Type:

Year:

Editor:

Author:

Page, Thomas Daniel; Yang, Sheng; Zhao, Yaoyao Fiona

Series:

Institution:

Section:

DOI number:

ISSN:

Abstract:

As additive manufacturing (AM) continues to grow in its abilities, so does the need for a quick and effective method of determining how it should be applied. Over time, these methods are naturally developed and passed on as tacit knowledge. However, with the rapid advancement of AM technologies, identifying parts which are eligible for AM as well as gaining insight on what value it may add to a product needs to be modelled in an objective and transferrable way. This paper presents a framework for determining the candidacy of a part or assembly for AM, represented by its economic feasibility and potential for AM-specific benefits. A set of selection criteria is developed with the goal of fast-screening in mind; that is specific data which can be automatically extracted from CAD models and resource planning databases. A case study is performed to validate the criteria and decision model chosen, as well as gain insight to the potential for a more widespread application. The decision model successfully identified economic feasibility and AM potentials, which suggests the results of the case study show promise for a semi-automatic decision support system for identifying AM candidates.

Keywords:

Additive Manufacturing, Decision making, Machine learning, Selection criteria