher":"MDPI AG","issue":"1","license":[{"start":{"date-parts":[[2022,12,24]],"date-time":"2022-12-24T00:00:00Z","timestamp":1671840000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"The National Key R&amp;D plan of China","award":["2018YFB1702203"],"award-info":[{"award-number":["2018YFB1702203"]}]},{"name":"The National Key R&amp;D plan of China","award":["No. ICT2022B31"],"award-info":[{"award-number":["No. ICT2022B31"]}]},{"name":"The Open Research Project of the State Key Laboratory of Industrial Control Technology, Zhejiang University, China","award":["2018YFB1702203"],"award-info":[{"award-number":["2018YFB1702203"]}]},{"name":"The Open Research Project of the State Key Laboratory of Industrial Control Technology, Zhejiang University, China","award":["No. ICT2022B31"],"award-info":[{"award-number":["No. ICT2022B31"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Durability and reliability are the major bottlenecks of the proton-exchange-membrane fuel cell (PEMFC) for large-scale commercial deployment. With the help of prognostic approaches, we can reduce its maintenance cost and maximize its lifetime. This paper proposes a hybrid prognostic method for PEMFCs based on a decomposition forecasting framework. Firstly, the original voltage data is decomposed into the calendar aging part and the reversible aging part based on locally weighted regression (LOESS). Then, we apply an adaptive extended Kalman filter (AEKF) and long short-term memory (LSTM) neural network to predict those two components, respectively. Three-dimensional aging factors are introduced in the physical aging model to capture the overall aging trend better. We utilize the automatic machine-learning method based on the genetic algorithm to train the LSTM model more efficiently and improve prediction accuracy. The aging voltage is derived from the sum of the two predicted voltage components, and we can further realize the remaining useful life estimation. Experimental results show that the proposed hybrid prognostic method can realize an accurate long-term voltage-degradation prediction and outperform the single model-based method or data-based method.<\/jats:p>","DOI":"10.3390\/s23010166","type":"journal-article","created":{"date-parts":[[2022,12,27]],"date-time":"2022-12-27T02:55:07Z","timestamp":1672109707000},"page":"166","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":24,"title":["A Hybrid Prognostic Method for Proton-Exchange-Membrane Fuel Cell with Decomposition Forecasting Framework Based on AEKF and LSTM"],"prefix":"10.3390","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4851-0224","authenticated-orcid":false,"given":"Zetao","family":"Xia","sequence":"first","affiliation":[{"name":"Ningbo Innovation Center, Zhejiang University, Ningbo 315000, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yining","family":"Wang","sequence":"additional","affiliation":[{"name":"Ningbo Innovation Center, Zhejiang University, Ningbo 315000, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Longhua","family":"Ma","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering, NingboTech University, Ningbo 315000, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Zhu","sequence":"additional","affiliation":[{"name":"College of Control Science and Engineering, Zhejiang University, Hangzhou 310027, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongjie","family":"Li","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering, NingboTech University, Ningbo 315000, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jili","family":"Tao","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering, NingboTech University, Ningbo 315000, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7292-4056","authenticated-orcid":false,"given":"Guanzhong","family":"Tian","sequence":"additional","affiliation":[{"name":"Ningbo Innovation Center, Zhejiang University, Ningbo 315000, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2022,12,24]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Zhang, D., Li, X., Wang, W., and Zhao, Z. (2022). Internal Characterization-Based Prognostics for Micro-Direct-Methanol Fuel Cells under Dynamic Operating Conditions. Sensors, 22.","DOI":"10.3390\/s22114217"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"109721","DOI":"10.1016\/j.rser.2020.109721","article-title":"Prognostics methods and degradation indexes of proton exchange membrane fuel cells: A review","volume":"123","author":"Liu","year":"2020","journal-title":"Renew. Sustain. Energy Rev."