Yan Li

Yan Li

Auto-generated profile, based on publicly available information

Yan Li

School of Mechanical Engineering, Sichuan University, Chengdu 610065, China

Research Focus & Metrics

Academic Career Length

21Years (2006-Present)

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

Representative Publications

View All Publications
9 May 2006 in The International Journal of Advanced Manufacturing Technology
Verified
Journal Article
Closed access
PDF file
YLYan Li
Yan Li
JWJian Wang
Jian Wang
XLXianglong Li
Xianglong Li
WZWu Zhao
Wu Zhao

19 February 2020 in Journal of Computing and Information Science in Engineering
Verified
Journal Article
Closed access
PDF file
QLQiyu Liu
Qiyu Liu
KWKai Wang
Kai Wang
YLYan Li
Yan Li
Ying LiuYing Liu
Ying Liu

31 May 2010 in Expert Systems with Applications
Verified
Journal Article
Closed access
WLWenqiang Li
Wenqiang Li
YLYan Li
Yan Li
JWJian Wang
Jian Wang
XLXiaoying Liu
Xiaoying Liu

30 May 2018 in Artificial Intelligence for Engineering Design, Analysis and Manufacturing
Verified
Journal Article
Closed access
PDF file
LLLongfan Liu
Longfan Liu
YLYan Li
Yan Li
YXYan Xiong
Yan Xiong
JCJuan Cao
Juan Cao
PYPing Yuan
Ping Yuan
In the design process, different problem statements result in different problem-solving strategies. A proper problem statement is the key to effective problem-solving. Based on the characteristics of the product design process, we divided design problem statements into open-ended (OE), decision-making (DM), and constrained (CO) statements and attempted to investigate the influences of different problem statements on designers’ cognitive behaviors from three perspectives, namely divergent thinking, convergent thinking, and mental workload. Then we provided quantification description to these influences based on electroencephalography (EEG) technology. We conducted experiments on 19 participants and used the BrainProduct™ actiChamp-32 to record the EEG data. Results are as follows: (1) The higher task-related α power was found in the temporal and occipital regions in the OE task compared with that in the DM and CO tasks. The OE statement also would help designers get novel ideas by strengthening their divergent thinking. (2) In the DM and CO tasks, there was no significant difference in the impact of the brain region on convergent thinking, but activities in the left hemisphere were stronger than that in the right hemisphere. The DM and CO tasks have better performance in convergent thinking than the OE task. (3) In the CO task, the designer's mental workload is the highest and mainly related to the activation of the centroparietal and occipital regions. These findings help designers understand the design problem-solving process from the perspective of cognitive science and monitor their thinking modes in the design process so as to improve their design performance.

1 May 2021 in Computers in Industry
Verified
Journal Article
Closed access
CCChen Chen
Chen Chen
YTYe Tao
Ye Tao
YLYan Li
Yan Li
QLQiyu Liu
Qiyu Liu
SLSong Li
Song Li
ZTZhong Tang
Zhong Tang

20 August 2019 in IEEE Signal Processing Letters
Verified
Journal Article
Closed access
HYHui Yu
Hui Yu
KWKai Wang
Kai Wang
YLYan Li
Yan Li
WZWu Zhao
Wu Zhao
Although representation learning has been proved to be a promising and effective solution for intelligent fault diagnosis, existing methods still encounter classification performance degradation due to large intra-class variations of real-world applications. In this work, we present a novel representation learning method, namely class level autoencoder (CLAE) for fault diagnosis which aims to learn representative and discriminative features from vibration signals. Specifically, we formulate a novel loss function for representation learning by jointly minimizing the basic and class level reconstruction errors to restrain intra-class variations in the feature space. In addition, we propose a new and simple feature pooling strategy to effectively fuse various meaningful local features to capture efficient and inherent fault pattern information about the input. Extensive experimental results on rolling bearing dataset demonstrate that our proposed method achieves very competitive results compared to state-of-the-art methods. The code of the proposed method is available at https://github.com/KWflyer/CLAE.