Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Shaocheng Wu has a total of 48 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • TLPT-Net: A point transformer network dedicated to semantic segmentation of transmission line corridors

    by Shaocheng Wu, Linong Wang, Li Lu, Shengxuan Zu, Bin Song, Jiachen Gao

  • From Gap Configuration to Breakdown Voltage: A Novel Data-Driven Method for Predicting Breakdown Voltage

    by Shaocheng Wu, Linong Wang, Zisheng Zeng, Shengxuan Zu, Bin Song, Jiachen Gao

    Breakdown voltage prediction for air gaps is a crucial topic in high-voltage insulation research. Building upon existing studies and fundamental theories, the authors identify the gap configuration as the root cause influencing breakdown voltage. In light of this, the authors propose a novel approach for mapping the gap configuration to the breakdown voltage. Firstly, the data structuring method is proposed to abstract the air gap configuration into a mathematical point set. Secondly, inspired by the strengths of Graph Neural Networks and Transformers, the authors introduce a hybrid model, the Point Graph Transformer, which enable the prediction of the breakdown voltage through the point set. This approach is applicable to different gap configurations and influencing factors. To improve prediction accuracy and facilitate comparative studies, the authors present tailored data augmentation and padding strategies. Specifically, focusing on air gaps with two-dimensional axisymmetric structures, comprehensive breakdown voltage prediction research and comparative studies are conducted. Furthermore, ablation study is conducted and analyzed. The results demonstrate that the method deliver accurate breakdown voltage predictions, outperforming other methods. Notably, the evaluation metrics for the test set achieve a Mean Relative Error of 7.25%, Maximum Relative Error of 14.83%, and R-square of 96.86%.


  • Open Access

    RSA-PT: A Point Transformer-Based Semantic Segmentation Network for Uninterrupted Operation in a Distribution Network Scene

    by Deyu Nie, Linong Wang, Shaocheng Wu, Zhenyang Chen, Yongwen Li, Bin Song

    The digitization of uninterrupted operation in the distribution network is of great significance for improving people’s quality of life and promoting economic development. As an important means of achieving digitization, point cloud technology is crucial to the intelligent transformation of distribution network. To this end, the authors embedded the improved RSA (residual spatial attention) module and modified the loss function of network, proposing a deep learning network called RSA-PT for the semantic segmentation of a distribution network scene point cloud. According to the requirements of uninterrupted operation in the distribution network, the authors segmented the point cloud into the following ten classes: high-voltage line, low-voltage line, groundline, tower, ground, road, house, tree, obstacle, and car. Model and attention mechanism comparison experiments, as well as ablation studies, were conducted on the distribution network scene point cloud dataset. The experimental results showed that RSA-PT achieved mIoU (mean intersection over union), mA (mean accuracy), and OA (overall accuracy) indicators of 90.55%, 94.20%, and 97.20%, respectively. Furthermore, the mIoU of RSA-PT exceeded the baseline model by 6.63%. Our work could provide a technical foundation for the digital analysis of conditions for uninterrupted operation in distribution networks.


  • Open Access

    Prediction of Breakdown Voltage of Long Air Gaps Under Switching Impulse Voltage Based on the ISSA-XGBoost Model

    by Zisheng Zeng, Bin Song, Shaocheng Wu, Yongwen Li, Deyu Nie, Linong Wang

    In transmission lines, the discharge characteristics of long air gaps significantly influence the design of external insulation. Existing machine learning models for predicting breakdown voltage are typically limited to single gaps and do not account for the combined effects of complex factors. To address this issue, this paper proposes a novel prediction model based on the Improved Sparrow Search Algorithm-optimized XGBoost (ISSA-XGBoost). Initially, a comprehensive dataset of 46-dimensional electric field eigenvalues was extracted for each gap using finite element simulation software and MATLAB. Subsequently, the model incorporated a comprehensive set of input variables, including electric field eigenvalues, gap distance, waveform and polarity of the switching impulse voltage, temperature, relative humidity, and atmospheric pressure. After training, the ISSA-XGBoost model achieved a Mean Absolute Percentage Error (MAPE) of 7.85%, a Root Mean Squared Error (RMSE) of 56.92, and a Coefficient of Determination (R2) of 0.9938, indicating high prediction accuracy. In addition, the ISSA-XGBoost model was compared with traditional machine learning models and other optimization algorithms. These comparisons further substantiated the efficacy and superiority of the ISSA-XGBoost model. Notably, the model demonstrated exceptional performance in terms of predictive accuracy under extreme atmospheric conditions.


