NOTICE: Due to a lapse in annual appropriations, most of this website is not being updated. Learn more.
Form submissions will still be accepted but will not receive responses at this time. Sections of this site for programs using non-appropriated funds (such as NVLAP) or those that are excepted from the shutdown (such as CHIPS and NVD) will continue to be updated.
An official website of the United States government
Here’s how you know
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
Secure .gov websites use HTTPS
A lock (
) or https:// means you’ve safely connected to the .gov website. Share sensitive information only on official, secure websites.
INVESTIGATING GREY-BOX MODELING FOR PREDICTIVE ANALYTICS IN SMART MANUFACTURING
Published
Author(s)
Peter O. Denno, Yan Lu, Paul Witherell, Sundar Krishnamurty, Ian Grosse, Douglas Eddy
Abstract
This paper develops a grey-box modeling approach that combines manufacturing knowledge-based (white-box) models with statistical (black-box) metamodels to improve model reusability and predictability. A white-box model can utilize different types of existing knowledge such as physical theory, high fidelity simulation or historical experimental data to build the foundation of the general model. The difference between a white-box prediction and actual empirical data, namely the residual, can be modeled to generate a black-box by use of the Kriging method. The combination of the white-box and black-box models constructs the parallel hybrid structure of a grey-box. For any new point prediction, the basic solution from the white-box combines the estimated residual from the black-box to produce the final grey-box solution. This approach was developed in this work for manufacturing processes, with a case study implemented with the powder bed fusion additive manufacturing process, but can be extended to other common modeling applications. Two illustrative case studies are brought into this study to test this grey-box modeling approach; first for pure mathematical rigor and second for manufacturing specifically. The result of the case studies shows that the grey-box models can lower predictive errors. Moreover, the resulting black-box model that represents any residual is a usable, accurate metamodel.
Proceedings Title
ASME 2017 International Design Engineering Technical Conferences & Computers and Information in
Engineering Conference
Denno, P.
, Lu, Y.
, Witherell, P.
, Krishnamurty, S.
, Grosse, I.
and Eddy, D.
(2017),
INVESTIGATING GREY-BOX MODELING FOR PREDICTIVE ANALYTICS IN SMART 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=923074
(Accessed October 10, 2025)