Danqi Li

This study investigates the performance of a cable bolt system under direct shearing to simulate relative rock strata under horizontal or so called “sliding”, with the primary goal of assisting in the optimisation of cable bolting practice to control roof failure in underground excavations. The multi axis substructure testing (MAST) facility was employed to develop a novel large-scale testing system. A widely used locally sourced cable bolt was selected with various testing conditions concerning the absence or presence of anchorage, grouting and cable bolt pre-tensioning, including lateral restraint to the embedment. The study shows that pre-tensioning can enhance early-stage stiffness, particularly when a lateral restraint is applied to the embedment, but its effect diminishes at larger displacements due to grout fracturing, cable bolt sandwiching, cable bolt yielding and the cracking of the reinforced concrete embedment. Grouting was essential for proper load transfer and to eliminate excessive sliding, which has been seen in the un-grouted case, where with grouted systems, failure was predominantly associated with the joint interface cracks than any bond related failures. End anchorage had limited influence, where both anchored and un-anchored systems converged in stiffness at initial cracking, although, at larger displacements, un-anchored systems seemed to be more prone to the effects of slippage. Lateral restraint mitigated cantilever-action induced rotation and un-desired localised embedment interaction, although its impact on overall stiffness was mixed. These results highlight the combined effects of pre-tensioning, grout, anchorage and lateral restraint on system behaviour, and in overall, the study establishes the versatility of the MAST facility in accommodating shear testing of cable bolt systems.

This paper proposes an innovative approach that combines a QMIX algorithm (a multi-agent deep reinforcement learning algorithm, MADRL) with a Gaussian Mixture Model (GMM) algorithm for optimizing intelligent path planning and scheduling of mining trucks in open-pit mining environments. The focus of this method is twofold. Firstly, it achieves collaborative cooperation among multiple mining trucks using the QMIX algorithm. Secondly, it integrates the GMM algorithm with QMIX for modeling, predicting, classifying and analyzing existing vehicle outcomes, to enhance the navigation capabilities of mining trucks within the environment. Through simulation experiments, the effectiveness of this combined algorithm was validated in improving vehicle operational efficiency, reducing non-working waiting time, and enhancing transportation efficiency. Moreover, this research compares the results of the algorithm with single-agent deep reinforcement learning algorithms, demonstrating the advantages of multi-agent algorithms in environments characterized with multi-agent collaboration. The QMIX-GMM mixed framework outperformed traditional approaches as complexity increased in the mining environments. The study provides new technological insights for intelligent planning of mining trucks and offers significant reference value for the automation of multi-agent collaboration in other environments. The limitation has been with regard to the maximum fleet size considered in the study being suitable to small or mid-scale mines.