NSGA-II multi-objectives optimization algorithm for energy management control of hybrid electric vehicle

Abstract

The currently existing energy management control optimization for hybrid electric vehicle (HEV) mainly focuses on fuel economy. Apart from this, there has been some consideration of the impact of emissions, but almost no attention has been paid to drivability performance. Therefore, from the point of view of multi-objectives optimization, the influences of fuel economy, emission and drivability performance on the energy management are comprehensively considered for a parallel HEV. The energy management control parameters and driveline parameters are selected to be optimized parameters. Then, the NSGA-II (Fast Non-dominated Sorting Genetic Algorithm-II) algorithm is proposed to solve the multi-objectives optimization problem. Furthermore, the multi-objectives optimization method for HEV energy management control is established and comparatively simulated with the parallel electric assist control strategy. The results show that the evaluation index of drivability decreases by 27.12% from the maximum and the average enhancement effect of optimization falls by 20.84%. The evaluation index of fuel economy declines by 22.30% from the maximum and the average index drops by 20.26%. The comprehensive index of emission performance descends by 11.33% from the maximum. The proposed multi-objectives optimization algorithm has good convergence and distribution, and obtains more Pareto optimal solution sets, which can provide more selectivity in building HEV energy management control strategies.