Credibility Assessment of Machine Learning in a Manufacturing Process Application
Gregory A. Banyay, Clarence L. Worrell, Scott E. Sidener, Joshua S. Kaizer · Journal of Verification Validation and Uncertainty Quantification · 2021
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.