基于SPEA2的参数化产品族优化设计

Parametric product family optimization design based on SPEA2

针对多目标优化算法的参数化产品族优化设计存在优化的效率及其有效性取决于算法优劣的问题,鉴于SPEA2求解多目标优化问题具有运算速度较快、稳定性较强、解分布均匀性较高等特点,研究了基于SPEA2的参数化产品族优化设计。将参数化产品族优化设计过程划分为两个阶段:第1阶段进行实例产品独立优化,基于设计变量的变异系数决定平台常量和可调节变量集合,并决定平台常量取值;第2阶段进行基于产品平台的产品族优化设计,获得实例产品的可调节变量取值。以通用电动机产品族优化设计为例,其优化结果表明,采用SPEA2求解时产品族的综合性能得到了较显著的提高。

The parametric product family optimization design is based on multi-objective optimization algorithm,thus the efficiency and effectiveness of the optimization depend on the performance of the algorithm. In view of the characteristics of SPEA2（ high speed of calculation,strong stability and high uniformity of solutions distribution）,so the parametric products family optimization is designed based on SPEA2. The process of family optimization design was divided into two phases. The first phase was independent optimization of the instance products. The coefficient of variation based on design variables determines the set of constant and adjustable variables,and determines the value of the platform. The second one was that the product family optimization design is based on the product platform to get the values of the scale-based variables of the instance products. The results of the optimization show that by SPEA2 to solve the multi-objective problems of the parametric product family optimization,the comprehensive performances of the products family are improved obviously.