Wanxiang Li

Wanxiang Li

Auto-generated profile, based on publicly available information

Wanxiang Li

School of Electrical Engineering, Xi’an Jiaotong University, Xi’an 710049, People’s Republic of 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
24 April 2023 in Engineering Applications of Artificial Intelligence
Verified
Journal Article
Closed access
WLWanxiang Li
Wanxiang Li
ZSZhiwu Shang
Zhiwu Shang
JZJie Zhang
Jie Zhang
MGMaosheng Gao
Maosheng Gao
SQShiqi Qian
Shiqi Qian

1 June 2021 in Engineering Applications of Artificial Intelligence
Verified
Journal Article
Closed access
WLWanxiang Li
Wanxiang Li
ZSZhiwu Shang
Zhiwu Shang
MGMaosheng Gao
Maosheng Gao
SQShiqi Qian
Shiqi Qian
BZBaoren Zhang
Baoren Zhang
JZJie Zhang
Jie Zhang

14 July 2022 in Reliability Engineering & System Safety
Verified
Journal Article
Closed access
WLWanxiang Li
Wanxiang Li
ZSZhiwu Shang
Zhiwu Shang
MGMaosheng Gao
Maosheng Gao
SQShiqi Qian
Shiqi Qian
ZFZehua Feng
Zehua Feng

20 December 2021 in Complex & Intelligent Systems
Verified
Journal Article
Open access
PDF file
ZSZhiwu Shang
Zhiwu Shang
BZBaoren Zhang
Baoren Zhang
WLWanxiang Li
Wanxiang Li
SQShiqi Qian
Shiqi Qian
JZJie Zhang
Jie Zhang
Convolution neural network (CNN) has been widely used in the field of remaining useful life (RUL) prediction. However, the CNN-based RUL prediction methods have some limitations. The receptive field of CNN is limited and easy to happen gradient vanishing problem when the network is too deep. The contribution differences of different channels and different time steps to RUL prediction are not considered, and only use deep learning features or handcrafted statistical features for prediction. These limitations can lead to inaccurate prediction results. To solve these problems, this paper proposes an RUL prediction method based on multi-layer self-attention (MLSA) and temporal convolution network (TCN). The TCN is used to extract deep learning features. Dilated convolution and residual connection are adopted in TCN structure. Dilated convolution is an efficient way to widen receptive field, and the residual structure can avoid the gradient vanishing problem. Besides, we propose a feature fusion method to fuse deep learning features and statistical features. And the MLSA is designed to adaptively assign feature weights. Finally, the turbofan engine dataset is used to verify the proposed method. Experimental results indicate the effectiveness of the proposed method.

28 June 2023 in Microbiology and Molecular Biology Reviews
Verified
Journal Article
Closed access
SLSi Liu
Si Liu
YHYanhong Han
Yanhong Han
WLWan-Xiang Li
Wan-Xiang Li
SDShou-Wei Ding
Shou-Wei Ding
Immune recognition of viral genome-derived double-stranded RNA (dsRNA) molecules and their subsequent processing into small interfering RNAs (siRNAs) in plants, invertebrates, and mammals trigger specific antiviral immunity known as antiviral RNA interference (RNAi). Immune sensing of viral dsRNA is sequence-independent, and most regions of viral RNAs are targeted by virus-derived siRNAs which extensively overlap in sequence.

9 June 2021 in Chinese Journal of Mechanical Engineering
Verified
Journal Article
Open access
PDF file
ZSZhiwu Shang
Zhiwu Shang
WLWanxiang Li
Wanxiang Li
MGMaosheng Gao
Maosheng Gao
XLXia Liu
Xia Liu
YYYan Yu
Yan Yu
For a single-structure deep learning fault diagnosis model, its disadvantages are an insufficient feature extraction and weak fault classification capability. This paper proposes a multi-scale deep feature fusion intelligent fault diagnosis method based on information entropy. First, a normal autoencoder, denoising autoencoder, sparse autoencoder, and contractive autoencoder are used in parallel to construct a multi-scale deep neural network feature extraction structure. A deep feature fusion strategy based on information entropy is proposed to obtain low-dimensional features and ensure the robustness of the model and the quality of deep features. Finally, the advantage of the deep belief network probability model is used as the fault classifier to identify the faults. The effectiveness of the proposed method was verified by a gearbox test-bed. Experimental results show that, compared with traditional and existing intelligent fault diagnosis methods, the proposed method can obtain representative information and features from the raw data with higher classification accuracy.