Abstract
Hydrogen fuel cells lifetime is essential for vehicles utilization and machines, which has been concerned by existing researchers. However, existing prediction is based on mathematical calculation and leaks the parameters of other situations including using situation and cells surroundings. This paper presents a novel approach to predict the lifetime of hydrogen fuel cells using a multi-layer perceptron (MLP) model by measuring the cell voltages. The lifetime of hydrogen fuel cells is a critical factor in their successful application and deployment. In this work, a MLP model is utilized to predict the lifetime of hydrogen fuel cells based on various input parameters including temperature, voltage and current information. The model is trained and tested on a dataset of experimental results from a laboratory-scale hydrogen fuel cell. The results demonstrate that the proposed MLP model is able to accurately predict the lifetime of hydrogen fuel cells with a mean absolute error of 0.17 years. This approach is promising for the development of hydrogen fuel cell technology and could be used to optimize the design and operation of fuel cells.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Lin R-H, Xi X-N, Wang P-N, Wu B-D, Tian S-M (2018) Review on hydrogen fuel cell condition monitoring and prediction methods. Int J Hydrogen Energy
Quan S, Wang Y-X, Xiao X, He H, Sun F (2021) Disturbance prediction-based enhanced stochastic model predictive control for hydrogen supply and circulating of vehicular fuel cells. Energy Convers Manag
Fu Z, Chen Q, Zhang L, Fan J, Zhang H, Deng Z (2021) Research on energy management strategy of fuel cell power generation system based on Grey–Markov chain power prediction. Energy Rep 7(Supplement 1)
Long B, Wu K, Li P, Li M (2022) A novel remaining useful life prediction method for hydrogen fuel cells based on the gated recurrent unit neural network. Appl Sci
Huang D-W, Qi D-Q, Yu N (2016) Capacity allocation of hydrogen production and fuel cells in wind farm based on stochastic prediction error. In: International conference on energy development and environmental protection (EDEP 2016)
Shi Y, Xiao J, Quan S, Pan M, Zhang L (2009) Fractal model for prediction of effective hydrogen diffusivity of gas diffusion layer in proton exchange membrane fuel cell. Int J Hydrogen Energy
Zhang B, Pang L, Shen X, Gao Y (2016) Measurement and prediction of detonation cell size in binary fuel blends of methane/hydrogen mixtures. Fuel
Hydrogen; researchers from Russian Academy of Science detail new studies and findings in the area of hydrogen (lifetime prediction for the hydrogen-air fuel cells). Chemicals & Chemistry (2015)
Pei P, Chen D, Wu Z, Ren P (2019) Nonlinear methods for evaluating and online predicting the lifetime of fuel cells. Appl Energy
Lin X, Wang Z, Wu J (2020) Energy management strategy based on velocity prediction using back propagation neural network for a plug‐in fuel cell electric vehicle. Int J Energy Res
Hu X, Zou C, Tang X, Liu T, Hu L (2020) Cost-optimal energy management of hybrid electric vehicles using fuel cell/battery health-aware predictive control. IEEE Trans Power Electron
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Zhou, X., Liu, Q. (2024). Hydrogen Fuel Cells Lifetime Prediction Based on Multi-layer Perceptron. In: Yadav, S., Arya, Y., Muhamad, N.A., Sebaa, K. (eds) Energy Power and Automation Engineering. ICEPAE 2023. Lecture Notes in Electrical Engineering, vol 1118. Springer, Singapore. https://doi.org/10.1007/978-981-99-8878-5_2
Download citation
DOI: https://doi.org/10.1007/978-981-99-8878-5_2
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-8877-8
Online ISBN: 978-981-99-8878-5
eBook Packages: EnergyEnergy (R0)