Prediction Of Rock Fragmentation Research Articles

Optimization of an Artificial Neural Network Using Four Novel Metaheuristic Algorithms for the Prediction of Rock Fragmentation in Mine Blasting

Optimization of an Artificial Neural Network Using Four Novel Metaheuristic Algorithms for the Prediction of Rock Fragmentation in Mine Blasting

APPLICATION OF IMAGE DIGITAL PROCESSING TO EVALUATE ACCURACY IN PREDICTING ROCK FRAGMENTATION INDUCED BY BLASTING

Predicting rock fragmentation induced by blasting operation is important in order to evaluate the success of blasting operation. It is necessary to select a method that is in accordance with the characteristics of geological condition and rock mass so that it can quickly provide accurate information. This study aims to evaluate whether Kuz-Ram model is accurate enough in predicting fragmentation of andesite. The analysis was carried out statistically by comparing the andesite fragmentation based on theoretical calculation method by Kuz-Ram model to the fragmentation based on image analysis method by Split Desktop which represents the actual field condition. The data were obtained from 30 blasting operations on andesite. The analysis result shows that the fragmentation based on the theoretical calculation using Kuz-Ram model is not significantly different from the fragmentation based on Split Desktop. The maximum error of percent passing predicted by Kuz-Ram model is around 7% with an average error of 4.94%. Based on the result, calculation using Kuz-Ram theory can be performed to predict fragmentation of andesite.

Extension of reliability information of Z-numbers and fuzzy cognitive map: Development of causality-weighted rock engineering system to predict and risk assessment of blast-induced rock size distribution

Blasting operations in surface mines have the primary purpose of fragmenting the rock mass into a size that is optimal and economically viable for the mine. This ideal size has an impact on every step of the mining operation, from loading and hauling through crushing and grinding. To put it another way, the economics of the mine or facility as a whole are significantly impacted by having the ideal size distribution. This research offers a causality-based rock engineering system (RES) for risk assessment and prediction of rock fragmentation generated by blasting in surface mines. The fuzzy cognitive map was utilized in the proposed approach in order to weight the RES in accordance with the reliability information provided by the Z-number theory. This model of the RES that is weighted according to causality and based on reliability is abbreviated as causality-weighted rock engineering system based on reliability (CWRESR). The construction of the model makes use of a database that was obtained from the Sarcheshmeh copper mine. The findings indicated that the overall risk level of fragmentation was somewhere between high and very high, with a vulnerability index (VI) of 69.73 cm. As a result, controlled blasting operations are strongly advised as a means of lowering the amount of risk. In addition, the suggested model was able to predict rock fragmentation with a coefficient of determination (R2) of 0.9462 and 9646 for the training and testing phase, respectively, demonstrating that the CWRESR model is superior to other models in its ability to predict rock fragmentation.

Enhancing rock fragmentation assessment in mine blasting through machine learning algorithms: a practical approach

The optimization of blasting operations greatly benefits from the prediction of rock fragmentation. The main factors that affect fragmentation are rock mass characteristics, blast geometry, and explosive properties. This paper is a step towards the implementation of machine learning and deep learning algorithms for predicting the extent of fragmentation (in percentage) in open pit mining. While various parameters can affect rock fragmentation, this study considers ten among them (i.e., spacing, drill hole diameter, burden, average bench height, powder factor, number of holes, charge per delay, uniaxial compressive strength, specific drilling, and stemming) to train and test the models. However, due to a weak correlation with rock fragmentation, drill diameter, average bench height, compressive strength, stemming, and charge per delay are eliminated to reduce model complexity. A total of 219 data sets having five input features including the number of holes, spacing, burden, specific drilling, and powder factor are used to develop the models. Machine learning models (random forest regression, support vector regression, and XG boost), as well as a deep learning model (neural network regression), are applied to develop a practical way that can optimize the prediction of fragmentation. This study employs performance measures such as R-squared, RMSE, MSE, MAPE, and MAE. The optimization of the model revealed promising results, indicating that the architecture 5-64-32-16-1 exhibits strong performance. Specifically, the model achieved mean squared error (MSE) values of 41.32 and 28.59 on the training and test datasets, respectively. The R2 value for both training and test is 0.83. RFR is also performing well compared to SVR and XG boost with MSE values of 12.37 and 9.89 on training and testing data, respectively.in both sets, the R2 value is 94%. Based on permutation importance and shapely plot values, it is observed that the powder factor has the highest impact, while the burden has the lowest impact on fragmentation.

