A fuzzy intelligent design retrieving system for customer requirements. (11th December 2008)

• Record Type: Journal Article
• Authors: Yu, Li; Wang, Liya
• Is Part Of: International journal of computer applications technology. Volume 33:Number 2/3(2008)
• Page Start: 247
• Page End: 254
• Publication Date: 2008-12-11
• Subjects: conceptual design -- design retrieval -- customer requirements -- product specifications -- product design -- new product development -- NPD -- design reuse -- fuzzy design -- intelligent design -- intelligent retrieval -- neural networks; Technology -- Data processing -- Periodicals; 620.00285
• Languages: English
• ISSNs: 0952-8091

Abstract

In the conceptual design stage of developing new products, the utilisation of the existing designs can significantly reduce design time and cost. This paper proposes a fuzzy intelligent design retrieving system to provide design engineers with easy access to relevant designs and knowledge. It employs fuzzy ARTMAP (FAM) neural network as its key technique to retrieve reference designs based on Customer Requirements (CRs) and Product Specifications (PSs). FAM learns from historical transaction records. For newly emerging CRs, the system is able to retrieve reference designs that have similar PSs. By adjusting a single vigilance parameter, designers can retrieve a proper number of reference designs. Furthermore, it can create new groups of designs when new CRs fail to match any current grouping instances. Our implementation example shows that the proposed system is effective for retrieving designs in the conceptual design stage.