University of Surrey

Test tubes in the lab Research in the ATI Dance Research

Transfer learning for process fault diagnosis: Knowledge transfer from simulation to physical processes

Li, Weijun, Gu, Sai, Zhang, Xiangping and Chen, Tao (2020) Transfer learning for process fault diagnosis: Knowledge transfer from simulation to physical processes Computers & Chemical Engineering, 139, 106904.

[img] Text
Transfer Learning for Process Fault Diagnosis - AAM.docx - Accepted version Manuscript
Available under License Creative Commons Attribution.

Download (4MB)


Deep learning has shown great promise in process fault diagnosis. However, due to the lack of sufficient labelled fault data, its application has been limited. This limitation may be overcome by using the data generated from computer simulations. In this study, we consider using simulated data to train deep neural network models. As there inevitably is model-process mismatch, we further apply transfer learning approach to reduce the discrepancies between the simulation and physical domains. This approach will allow the diagnostic knowledge contained in the computer simulation being applied to the physical process. To this end, a deep transfer learning network is designed by integrating the convolutional neural network and advanced domain adaptation techniques. Two case studies are used to illustrate the effectiveness of the proposed method for fault diagnosis: a continuously stirred tank reactor and the pulp mill plant benchmark problem.

Item Type: Article
Divisions : Faculty of Engineering and Physical Sciences > Chemical and Process Engineering
Authors :
Zhang, Xiangping
Date : 4 August 2020
Funders : Engineering and Physical Sciences Research Council (EPSRC), Biotechnology and Biological Sciences Research Council (BBSRC), Unilever
DOI : 10.1016/j.compchemeng.2020.106904
Copyright Disclaimer : © 2020 The Authors. Published by Elsevier Ltd. This is an open access article under the CC BY license. (
Uncontrolled Keywords : Fault diagnosis; Transfer learning; Model-process mismatch; Deep learning; Computer simulation; Domain adaptation
Depositing User : Clive Harris
Date Deposited : 03 Jun 2020 20:54
Last Modified : 03 Jun 2020 20:54

Actions (login required)

View Item View Item


Downloads per month over past year

Information about this web site

© The University of Surrey, Guildford, Surrey, GU2 7XH, United Kingdom.
+44 (0)1483 300800