Performance evaluation of rock fragmentation prediction based on RF‐BOA, AdaBoost‐BOA, GBoost‐BOA, and ERT‐BOA hybrid models

AbstractRock fragmentation is an important indicator for assessing the quality of blasting operations. However, accurate prediction of rock fragmentation after blasting is challenging due to the complicated blasting parameters and rock properties. For this reason, optimized by the Bayesian optimization algorithm (BOA), four hybrid machine learning models, including random forest, adaptive boosting, gradient boosting, and extremely randomized trees, were developed in this study. A total of 102 data sets with seven input parameters (spacing‐to‐burden ratio, hole depth‐to‐burden ratio, burden‐to‐hole diameter ratio, stemming length‐to‐burden ratio, powder factor, in situ block size, and elastic modulus) and one output parameter (rock fragment mean size, X50) were adopted to train and validate the predictive models. The root mean square error (RMSE), the mean absolute error (MAE), and the coefficient of determination () were used as the evaluation metrics. The evaluation results demonstrated that the hybrid models showed superior performance than the standalone models. The hybrid model consisting of gradient boosting and BOA (GBoost‐BOA) achieved the best prediction results compared with the other hybrid models, with the highest R2 value of 0.96 and the smallest values of RMSE and MAE of 0.03 and 0.02, respectively. Furthermore, sensitivity analysis was carried out to study the effects of input variables on rock fragmentation. In situ block size (XB), elastic modulus (E), and stemming length‐to‐burden ratio (T/B) were set as the main influencing factors. The proposed hybrid model provided a reliable prediction result and thus could be considered an alternative approach for rock fragment prediction in mining engineering.

Prediction of rock fragmentation in a fiery seam of an open-pit coal mine in India

Spontaneous combustion of coal increases the temperature in adjoining overburden strata of coal seams and poses a challenge when loading blastholes. This condition, known as hot-hole blasting, is dangerous due to the increased possibility of premature explosions in loaded blastholes. Thus, it is crucial to load the blastholes with an appropriate amount of explosives within a short period to avoid premature detonation caused by high temperatures of blastholes. Additionally, it will help achieve the desired fragment size. This study tried to ascertain the most influencial variables of mean fragment size and their optimum values adopted for blasting in a fiery seam. Data on blast design, rock mass, and fragmentation of 100 blasts in fiery seams of a coal mine were collected and used to develop mean fragmentation prediction models using soft computational techniques. The coefficient of determination (R2), root mean square error (RMSE), mean absolute error (MAE), mean square error (MSE), variance account for (VAF) and coefficient of efficiency in percentage (CE) were calculated to validate the results. It indicates that the random forest algorithm (RFA) outperforms the artificial neural network (ANN), response surface method (RSM), and decision tree (DT). The values of R2, RMSE, MAE, MSE, VAF, and CE for RFA are 0.94, 0.034, 0.027, 0.001, 93.58, and 93.01, respectively. Multiple parametric sensitivity analyses (MPSAs) of the input variables showed that the Schmidt hammer rebound number and spacing-to-burden ratio are the most influencial variables for the blast fragment size. The analysis was finally used to define the best blast design variables to achieve optimum fragment size from blasting. The optimum factor values for RFA of S/B, ld/B and ls/ld are 1.03, 1.85 and 0.7, respectively.

Prediction of Rock Fragmentation in Bench Blasting Operations Based on Multi Parameters—A Case Study

Prediction of Rock Fragmentation in Bench Blasting Operations Based on Multi Parameters—A Case Study

Enhancing the Performance of LSSVM Model in Predicting Rock Fragmentation Size Via Optimization Algorithms

The prediction of rock fragmentation is critical to improve the efficiency and economy of blasting excavation. In this study, an attempt is made to predict the entire fragmentation size distribution using a least square support vector machine (LSSVM) model. In addition, three optimization algorithms—the bacterial foraging algorithm (BFO), artificial fish swarm algorithm (AFSA), and adaptive particle swarm optimization (APSO)–were used to determine the appropriate parameters of the LSSVM model. In the constructed LSSVM-BFO, LSSVM-AFSA and LSSVM-APSO models, the hole spacing, row spacing, change per delay and stemming were used as the input parameters, while the statistical rock fragmentation size was assigned as the output. The LSSVM model was also employed as a control group for comparing with the optimized models. The above-mentioned models were trained and tested based on a database comprising of 10 datasets collected from in-site testing of Altashi Water Control Project in China. The performance of the proposed models was compared by several statistical criteria. The viability and efficiency of the LSSVM-BFO model were confirmed with an R2 of 0.9960 and an RMSE of 1.8044, which were better than those of the LSSVM-AFSA, LSSVM-APSO and LSSVM. Last but not least, sensitivity analysis was also executed. The result of sensitivity analysis demonstrated when the size of rock fragmentation of prediction is less 80mm, the most effective parameter will be stemming; otherwise the most effective parameter will be hole spacing.

