Journal
IEEE TRANSACTIONS ON TRANSPORTATION ELECTRIFICATION
Volume 8, Issue 1, Pages 1454-1466Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TTE.2021.3111906
Keywords
Degradation; Predictive models; Reservoirs; Market research; Fuel cells; Genetic algorithms; Time series analysis; Genetic algorithm (GA); prognostics prediction; projection encoding; proton exchange membrane fuel cells (PEMFCs); stacked echo state network (ESN)
Funding
- National Natural Science Foundation of China [62173264]
- Ningbo Science and Technology Plan Project [2019B10116]
- Danish Energy Technology Development and Demonstration Program (EUDP) [640170582]
- Danish Agency for Science and Higher Education through the Proactive Energy Management Systems for Power-toHeat and Power-to-Gas Solutions (PRESS) Project
- Fundamental Research Funds for the Central Universities [2020YB034]
- China Scholarship Council [202006950031]
Ask authors/readers for more resources
This article proposes a method based on stacked echo state networks and genetic algorithms to predict the future degradation trend of proton exchange membrane fuel cells. The research results show that this method outperforms traditional prediction methods in terms of accuracy and generalization performance.
Durability is considered as one of the main technical obstacles to the large-scale commercialization of proton exchange membrane fuel cells (PEMFCs), which can be effectively improved through degradation prediction techniques. This article proposes a stacked echo state network (ESN) based on the genetic algorithm (GA) to predict the future degradation trend of PEMFCs. By alternately using the projection layer and the encoding layer, the proposed method can make full use of the temporal kernel property of the ESN to encode the multiscale and multilevel dynamics of the stack voltage, thereby obtaining more robust generalization performance and higher accuracy than the existing methods. Specifically, a stack voltage time series of PEMFCs is projected into the high-dimensional echo state space of the reservoir. Then, an autoencoder projects the echo state representation into the low-dimensional feature space. After that, the GA is utilized to optimize the hyperparameters of the developed model. Based on two open-source datasets of PEMFCs with different accelerated test conditions, this article systematically tested the proposed degradation prediction methods based on different model structures. Test results demonstrate that the proposed method is superior to traditional prediction methods in terms of accuracy and generalization performance.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available