This content is not included in
your SAE MOBILUS subscription, or you are not logged in.
A Comparative Study of Fuel Cell Prediction Models Based on Relevance Vector Machines with Different Kernel Functions
Technical Paper
2021-01-0728
ISSN: 0148-7191, e-ISSN: 2688-3627
This content contains downloadable datasets
Annotation ability available
Sector:
Event:
SAE WCX Digital Summit
Language:
English
Abstract
Fuel cell reactors, as the core components of fuel cell vehicles, have a short life problem that has always limited the development of fuel cell vehicles. The life attenuation curve of fuel cell shows nonlinear characteristics, and there is no model that can accurately predict its effect. This paper is based on the experimental data of the vehicle fuel cell reactor, which is derived from the 600 h durability test run by a 4 kW fuel cell reactor. The relevance vector machine, as a Bayes processing method that supports vector machine, is a data-driven method based on kernel functions. The regression model is established by the relevance vector machine, and the super-parameters are found by genetic algorithm, because the kernel function strongly affects the nonlinearity of the curve, and the decay curve of fuel cell reactor performance is predicted according to four different kernel functions. In this paper, according to four different kernel functions: polynomial kernel function, Gaussian radial basis kernel function, Sigmoid kernel function and the mixed kernel function, the corresponding prediction effect is discussed. The comparative analysis and error analysis of the prediction results of the relevance vector machine regression model of these four kernel functions show that the regression effect and prediction effect of the mixed kernel functions are the best, have better learning ability, and combine the advantages of two different kernel functions. The results of this paper can provide reference for the prediction of the performance attenuation of fuel cell reactors.
Authors
Citation
Geng, W., Hou, Y., and Lan, H., "A Comparative Study of Fuel Cell Prediction Models Based on Relevance Vector Machines with Different Kernel Functions," SAE Technical Paper 2021-01-0728, 2021, https://doi.org/10.4271/2021-01-0728.Data Sets - Support Documents
Title | Description | Download |
---|---|---|
Unnamed Dataset 1 | ||
Unnamed Dataset 2 | ||
Unnamed Dataset 3 | ||
Unnamed Dataset 4 | ||
Unnamed Dataset 5 |
Also In
References
- Pei , P. , Chang , Q. , and Tang , T. A Quick Evaluating Method for Automotive Fuel Cell Lifetime International Journal of Hydrogen Energy 33 14 3829 3836 2008
- Wu , Y. , Breaz , E. , Gao , F. et al. A Modified Relevance Vector Machine for PEM Fuel-Cell Stack Aging Prediction IEEE Transactions on Industry Applications 52 3 2573 2581 2016
- Wu , Y. , Breaz , E. , Gao , F. et al. Nonlinear Performance Degradation Prediction of Proton Exchange Membrane Fuel Cells Using Relevance Vector Machine IEEE Transactions on Energy Conversion 31 4 1570 1582 2016
- Wu , Y. , Breaz , E. , Gao , F. , et al. Prediction of PEMFC Stack Aging Based on Relevance Vector Machine Transportation Electrification Conference and Expo IEEE 2015 1 5
- Shen , Y.I.N. , Xiaochen , X.I.E. , LAM , J. et al. An Improved Incremental Learning Approach for KPI Prognosis of Dynamic Fuel Cell System[J] IEEE Transactions on Cybernetics 46 12 3135 3144 2016
- Petrone , R. , Hissel , D. , Pera , M.C. et al. Accelerated Stress Test Procedures for PEM Fuel Cells Under Actual Load Constraints: State-of-Art and Proposals International Journal of Hydrogen Energy 40 36 12489 12505 2015
- Yuan , X.Z. , Li , H. , Zhang , S. et al. A Review of Polymer Electrolyte Membrane Fuel Cell Durability Test Protocols Journal of Power Sources 196 22 9107 9116 2011
- [8] Bressel , M. , Hilairet , M. , Hissel , D. et al. Remaining Useful Life Prediction and Uncertainty Quantification of Proton Exchange Membrane Fuel Cell Under Variable Load IEEE Transactions on Industrial Electronics 63 4 2569 2577 2016
- Onanena , R. , Oukhellou , L. , Candusso , D. et al. Fuel Cells Static and Dynamic Characterizations as Tools for the Estimation of their Ageing Time International Journal of Hydrogen Energy 36 2 1730 1739 2011
- Huang , Y. , Hou , Y. , Zhang , J. et al. Comparison of Duty Cycles for Fuel Cell Durability Bench Tests Battery 6 2017