Observer-Based Discrete Adaptive Neural Network Control for Automotive PEMFC Air-Feed Subsystem

Abstract

Polymer electrolyte membrane fuel cell (PEMFC) air-feed subsystem is usually affected negatively by system uncertainty and unavailable variable. This paper investigates a discrete neural network control with an observer for the oxygen excess ratio (OER) control. The control goal is to avoid oxygen starvation and maintain the optimal net power. Specifically, by utilizing coordinate transformation and Euler approximation, the discrete strict-feedback form is obtained, and the backstepping technique can be applied. To estimate the unavailable variable with the measurable system output, a discrete neural network observer is proposed. Besides, the discrete neural network controller is designed to tackle the system uncertainty and achieve an ideal OER tracking. Finally, the system tracking error is proved to be semi-globally uniformly ultimately bounded by Lyapunov stability theory. Numerical simulations and hardware-in-loop (HIL) experiments are presented to demonstrate the effectiveness and superiorities of the proposed controller.