Fusion Domain-Adaptation CNN Driven by Images and Vibration Signals for Fault Diagnosis of Gearbox Cross-Working Conditions

• Published in: Entropy (Basel, Switzerland) Vol. 24; no. 1; p. 119
• Main Authors: Mao, Gang, Zhang, Zhongzheng, Qiao, Bin, Li, Yongbo
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 13.01.2022; MDPI
• Subjects: Adaptation; Artificial neural networks; Bias; Condition monitoring; Deep learning; Domains; Fault diagnosis; gearbox; Gearboxes; Infrared imagery; Machinery; Methods; multi-source heterogeneous fusion; Neural networks; Signal monitoring; Structural failure; transfer learning; Vibration measurement; Vibration monitoring; Working conditions; deep learning; transfer learning; fault diagnosis; gearbox; multi-source heterogeneous fusion
• ISSN: 1099-4300; 1099-4300
• DOI: 10.3390/e24010119

The vibration signal of gearboxes contains abundant fault information, which can be used for condition monitoring. However, vibration signal is ineffective for some non-structural failures. In order to resolve this dilemma, infrared thermal images are introduced to combine with vibration signals via fusion domain-adaptation convolutional neural network (FDACNN), which can diagnose both structural and non-structural failures under various working conditions. First, the measured raw signals are converted into frequency and squared envelope spectrum to characterize the health states of the gearbox. Second, the sequences of the frequency and squared envelope spectrum are arranged into two-dimensional format, which are combined with infrared thermal images to form fusion data. Finally, the adversarial network is introduced to realize the state recognition of structural and non-structural faults in the unlabeled target domain. An experiment of gearbox test rigs was used for effectiveness validation by measuring both vibration and infrared thermal images. The results suggest that the proposed FDACNN method performs best in cross-domain fault diagnosis of gearboxes via multi-source heterogeneous data compared with the other four methods.