Scale-Based product family optimization design based on the improved AMPSO in selecting optimum strategy

Abstract

Abstract The main contribution of this paper is to propose a two-stage scale-based product family design method (TPFDM) based on an improved adaptive mutation particle swarm optimization (AMPSO) algorithm. To do that, the problem involved in scale-based product family design is analyzed and modelled. A two-stage optimized design process is built to solve the problem. To build and optimize the product family platform, a multi-objectives model about the product family design problem is established. The multi-objectives problem and each parameter's sensitivity as well as variation index about objectives are solved via an intelligent optimization algorithm. The platform constants and non-platform variables are discriminated by sensitivity and variation index in the first stage. The main work of the second stage is to optimize products based on product platform via the intelligent optimization algorithm. Moreover, in order to overcome the early maturity phenomenon of the particle swarm optimization algorithm, an improved AMPSO algorithm is proposed to introduce the concept of the non-individual optimum strategy and the dominate strategy. Finally, aerial magnetorheological fluid damper family design is used as an example to demonstrate effectiveness and feasibility of the proposed method.