Investigating predictive metamodeling for additive manufacturing

Published

August 21, 2016

Author(s)

Zhuo Yang, Douglas Eddy, Sundar Krishnamurty, Ian Grosse, Peter O. Denno, Felipe F. Lopez

Abstract

Additive manufacturing processes offer significant commercial advantages due to unique and advanced process capabilities. Production of metal parts can involve trial and error. This is often due to limited understanding of variability in properties and the causes of that variability. Predictive metamodels can provide a mathematical framework for capturing the system behavior in AM and offer a reusable and composable paradigm to study, analyze, diagnose, forecast, and design AM processes and AM manufactured parts. However, AM has its unique set of challenges. These challenges include the complexity and interrelationships of numerous physical phenomena occurring in the process. Furthermore, it is very expensive to run the number of experiments needed for metamodel construction, and historical data can be limited in terms of the size of a generated data set. To address these challenges, this work analyzes and prescribes metamodeling techniques to select optimal sample points, construct and update metamodels, and test them for specific and isolated physical phenomena. A simplified case study of two different laser welding process experiments is presented to illustrate the potential use of these concepts. We conclude with a discussion on potential future directions, such as data and model integration to predict the global results of interest while also accounting for sources of uncertainty.

Proceedings Title

Proceedings of the ASME 2016 International Design Engineering Technical Conferences & Computers
and Information in Engineering Conference

Conference Dates

August 21-24, 2016

Conference Location

Charllote, NC, US

Conference Title

ASME 2016 International Design Engineering Technical Conferences & Computers and Information in
Engineering Conference

Pub Type

Conferences

Download Paper

Local Download

Keywords

metamodels, additive manufacturing, space filling sampling, model updating

Citation

Yang, Z. , Eddy, D. , Krishnamurty, S. , Grosse, I. , Denno, P. and Lopez, F. (2016), Investigating predictive metamodeling for additive manufacturing, Proceedings of the ASME 2016 International Design Engineering Technical Conferences & Computers and Information in Engineering Conference, Charllote, NC, US, [online], https://tsapps.nist.gov/publication/get_pdf.cfm?pub_id=920562 (Accessed December 14, 2024)