genetic algorithm

The large-scale open-pit mine production planning problem is an NP-hard issue. That is, it cannot be solved in a reasonable computational time. To solve this problem, various methods, including metaheuristic methods, have been proposed to reduce the computation time. One of these methods is the genetic algorithm (GA) which can provide near-optimal solutions to the problem in a shorter time. This paper aims to evaluate the efficiency of the GA technique based on the pit values and computational times compared with other methods of designing the ultimate pit limit (UPL). In other words, in addition to GA evaluation in UPL design, other proposed methods for UPL design are also compared. Determining the UPL of an open-pit mine is the first step in production planning. UPL solver selects blocks whose total economic value is maximum while meeting the slope constraints. In this regard, various methods have been proposed, which can be classified into three general categories: Operational Research (OR), heuristic, and metaheuristic. The GA, categorized as a metaheuristic method, Linear Programming (LP) model as an OR method, and Floating Cone (FC) algorithm as a heuristic method, have been employed to determine the UPL of open-pit mines. Since the LP method provides the exact answer, consider the basics. Then the results of GA were validated based on the results of LP and compared with the results of FC. This paper used the Marvin mine block model with characteristics of 53271 blocks and eight levels as a case study. Comparing the UPL value's three ways revealed that the LP model received the highest value by comparing the value obtained from GA and the FC algorithm's lowest value. However, the GA provided the results in a shorter time than LP, which is more critical in large-scale production planning problems. By performing the sensitivity analysis in the GA on the two parameters, crossover and mutation probability, the GA's UPL value was modified to 20940. Its UPL value is only 8% less than LP's UPL value.

Surface settlement induced by tunneling is one of the most crucial problems in urban environments. Hence, accurate prediction of soil geotechnical properties is an important prerequisite in the minimization of it. In this research work, the amount of surface settlement is predicted using three-dimensional numerical simulation in the finite difference method and Artificial Neural Network (ANN). In order to determine the real geotechnical properties of soil layers around the tunnel; back-analysis is carried out using the optimization algorithm and monitoring data. Among the different optimization methods, genetic algorithm (GA) and particle swarm optimization (PSO) are selected, and their performance is compared. The results obtained show that the artificial neural network has a high ability with the amounts of R=0.99, RMSE=0.0117, and MSE= 0.000138 in predicting the surface settlement obtained from 150 simulations from randomly generated data. Comparing the results of back-analysis using the optimization algorithm, the genetic algorithm shows less error than the particle swarm algorithm in different initial populations. In all cases of analysis, the calculation time for both algorithms lasts about 5 minutes, which indicates the applicability of both algorithms in optimizing the parameters in mechanized tunneling in a short time.

The surface settlement is an essential parameter in the operation of mechanized tunneling that should be determined before excavation. The surface settlement analysis caused by mechanized tunneling is a geo-technical problem characterized by various sources of uncertainty. Unlike the deterministic methods, the reliability analysis can take into account the uncertainties for the surface settlement assessment. In this work, the reliability analysis methods (second-order reliability method (SORM), Monte Carlo simulation (MCS), and first-order reliability method (FORM)) based on the genetic algorithm (GA) are utilized to build models for the reliability analysis of the surface settlement. Specifically, for large-scale projects, the limit state function (LSF) is non-linear and hard to apply based on the reliability methods. In order to resolve this problem, the GMDH (group method of data handling) neural network can estimate LSF without the need for additional assumptions about the function form. In this work, the GMDH neural network is adapted to obtain LSF. In the GMDH neural network, the tail void grouting pressure, groundwater level from tunnel invert, depth, average penetrate rate, distance from shaft, pitching angle, average face pressure, and percent tail void grout filling are used as the input parameters. At the same time, the surface settlement is the output parameter. The field data from the Bangkok subway is used in order to illustrate the capabilities of the proposed reliability methods.