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"78","DOI":"10.1016\/j.ress.2015.12.003","article-title":"Degradations analysis and aging modeling for health assessment and prognostics of PEMFC","volume":"148","author":"Jouin","year":"2016","journal-title":"Reliab. Eng. Syst. Saf."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"104","DOI":"10.1016\/j.jpowsour.2008.06.006","article-title":"A review of PEM fuel cell durability: Degradation mechanisms and mitigation strategies","volume":"184","author":"Wu","year":"2008","journal-title":"J. Power Sources"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1016\/j.jpowsour.2018.10.043","article-title":"A highly selective proton exchange membrane with highly ordered, vertically aligned, and subnanosized 1D channels for redox flow batteries","volume":"406","author":"Yan","year":"2018","journal-title":"J. Power Sources"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"17740","DOI":"10.1039\/C8TA06717A","article-title":"Sulfonated graphene oxide-decorated block copolymer as a proton-exchange membrane: Improving the ion selectivity for all-vanadium redox flow batteries","volume":"6","author":"Aziz","year":"2018","journal-title":"J. Mater. Chem. A"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"16976","DOI":"10.1016\/j.ijhydene.2019.06.108","article-title":"Highly stable graphene oxide composite proton exchange membrane for electro-chemical energy application","volume":"45","author":"Rajput","year":"2020","journal-title":"Int. J. Hydrogen Energy"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"1930","DOI":"10.1016\/j.ijhydene.2018.11.100","article-title":"Fuel cell health prognosis using Unscented Kalman Filter: Postal fuel cell electric vehicles case study","volume":"44","author":"Chen","year":"2019","journal-title":"Int. J. Hydrogen Energy"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Cigolotti, V., Genovese, M., and Fragiacomo, P. (2021). Comprehensive review on fuel cell technology for stationary applications as sustainable and efficient poly-generation energy systems. Energies, 14.","DOI":"10.3390\/en14164963"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"11868","DOI":"10.1016\/j.ijhydene.2017.02.146","article-title":"Load profile based empirical model for the lifetime prediction of an automotive PEM fuel cell","volume":"42","author":"Zhang","year":"2017","journal-title":"Int. J. Hydrogen Energy"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Peng, C., Chen, Y., Chen, Q., Tang, Z., Li, L., and Gui, W. (2021). A Remaining Useful Life prognosis of turbofan engine using temporal and spatial feature fusion. Sensors, 21.","DOI":"10.3390\/s21020418"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Yang, J., Peng, Y., Xie, J., and Wang, P. (2022). Remaining Useful Life Prediction Method for Bearings Based on LSTM with Uncertainty Quantification. Sensors, 22.","DOI":"10.3390\/s22124549"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"220","DOI":"10.1016\/j.apenergy.2015.11.071","article-title":"Extended Kalman filter for prognostic of proton exchange membrane fuel cell","volume":"164","author":"Bressel","year":"2016","journal-title":"Appl. Energy"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"440","DOI":"10.1016\/j.rser.2016.11.009","article-title":"A review on prognostics and health monitoring of proton exchange membrane fuel cell","volume":"75","author":"Sutharssan","year":"2017","journal-title":"Renew. Sustain. Energy Rev."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Zhang, X., and Pisu, P. (2012, January 23\u201327). An Unscented Kalman Filter Based Approach for the Health Monitoring and Prognostics of a Polymer Electrolyte Membrane Fuel Cell. Proceedings of the Annual Conference of the PHM Society, Minneapolis, MN, USA.","DOI":"10.36001\/phmconf.2012.v4i1.2167"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"F1315","DOI":"10.1149\/2.1031412jes","article-title":"PEMFC durability: Spatially resolved Pt dissolution in a single cell","volume":"161","author":"Dhanushkodi","year":"2014","journal-title":"J. Electrochem. Soc."