Enhancing Experimental Efficiency in Materials Design: A Comparative Study of Taguchi and Machine Learning Methods

TL;DR

This paper compares Taguchi and machine learning methods, specifically Gaussian process regression, for optimizing complex parameters in materials design, demonstrating ML's superior accuracy and efficiency in predicting process outcomes.

Contribution

It introduces an active learning GPR model with uncertainty-based exploration to improve materials process optimization over traditional Taguchi DOE methods.

Findings

GPR outperforms Taguchi in accuracy and efficiency

Active learning accelerates convergence in process prediction

GPR effectively captures non-linear dependencies in materials data

Abstract

Materials design problems often require optimizing multiple variables, rendering full factorial exploration impractical. Design of experiment (DOE) methods, such as Taguchi technique, are commonly used to efficiently sample the design space but they inherently lack the ability to capture non-linear dependency of process variables. In this work, we demonstrate how machine learning (ML) methods can be used to overcome these limitations. We compare the performance of Taguchi method against an active learning based Gaussian process regression (GPR) model in a wire arc additive manufacturing (WAAM) process to accurately predict aspects of bead geometry, including penetration depth, bead width, and height. While Taguchi method utilized a three-factor, five-level L25 orthogonal array to suggest weld parameters, the GPR model used an uncertainty-based exploration acquisition function coupled with latin hypercube sampling for initial training data. Accuracy and efficiency of both models was evaluated on 15 test cases, with GPR outperforming Taguchi in both metrics. This work applies to broader materials processing domain requiring efficient exploration of complex parameters.