  • A Visual and Automated Calculation Method for Hazardous Areas of Live-Line Work Based on Point Cloud

    by Shaocheng Wu, Linong Wang, Guanjian Wang, Shengxuan Zu, Jiachen Gao, Bin Song

    Traditional live-line work often relies on experience and manual labour. At present, the safety assessment of live-line work scenes adopts unified standards. However, due to the complexity of live-line work scenes, the unified standard cannot accurately measure and evaluate its safety. To address these issues, this article proposes a new method for identifying the hazardous areas in live-line work scenes. The proposed method consists of 2 parts. Firstly, PointMGA, whose baseline model is PointNet++, is proposed to segment the point clouds of the transmission scenes. The experimental results demonstrate that the PointMGA achieves higher segmentation accuracy compared to both the PointNet++ model and PointNet segmentation models. Specifically, our method achieved an overall accuracy of 99.1% and 99.5% on the validation and testing sets, respectively, with a Mean Intersection over Union (MIoU) of 96.7% and 99.7%. The second part of the method involves using the Farthest Point Sampling- Bisection Region Growing (FPS-BRG) distance algorithm to calculate the hazardous areas within the specific transmission scenes. This algorithm ensures accuracy and significantly improves computational efficiency by over 8 times. The results demonstrate the effectiveness of the approach in enhancing the automation and safety of live-line work in complex transmission scenes.


  • Open Access

    Semantic Segmentation of Distribution Network Point Clouds Based on NF-PTV2

    by Long Han, Bin Song, Shaocheng Wu, Deyu Nie, Zhenyang Chen, Linong Wang

    An on-site survey is the primary task of working live in distribution networks. However, the traditional manual on-site survey method is not only not very intuitive but also inefficient. The application of 3D point cloud technology has opened up new avenues for on-site surveys in life working in distribution networks. This paper focused on the application of the Point Transformer V2(PTV2) model in the segmentation of distribution network point clouds. Given its deficiencies in boundary discrimination ability and limited feature extraction ability when processing the point clouds of distribution networks, an improved Non-local Focal Loss-Point Transformer V2 (NF-PTV2) model was proposed. With PTV2 as its core, this model incorporated the Non-Local attention to capturing long-distance feature dependencies, thereby compensating for the PTV2 model’s shortcomings in extracting features of large-scale objects with complex features. Simultaneously, the Focal Loss function was introduced to address the issue of class imbalance and enhance the model’s learning ability for small complex samples. The experimental results demonstrated that the overall accuracy (OA) of this model on the distribution network dataset reached 93.28%, the mean intersection over union (mIoU) reached 81.58%, and the mean accuracy (mAcc) reached 87.21%. In summary, the NF-PTV2 model proposed in this article demonstrated good performance in the point cloud segmentation task of the distribution network and can accurately identify various objects, which, to some extent, overcomes the limitations of the PTV2 model.


  • Open Access

    Semantic Segmentation of Key Categories in Transmission Line Corridor Point Clouds Based on EMAFL-PTv3

    by Li Lu, Linong Wang, Shaocheng Wu, Shengxuan Zu, Yuhao Ai, 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.


  • Open Access

    Diagnosis of Reverse-Connection Defects in High-Voltage Cable Cross-Bonded Grounding System Based on ARO-SVM

    by Yuhao Ai, Bin Song, Shaocheng Wu, Yongwen Li, Li Lu, Linong Wang

    High-voltage (HV) cables are increasingly used in urban power grids, and their safe operation is critical to grid stability. Previous studies have analyzed various defects, including the open circuit in the sheath loop, the flooding in the cross-bonded link box, and the sheath grounding fault. However, there is a paucity of research on the defect of the reverse direction between the inner core and the outer shield of the coaxial cable. Firstly, this paper performed a theoretical analysis of the sheath current in the reversed-connection state and established a simulation model for verification. The outcomes of the simulation demonstrate that there are significant variations in the amplitudes of the sheath current under different reversed-connection conditions. Consequently, a feature vector was devised based on the amplitude of the sheath current. The support vector machine (SVM) was then applied to diagnose the reversed-connection defects in the HV cable cross-bonded grounding system. The artificial rabbits optimization (ARO) algorithm was adopted to optimize the SVM model, attaining an impressively high diagnostic accuracy rate of 99.35%. The effectiveness and feasibility of the proposed algorithm are confirmed through the analysis and validation of the practical example.


  • Open Access

    Power Pylon Type Identification and Characteristic Parameter Calculation from Airborne LiDAR Data

    by Shengxuan Zu, Linong Wang, Shaocheng Wu, Guanjian Wang, Bin Song

    Reconstructing three-dimensional (3D) models of power equipment plays an increasingly important role in advancing digital twin power grids. To reconstruct a high-precision model, it is crucial to accurately obtain the pylon type and its necessary parameter information before modeling. This study proposes an improved method for identifying pylon types based on similarity measurement and a linearly transformed dataset. It begins by simplifying the identification of point clouds using the pylon shape curve. Subsequently, the resemblance between the curve and those curves within the dataset is evaluated using a similarity measurement to determine the pylon type. A novel method is proposed for calculating the characteristic parameters of the pylon point clouds. The horizontal and vertical distribution characteristics of the pylon point clouds are analyzed to identify key segmentation positions based on their types. Feature points are derived from key segmentation positions to calculate the characteristic parameters. Finally, the pylon 3D models are reconstructed on the basis of the calculated values. The experimental results showed that, compared with other similarity measurements, the Hausdorff distance had the best effect as a similarity measurement using the linearly transformed dataset, with an overall evaluation F-score of 86.4%. The maximum relative error of the calculated pylon parameters did not exceed 5%, affirming the feasibility of the algorithm.