Research On Multi-Objective Particle Swarm Optimization And The Application In Hybrid Electric Vehicle Parameter Optimization

Many real-world complex engineering and scientific problems can be summarized as optimization problems, researching on fuel consumption and pollutant emissions parameters of hybrid vehicles optimization problem belong to optimization category. Researching on hybrid vehicle parameter setting problem, not only help to improve the accuracy of decision-makers, but also become a prerequisite which protect the environment and save the energy. To further improve the level of research in the field of smart car and to achieve the purpose of energy saving, this paper combine the with the advantage of particle swarm optimization algorithm in solving multi-objective problems, three speed coefficient of MOPSO simultaneously improved optimization algorithm, and applied to a parallel hybrid vehicle has important scientific significance and practical value, it is a beneficial and necessary exploration to solve complex parameter optimization problems and to further the field of smart car in the future.This study focus on multi-objective particle swarm optimization algorithm of evolutionary algorithm and parallel hybrid vehicles a plurality of parameters research questions, conducting the following research work and made corresponding innovations:1. Design a multi-objective particle swarm optimization algorithm with balancing each speed coefficient, put forward three different formular according inertia weight of particle, global optimization and local optimization information, using the three formular balanced optimize speed coefficient of MOPSO algorithm, and then On 7 standard test functions for testing, and compare with 5 kinds of algorithms, experimental results show that, this paper prove the improved algorithm for improving the accuracy of the algorithm and avoid premature local optimum particle has certain advantages.2.Successfully applying improved multi-objective optimization particle swarm optimization in parallel hybrid vehicle parameters, optimizing fuel consumption and hybrid vehicles emissions optimization, simulating based on ADVISOR simulation platform and urban driving cycles (UDDS), finally compare with NSGA-Ⅱ algorithm and MOPSO algorithm. Experimental results show that it is a big advantage that the parameters optimized to reduce fuel consumption and reduce emissions of pollutants.In addition to the advantages of cross-disciplinary play. Smart car sector provides a new way of thinking.The above work not only enriches the theory of PSO on the field of multi-objective optimization, but also extends the application field of evolutionary algorithm in further expansion, with its intelligent combination of car-related research, it provides a new way and promotes the application of the smart car.