Decision Support Within Customized Products Using Computational Intelligence. Issue 2 (2022)

• Record Type: Journal Article
• Authors: Relich, Marcin; Wójcik, Robert
• Is Part Of: IFAC-PapersOnLine. Volume 55:Issue 2(2022)
• Page Start: 211
• Page End: 216
• Publication Date: 2022
• Subjects: cost estimation -- decision support systems -- modelling -- decision making -- new product development -- predictive analytics -- product design; Automatic control -- Periodicals; 629.805
• DOI: 10.1016/j.ifacol.2022.04.195
• Languages: English
• ISSNs: 2405-8963

Abstract

Abstract: The paper presents the use of computational intelligence techniques to cost estimation and identification of possibilities of cost reduction at the early phase of new product development. Parametric estimation models are based on artificial neural networks and neuro-fuzzy systems that identify dependencies between product parameters and the costs of product development, manufacturing, and after-sales service. These dependencies are also used to search for the possibility of cost reduction through changes in designing a customized product. A problem of cost optimization is specified in terms of a constraint satisfaction problem and solved using constraint programming. All possible solutions are identified within requirements for a new product and business resources. The presented method consists of five steps: collecting data, conducting sensitivity analysis, identifying relationships, estimating costs, and identifying possible variants that ensure target costs. An example of the proposed approach refers to mass-customized products.