改进粒子群算法的行星齿轮系统多目标优化研究
Research on Multi-objective Optimization of Planetary Gear System with Improved Particle Swarm Optimization

在行星齿轮多目标优化中，传统粒子群算法（PSO）与自适应权重粒子群算法（APSO）在复杂约束下不易收敛或易陷入局部最优。为此，提出改进的自适应权重粒子群算法（D-APSO）并进行行星齿轮高功率密度的多目标优化设计，以最小体积、最大传动效率和最小中心距为多目标优化函数，综合考虑行星齿轮传动的边界协调条件，利用惩罚函数法处理约束条件，对目标进行D-APSO算法下的优化计算。结果表明：D-APSO算法在优化求解效果和速度上明显优于传统PSO算法和APSO算法，在满足行星齿轮系统承载性能的条件下，使行星齿轮系统具有更小的体积及中心距，并表现出更优的传动效率。
In the multi-objective optimization of planetary gears, traditional particle swarm optimization (PSO) and adaptive weight particle swarm optimization (APSO) algorithms are not easy to converge or fall into local optimum under complex constraints. An improved adaptive weight particle swarm optimization (D-APSO) method is proposed and used to a multi-objective optimization design of the high power density of the planetary gear. With the minimum volume, maximum transmission efficiency and minimum central moment as the multi-objective optimization function, the penalty function method is used to deal with the constraint condition and the planetary gear boundary condition, and the objective is optimized by D-APSO algorithm. The calculation results show that the D-APSO algorithm is superior to the traditional PSO and the APSO algorithms in optimization speed and solution accuracy. While satisfying the carrier performance of the planetary gear system, the D-APSO algorithm can obtain smaller volume, smaller central distance and better transmission efficiency of the planetary gear system