Plastic Manufacturing Process Selection Methodology Using Self-Organising Map (SOM)/Fuzzy Analysis

Abstract

For plastic products, one of the crucial decisions made during the preliminary design stage is the selection of an appropriate manufacturing process. In many industries, the selection of the manufacturing process is primarily based on the empirical knowledge and past experience of the manufacturing personnel. This selection procedure may result in inconsistent or poor choices if the manufacturing personnel fail to map correctly the product characteristics with the manufacturing efficacy of various manufacturing processes. This paper presents an intelligent self-organising map (SOM)/fuzzy-based model to aid designers in the selection of an appropriate plastic manufacturing process. The plastic part attributes are broadly classified into three main categories: part characteristics, material type, and production requirements. A fuzzy membership function is generated for each of the attributes using the self-organising map paradigm. Fuzzy associative memories (FAMs) are used to perform reasoning on these input fuzzy sets to derive the output fuzzy sets. The output fuzzy sets are then defuzzified to determine the process compatibility scores (PCS). The working of the proposed model is demonstrated using an example case.