Abstract
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.
Highlights
The gearboxes play an irreplaceable role in the mechanical power system, which usually works in harsh and complex environments [1,2]
The methods based on deep learning are prominent because they can adaptively learn the fault information hidden in the collected signals, such as long short-term memory network (LSTM) [4], recurrent neural network (RNN) [5] and convolutional neural network (CNN) [6]
Four methods are employed for comparison on the test tasks T1~T5 to illustrate the superiority of the proposed fusion domain-adaptation convolutional neural network (FDACNN)
Summary
The gearboxes play an irreplaceable role in the mechanical power system, which usually works in harsh and complex environments [1,2]. Chen et al [15] proposed the transfer neural network to diagnose the faults of the rotary machinery, which pre-trains a 1D-CNN with the source data and uses the limited target data to fine-tune the model to obtain a transfer convolutional neural network. It is rare to use infrared thermal images and vibration signals to diagnose structured and unstructured failure states in unlabeled target domains. The fusion of the preprocessed vibration signal and the infrared thermal image makes the fault information in the training sample more abundant and obvious. A fusion domain-adaptation CNN fault diagnosis method for gearboxes is explored It can extract domain invariant features from the fusion information of vibration signals and infrared thermal images and implement gearbox fault diagnosis in an unlabeled target domain.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
