Post-Prognostics Decision for Optimizing the Commitment of Fuel Cell Systems

Abstract

Abstract: In a post-prognostics decision context, this paper addresses the problem of maximizing the useful life of a platform composed of several parallel machines under service constraint. Application on multi-stack fuel cell systems is considered. In order to propose a solution to the insufficient durability of fuel cells, the purpose is to define a commitment strategy by determining at each time the contribution of each fuel cell stack to the global output so as to reach the demand as long as possible. Two algorithms making use of convex optimization are proposed to cope with the assignment problem. First one is based on the Mirror-prox for Saddle Points method and second one uses the Lasso (Least Absolute Shrinkage and Selection Operator) principle. Results based on computational experiments assess the efficiency of these two approaches in comparison with an intuitive resolution performing successive basic convex projections onto the sets of constraints associated to the optimization problem.