Machine learning model of acoustic signatures: towards digitalised thermal spray manufacturing.

Viswanathan, V.; McCloskey, Alex; Mathur, Ruchir; Nguyen, Dinh T.; Faisal, Nadimul Haque; Prathuru, Anil; Llavori, Iñigo; Murphy, Adrian; Tiwari, Ashutosh; Matthews, Allan; Agrawal, Anupam; Goel, Saurav

Abstract

Thermal spraying, an important industrial surface manufacturing process in sectors such as aerospace, energy and biomedical, remains a skill intensive process often involving multiple trial runs impacting the yield. The core research challenge in digitalisation of the thermal spraying process lies in instrumenting the manufacturing platform, as the process includes harsh conditions such as UV rays, high-plasma temperatures, dusty chemical environments and inaccessibility of the spray booth. This paper introduces a novel application of machine learning to the acoustic emission spectra of thermal spraying. By transitioning from the amplitude-time domain to a Fourier-transformed frequency-time domain, it is possible to predict anomalies in real-time - a crucial step towards sustainable material and manufacturing digitalisation. Our experimental results also indicate that this method is suitable for industrial applications, by generating useful data that can be used to develop Visual Geometry Group (VGG) transfer learning models to overcome the traditional limitations of convoluted neural networks (CNN).

Citation

VISWANATHAN, V., MCCLOSKEY, A., MATHUR, R., NGUYEN, D.T., FAISAL, N.H., PRATHURU, A., LLAVORI, I., MURPHY, A., TIWARI, A., MATTHEWS, A., AGRAWAL, A. and GOEL, S. 2024. Machine learning model of acoustic signatures: towards digitalised thermal spray manufacturing. Mechanical systems and signal processing [online], 208, article number 111030. Available from: https://doi.org/10.1016/j.ymssp.2023.111030

• Journal Article Type: Article
• Acceptance Date: Dec 11, 2023
• Online Publication Date: Dec 19, 2023
• Publication Date: Feb 15, 2024
• Deposit Date: Jan 5, 2024
• Publicly Available Date: Jan 5, 2024
• Journal: Mechanical systems and signal processing
• Print ISSN: 0888-3270
• Electronic ISSN: 1096-1216
• Publisher: Elsevier
• Peer Reviewed: Peer Reviewed
• Volume: 208
• Article Number: 111030
• DOI: https://doi.org/10.1016/j.ymssp.2023.111030
• Keywords: Thermal spraying; Acoustics; Machine learning; Manufacturing; Manufacturing technology
• Public URL: https://rgu-repository.worktribe.com/output/2193625