Gao, F, Kang, H & Liu, W 2026, 'An artificial-intelligence-enhanced approach for ground stability assessment 
using large-scale datasets of rockbolt load and roadway convergence', in D Cumming-Potvin & J Wesseloo (eds), Ground Support 2026: Proceedings of the 11th International Conference on Ground Support in Mining, Australian Centre for Geomechanics, Perth, pp. 1-7, https://doi.org/10.36487/ACG_repo/2625_21
(https://papers.acg.uwa.edu.au/p/2625_21_Gao/)
Abstract: Ground stability assessment is a fundamental requirement for maintaining the safety and functionality of underground openings such as coal mine roadways and tunnels. Conventional assessment methods often rely on sparse measurements and manual interpretation, which limit both accuracy and efficiency. To overcome these limitations, we propose a novel data-driven approach that integrates LiDAR-based 3D scanning with deep learning algorithms to automatically identify rockbolts, measure bolt loads, and measure roadway convergence with high precision. By combining these 2 extensive datasets, we establish a comprehensive framework for evaluating ground stability and detecting zones susceptible to instability or rockfall. The developed method enables continuous, automated monitoring and significantly improves the reliability of stability evaluation compared with traditional visual or point-based measurements.

Keywords: roadway, rockbolts, laser scanning, artificial intelligence