A new framework for evaluation of rock fragmentation in open pit mines

The main purpose of blasting in open pit mines is to produce the feed for crushing stage with the optimum dimensions from in situ rocks. The size distribution of muck pile indicates the efficiency of blasting pattern to reach the required optimum sizes. Nevertheless, there is no mature model to predict fragmentation distribution to date that can be used in various open pit mines. Therefore, a new framework to evaluate and predict fragmentation distribution is presented based on the image analysis approach. For this purpose, the data collected from Jajarm bauxite mine in Iran were used as the sources in this study. The image analysis process was performed by Split-Desktop software to find out fragmentation distribution, uniformity index and average size of the fragmented rocks. Then, two different approaches including the multivariate regression method and the decision-making trial and evaluation laboratory(DEMATEL) technique were incorporated to develop new models of the uniformity index and the average size to improve the Rosin-Rammler function. The performances of the proposed models were evaluated in four blasting operation sites. The results obtained indicate that the regression model possesses a better performance in prediction of the uniformity index and the average size and subsequently the fragmentation distribution in comparison with DEMATEL and conventional Rosin-Rammler models.

Evaluating performance of cutting machines during sawing dimension stones

The performance of cutting machines in terms of energy consumption and vibration directly affects the production costs. In this work, our aim was to evaluate the performance of cutting machines using hybrid intelligent models. For this purpose, a systematic experimental work was performed. A database of the carbonate and granite rocks was established, in which the physical and mechanical properties of these rocks (i.e., UCS, elastic modulus, Mohs hardness, and Schmiazek abrasivity factor) and the operational parameters (i.e., depth of cut and feed rate) were considered as the input parameters. The predictive models were developed incorporating a combination of the multi-layered perceptron artificial neural networks and genetic algorithm (GANN-BP) and the support vector regression method and Cuckoo optimization algorithm (COA-SVR). The results obtained indicated that the performance of the developed GANN-BP and COA-SVR models was close to each other and that these models had good agreements with the measured values. These results also showed that these proposed models were suitable tools in evaluating the performance of cutting machines.