Adaptive optimization of traffic flows in underground mine workings based on artificial intelligence methods

Abstract

This study focuses on the development and evaluation of methods for AI-based adaptive optimization of traffic flows in underground mine workings. Relevance of the topic is defined by the need to enhance the efficiency and safety of transport operations in the mining industry. The research applies an integrated approach that combines the methods of machine learning, simulation modeling and multi-criteria optimization. The observational database includes information on traffic flows at five mining operations for the period of 2020-2023. The results demonstrate that implementation of the adaptive artificial intelligence methods can reduce the average transportation time by 22%, increase the throughput of the mine workings by 18%, and reduce the energy costs by 14% as compared to the baseline scenario. The proposed solutions contribute to improvement of economic efficiency and environmental sustainability of mining enterprises. Further research can be aimed at expanding the functionality of intelligent transportation systems and their integration with the digital twins of mine workings.