Lu, Jun, and Zahedi, Ahmad (2012) Constrained model predictive control of proton exchange membrane fuel cell based on a combined empirical and mechanistic model. Journal of Renewable and Sustainable Energy, 4 (5). 053116. pp. 1-15.

PDF (Published Version) - Published Version Restricted to Repository staff only

 

4

2

Abstract

The modelling and control of proton exchange membrane fuel cell (PEMFC) possess great challenges due to PEMFC system's inherent nonlinearities, time-varying characteristics, and tight operating constraints. In this paper, a constrained model predictive control (MPC) strategy is designed based on a combined empirical and mechanistic model of PEMFC. First, we propose a hybrid modelling approach based on the combination of prior knowledge, under the form of the mechanistic submodel, with the empirical submodel devoted to the extraction of knowledge from operating data. The empirical submodel is a support vector machine (SVM) model, which predicts the voltage at different stack currents and temperatures under the reference hydrogen and oxygen partial pressure. The mechanistic submodel calculates the correction voltage by taking account of hydrogen and oxygen partial pressure changes. To prevent reactant starvation and excessive pressure difference across the membrane, dynamic constraints are then designed for the constrained MPC of PEMFC. The standard particle swarm optimization algorithm is modified to solve the resulting constrained optimization problem formulated by the constrained MPC. Simulation results demonstrate that the proposed method can deal with the constraints and achieve satisfactory performance.

Actions (Repository Staff Only)

Item Control Page