Bedrock unconfined compressive strength (UCS) is a key parameter in designing thegeosciences and building related projects comprising both the underground and surface rock structures. Determination of rock UCS using standard laboratory tests is a complicated, expensive, and time-consuming process, which requires fresh core specimens. However, preparing fresh cores is not always possible, especially during the drilling operation in cracked, fractured, and weak rocks. Therefore, some attempts have recently been made to develop the indirect methods, i.e. intelligent predictive models for rock UCS estimation, which require no core preparation and laboratory equipment. This work focuses on the application of new combinations of intelligent techniques including adoptive neuro-fuzzy inference system (ANFIS), genetic algorithm (GA), and particle swarm optimization (PSO) in order to predict rock UCS. These models were constructed based on the collected laboratory datasets upon 93 core specimens ranging from weak to very strong rock types. The proposed hybrid model results were compared with each other, and the real data and multiple regression (MR) results. These comparisons were made using coefficient of correlation, mean of square error, mean of absolute error, and variance account for indices. The comparison results proved that the ANFIS-GA combination had a relatively higher accuracy than the ANFIS-PSO combination, and both had a higher capability than the MR model. Furthermore, the ANFIS-GA and ANFIS-PSO model results were completely in accordance with the UCS laboratory test, and they were more accurate than the previous single/hybrid intelligent models. Lastly, a parametric study of the suggested models showed that the density and Schmidt hammer rebound had the highest influence, and porosity had the lowest influence on the output (UCS).

Truck-Shovel fleet, as the most common transportation system in open-pit mines, has a significant part of mining costs, for which optimal management can lead to substantial cost reductions. Among the available dispatch mathematical models, the multi-stage approach is well suited for allocating trucks to respected shovels in a dynamic dispatching program. However, with this kind of modeling sequencing of the allocated trucks is not possible though it is important to find out the best solution so that getting the minimum accrued cost. To comply with the shortcoming of the traditional model, in this paper, a new hybrid model is developed and applied in Copper Mine of Iran, in which for each truck an allocation matrix is considered as input to the genetic algorithm implemented to determine the best solution. According to the obtained results, the optimal sequencing of the trucks can result in a significant (31%) cost reduction in a shift.

Predicting the wear performance of circular diamond saw in the process of sawing hard dimensional stone is an important step in reducing production costs in the stone sawing industry. In the present research work, the effective parameters on circular diamond saw wear are defined, and then the weight of each parameter is determined through adopting a fuzzy rock engineering system (Fuzzy RES) based on defining an accurate Gaussian pattern in fuzzy logic with analogous weighting. After this step, genetic algorithm (GA) is used to determine the levels of the four major variables and the amounts of the saw wear (output parameter) in the classification operation based on the fixed, dissimilar, and logarithmic spanning methods. Finally, a mathematical relationship is suggested for evaluation of the accuracy of the proposed models. The main contribution of our method is the novelty of combination of these methods in fuzzy RES. Before this work, all Fuzzy RESs only use simple membership functions and uniform spanning. Using GA for spanning and normal distribution as membership function based upon our latest work is the first work in fuzzy RES. To verify the selected proposed model, rock mechanics tests are conducted on nine hard stone samples, and the diamond saw wear is measured and compared with the proposed model. According to the results obtained, the proposed model exhibits acceptable capabilities in predicting the circular diamond saw wear.

The generalized effective-medium theory of induced polarization (GEMTIP) is a newly developed relaxation model that incorporates the petro-physical and structural characteristics of polarizable rocks in the grain/porous scale to model their complex resistivity/conductivity spectra. The inversion of the GEMTIP relaxation model parameter from spectral-induced polarization data is a challenging issue because of the highly non-linear dependency of the observed data on the model parameter and non-uniqueness of the problem. To solve these problems as well as scape the local minima of the highly complicated cost function, the genetic algorithm (GA) can be applied but it has proven to be time-intensive computationally. However, this drawback can be resolved by incorporating a faster algorithm, e.g. particle swarm optimization (PSO). The aim of this work is to investigate whether recovering the model parameter of the ellipsoidal GEMTIP model from SIP data using the combined GA and PSO algorithms is possible. To achieve this aim, we set the best calculated individuals using GA as the search space of PSO, and then the best location achieved by PSO in each iteration is assigned as the updated model parameters. The results of our research work reveal that the model parameters can effectively be recovered using the approach proposed in this paper but the time constant of a noisy data that arises from the adverse dependency of this parameter on the ellipticity of a polarizable grain. Moreover, the execution time of the ellipsoidal GEMTIP modeling of complex resistivity data can be significantly improved using the proposed algorithm.

