shaocheng Wu

Mr. shaocheng Wu


Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
26 June 2023 in Electronics
Verified
Journal Article
Open access
PDF file
GWGuanjian Wang
Guanjian Wang
LWLinong Wang
Linong Wang
SWshaocheng Wu
shaocheng Wu
SZShengxuan Zu
Shengxuan Zu
BSBin Song
Bin Song
Automated extraction of key points from three-dimensional (3D) point clouds in transmission corridors provides technical support for digital twin construction and risk management of the power grid. However, accurately and efficiently segmenting the point clouds of transmission corridors remains a challenging problem. Traditional segmentation methods for transmission corridors suffer from low accuracy and poor generalization ability, and the potential of deep learning in this field has been overlooked. Therefore, the PointNet++ deep learning model is employed as the backbone network for the segmentation of 3D point clouds in transmission corridors. Additionally, given the distinct distribution of key components, an end-to-end CA-PointNet++ architecture is proposed by integrating the Coordinate Attention (CA) module with PointNet++. This approach captures long-distance spatial contextual features and improves feature saliency for more precise segmentation. Furthermore, CA-PointNet++ is evaluated on a dataset of 3D point clouds collected by unmanned aerial vehicles (UAV) equipped with Light Detection and Ranging (LiDAR) for inspecting transmission corridors. The results show that CA-PointNet++ achieved 93.7% overall accuracy (OA) and 67.4% mean Intersection over Union (mIoU). Comparative studies with established deep learning models confirm that our proposed CA-PointNet++ exhibits high accuracy and strong generalization ability for point cloud segmentation tasks in transmission corridors.

20 November 2023 in IEEE Sensors Journal
Verified
Journal Article
Closed access
SWshaocheng Wu
shaocheng Wu
LWLinong Wang
Linong Wang
BSBin Song
Bin Song
JGJiachen Gao
Jiachen Gao
The presence of deteriorated insulators in power grids poses a significant threat to the safety of power transmission. The Electric Field Detection Method (EFDM) is considered an effective approach for detecting low or zero value insulators on high-voltage transmission lines. In this paper, we analyzed the effects of the detection device, measurement angle, and insulator deterioration on the axial electric field value of insulator strings using both test values and simulation values. Our results indicated that the detection device had minimal impact on the normalized values of the axial electric field, whereas the measurement angle affected the values. However, the errors between the test values and the simulation values at the ends of the insulator strings were larger, indicating that the measurement device is better suited for measuring at non-ends of the insulator strings. Based on our findings, we used the detection device to measure the electric field of insulator strings on a 220 kV transmission line. The results of the measurement showed that the electric field detector could accurately measure the axial electric field of the insulator string and detect deteriorated insulators, thereby providing a more effective measurement method. Our research thus confirms the feasibility of the electric field detection method in actual power transmission lines.

23 March 2023 in IET Science, Measurement & Technology
Verified
Journal Article
Open access
QTQipeng Tan
Qipeng Tan
BSBin Song
Bin Song
LWLinong Wang
Linong Wang
SWshaocheng Wu
shaocheng Wu
Air‐insulated switchgear plays an important role in distribution network and partial discharge (PD) is one of the common faults in its operation. The method of gas component analysis, which is to detect chemical gas products, is a novel one to discover PD. In order to study the feasibility of the method, the monitoring experiment of characteristic gases, comprising carbon monoxide (CO), nitrogen dioxide (NO 2 ), and ozone (O 3 ), of metal protrusion PD is carried out. This paper conducts the comparative experiments on three main factors affecting PD: voltage, air humidity and degree of protrusion, as well as studies how they affect the formation of characteristic gases. According to the experimental result, higher applied voltage promotes the formation of characteristic gases in the same conditions. In addition, with the increase of humidity from 40% to 75%, the generation of gases is inhibited. Furthermore, when the needle–plate distance is 30 mm, the gas concentration has almost no change within 6 h, which is different from that of 10 mm. In conclusion, the difference in gases concentration reveals the influence of three main factors on the generation of characteristic gases and provides an analytical basis for PD detection by gas composition analysis.

