Adaptability analysis of design for additive manufacturing by using fuzzy Bayesian network approach

Abstract

The rapid development of Additive Manufacturing (AM) has been conspicuous and appealing towards manufacturing end-use products and components over the past decade. The continual advancement of AM has brought many advantages such as personalization and customization, reduction of material waste, cutting off the existence of special tooling during fabrication, etc. However, the AM approach has its limitations, such as a lack of knowledge of AM process activities and the progressive industrialization of AM, which makes the design process activities unstable, unpredictable, and have a limited effect. The concept of “design for AM (DFAM)” is increasing, which means we have the opportunity to concentrate almost totally on product functioning. Therefore, the entire design paradigm must be revised to accommodate new production capabilities, geometries, and parameters to avoid molding or machine tooling technology constraints. Few studies have attempted to provide systematic and quantitative knowledge of the relationship between these elements and the feasibility of the design process, making it difficult for designers to assess and control AM industrialization. For this reason, DFAM is needed to reform AM from rapid manufacturing to a mainstream manufacturing method. This paper put forward a framework based on the Fuzzy Bayesian Network (FBN) for DFAM decision-making. Twenty impact factors were encapsulated from experts’ experience and existing literature to investigate the potential adaptability of DFAM. The proposed approach uses expert knowledge and Fuzzy Set Theory (FST) presented with Triangular Fuzzy Numbers (FFN) to perceive the uncertainties. The Bayesian Network (BN) captures the causal relationships and dependencies among the impact components and analyzes the DFAM adaptability for robust probabilistic reasoning. A robot arm claw was used to show the effectiveness of our approach. The results showed that FBN could be used to guide DFAM adaptability in the manufacturing industry.