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"188","DOI":"10.1016\/j.jpowsour.2007.12.007","article-title":"Modeling of PEM fuel cell Pt\/C catalyst degradation","volume":"178","author":"Bi","year":"2008","journal-title":"J. Power Sources"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Polverino, P., and Pianese, C. (2016, January 7\u20139). Model-based prognostic algorithm for online RUL estimation of PEMFCs. Proceedings of the 2016 3rd Conference on Control and Fault-Tolerant Systems (SysTol), Barcelona, Spain.","DOI":"10.1109\/SYSTOL.2016.7739814"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"481","DOI":"10.1016\/j.ijhydene.2013.10.054","article-title":"Prognostics of PEM fuel cell in a particle filtering framework","volume":"39","author":"Jouin","year":"2014","journal-title":"Int. J. Hydrogen Energy"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"8171","DOI":"10.1007\/s00521-018-3901-7","article-title":"Estimation algorithm research for lithium battery SOC in electric vehicles based on adaptive unscented Kalman filter","volume":"31","author":"Li","year":"2019","journal-title":"Neural Comput. Appl."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"11128","DOI":"10.1016\/j.ijhydene.2014.05.005","article-title":"Proton exchange membrane fuel cell degradation prediction based on adaptive neuro-fuzzy inference systems","volume":"39","author":"Silva","year":"2014","journal-title":"Int. J. Hydrogen Energy"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"6077","DOI":"10.1109\/TIE.2018.2873105","article-title":"Short-term prognostics of PEM fuel cells: A comparative and improvement study","volume":"66","author":"Liu","year":"2018","journal-title":"IEEE Trans. Ind. Electron."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Morando, S., Jemei, S., Gouriveau, R., Zerhouni, N., and Hissel, D. (2013, January 10\u201313). Fuel cells prognostics using echo state network. Proceedings of the IECON 2013-39th Annual Conference of the IEEE Industrial Electronics Society, Vienna, Austria.","DOI":"10.1109\/IECON.2013.6699377"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"113825","DOI":"10.1016\/j.enconman.2021.113825","article-title":"Remaining useful life prediction of PEMFC systems under dynamic operating conditions","volume":"231","author":"Hua","year":"2021","journal-title":"Energy Convers. Manag."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"102","DOI":"10.1016\/j.apenergy.2018.09.111","article-title":"Data-driven proton exchange membrane fuel cell degradation predication through deep learning method","volume":"231","author":"Ma","year":"2018","journal-title":"Appl. Energy"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"910","DOI":"10.1016\/j.apenergy.2019.01.023","article-title":"Remaining useful life estimation for proton exchange membrane fuel cells using a hybrid method","volume":"237","author":"Liu","year":"2019","journal-title":"Appl. Energy"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"379","DOI":"10.1109\/TIE.2019.2893827","article-title":"Adaptive prognostic of fuel cells by implementing ensemble echo state networks in time-varying model space","volume":"67","author":"Li","year":"2019","journal-title":"IEEE Trans. Ind. Electron."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"2318","DOI":"10.1109\/TTE.2021.3075531","article-title":"A Hybrid Prognostic Method for PEMFC with Aging Parameter Prediction","volume":"7","author":"Ma","year":"2021","journal-title":"IEEE Trans. Transp. Electrif."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"336","DOI":"10.1109\/TR.2015.2454499","article-title":"Joint particle filters prognostics for proton exchange membrane fuel cell power prediction at constant current solicitation","volume":"65","author":"Jouin","year":"2015","journal-title":"IEEE Trans. Reliab."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"1472","DOI":"10.1016\/j.ijhydene.2016.05.286","article-title":"Proton exchange membrane fuel cell ageing forecasting algorithm based on Echo State Network","volume":"42","author":"Morando","year":"2017","journal-title":"Int. J. Hydrogen Energy"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Kimotho, J.K., Meyer, T., and Sextro, W. (August, January China). PEM fuel cell prognostics using particle filter with model parameter adaptation. Proceedings of the 2014 International Conference on Prognostics and Health Management, Zhangjiajie, NJ, USA.","DOI":"10.1109\/ICPHM.2014.7036406"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"2035","DOI":"10.1007\/s00521-020-05105-0","article-title":"A rest-time-based prognostic model for remaining useful life prediction of lithium-ion battery","volume":"33","author":"Deng","year":"2021","journal-title":"Neural Comput. Appl."