Machine learning model of acoustic signatures: Towards digitalised thermal spray manufacturing

  1. Viswanathan, V.
  2. McCloskey, Alex
  3. Mathur, Ruchir
  4. Nguyen, Dinh T.
  5. Faisal, Nadimul Haque
  6. Prathuru, Anil
  7. Llavori, Iñigo
  8. Murphy, Adrian
  9. Tiwari, Ashutosh
  10. Matthews, Allan
  11. Agrawal, Anupam
  12. Goel, Saurav
Revue:
Mechanical Systems and Signal Processing

ISSN: 0888-3270

Année de publication: 2024

Volumen: 208

Pages: 111030

Type: Article

DOI: 10.1016/J.YMSSP.2023.111030 GOOGLE SCHOLAR lock_openAccès ouvert editor

D'autres publications dans: Mechanical Systems and Signal Processing

Résumé

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 thermal spraying process lies in instrumenting the manufacturing platform as the process includes harsh conditions, including UV Rays, high-plasma temperature, dusty chemical environment, and spray booth inaccessibility. 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 digitalization. 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).

€ Voir financement

Information sur le financement

All authors acknowledge the financial support provided by the UKRI via Grants No. EP/S036180/1, EP/W033178/1 and EP/T024607/1, Hubert Curien Partnership award 2022 from the British Council and the International exchange Cost Share award by the Royal Society (IEC\NSFC\223536). AT is thankful to the Royal Academy to support him with the Research Chair award (RCSRF1718\5\41). AM and IV also gratefully acknowledge the financial support given by the Eusko Jaurlaritza via Grants No. KK-2020/00063 (SUSIE) and KK-2022/00080 (MINAKU)

Financeurs

  • UKRI United Kingdom
    • EP/S036180/1
    • EP/W033178/1
    • EP/T024607/1
  • Royal Academy United Kingdom
    • RCSRF1718\5\41
  • Eusko Jaurlaritza Spain
    • KK-2020/00063
    • KK-2022/00080
  • Royal Society United Kingdom
    • IEC\NSFC\223536

Références bibliographiques

  • Viswanathan, (2021), Emergent Materials, pp. 1
  • Faisal, (2022), ChemNanoMat, pp. e202200384, 10.1002/cnma.202200384
  • Hardwicke, (2013), J. Therm. Spray Technol., 22, pp. 564, 10.1007/s11666-013-9904-0
  • Vardelle, (2016), J. Therm. Spray Technol., 25, pp. 1376, 10.1007/s11666-016-0473-x
  • Malamousi, (2022), Surf. Coat. Technol., 433, 10.1016/j.surfcoat.2022.128138
  • Zhao, (2023), Surf. Coat. Technol., 461, 10.1016/j.surfcoat.2023.129435
  • Gao, (2022), Surf. Coat. Technol., 441, 10.1016/j.surfcoat.2022.128569
  • Zhao, (2023), J. Manuf. Process., 98, pp. 173, 10.1016/j.jmapro.2023.05.022
  • Zhang, (2009), J. Therm. Spray Technol., 18, pp. 23, 10.1007/s11666-008-9214-0
  • Faisal, (2011), J. Therm. Spray Technol., 20, pp. 1071, 10.1007/s11666-011-9620-6
  • Deng, (2012), Surf. Coat. Technol., 206, pp. 3875, 10.1016/j.surfcoat.2012.03.038
  • Agapakis, (1992), J. Therm. Spray Technol., 1, pp. 19, 10.1007/BF02657013
  • Li, (2020), Procedia Manuf., 48, pp. 643, 10.1016/j.promfg.2020.05.093
  • Yang, (2020), Materials, 13, pp. 5755, 10.3390/ma13245755
  • J. Lee, J. Singh, M. Azamfar, V. Pandhare, Industrial AI and predictive analytics for smart manufacturing systems, Smart Manufacturing, Elsevier2020, pp. 213-244.
  • Maschler, (2022), Procedia CIRP, 107, pp. 511, 10.1016/j.procir.2022.05.017
  • H. Tercan, A. Guajardo, T. Meisen, Industrial Transfer Learning: Boosting Machine Learning in Production, 2019 IEEE 17th International Conference on Industrial Informatics (INDIN), 2019, pp. 274-279.
  • K. Simonyan, A. Zisserman, Very deep convolutional networks for large-scale image recognition, arXiv preprint arXiv:1409.1556 (2014).
  • Zhao, (2018), Ieee Access, 7, pp. 984, 10.1109/ACCESS.2018.2886095
  • Droubi, (2017), J. Constr. Steel Res., 134, pp. 28, 10.1016/j.jcsr.2017.03.012