Evaluating Iron Ore Characteristics through Machine Learning and 2D LiDAR Technology

Conveyor belts are the most effective way to transport ore in a mining complex. The ore that comes from the mining areas can be heterogeneous in size and type. As the ore needs to pass through several processing steps, online information about the ore’s type and degree of fragmentation can help improve mineral processing for both safety and efficiency. Current instrumentation systems are expensive and require frequent calibration and maintenance. This paper presents a novel intelligent instrument for online recognition of type and degree of fragmentation. A 2D LiDAR sensor and machine learning techniques were used to estimate the characteristics of iron ore particles on conveyor belts. An experiment was conducted using several types of ore and granulometry. Five machine learning models were compared using statistical methods, including analysis of average accuracy and normality and hypotheses tests. Among them, the Random Forest models achieved the highest average accuracy, 93.81% for ore type and 85.52% for the degree of fragmentation. These models were improved by a voting mechanism, resulting in a reduction of classification errors of 93.3% for ore type and 99.2% for the degree of fragmentation. These findings demonstrate potential for improving mineral processing controls and elevating operational safety within the mining sector.