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"314","DOI":"10.1016\/j.jpowsour.2018.06.098","article-title":"Online remaining useful lifetime prediction of proton exchange membrane fuel cells using a novel robust methodology","volume":"399","author":"Zhou","year":"2018","journal-title":"J. Power Sources"},{"key":"ref_34","unstructured":"Mao, L., and Jackson, L. (2021, October 20). IEEE 2014 Data Challenge Data. Available online: https:\/\/repository.lboro.ac.uk\/articles\/dataset\/IEEE_2014_Data_Challenge_Data\/3518141\/1."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"5470","DOI":"10.1016\/j.ijhydene.2018.10.042","article-title":"Remaining useful life prediction of PEMFC based on long short-term memory recurrent neural networks","volume":"44","author":"Liu","year":"2019","journal-title":"Int. J. Hydrogen Energy"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"7067","DOI":"10.1016\/j.eswa.2012.01.039","article-title":"A review and comparison of strategies for multi-step ahead time series forecasting based on the NN5 forecasting competition","volume":"39","author":"Taieb","year":"2012","journal-title":"Expert Syst. Appl."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"2569","DOI":"10.1109\/TIE.2016.2519328","article-title":"Remaining useful life prediction and uncertainty quantification of proton exchange membrane fuel cell under variable load","volume":"63","author":"Bressel","year":"2016","journal-title":"IEEE Trans. Ind. Electron."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"274","DOI":"10.1016\/S0378-7753(01)01029-1","article-title":"Incorporation of voltage degradation into a generalised steady state electrochemical model for a PEM fuel cell","volume":"106","author":"Fowler","year":"2002","journal-title":"J. Power Sources"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"30994","DOI":"10.1016\/j.ijhydene.2020.08.082","article-title":"Performance degradation prediction of proton exchange membrane fuel cell using a hybrid prognostic approach","volume":"45","author":"Pan","year":"2020","journal-title":"Int. J. Hydrogen Energy"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"261","DOI":"10.1177\/0049124104268644","article-title":"Multimodel inference: Understanding AIC and BIC in model selection","volume":"33","author":"Burnham","year":"2004","journal-title":"Sociol. Methods Res."},{"key":"ref_41","unstructured":"Bodenhofer, U. (2021, October 20). Genetic Algorithms: Theory and Applications. Lecture notes, Fuzzy Logic Laboratorium Linz-Hagenberg, Winter, 2004. Available online: http:\/\/www.flll.jku.at\/div\/teaching\/Ga\/notes.pdf."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"80","DOI":"10.1016\/j.jpowsour.2015.11.087","article-title":"An adaptive remaining energy prediction approach for lithium-ion batteries in electric vehicles","volume":"305","author":"Wang","year":"2016","journal-title":"J. Power Sources"},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Sundermeyer, M., Schl\u00fcter, R., and Ney, H. (2012, January 9\u201313). LSTM neural networks for language modeling. Proceedings of the Thirteenth Annual Conference of the International Speech Communication Association, Portland, OR, USA.","DOI":"10.21437\/Interspeech.2012-65"},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Siami-Namini, S., Tavakoli, N., and Namin, A.S. (2019, January 9\u201312). The performance of LSTM and BiLSTM in forecasting time series. Proceedings of the 2019 IEEE International Conference on Big Data (Big Data), Los Angeles, CA, USA.","DOI":"10.1109\/BigData47090.2019.9005997"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/1\/166\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T01:49:53Z","timestamp":1760147393000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/1\/166"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,24]]},"references-count":44,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2023,1]]}},"alternative-id":["s23010166"],"URL":"https:\/\/doi.org\/10.3390\/s23010166","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,12,24]]}}}