HZHeng Zhang

Heng Zhang

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Heng Zhang has a total of 20 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Knowledge‐guided digital twin modeling method of generating hierarchical scenes for a high‐speed railway

    by Heng Zhang, Wen Zhao, Zujie Han, Jun Zhu, Qing Zhu, Zhu Xu, Dejun Feng, Yongjun Song, Shufeng Song, Bo Zhang, et al.

    China's railway construction is rapidly transitioning toward integrated management of “stakeholders, management elements, and management processes”. Therefore, comprehensive and whole‐process digital twin scene modeling is urgently needed for intelligent railway construction. However, the requirements of three‐dimensional scenes in different stages vary hierarchically, resulting in a lack of construction semantics and limited universality in modeling. This article proposes a knowledge‐guided digital twin modeling method of hierarchical scenes for a high‐speed railway. We first build a knowledge graph of “knowledge‐model‐data” to achieve an accurate and hierarchical description of railway scenes. We then establish a parameter‐driven modeling method that integrates knowledge guidance and primitive combination to generate a display scene and a virtual design scene automatically. Third, we propose joint linkage and model growth methods for construction action modeling, which are used to generate a virtual construction scene. Finally, in response to the hierarchical scene‐generating requirements in different stages, we conduct intelligent modeling experiments for the entire design and construction process. The knowledge graph of the hierarchical semantic description mode significantly improves the flexibility and universality of the modeling method. The proposed modeling method for the entire process contributes to the rapid representation of design data, in‐depth design, visual exploration, and dynamic optimization of the construction process. This article provides a reliable digital twin modeling solution for the entire process to improve design and construction quality.


  • InsuDet: A Fault Detection Method for Insulators of Overhead Transmission Lines Using Convolutional Neural Networks

    by Xingtuo Zhang, Yiyi Zhang, Jiefeng Liu, Chaohai Zhang, Xueyue Xue, Heng Zhang, Wei Zhang

    One of the key tasks of the overhead line power equipment inspection based on aerial images acquired by unmanned aerial vehicles is to determine whether the insulators are faulty. However, the fault area on the insulator string occupies a relatively small portion of the entire image, which will make detection difficult. This article presents an intelligent fault detection method for overhead line insulators based on aerial images and improved you only look once (YOLOv3) deep learning technology. In our model, a densely connected feature pyramid network (FPN) is proposed. First, this network can improve the utilization rate of the strong semantic information of deep features and the localization information of shallow features, thereby improving the small insulator fault (missing-cap) detection performance of the YOLOv3 model. Second, this network reduces the number of parameters of the YOLOv3 model, resulting in a low risk of network over-fitting for small datasets. The experimental results on the CPLID dataset show that our model has higher detection accuracy in localization of overhead line insulators and detection of insulator missing-cap faults compared with the existing works.