Comparative study on prediction of fuel cell performance using machine learning approaches
journal contributionposted on 19.09.2016, 12:22 by Lei Mao, Lisa Jackson
Any type of content formally published in an academic journal, usually following a peer-review process.
This paper provides a comparative study to evaluate the effectiveness of machine learning techniques in predicting fuel cell performance. Several methods applied in fuel cell prognostics are selected, including a neural network, an adaptive neuro-fuzzy inference system, and a particle filtering approach. Test data from a fuel cell system is used for the evaluation. From the results, the advantages and disadvantages of these approaches are compared, which can provide a general framework for the selection of the necessary algorithms for fuel cell prognostics under different conditions.
This work is supported by grant EP/K02101X/1 for Loughborough University, Department of Aeronautical and Automotive Engineering from the UK Engineering and Physical Sciences Research Council (EPSRC).
- Aeronautical, Automotive, Chemical and Materials Engineering
- Aeronautical and Automotive Engineering