A genetic algorithm based energy optimization model for electric vehicles is proposed to address the issue of difficulty in optimizing rule-based energy management strategies.First,determine the population size of the genetic algorithm,then initialize the population through optimizing parameter selection and coding,determine the fitness function,determine the selection,crossover and mutation operators,improve the genetic algorithm and set the number of iterations to build an optimization model for energy and energy management of electric vehicles,and finally conduct energy consumption simulation experiments of electric vehicles under WLTC cycle,CLTC cycle and NEDC cycle.The simulation results show that the model proposed in this study reduces the total energy consumption of the driving motor of electric vehicles under WLTC cycle conditions by 5.62％,CLTC cycle conditions by 6.83％,and NEDC cycle conditions by 4.01％compared to the energy optimization model based on average allocation.The optimization strategy of this study can reduce the computational workload in energy optimization management of electric vehicles,improve optimization accura-cy,have good adaptability,energy-saving effects,and broad application prospects.
维普
万方数据