Search

This paper addresses the collection, analysis, and optimization of log data related to the truck haulage system in a mine. After selecting an underground mine in South Korea as the research area, the Mine Production Management System (MPMS) using Bluetooth beacons and tablet PCs was utilized to collect log data related to the haulage system over 18 months. Through the analysis of the collected log data, strategies to enhance the productivity and efficiency of the haulage system were derived. Weekly analysis of log data files was performed, identifying periods with abnormal truck cycle times and conducting an analysis of the underlying causes. It was revealed that the truck cycle time is influenced by the haulage system, equipment operation, and the log data collection system. To shorten truck cycle times and improve the productivity and efficiency of transportation systems, continuous collection and regular analysis of log data and dynamic system and equipment operation based on this are important. Analyzing log data collected over an extended period can help predict future trends in the haulage system and formulate measures and strategies in response. Therefore, it can serve as a valuable decision-making tool for establishing short-term, medium-term, and long-term production and operation plans. [ABSTRACT FROM AUTHOR]

This study focuses on addressing the complexity inherent in various amplitude components of blast-induced ground vibration (BIGV), encompassing vertical, radial, transversal, and the vectoral sum of PPVs of particle velocity. It takes into account their nonlinearity across diverse quarry environments, and aims to present an enhanced nonlinear intelligent system for accurate prediction of these components. Multiple artificial intelligence models were explored and developed for this purpose, including a support vector machine (SVM), an adaptive neural network based on the fuzzy inference system (ANFIS), and a novel hybrid model that combines earthworm optimisation (EO) and ANFIS (EO-ANFIS). The study also leverages the empirical model offered by the United States Bureau of Mines. The outcomes highlighted that the predictions of the three individual components prove to be more accurate compared to the vectoral sum of PPVs of particle velocity. However, the latter remains a valuable metric for evaluating the magnitude of BIGV in open-pit mines. Notably, the hybrid EO-ANFIS model emerges as the most accurate, achieving an impressive ~ 75% accuracy across 10 quarries characterised by distinct geological conditions. [ABSTRACT FROM AUTHOR]

This study proposes a novel approach for enhancing the productivity of mining haulage systems by developing a hybrid model that combines machine learning (ML) and discrete event simulation (DES) techniques to predict ore production. This study utilized time data collected from a limestone underground mine using tablet computers and Bluetooth beacons for 15 weeks. The collected data were used to train an ML model to predict truck cycle time, and the support vector regression with particle swarm optimization (PSO–SVM) model demonstrated the best performance. The PSO–SVM model accurately predicted cycle time with a mean absolute error (MAE) of 2.79 min, mean squared error (MSE) of 14.29 min2, root mean square error (RMSE) of 3.79 min, and coefficient of determination (R2) of 0.68. The output of the ML model was linked to the DES model to predict ore production for each truck, section, and time period. Verification of the DES model demonstrated its ability to accurately simulate the haulage system in the study area by comparing production logs with the simulation results. This study's novel approach offers a new method for predicting ore production and determining the optimal equipment combination for each workplace, thus enhancing productivity in mining haulage systems. [ABSTRACT FROM AUTHOR]