A novel fault early warning method for centrifugal blowers based on stacked denoising autoencoder and transfer learning

Centrifugal blowers are easy to get faults due to the harsh working environment, and appropriate fault early warning is of great significance for predictive maintenance. Traditional fault early warning methods have poor resistance and feature learning ability in dealing with multivariate data with n...

Full description

Saved in:
Bibliographic Details
Published in:Journal of manufacturing systems Vol. 76; pp. 443 - 456
Main Authors: Zhang, You, Li, Congbo, Tang, Ying, Zhang, Xu, Zhou, Feng
Format: Journal Article
Language:English
Published: Elsevier Ltd 01.10.2024
Subjects:
Centrifugal blowers
Fault early warning
Stacked denoising autoencoder
Transfer learning
Centrifugal blowers
Stacked denoising autoencoder
Transfer learning
Fault early warning
ISSN:0278-6125
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Centrifugal blowers are easy to get faults due to the harsh working environment, and appropriate fault early warning is of great significance for predictive maintenance. Traditional fault early warning methods have poor resistance and feature learning ability in dealing with multivariate data with noise, and cannot achieve domain adaptation in different working environments. Aimed at solving these problems, this paper proposes a novel fault early warning method for centrifugal blowers based on stacked denoising autoencoder with sliding window (SW-SDAE) and transfer learning. The developed SW-SDAE model can effectively learn representative degradation features and temporal dependence from multivariate time-series data with noise. The reconstruction errors of SW-SDAE are used to construct the health indicators, which accurately characterizes the health status of the centrifugal blower. Meanwhile, transfer learning is employed to solve the problem of domain adaptation for different working environments. The established source domain warning model is successfully transferred to the target domain by minimizing the maximum mean discrepancy. When the health indicator exceeds the warning threshold, a fault early warning is performed. Experimental results demonstrate that the developed SW-SDAE warning model integrating transfer learning significantly resists the interference of noise and improves the domain adaptability for different working conditions. The proposed method achieves fault early warning 5.67 h without false alarms before failure and shows superior warning performance compared with traditional warning methods. •A stacked denoising autoencoder model with sliding window is developed to construct health indicators and achieve fault early warning.•A transfer learning method for solving domain adaption is employed in the fault early warning.•The fault warning model fully learns representative degradation features and temporal dependencies from multivariate time-series data with noise.•The proposed method significantly improves the domain adaptability for different working conditions and shows superior warning performance.
ISSN:0278-6125
DOI:10.1016/j.jmsy.2024.08.013