Improvement of Small-Scale Dolomite Blasting Productivity: Comparison of Existing Empirical Models with Image Analysis Software and Artificial Neural Network Models

Abstract

Assessment of blast results is a significant approach for the improvement of mining operations. The different procedures for investigating rock fragmentation have their limitations, causing different variation prediction errors. Thus every technique is site-explicit, and applicable for a few explicit purposes. This work evaluates the existing empirical blast fragmentation model predictions in the case study of small-scale dolomite quarries. An attempt is made to compare the prediction accuracy of the modified Kuz-Ram model, Lawal 2021 model, and Kuznetsov-Cunningham-Ouchterlony (KCO) model with the WipFrag© analysis result and proposed artificial neural network (ANN) models. The prediction error analysis of the current models and that of the new proposed ANN models is evaluated using the three model assessment indices. The assessment indices uncover that the KCO model when compared to the modified Kuz-Ram model has the least error for most blast round percentage passing size predicted. However, the proposed artificial neural network models show high prediction exactness in predicting blast fragment mean size than the existing empirical models. Therefore, the proposed ANN models can be used to improve the productivity of small-scale dolomite blasting operation results for practical purposes.