Degradation prediction of proton exchange membrane fuel cell based on grey neural network model and particle swarm optimization

2019 ◽  
Vol 195 ◽  
pp. 810-818 ◽  
Author(s):  
Kui Chen ◽  
Salah Laghrouche ◽  
Abdesslem Djerdir
Keyword(s):  
Neural Network ◽  
Particle Swarm Optimization ◽  
Fuel Cell ◽  
Network Model ◽  
Neural Network Model ◽  
Proton Exchange Membrane ◽  
Particle Swarm ◽  
Proton Exchange ◽  
Swarm Optimization ◽  
Exchange Membrane

scholarly journals Performance Analysis and Optimization of a High-Temperature PEMFC Vehicle Based on Particle Swarm Optimization Algorithm

Membranes ◽  
2021 ◽  
Vol 11 (9) ◽  
pp. 691
Author(s):  
Yanju Li ◽  
Zheshu Ma ◽  
Meng Zheng ◽  
Dongxu Li ◽  
Zhanghao Lu ◽  
...  
Keyword(s):  
Particle Swarm Optimization ◽  
High Temperature ◽  
Fuel Cell ◽  
Power Density ◽  
Proton Exchange Membrane ◽  
Particle Swarm ◽  
Proton Exchange ◽  
Swarm Optimization ◽  
Output Performance ◽  
Exchange Membrane

In this paper, a high-temperature proton exchange membrane fuel cell (HT-PEMFC) model using the polybenzimidazole membrane doped with phosphoric acid molecules is developed based on finite time thermodynamics, considering various polarization losses and losses caused by leakage current. The mathematical expressions of the output power density and efficiency of the HT-PEMFC are deduced. The reliability of the model is verified by the experimental data. The effects of operating parameters and design parameters on the output performance of the HT-PEMFC are further analyzed. The particle swarm optimization (PSO) algorithm is used for the multi-objective optimization of the power density and efficiency of the HT-PEMFC. The results show that the output performance of the optimized HT-PEMFC is improved. Then, according to the different output performance of the low-temperature proton exchange membrane fuel cell (LT-PEMFC), HT-PEMFC, and optimized HT-PEMFC, different design schemes are provided for a fuel cell vehicle (FCV) powertrain. Simulation tests are conducted under different driving cycles, and the results show that the FCV with the optimized HT-PEMFC is more efficient and consumes less hydrogen.

Research on neural network model for new energy industry economy based on particle swarm optimization

2020 ◽  
Vol 38 (6) ◽  
pp. 7267-7277
Author(s):  
Xuhua Kang ◽  
Yuzheng Zhang ◽  
Huwei Zhang ◽  
Shenzhao Li ◽  
Wenjing Gao
Keyword(s):  
Neural Network ◽  
Particle Swarm Optimization ◽  
Network Model ◽  
Neural Network Model ◽  
Particle Swarm ◽  
Energy Industry ◽  
Swarm Optimization ◽  
New Energy
Sign in / Sign up

Export Citation Format

Share Document