Abstract

Fault diagnosis of the bearing is vital for the safe and reliable operation of rotating machines in the manufacturing industry. Convolutional neural networks (CNNs) have been popular in bearing fault diagnosis by right of robust and reliable feature extraction ability. However, the collected vibrational signals from machines are usually corrupted by unrelated noises due to complicated transfer path modulations and component coupling. As traditional CNN lacks the denoising structure, its capability of extracting features from vibrational features is restrained by noise disturbances. In response to the above issue, this paper first proposes a simple but efficient Gramian-based noise reduction strategy called Gramian Noise Reduction (GNR) based on the periodic self-similarity of vibrational signals. Second, for the problem of lacking denoising structure in traditional CNNs, a novel end-to-end GNR-based CNN model, termed as Gramian Time Frequency Enhancement Network (GTFE-Net), is presented for bearing fault diagnosis. The GTFE-Net has three branches to parallelly process the raw original signal, the GNR denoised signal, and the frequency spectrums, respectively. GNR is integrated into the GTFE-Net, prompting the network to pay more attention to feature extraction rather than noise suppression. Three case studies using test rig and real engineering datasets are performed to verify the effectiveness of the proposed method for bearing fault diagnosis. The experimental results show that the GTFE-Net can reduce the useless noises in vibrational signals and deliver a remarkable improvement in classification performance compared with the six state-of-the-art methods. The source code is available at

Full Text
Published version (Free)

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 call