A method for product personalized design based on prospect theory improved with interval reference. (November 2018)

• Record Type: Journal Article
• Authors: Dou, Runliang; Lin, Dandan; Nan, Guofang; Lei, Siyuan
• Is Part Of: Computers & industrial engineering. Volume 125(2018)
• Page Start: 708
• Page End: 719
• Publication Date: 2018-11
• Subjects: Product personalized design -- Interactive genetic algorithm -- Prospect theory -- Customer demand; Engineering -- Data processing -- Periodicals; Industrial engineering -- Periodicals; 620.00285
• DOI: 10.1016/j.cie.2018.04.056
• Languages: English
• ISSNs: 0360-8352

Abstract

Highlights: Prospect theory is improved with interval reference based on user cognition rules. An interactive genetic algorithm based on the improved prospect theory is proposed. The interval prospect value is used to represent the individual fitness value. An interval sorting strategy based on dominance degree is used to rank individuals. A product personalized system is developed to verify the algorithm's effectiveness. Abstract: How to rapidly and accurately response to customers' demands is the key in product personalized design, which could be perfectly achieved by interactive genetic algorithm (IGA) emphasizing on collaborative interaction and user participation through human–computer interaction. However IGA widely adopted now neglects the impact of decision makers' psychological changes on decision-making behaviors. It's hard to capture customers' demands and grasp their preferences, generating slow convergence speed and heavy user fatigue. Thus an interactive genetic algorithm based on prospect theory improved with interval reference (IGA-PTIR) is proposed in the paper. In IGA-PTIR, an evolutionary individual's fitness value is represented by interval prospect value of prospect theory improved with interval reference instead of single reference in order to correct individual fitness deviation caused by ambiguity and uncertainty of user cognition. An interval number sorting strategy based on dominance degree is then adopted to rank individuals, which makes it possible to perform subsequent operations of selection, crossover and mutation. In the paper, IGA-PTIR is applied into automobile wheel hub design system and compared with traditional interactive genetic algorithms (TIGA). Experimental results indicate that the proposed algorithm can increase convergence speed, ease user fatigue, and improve search performance to a large extent.