Multi‐objective particle swarm optimisation of complex product change plan considering service performance

Abstract

Design change is an inevitable part of the product development process. This study proposes an improved binary multi‐objective PSO algorithm guided by problem characteristics (P‐BMOPSO) to solve the optimisation problem of complex product change plan considering service performance. Firstly, a complex product multi‐layer network with service performance is established for the first time to reveal the impact of change effect propagation on the product service performance. Secondly, the concept of service performance impact (SPI) is defined by decoupling the impact of strongly associated nodes on the service performance in the process of change affect propagation. Then, a triple‐objective selection model of change nodes is established, which includes the three indicators: SPI degree, change cost, and change time. Furthermore, an integer multi‐objective particle swarm optimisation algorithm guided by problem characteristics is developed to solve the model above. Experimental results on the design change problem of a certain type of Skyworth TV verify the effectiveness of the established optimisation model and the proposed P‐BMOPSO algorithm.

An Interactive Estimation of the Distribution Algorithm Integrated with Surrogate-Assisted Fitness

“…Product optimization design (or optimal product design, OPD) refers to the optimization of product recommendation, market share, and product line configuration by collecting user preference information for product concepts [1]. This problem is prevalent in various domains, including product design [2,3], the supply chain [4], and personalized recommendations [5]. Among these, the collection of user preference information is a key factor in solving this problem and has a direct influence on the optimization results.…”