Publications by authors named "Qingbin Tong"
Article Synopsis
- Deep transfer learning is utilized for enhancing models in cross-domain fault diagnosis of rolling bearings, where traditional methods struggle with differing data distributions.
- The proposed deep reconstruction transfer convolutional neural network (DRTCNN) leverages unsupervised training and a deep reconstruction convolutional autoencoder to extract features that are consistent across domains.
- A new subdomain alignment loss function and a label smoothing algorithm are introduced to improve classification accuracy and model robustness by addressing issues related to data distribution and label reliability.
The transient pulses caused by local faults of rolling bearings are an important measurement information for fault diagnosis. However, extracting transient pulses from complex nonstationary vibration signals with a large amount of background noise is challenging, especially in the early stage. To improve the anti-noise ability and detect incipient faults, a novel signal de-noising method based on enhanced time-frequency manifold (ETFM) and kurtosis-wavelet dictionary is proposed.
View Article and Find Full Text PDF