XLXiaowei Li

Xiaowei Li

*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


Xiaowei Li has a total of 11 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Real-Time Underground Fire Detection on Coal Mine IoVT Systems: An Edge-Deployed Efficient YOLO-Architecture

    by Xiaowei Li, Wei Yang, Jiaqi Wu, Zehua Wang, Qichong Tian, Tao Ye, Wei Chen, F. Richard Yu, Victor C. M. Leung

    Underground fires pose a significant threat to production safety in coal mines, and existing detection methods suffer from drawbacks such as poor adaptability to complex subterranean environments and excessive model parameters. To address the need for deploying object detection models on resource-constrained devices, this article proposes a novel and efficient algorithm for underground fire YOLO (UF-YOLO). The core innovation of this method is threefold: first, the StarNet module is introduced into the backbone to significantly reduce model parameters and computational complexity without sacrificing accuracy; second, the cross-scale context fusion module (CCFM) is integrated into the neck to enhance the model’s detection capability for fires of various scales, particularly small targets; and finally, partial convolution (PConv) is integrated to extract spatial features more efficiently, further reducing redundant computations and memory access. On our self-built mine fire image dataset (MFID), compared to the baseline model YOLOv11m, UF-YOLO reduces parameters by 77.1%, and increases inference speed by 60.6%. Experimental results on the public COCO val 2017 dataset demonstrate that the proposed method outperforms state-of-the-art (SOTA) models such as YOLOv12. The results confirm that UF-YOLO can be efficiently deployed on the edge-side of coal mine Internet of Video Things (IoVT) monitoring systems to perform accurate and real-time fire detection. This work provides a new intelligent paradigm for the real-time monitoring of underground fires.


  • Inspection of Mine Wire Rope Using Magnetic Aggregation Bridge Based on Magnetic Resistance Sensor Array

    by Hongyao Wang, Jie Tian, Xiaowei Li, Xin Lv

    Early detection of damage to wire ropes used in coal mine winching and traction systems is important for avoiding production delays and for the safety of personnel entering the mine. This study proposes a new magnetic aggregation bridge detection method utilizing a magnetic resistance sensor array, which addresses the shortcomings of present methods for testing the integrity of wire ropes used in coal mining operations. First, the structure and types of damage incurred by such ropes are analyzed. The detection principle of the proposed method and the optimization of magnetic induction strength regions are then described. The selection of three types of magnetic sensitivity detection elements are compared and analyzed. On this basis, the magnetic aggregation method for inspecting wire rope, based on magnetic resistance sensor array, is studied in detail, including the detection effect of including or omitting a magnetic aggregation device. Different structures and sizes of magnetic aggregation devices are examined for their performance effect, showing measures to improve the effect of magnetization detection and selection methods for the magnetic resistance sensor.A detection method using a magnetic resistance sensor array combination matched with the magnetic field focusing model was discussedin detail. Finally, the proposed method is verified experimentally. The results show that the prototype sensor based on the proposed method can clearly detect multiple types of damage to wire rope, achieving a maximum signal-to-noise ratio of 60 dB and a considerable detection effect, compared to the conventional magnetic flux leakage defect detection sensor.