Genetic algorithm optimized neural network based fuel cell hybrid electric vehicle energy management strategy under start-stop condition

Abstract

Because of its high efficiency, no emission, low noise and many other advantages, proton exchange membrane fuel cell is considered to be able to be applied in automobiles to replace the traditional internal combustion engine. In order to improve the lifespan of fuel cell, the design of energy management strategy becomes the focus of research. This paper addresses the energy management strategy of fuel cell hybrid electric vehicle- fuel cell as the main power source, battery as the auxiliary power source. Existing researches are summarized and a new algorithm is proposed. As frequent startup, shutdown and rapid load change can reduce the lifespan of fuel cell, it is necessary to avoid this situation as far as possible. For this purpose, the reported work proposes Neural Network Optimized by Genetic Algorithm (NNOGA) as an effective strategy of the studied system. Through the optimization of genetic algorithm, the neural network can be trained pertinently, and the trained network can consciously avoid specific outputs according to the requirements. With the help of the optimization ability of Neural Network Optimized by Genetic Algorithm, which can change the preference of the trained neural network, the network can consciously avoid unnecessary start-stop and fast load change. Therefore, lifespan of fuel cell is prolonged. Simulation and comparative experiments verify the validity of the proposed algorithm.