Efficient Training of Large-Scale Industrial Fault Diagnostic Models through Federated Opportunistic Block Dropout

Authors

  • Yuanyuan Chen School of Computer Science and Engineering, Nanyang Technological University, Singapore
  • Zichen Chen School of Computer Science and Engineering, Nanyang Technological University, Singapore University of California, Santa Barbara, CA, USA
  • Sheng Guo ENN Group, Beijing, China
  • Yansong Zhao School of Computer Science and Engineering, Nanyang Technological University, Singapore
  • Zelei Liu School of Computer Science and Engineering, Nanyang Technological University, Singapore
  • Pengcheng Wu School of Computer Science and Engineering, Nanyang Technological University, Singapore
  • Chengyi Yang ENN Group, Beijing, China
  • Zengxiang Li ENN Group, Beijing, China
  • Han Yu School of Computer Science and Engineering, Nanyang Technological University, Singapore

DOI:

https://doi.org/10.1609/aaai.v37i13.26836

Keywords:

Federaed Learning, Dropout, Block Importance, Industrial Fault Diagnostics

Abstract

Artificial intelligence (AI)-empowered industrial fault diagnostics is important in ensuring the safe operation of industrial applications. Since complex industrial systems often involve multiple industrial plants (possibly belonging to different companies or subsidiaries) with sensitive data collected and stored in a distributed manner, collaborative fault diagnostic model training often needs to leverage federated learning (FL). As the scale of the industrial fault diagnostic models are often large and communication channels in such systems are often not exclusively used for FL model training, existing deployed FL model training frameworks cannot train such models efficiently across multiple institutions. In this paper, we report our experience developing and deploying the Federated Opportunistic Block Dropout (FedOBD) approach for industrial fault diagnostic model training. By decomposing large-scale models into semantic blocks and enabling FL participants to opportunistically upload selected important blocks in a quantized manner, it significantly reduces the communication overhead while maintaining model performance. Since its deployment in ENN Group in February 2022, FedOBD has served two coal chemical plants across two cities in China to build industrial fault prediction models. It helped the company reduce the training communication overhead by over 70% compared to its previous AI Engine, while maintaining model performance at over 85% test F1 score. To our knowledge, it is the first successfully deployed dropout-based FL approach.

Downloads

Published

2024-07-15

How to Cite

Chen, Y., Chen, Z., Guo, S., Zhao, Y., Liu, Z., Wu, P., Yang, C., Li, Z., & Yu, H. (2024). Efficient Training of Large-Scale Industrial Fault Diagnostic Models through Federated Opportunistic Block Dropout. Proceedings of the AAAI Conference on Artificial Intelligence, 37(13), 15485-15493. https://doi.org/10.1609/aaai.v37i13.26836

Issue

Section

IAAI Technical Track on deployed Highly Innovative Applications of AI