Forecasting the remaining useful life of proton exchange membrane fuel cells by utilizing nonlinear autoregressive exogenous networks enhanced by genetic algorithms
The Proton Exchange Membrane Fuel Cell (PEMFC), known for its efficient energy conversion, minimal electrolyte leakage, and low operating temperature, shows great potential as a clean energy source. However, its lifespan is limited due to degradation during normal operation, which, if uncontrolled,...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-10-01
|
| Series: | Journal of Power Sources Advances |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2666248523000240 |
| _version_ | 1797397527538958336 |
|---|---|
| author | Yitong Shen Mohamad Alzayed Hicham Chaoui |
| author_facet | Yitong Shen Mohamad Alzayed Hicham Chaoui |
| author_sort | Yitong Shen |
| collection | DOAJ |
| description | The Proton Exchange Membrane Fuel Cell (PEMFC), known for its efficient energy conversion, minimal electrolyte leakage, and low operating temperature, shows great potential as a clean energy source. However, its lifespan is limited due to degradation during normal operation, which, if uncontrolled, can result in dangerous failures such as explosions. Hence, accurately estimating the remaining useful life (RUL) is vital. In this research, a combined prediction method using genetic algorithms (GA) and nonlinear autoregressive neural networks (NARX) with external inputs is proposed. The method's performance was trained and validated using the 2014 IEEE PHM Data Challenge dataset, and it was compared to two commonly used artificial neural network algorithms: GA-based backpropagation neural network (GA-BPNN) and GA-based time delay neural network (GA-TDNN). The findings demonstrate that the proposed approach surpasses the other two artificial neural network algorithms in terms of prediction accuracy. Although GA is known for its computational requirement, optimization is performed offline. Once optimal neural network (NN) hyper-parameters are determined, the optimized NN is used online for RUL prediction. |
| first_indexed | 2024-03-09T01:11:19Z |
| format | Article |
| id | doaj.art-1a966cdde2d7423eaba8a3e9a7403c4e |
| institution | Directory Open Access Journal |
| issn | 2666-2485 |
| language | English |
| last_indexed | 2024-03-09T01:11:19Z |
| publishDate | 2023-10-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Journal of Power Sources Advances |
| spelling | doaj.art-1a966cdde2d7423eaba8a3e9a7403c4e2023-12-11T04:17:33ZengElsevierJournal of Power Sources Advances2666-24852023-10-0124100132Forecasting the remaining useful life of proton exchange membrane fuel cells by utilizing nonlinear autoregressive exogenous networks enhanced by genetic algorithmsYitong Shen0Mohamad Alzayed1Hicham Chaoui2Intelligent Robotic and Energy Systems Research Group (IRES), The Department of Electronics, Carleton University, Ottawa, ON, K1S 5B6, CanadaIntelligent Robotic and Energy Systems Research Group (IRES), The Department of Electronics, Carleton University, Ottawa, ON, K1S 5B6, Canada; Corresponding author.Intelligent Robotic and Energy Systems Research Group (IRES), The Department of Electronics, Carleton University, Ottawa, ON, K1S 5B6, Canada; The Department of Electrical and Computer Engineering, Texas Tech University, Lubbock, TX, 79409, USAThe Proton Exchange Membrane Fuel Cell (PEMFC), known for its efficient energy conversion, minimal electrolyte leakage, and low operating temperature, shows great potential as a clean energy source. However, its lifespan is limited due to degradation during normal operation, which, if uncontrolled, can result in dangerous failures such as explosions. Hence, accurately estimating the remaining useful life (RUL) is vital. In this research, a combined prediction method using genetic algorithms (GA) and nonlinear autoregressive neural networks (NARX) with external inputs is proposed. The method's performance was trained and validated using the 2014 IEEE PHM Data Challenge dataset, and it was compared to two commonly used artificial neural network algorithms: GA-based backpropagation neural network (GA-BPNN) and GA-based time delay neural network (GA-TDNN). The findings demonstrate that the proposed approach surpasses the other two artificial neural network algorithms in terms of prediction accuracy. Although GA is known for its computational requirement, optimization is performed offline. Once optimal neural network (NN) hyper-parameters are determined, the optimized NN is used online for RUL prediction.http://www.sciencedirect.com/science/article/pii/S2666248523000240Genetic algorithmNonlinear autoregressive neural networkProton exchange membrane fuel cell |
| spellingShingle | Yitong Shen Mohamad Alzayed Hicham Chaoui Forecasting the remaining useful life of proton exchange membrane fuel cells by utilizing nonlinear autoregressive exogenous networks enhanced by genetic algorithms Journal of Power Sources Advances Genetic algorithm Nonlinear autoregressive neural network Proton exchange membrane fuel cell |
| title | Forecasting the remaining useful life of proton exchange membrane fuel cells by utilizing nonlinear autoregressive exogenous networks enhanced by genetic algorithms |
| title_full | Forecasting the remaining useful life of proton exchange membrane fuel cells by utilizing nonlinear autoregressive exogenous networks enhanced by genetic algorithms |
| title_fullStr | Forecasting the remaining useful life of proton exchange membrane fuel cells by utilizing nonlinear autoregressive exogenous networks enhanced by genetic algorithms |
| title_full_unstemmed | Forecasting the remaining useful life of proton exchange membrane fuel cells by utilizing nonlinear autoregressive exogenous networks enhanced by genetic algorithms |
| title_short | Forecasting the remaining useful life of proton exchange membrane fuel cells by utilizing nonlinear autoregressive exogenous networks enhanced by genetic algorithms |
| title_sort | forecasting the remaining useful life of proton exchange membrane fuel cells by utilizing nonlinear autoregressive exogenous networks enhanced by genetic algorithms |
| topic | Genetic algorithm Nonlinear autoregressive neural network Proton exchange membrane fuel cell |
| url | http://www.sciencedirect.com/science/article/pii/S2666248523000240 |
| work_keys_str_mv | AT yitongshen forecastingtheremainingusefullifeofprotonexchangemembranefuelcellsbyutilizingnonlinearautoregressiveexogenousnetworksenhancedbygeneticalgorithms AT mohamadalzayed forecastingtheremainingusefullifeofprotonexchangemembranefuelcellsbyutilizingnonlinearautoregressiveexogenousnetworksenhancedbygeneticalgorithms AT hichamchaoui forecastingtheremainingusefullifeofprotonexchangemembranefuelcellsbyutilizingnonlinearautoregressiveexogenousnetworksenhancedbygeneticalgorithms |