Stochastic seismic inversion is a family of inversion algorithms in which the inverse solution was carried out using geostatistical simulation. In this work, a new 3D stochastic seismic inversion was developed in the MATLAB programming software. The proposed inversion algorithm is an iterative procedure that uses the principle of cross-over genetic algorithms as the global optimization technique.
The model perturbation towards the objective function is performed recurring to direct sequential simulation and co-simulation. This new algorithm was applied to a synthetic dataset with and without noise. The results obtained for the inverted impedance were satisfactory in both cases. In addition, a real dataset was chosen to be applied by the algorithm. Good results were achieved regarding the real dataset. For the purpose of validation, blind well tests were done for both the synthetic and real datasets. The results obtained showed that the algorithm was able to produce inverted impedance that fairly matched the well logs. Furthermore, an uncertainty analysis was performed for both the synthetic and real datasets. The results obtained indicate that the variance of acoustic impedance is increased in areas far from the well location.

In an Open-Pit Production Scheduling (OPPS) problem, the goal is to determine the mining sequence of an orebody as a block model. In this article, linear programing formulation is used to aim this goal. OPPS problem is known as an NP-hard problem, so an exact mathematical model cannot be applied to solve in the real state. Genetic Algorithm (GA) is a well-known member of evolutionary algorithms that widely are utilized to solve NP-hard problems. Herein, GA is implemented in a hypothetical Two-Dimensional (2D) copper orebody model. The orebody is featured as two-dimensional (2D) array of blocks. Likewise, counterpart 2D GA array was used to represent the OPPS problem’s solution space. Thereupon, the fitness function is defined according to the OPPS problem’s objective function to assess the solution domain. Also, new normalization method was used for the handling of block sequencing constraint. A numerical study is performed to compare the solutions of the exact and GA-based methods. It is shown that the gap between GA and the optimal solution by the exact method is less than % 5; hereupon GA is found to be efficiently in solving OPPS problem.

Like most limestone mines, which produce the raw materials required for cement companies, the transportation cost of the raw materials used in the Shahrood Cement Company is high. It has been tried to build the crushing and grinding plant close to the mine as much as possible. On the other hand, blasting has harmful effects, and the impacts of blast-induced damages on the sensitive machinery, equipment, and buildings are considerable. In such mines, among the blasting effects, blast-induced vibrations have a great deal of importance. This research work was conducted to analyze the blasting effects, and to propose a valid and reliable formula to predict the blast-induced vibration impacts in such regions, especially for the Shahrood Cement Company. Up to the present time, different indices have been introduced to quantify the blast vibration effects, among which peak particle velocity (PPV) has been widely considered by a majority of researchers. In order to establish a relationship between PPV and the blast site properties, different formulas have been proposed till now, and their frequently-used versions have been employed in the general form of , where W and D are the maximum charge per delay and the distance from the blast site, respectively, and , , and describe the site specifications. In this work, a series of tests and field measurements were carried out, and the required parameters were collected. Then in order to generalize the relationship between different limestone mines, and also to increase the prediction precision, the related data for similar limestone mines was gathered from the literature. In order to find the best equation fitting the real data, a simple regression model with genetic algorithm was used, and the best PPV predictor was achieved. At last, the results obtained for the best predictor model were compared with the real measured data by means of a correlation analysis.

In this study, a hybrid intelligent model has been designed to predict groundwater inflow to a mine pit during its advance. Novel hybrid method coupling artificial neural network (ANN) with genetic algorithm (GA) called ANN-GA, was utilised. Ratios of pit depth to aquifer thickness, pit bottom radius to its top radius, inverse of pit advance time and the hydraulic head (HH) in the observation wells to the distance of observation wells from the centre of pit were used as inputs to the network. An ANN-GA with 4-5-3-1 arrangement was found capable to predict the groundwater inflow to mine pit. The accuracy and reliability of model was verified by field data. Predicted results were very close to the field data. The correlation coefficient (R) value was 0.998 for training set, and in testing stage it was 0.99.