imperialistic competition algorithm

Optimization of haulage system in open pit mines is very important due to its high operating costs. Till now a large no. of researches have been conducted to optimize the truck fleet size in an open pit mine in dispatching and non-dispatching modes. These researches have gained many achievements in this regard and still they are going to continue. On the other hand, nowadays, application of artificial intelligence is spreading vastly to optimize systems in the field of (mining) engineering, especially in np-hard problems. One of the new meta-heuristic algorithms in engineering field is Imperialistic Competition (IC), which is developed primarily for electrical systems. Recently, it has found its application in the field of mining systems as well. In this paper, application of IC algorithm for optimization of haulage system in open pit mines is introduced. Implementation of the IC algorithm for Songon Copper mine was validated with comparison of its results with those of Genetic algorithm. Comparison showed promising results. Optimization of the system with IC algorithm improves the mine production from 32 thousand tons as the current situation to 37 thousand tons, while optimization of the system with Genetic algorithm improves the mine production to 35 thousand tones.

In determining the optimal points of production drilling, it is important to identify areas of suitable reservoir quality. For this purpose, the use of geochemical data, which is usually small in number, is common. This data discontinuity creates information gaps. If one uses more continuous data so that its modeling accuracy is suitable, the drilling could be then performed with more success. In this study, seismic and well logs data were used to classify the quality of gas facies by two non-parametric statistical (Parzen) and supervised deep learning techniques (long-term short-term memory network (LSTM)). The LSTM network was then also optimized by two heuristic optimization methods (Imperialistic competition algorithm and Whale algorithm). The obtained results indicate that both methods produce good results in classification so that the modeling accuracy of gas facies quality using supervised deep learning technique (87%) is more than that of the non-parametric Parzen (83%) method. Moreover, the application of optimization algorithms has increased the classification accuracy. The best accuracy is related to the LSTM network optimized with the imperialistic competition algorithm (90%). Geochemical reports and well cores data show the high validity of these models.