Xin Chen

Xin Chen

Auto-generated profile, based on publicly available information

Xin Chen

Shandong Hedui Intelligent Technology Company, Ltd., Shandong, China

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

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

Representative Publications

View All Publications
15 March 2022 in IEEE Transactions on Power Delivery
Verified
Journal Article
Closed access
Hanbo ZhengHanbo Zheng
Hanbo Zheng
YCYaohui Cui
Yaohui Cui
WYWenqiang Yang
Wenqiang Yang
JLJinheng Li
Jinheng Li
LJLiming Ji
Liming Ji
XCXin Chen
Xin Chen
The infrared image diagnostic technology of substation equipment is often interfered by its complex background, and cannot reflect the effective temperature information of the equipment, which is not conducive to the realization of subsequent fault diagnosis. In order to solve this problem, an improved CenterNet is proposed to improve the recognition effect of substation equipment under complex backgrounds. First, a richer substation infrared image dataset is established. Second, the Iresgroup structure is proposed as a backbone to further improve the feature learning ability of CenterNet. In the Iresgroup structure, an improved projection shortcut and Iresnet structure are improved to control the number of ReLUs on the main path, which can further improve the detection accuracy of the model, with higher robustness. In addition, the group conv structure is used to further improve the model, so that the model maintains the same amount of parameters while strengthening its feature learning ability. At last, The hyperparameters of centerNet have been redesigned to further improve the accuracy of the proposed method. The results show that compared with the several native backbones of the CenterNet and several mainstream detection models, this method has a significant improvement of 2% to 4% on mAP, and the improvement of single-type objects is as high as 7.4%. It can be seen that this method has achieved excellent detection results and can provide key technical support for fault detection of substation equipment.

12 August 2021 in IEEE Transactions on Sustainable Energy
Verified
Journal Article
Closed access
JMJianchao Ma
Jianchao Ma
Hanbo ZhengHanbo Zheng
Hanbo Zheng
JZJunhui Zhao
Junhui Zhao
XCXin Chen
Xin Chen
JZJinqian Zhai
Jinqian Zhai
CZchaohai zhang
chaohai zhang
Due to the continuous expansion of grid-connected renewable energy sources (RESs), the local-based methods of islanding detection are facing new challenges. We propose a communication-based detection method based on topology graph path query that can achieve improved results. This method uses existing communication technology and intelligent electronic devices (IEDs) in distribution networks to construct a distributed islanding information system. The bidirectional breadth first search (B-BFS) algorithm is used to conduct an offline path accessibility query to establish the decision islanding path (DIP) database. Then the method can quickly obtain results of islanding detection from online verification when the state of the line changes. On this basis, according to the topological structure and operation characteristics of the distribution network, we propose to use the Dijkstra algorithm based on closed-loop constraints to query the shortest path and select appropriate tie switch. This can achieve the goal of preventing islands by maintaining connectivity through synchronous switch operations. The proposed method has been verified on testing systems, and the results show that: (1) The distributed islanding information system has outstanding performance in solving islanding problems; (2) The proposed detection method has a convincing real-time performance; (3) The method of islanding prevention can fundamentally avoid the emergence of unplanned islands and their subsequent negative effects.