Article Details

Abstract

With the increase of coal mining depth, gas outburst has become an important factor restricting coal mining. Counting gas drill rods in coal mines underground has important guiding significance for underground gas extraction. At present, the main used traditional manual counting method is more time-consuming and laborious. To solve the above problems, an intelligent identification method of underground gas drill rods based on YOLOv5 is proposed. This method fully extracts and aggregates the drill rod features through the object detection algorithm YOLOv5 and outputs the final detection results. The BOLT-1000 drill rod dataset is constructed by collecting drill rod data through multi-angle camera arrangement, and the experimental platform is built for training and verification. The experimental results show that the method has high accuracy and robustness on the self-made dataset, and can accurately identify the underground gas drill rods.

Keywords

Object Detection; gas extraction; drill rod identification; YOLOv5

References

1. [1] Sun Jiping, Chen Huisheng Smart Mining and 5G and Wi Fi 6 [J]. Industrial and Mining Automation, 2019, 45 (10): 1-4
2. [2] Kingdom Law, Wang Hong, Ren Huaiwei, etc Smart Coal Mine 2025 Scenario Goals and Development Path [J]. Journal of Coal Industry, 2018, 43 (2): 295-305
3. [3] Zhang Kexue, Lv Xinmiao, Zheng Qingxue, etc Research on Intelligent Mining Network Firewall Technology Based on eNSP [J]. China Coal, 2024, 50 (8): 94-103
4. [4] Ru Hongfang, Wang Keshuo, Wang Guoxin Improved YOLOv4 Network for Pedestrian Detection in Coal Mines [J]. Journal of Heilongjiang University of Science and Technology, 2022, 32 (4): 557-562
5. [5] Wang Xuan, Wu Jiaqi, Yang Kang, etc Method for detecting human posture underground in coal mines [J]. Industrial and Mining Automation, 2022, 48 (5): 79-84
6. [6] Hao Shuai, Zhang Xu, Ma Xu, etc Foreign object detection of coal mine conveyor belt based on CBAM-YOLOv5 [J]. Journal of Coal Industry, 2022, 47 (11): 4147-4156
7. [7] Zuo Mingcheng, Jiao Wenhua Safety helmet wearing recognition algorithm for underground coal mine operation scenarios [J]. Chinese Journal of Safety Science, 2024, 34 (3): 237-246
8. [8] Wang Maosen, Bao Jiusheng, Bao Zhouyang, etc PT object detection algorithm for coal mine underground inspection robot integrating pyramid structure and attention mechanism [J]. Coal Science and Technology, 2024, 52 (6): 206-215
9. [9] Liao Zhiwei, Gao Long, Cao Jun, etc Research on foreign object detection method for scraper conveyor based on deep learning [J]. China Coal, 2024, 50 (8): 165-170
10. [10] Zhao Wei, Wang Shuang, Zhao Dongyang Multi object detection of unmanned electric locomotives in coal mines based on SD-YOLOv5s-4L [J]. Industrial and Mining Automation, 2023, 49 (11): 121-128

About the authors

Jiang Bowen (1997-), male, Han ethnicity, from Hefei, Anhui, assistant engineer, master's student, research direction: coal mine big data and deep learning applications; Zhang Ruonan (1997-), male, Han ethnicity, from Huainan, Anhui, engineer, master's student, research direction: coal mine big data and deep learning applications; Xu Ping'an (1989-), male, Han ethnicity, from Huainan, Anhui Province, is a master's student, senior engineer, and master's student. His research direction is gas monitoring and control; Xie Yuqi (1997-), male, Han ethnicity, from Huainan, Anhui Province, assistant engineer, master's student, research direction: computer vision.