28 August 2023 in IEEE Transactions on Dielectrics and Electrical Insulation
Verified
Journal Article
Closed access
JGJiachen Gao
Jiachen Gao
TDTongshu Ding
Tongshu Ding
YFYaqi Fang
Yaqi Fang
KLKai Liu
Kai Liu
SWshaocheng Wu
shaocheng Wu
ACAndrea Cavallini
Andrea Cavallini
Long air gaps containing a floating conductor are common in transmission and substation projects. As the floating electrode moved across the gap, the lowest breakdown voltage area (LBA) can be observed. In this article, an experimental platform for observing and measuring discharges in rod-rod-plane air gaps is used to investigate the discharge mechanism in the LBA. The results indicate that the existence of the LBA is related to the minimum voltage for the discharge channel formation in sub-gap 1 (facing the high-voltage rod) and the breakdown voltage of sub-gap 2 (facing the grounded plane). When the floating electrode is closer to the high-voltage electrode than the LBA, the breakdown voltage is increased because the potential of the floating electrode does not reach the breakdown voltage of sub-gap 2 at the time the discharge short circuits sub-gap 1. When the floating electrode is further away from the high-voltage electrode than the LBA, the breakdown voltage is increased because the discharge channel formation in sub-gap 1 requires a higher voltage. The LBA corresponds to the area where these two different phenomena can happen with minimum voltage. The results can contribute to modeling the discharge of a long air gap containing a floating conductor.

1 March 2022 in AIP Advances
Verified
Journal Article
Open access
PDF file
SWshaocheng Wu
shaocheng Wu
LWLinong Wang
Linong Wang
JGJiachen Gao
Jiachen Gao
CXCheng Xie
Cheng Xie
LLLei Liu
Lei Liu
ELEnwen Li
Enwen Li
With the increase of both voltage level and the transmission capacity, more attention has been paid to the external insulation of transmission lines. As the main external insulation medium of transmission line, the air gap’s dielectric strength will change when there are floating conductors. In this paper, we established an experiment platform to study the effects of floating conductors, simulated by floating rod electrode, on breakdown voltage, breakdown time, electric field distribution and discharge physical process of long air gaps under lightning impulse. The results showed that the intervention of floating electrode reduced the breakdown voltage and breakdown time of long air gaps, and the position with the longest breakdown time was the same as the position with the lowest breakdown voltage. In addition, the intervention of floating electrode improved the spatial electric field and complexity of discharge physical process.

8 February 2025 in Electronics
Verified
Journal Article
Open access
PDF file
LLLi Lu
Li Lu
LWLinong Wang
Linong Wang
SWshaocheng Wu
shaocheng Wu
SZShengxuan Zu
Shengxuan Zu
YAYuhao Ai
Yuhao Ai
BSBin Song
Bin Song
Accurate and efficient segmentation of key categories of transmission line corridor point clouds is one of the prerequisite technologies for the application of transmission line drone inspection. However, current semantic segmentation methods are limited to a few categories, involve cumbersome processes, and exhibit low accuracy. To address these issues, this paper proposes EMAFL-PTv3, a deep learning model for semantic segmentation of transmission line corridor point clouds. Built upon Point Transformer v3 (PTv3), EMAFL-PTv3 integrates Efficient Multi-Scale Attention (EMA) to enhance feature extraction at different scales, incorporates Focal Loss to mitigate class imbalance, and achieves accurate segmentation into five categories: ground, ground wire, insulator string, pylon, and transmission line. EMAFL-PTv3 is evaluated on a dataset of 40 spans of transmission line corridor point clouds collected by a drone in Wuhan and Xiangyang, Hubei Province. Experimental results demonstrate that EMAFL-PTv3 outperforms PTv3 in all categories, with notable improvements in the more challenging categories: insulator string (IoU 67.25%) and Pylon (IoU 91.77%), showing increases of 7.06% and 11.39%, respectively. The mIoU, mA, and OA scores reach 90.46%, 92.86%, and 98.07%, representing increases of 5.49%, 2.75%, and 2.44% over PTv3, respectively, proving its superior performance.