Search for Author, Title, Keyword
Reconstruction-based stacked sparse auto-encoder for nonlinear industrial process fault diagnosis
More details
Hide details
School of Energy and Environment, Southeast University, China
Nanjing Nari-Relays Electric Co., Ltd, China
Submission date: 2023-09-27
Final revision date: 2023-10-13
Acceptance date: 2023-11-25
Online publication date: 2023-11-26
Publication date: 2023-11-26
Corresponding author
Shaojun Ren   

School of Energy and Environment, Southeast University, China
Eksploatacja i Niezawodność – Maintenance and Reliability 2024;26(1):175873
  • A novel RBSSAE based fault diagnosis framework is developed for large-scale system.
  • A generalized RB index calculation algorithm for deep neural networks is proposed.
  • The search procedure of reconstruction directions is optimized using the SFFS method.
  • The optimal reconstruction magnitudes are calculated by Stephenson iterative method.
  • The proposed RBSSAE has outstanding diagnostic performance and computational efficiency.
The reconstruction-based (RB) approach can effectively suppress the misdiagnosis problem due to the smearing effect in fault isolation. However, the current exploration of the RB approach for large-scale nonlinear systems is still limited. Therefore, this paper proposes a reliable and effective fault diagnosis method based on a reconstruction-based stacked sparse autoencoder (RBSSAE) for high-dimensional industrial systems. In RBSSAE, a reconstruction-based index achieved by the Steffensen iterative method is developed to check whether the given variable(s) are responsible for the faults efficiently. However, the number of possible faulty variable combinations grows exponentially with the system dimension or actual abnormal variables, causing an unbearable computational burden. Hence, the proposed RBSSAE utilizes a sequential floating forward selection approach to rapidly isolate the most decisive variable combination, meeting a requirement of online fault diagnosis. Finally, the effectiveness of the RBSSAE is verified on a numerical example and a real industrial case.
This work is supported by the National Key R&D Program of China (No. 2022YFB4100700).
Journals System - logo
Scroll to top