Dong Lu

Dong Lu

Auto-generated profile, based on publicly available information

Dong Lu

School of Automation, Nanjing University of Science and Technology, Nanjing, People’s Republic of China

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

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

Representative Publications

View All Publications
30 May 2024 in Engineering Research Express
Verified
Journal Article
Closed access
DLDong Lu
Dong Lu
JYJing Yang
Jing Yang
LMLyu Ming
Lyu Ming
JZJie Zhang
Jie Zhang
The development of infrared image detection technology has improved the real-time performance and safety of fault diagnosis. To address the problem of insufficient features caused by the low resolution of infrared images, a fault diagnosis model for induction motor infrared images based on Dual-Stream Attention Convolutional (DSAC) is proposed. Firstly, this model employs a dual-stream convolutional neural network to extract spatial features in the X and Y directions of the infrared images separately. This dual-stream structure allows the network to simultaneously learn and utilize information from both X and Y directions, enabling a more comprehensive capture of temperature distribution and variation trends in the infrared images. Then, a convolutional attention mechanism is introduced to assign weights to the obtained features. The attention maps generated by the convolutional attention layer enhance key features while suppressing unimportant information, thereby enhancing the focusing performance of the DSAC model on critical features. Finally, the weighted dual-stream features are fused to achieve the goal of fault diagnosis for induction motor infrared images. The DSAC model is validated using the induction motor infrared image dataset from Babol Noshirvani University of Technology, demonstrating excellent diagnostic accuracy and speed on small sample datasets, providing a feasible solution for fault diagnosis of induction motor infrared images.

23 April 2024
Verified
Book Chapter
Closed access
PDF file
DLDong Lu
Dong Lu
MLMing Lyu
Ming Lyu
BYBowen Yu
Bowen Yu
HLHao Liu
Hao Liu
JZJie Zhang
Jie Zhang

24 May 2024
Verified
Conference Paper
Open access
NXNan Xiao
Nan Xiao
WYWenjie Ye
Wenjie Ye
LYLin Yu
Lin Yu
DLDong Lu
Dong Lu
JZJie Zhang
Jie Zhang
In network science, identifying key nodes is crucial for understanding and optimizing the structure and functionality of complex networks. The traditional K-shell decomposition method has limitations in revealing the core structure of networks, often overlooking the interactions among nodes and the global characteristics of the network. This study proposes an improved K-shell algorithm that incorporates the concept of "Neighbor Degree Sum" to differentiate nodes with the same k-value more finely and assess node importance more accurately. By considering both the connectivity of the nodes and their neighbors, the algorithm achieves a more nuanced stratification, enhancing the precision of key node identification. Validation on social network datasets demonstrates that this algorithm outperforms traditional methods in effectively identifying key nodes, deepening our understanding of the mechanisms behind key node identification in complex networks, and providing new tools for fields such as social network analysis, internet maintenance, and traffic optimization.