Jinliang Wu

Jinliang Wu

Auto-generated profile, based on publicly available information

Jinliang Wu

School of Artificial Intelligence, Chongqing University of Technology, Chongqing 400054, China

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
18 October 2021 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
XPXinglong Pei
Xinglong Pei
XZXiaoyang Zheng
Xiaoyang Zheng
JWJinliang Wu
Jinliang Wu
Owing to complex operational and measurement conditions, the data available to realize the effective training of deep models are often inadequate. Compared with traditional deep networks, Transformer exhibits a unique and excellent pattern recognition ability and has thus emerged as the de facto standard for processing tasks in many research fields. However, the application of Transformer architectures to fault diagnosis remains limited. To overcome these limitations and achieve highly accurate fault diagnosis, a novel Transformer convolution network (TCN) based on transfer learning is proposed. First, signal data are split into fixed-size patches, and the sequence of the linear embeddings of these patches is used as an input to a Transformer encoder. Subsequently, a convolutional neural network with a classifier layer is constructed to decode and classify patterns. The TCN is pretrained in the source domain and fine-tuned in the target domain by using a transfer learning strategy. Experiments to diagnose rotating machinery faults are conducted using bearing and gearbox datasets. The average diagnostic results for four transfer experiments are 99.71%, 99.97%, 99.83%, and 100.00%, and the proposed approach significantly outperforms state-of-the-art methods. The results demonstrate the exceptional robustness and effectiveness of the proposed method.

18 December 2020
Verified
Conference Paper
Closed access
XZXiaoyang Zheng
Xiaoyang Zheng
JWJinliang Wu
Jinliang Wu
ZYZeyu Ye
Zeyu Ye
Existing fault diagnosis methods based on Deep Learning require complicated and cumbersome preprocessing procedures heavily relying on signal processing and manual feature extraction techniques, which fails to maximize the superiority of the adaptive representation capability of Deep Learning. This paper proposes a novel end-to-end fault diagnosis approach combined convolutional neural network (CNN) with Bidirectional Long Short-Term Memory (BiLSTM) and Attention Mechanism. Specifically, one dimensional CNN is utilized to perform local feature extraction and dimension reduction on the input signal data. Then, the BiLSTM network is adopted to extract high-level features from the above results. The miscellaneous features extracted are filtered out by using Attention Mechanism. Finally, the learned features are implemented to train Softmax classifier for identifying fault types. To evaluate the effectiveness of the proposed model, experiments are carried out on two different datasets by using ten-fold cross validation approach. The results demonstrate that the proposed model is capable to learn features adaptively with fewer steps while ensuring higher accuracy compared with other state-of-art fault diagnosis methods.