Parameter Optimization of the Power and Energy System of Unmanned Electric Drive Chassis Based on Improved Genetic Algorithms of the KOHONEN Network

Abstract

For unmanned electric drive chassis parameter optimization problems, an unmanned electric drive chassis model containing power systems and energy systems was built using CRUISE, and as the traditional genetic algorithm is prone to falling into the local optima, an improved isolation niche genetic algorithm based on KOHONEN network clustering (KIGA) is proposed. The simulation results show that the proposed KIGA can reasonably divide the initial niche populations. Compared with the traditional genetic algorithm (GA) and the isolation niche genetic algorithm (IGA), KIGA can achieve faster convergence and a better global search ability. The comprehensive performance of the unmanned electric drive chassis in terms of power and economy was increased by 8.26% with a set of better solutions. The results show that simultaneous power system and energy system parameter optimization can enhance unmanned electric drive chassis performance and that KIGA is an efficient method for optimizing the parameters of unmanned electric drive chassis.