Credibility Assessment of Machine Learning in a Manufacturing Process Application

Gregory A. Banyay; Clarence L. Worrell; Scott E. Sidener; Joshua S. Kaizer

doi:10.1115/1.4051717

Credibility Assessment of Machine Learning in a Manufacturing Process Application

Gregory A. Banyay, Clarence L. Worrell, Scott E. Sidener, Joshua S. Kaizer

Research output: Contribution to journal › Article › peer-review

1 Scopus citations

Abstract

We present a framework for establishing credibility of a machine learning (ML) model used to predict a key process control variable setting to maximize product quality in a component manufacturing application. Our model coupled a purely data-based ML model with a physics-based adjustment that encoded subject matter expertise of the physical process. Establishing credibility of the resulting model provided the basis for eliminating a costly intermediate testing process that was previously used to determine the control variable setting.

Original language	English (US)
Article number	031007
Journal	Journal of Verification, Validation and Uncertainty Quantification
Volume	6
Issue number	3
DOIs	https://doi.org/10.1115/1.4051717
State	Published - Sep 2021

All Science Journal Classification (ASJC) codes

Statistics and Probability
Modeling and Simulation
Computer Science Applications
Computational Theory and Mathematics

Access to Document

10.1115/1.4051717

Cite this

@article{52d9c3ac6edf4807859a03307ec591ae,

title = "Credibility Assessment of Machine Learning in a Manufacturing Process Application",

abstract = "We present a framework for establishing credibility of a machine learning (ML) model used to predict a key process control variable setting to maximize product quality in a component manufacturing application. Our model coupled a purely data-based ML model with a physics-based adjustment that encoded subject matter expertise of the physical process. Establishing credibility of the resulting model provided the basis for eliminating a costly intermediate testing process that was previously used to determine the control variable setting.",

author = "Banyay, {Gregory A.} and Worrell, {Clarence L.} and Sidener, {Scott E.} and Kaizer, {Joshua S.}",

note = "Publisher Copyright: {\textcopyright} 2021 by ASME",

year = "2021",

month = sep,

doi = "10.1115/1.4051717",

language = "English (US)",

volume = "6",

journal = "Journal of Verification, Validation and Uncertainty Quantification",

issn = "2377-2158",

publisher = "American Society of Mechanical Engineers(ASME)",

number = "3",

}

TY - JOUR

T1 - Credibility Assessment of Machine Learning in a Manufacturing Process Application

AU - Banyay, Gregory A.

AU - Worrell, Clarence L.

AU - Sidener, Scott E.

AU - Kaizer, Joshua S.

PY - 2021/9

Y1 - 2021/9

N2 - We present a framework for establishing credibility of a machine learning (ML) model used to predict a key process control variable setting to maximize product quality in a component manufacturing application. Our model coupled a purely data-based ML model with a physics-based adjustment that encoded subject matter expertise of the physical process. Establishing credibility of the resulting model provided the basis for eliminating a costly intermediate testing process that was previously used to determine the control variable setting.

AB - We present a framework for establishing credibility of a machine learning (ML) model used to predict a key process control variable setting to maximize product quality in a component manufacturing application. Our model coupled a purely data-based ML model with a physics-based adjustment that encoded subject matter expertise of the physical process. Establishing credibility of the resulting model provided the basis for eliminating a costly intermediate testing process that was previously used to determine the control variable setting.

UR - http://www.scopus.com/inward/record.url?scp=85127367484&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85127367484&partnerID=8YFLogxK

U2 - 10.1115/1.4051717

DO - 10.1115/1.4051717

M3 - Article

AN - SCOPUS:85127367484

SN - 2377-2158

VL - 6

JO - Journal of Verification, Validation and Uncertainty Quantification

JF - Journal of Verification, Validation and Uncertainty Quantification

IS - 3

M1 - 031007

ER -

Credibility Assessment of Machine Learning in a Manufacturing Process Application

Abstract

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this