A DOMAIN DRIVEN APPROACH TO METAMODELING IN ADDITIVE MANUFACTURING

Published

September 6, 2017

Author(s)

Peter O. Denno, Yan Lu, Paul Witherell, Sundar Krishnamurty, Ian Grosse, Douglas Eddy

Abstract

Recent studies have shown advantages to utilizing metamodeling techniques to mimic, analyze, and optimize system input-output relationships in Additive Manufacturing (AM). This paper addresses a key challenge in applying such metamodeling methods, namely the selection of the most appropriate metamodel, by taking advantage of AM domain-specific information derived from physics, heuristics and prior knowledge. Specifically, domain-specific input/output models and their interrelationships are studied as a basis for a domain-driven metamodeling approach in additive manufacturing (AM). As part of this work, a metamodel selection process is introduced that evaluates both global and local modeling performances with different AM datasets for three popular surrogate metamodels (polynomial regression (PR), Kriging, and artificial neural network (ANN)). A salient feature of this domain-driven approach is its ability to seamlessly integrate prior knowledge and instances in the model selection process without requiring specific information about the data. The approach is demonstrated with the aid of a metal powder bed fusion (PBF) case study and the results are discussed

Proceedings Title

ASME 2017 International Design Engineering Technical Conferences & Computers and Information in
Engineering Conference

Conference Dates

August 6-9, 2017

Conference Location

Cleveland, OH, US

Conference Title

CIE

Pub Type

Conferences

Download Paper

Local Download

Keywords

Smart Manufacturing, Additive Manufacturing, Metamodeling, Surrogate Model

Citation

Denno, P. , Lu, Y. , Witherell, P. , Krishnamurty, S. , Grosse, I. and Eddy, D. (2017), A DOMAIN DRIVEN APPROACH TO METAMODELING IN ADDITIVE MANUFACTURING, ASME 2017 International Design Engineering Technical Conferences & Computers and Information in Engineering Conference, Cleveland, OH, US, [online], https://tsapps.nist.gov/publication/get_pdf.cfm?pub_id=923073 (Accessed October 8, 2024)