Active learning-driven uncertainty reduction for in-flight particle characteristics of atmospheric plasma spraying of silicon

Memon, Halar; Gjerde, Eskil; Lynam, Alex; Chowdhury, Amiya; De Maere, Geert; Figueredo, Grazziela; Hussain, Tanvir

Abstract

The first-of-its-kind use of the active learning (AL) framework in thermal spray is adapted to enhance the prediction accuracy of the in-flight particle characteristics. The successful AL framework implementation via Bayesian Optimisation is beneficial in, first, reducing the maximum uncertainty, which greatly improves the prediction accuracy and informativeness of the existing database. Second, it reduces local uncertainty around a contrived test point that offers the capability to find improvement in a limited search area, allowing an accurate prediction around a desired test point. The dataset for Machine Learning (ML) training consists of 26 atmospheric plasma spray (APS) parameters of silicon and a further six AL-guided spray runs carried out to reduce maximum uncertainty in the initial database. On average, a 52.9% improvement (error reduction) of RMSE and an R2 increase of 8.5% were reported on the predicted in-flight particle velocities and temperatures after the AL-driven optimisation. Furthermore, the contrived test point optimisation to predict the best possible characteristics in a limited search space resulted in a three-fold increase in prediction accuracy compared to the non-optimised prediction. The AL-driven optimisation proved to be greatly beneficial for resource-intensive thermal spraying, as the framework not only allowed an accurate prediction of the in-flight particle characteristics but also found expected improvement around a desired in-flight characteristic. Furthermore, the framework uses the Gaussian Process (GP) ML model as a surrogate that generalises a global solution without necessarily involving physical and underlying mechanisms, thus extending the framework to other thermal spraying methods.

Citation

Memon, H., Gjerde, E., Lynam, A., Chowdhury, A., De Maere, G., Figueredo, G., & Hussain, T. (2024). Active learning-driven uncertainty reduction for in-flight particle characteristics of atmospheric plasma spraying of silicon. Engineering Applications of Artificial Intelligence, 128, Article 107465. https://doi.org/10.1016/j.engappai.2023.107465

• Journal Article Type: Article
• Acceptance Date: Nov 6, 2023
• Online Publication Date: Nov 18, 2023
• Publication Date: 2024-02
• Deposit Date: Feb 5, 2024
• Publicly Available Date: Feb 6, 2024
• Journal: Engineering Applications of Artificial Intelligence
• Print ISSN: 0952-1976
• Electronic ISSN: 0952-1976
• Publisher: Elsevier
• Peer Reviewed: Peer Reviewed
• Volume: 128
• Article Number: 107465
• DOI: https://doi.org/10.1016/j.engappai.2023.107465
• Keywords: Atmospheric plasma spray; Machine learning; Bayesian optimisation; Active learning; Thermal spray
• Public URL: https://nottingham-repository.worktribe.com/output/27599528
• Additional Information: This article is maintained by: Elsevier; Article Title: Active learning-driven uncertainty reduction for in-flight particle characteristics of atmospheric plasma spraying of silicon; Journal Title: Engineering Applications of Artificial Intelligence; CrossRef DOI link to publisher maintained version: https://doi.org/10.1016/j.engappai.2023.107465; Content Type: article; Copyright: © 2023 The Authors. Published by Elsevier Ltd.