A SUPER-METAMODELLING FRAMEWORK TO OPTIMIZE SYSTEM PREDICTABILITY

Published

August 25, 2018

Author(s)

Yan Lu, Douglas Eddy, Sundar Krishnamurty, Ian Grosse

Abstract

Statistical metamodels can robustly predict manufacturing process and engineering systems design results. Various techniques, such as Kriging, polynomial regression, artificial neural network and others, are each best suited for different scenarios that can range across a design space. Thus, methods are needed to identify the most appropriate metamodel or model composite for a given problem. To account for pros and cons of different metamodeling techniques for a wide diversity of data sets, in this paper we introduce a super-metamodel optimization framework (SMOF) to improve overall prediction accuracy by integrating different metamodeling techniques without a need for additional data. The SMOF defines an iterative process first to construct multiple metamodels using different methods and then aggregate them into a weighted composite and finally optimize the super-metamodel through advanced sampling. The optimized super-metamodel can reduce an overall prediction error and sustains the performance regardless of dataset variation. To verify the method, we apply it to 24 test problems representing various scenarios. A case study conducted with additive manufacturing process data shows method effectiveness in practice.

Proceedings Title

38th Computers and Information in Engineering Conference (CIE)

Conference Dates

August 27-29, 2018

Conference Location

Quebec, CA

Conference Title

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

Pub Type

Conferences

Download Paper

Local Download

Keywords

predictive metamodeling, optimization

Citation

Lu, Y. , Eddy, D. , Krishnamurty, S. and Grosse, I. (2018), A SUPER-METAMODELLING FRAMEWORK TO OPTIMIZE SYSTEM PREDICTABILITY, 38th Computers and Information in Engineering Conference (CIE), Quebec, CA, [online], https://tsapps.nist.gov/publication/get_pdf.cfm?pub_id=925533 (Accessed April 23, 2024)