AI-Based Proton Exchange Membrane Fuel Cell Inlet Relative Humidity Control

• Published in: IEEE access Vol. 9; pp. 158496 - 158507
• Main Authors: Song, Yanpo, Wang, Xiangwei
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 2021; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Anodes; Artificial neural networks; Autoregressive processes; Back propagation networks; back propagation neural network proportion integration differentiation (BPPID) controller; Cathodes; Computational fluid dynamics; Controllers; Fuel cells; Fuzzy control; Humidity; humidity control; intelligent controller; Mathematical models; Moisture content; Moisture control; Neural networks; Proportional integral derivative; Proton exchange membrane fuel cell (PEMFC); Proton exchange membrane fuel cells; Protons; Relative humidity; Temperature control; Water heating; Water management
• ISSN: 2169-3536; 2169-3536
• DOI: 10.1109/ACCESS.2021.3130604

Humidity is a key factor affecting proton exchange membrane fuel cell (PEMFC) efficiency and output performance. Different working conditions have different requirements for humidity. Improper humidity may cause too high or too low water content inside the PEMFC, which will damage the output performance and even shorten the remaining useful life of PEMFC. Therefore, how to control humidity appropriately is a crucial subject. This paper establishes a PEMFC internal water management and inlet humidity model, and the influence of the change of anode inlet humidity on the performance of the PEMFC and the water content of the membrane is analyzed through computational fluid dynamics (CFD) simulation. And the direct control of the inlet humidity, which is difficult to be accurately measured, is converted to the temperature control of the bubble humidifier according to the proposed model, and a back propagation neural network proportion integration differentiation (BPPID) controller is proposed, which combines artificial neural network and digital PID control to adjust PID parameters in real time. The controller is applied to the temperature control of the bubble humidifier and compared with the traditional PID controller and the fuzzy PID controller. It is found that the performance of the BPPID controller is better through the comparison with the experimental results and the stabilization time it takes is only about 50% of that of other controllers.