imperialist competitive algorithm

In this research work, a comprehensive study is conducted to predict flyrock as a typical and undesirable phenomenon occurring during the blasting operation in open-pit mining. Despite the availability of several empirical methods for predicting the flyrock distance, the complexity of flyrock analysis has resulted in the low performance of these models. Therefore, the statistical and robust artificial intelligence techniques are applied for flyrock prediction in the Sungun copper mine in Iran. For this purpose, the linear multivariate regression (LMR), imperialist competitive algorithm (ICA), adaptive neuro-fuzzy inference system (ANFIS), and artificial neural network (ANN) methods are applied to predict flyrock with effective parameters including the blasthole diameter, stemming, burden, powder factor, and maximum charge per delay. According to the attained results, the ANN model with the structure of 5-8-1, Levenberg-Marquardt as the learning algorithm, and log-sigmoid (logsig) as the transfer functions are selected as the optimal network with the RMSE and R2 values of 5.04 m and 95.6% to predict flyrock, respectively. Also it can be concluded that the ICA technique has a relatively high capability in predicting flyrock, with the LMR and ANFIS models placed in the next. Finally, the sensitivity analysis reveal that the powder factor and blasthole diameters have the most importance on the flyrock distance in the present work.

Twenty measured blast data from the Golegohar iron mine (southern Iran) were used to generalize nonlinear models for the estimation of dominant frequencies of blast waves using rock mass, explosive characteristics, and blast design. The imperialist Competitive Algorithm (ICA) was used to determine the nonlinear regression model coefficients. Possessing a good correlation coefficient, the proposed model can be directly used for predicting blast-induced dominant frequencies of waves. The determination coefficient (R2</sup>) found by the ACI-based nonlinear model was 0.98 for frequency, while that of the traditional Multivariate Linear Regression Model (MVLRM) was 0.89. Also, according to the calculation of other well-known statistical errors between the estimated and real measured values of frequency, ICA-based models have higher Variance Account for (VAF) value, as well as lower values of Route Mean Square Error (RMSE), Variance Absolute Relative Error (VARE), Median Absolute Error (MEDAE), and Mean absolute percentage error (MAPE)compared to the linear model. It was found that the proposed nonlinear model is more accurate and capable of estimating the values of the dominant frequency of blast waves.

In this work, we tried to automatically optimize the cost of the concrete segmental lining used as a support system in the case study of Mashhad Urban Railway Line 2 located in NE Iran. Two meta-heuristic optimization methods including particle swarm optimization (PSO) and imperialist competitive algorithm (ICA) were presented. The penalty function was used for unfeasible solutions, and the segmental lining structure was defined by nine design variables: the geometrical parameters of the lining cross-section, the reinforced feature parameters, and the dowel feature parameters used among the joints to connect the segment pieces. Furthermore, the design constrains were implemented in accordance with the American Concrete Institute code (ACI318M-08) and guidelines of lining design proposed by the International Tunnel Association (ITA). The objective function consisted of the total cost of structure preparation and implementation. Consequently, the optimum design of the system was analyzed using the PSO and ICA algorithms. The results obtained showed that the objective function of the support system by the PSO and ICA algorithms reduced 12.6% and 14% per meter, respectively.