Reduction of Fragment Size from Mining to Mineral Processing: A Review

The worldwide mining industry consumes a vast amount of energy in reduction of fragment size from mining to mineral processing with an extremely low-energy efficiency, particularly in ore crushing and grinding. Regarding such a situation, this article describes the effects of rock fragmentation by blasting on the energy consumption, productivity, minerals’ recovery, operational costs in the whole size reduction chain from mining to mineral processing, and the sustainability of mining industry. The main factors that influence rock fragmentation are analysed such as explosive, initiator, rock, and energy distribution including blast design, and the models for predicting rock fragmentation are briefly introduced. In addition, two important issues—fines and ore blending—are shortly presented. Furthermore, the feasibility of achieving an optimum fragmentation (satisfied by a minimum cost from drilling-blasting to crushing-grinding, maximum ore recovery ratio, high productivity, and minimum negative impact on safety and environment) is analysed. The analysis indicates that this feasibility is high. Finally, the measures and challenges for achieving optimum fragmentation are discussed.HighlightsThe effects of rock fragmentation on the whole size reduction chain from mining to mineral processing are described.The main factors influencing rock fragmentation by blasting are analysed.Main models for predicting rock fragmentation are briefly introduced and commented on.The feasibility, measures, and challenges of achieving optimum fragmentation are analysed.

XG Boost Algorithm to Simultaneous Prediction of Rock Fragmentation and Induced Ground Vibration Using Unique Blast Data

The two most frequently heard terms in the mining industry are safety and production. These two terms put a lot of pressure on blasting engineers and crew to give more while consuming less. The key to achieving the optimum blasting results is sophisticated bench analysis, which must be combined with design blast parameters for good fragmentation and safe ground vibration. Thus, a unique solution for forecasting both optimum fragmentation and reduced ground vibration using rock mass joint angle and blast design parameters will aid the blasting operations in terms of cost savings. To arrive at a proper understanding and a solution, 152 blasts were carried out in various mines by adjusting blast design parameters concerning the measured joint angle. The XG Boost, K-Nearest Neighbor, and Random Forest algorithms were evaluated, and the XG Boost outputs were shown to be superior in terms of Mean Absolute Percentage Error (MAPE), Root Mean Squared Error (RMSE), and Co-efficient of determination (R2) values. Using XG Boost, the decision-tree-based ensemble Machine Learning algorithm that uses a gradient-boosting framework and a simultaneous formula was developed to predict both fragmentation and ground vibration using joint angle and the same set of parameters.

Predicting rock fragmentation based on drill monitoring: A case study from Malmberget mine, Sweden

Fragmentation analysis is an essential part of the optimization process in any mining operation. The costs of loading, hauling, and crushing the rock are strongly influenced by the size distribution of the blasted rock. Several direct and indirect methods are used to analyse or predict fragmentation, but none is entirely applicable to fragmentation assessment in sublevel caving mines, mainly because of the limitations imposed by the underground environment and the lack of all the required data to adequately describe the rock mass. Over the past few years, measurement while drilling (MWD) data has emerged as a potential tool to provide more information about the in-situ rock mass. This research investigated if MWD can be used to predict rock fragmentation in sublevel caving. The MWD data obtained from a sublevel caving mine in northern Sweden were used to find the relationship between rock fragmentation and the nature of the rock mass. The loading operation of the mine was filmed for more than 12 months to capture images of loaded load-haul-dump (LHD) buckets. The blasted material in those buckets was classified into four categories based on the median particle size (X50). The results showed a stronger correlation for fine and medium fragmented material with rock type (MWD data) than coarser material. The paper presents a model for prediction of fragmentation, which concludes that it is possible to use MWD data for fragmentation prediction.

Prediction of blasting mean fragment size using support vector regression combined with five optimization algorithms

The main purpose of blasting operation is to produce desired and optimum mean size rock fragments. Smaller or fine fragments cause the loss of ore during loading and transportation, whereas large or coarser fragments need to be further processed, which enhances production cost. Therefore, accurate prediction of rock fragmentation is crucial in blasting operations. Mean fragment size (MFS) is a crucial index that measures the goodness of blasting designs. Over the past decades, various models have been proposed to evaluate and predict blasting fragmentation. Among these models, artificial intelligence (AI)-based models are becoming more popular due to their outstanding prediction results for multi-influential factors. In this study, support vector regression (SVR) techniques are adopted as the basic prediction tools, and five types of optimization algorithms, i.e. grid search (GS), grey wolf optimization (GWO), particle swarm optimization (PSO), genetic algorithm (GA) and salp swarm algorithm (SSA), are implemented to improve the prediction performance and optimize the hyper-parameters. The prediction model involves 19 influential factors that constitute a comprehensive blasting MFS evaluation system based on AI techniques. Among all the models, the GWO-v-SVR-based model shows the best comprehensive performance in predicting MFS in blasting operation. Three types of mathematical indices, i.e. mean square error (MSE), coefficient of determination (R2) and variance accounted for (VAF), are utilized for evaluating the performance of different prediction models. The R2, MSE and VAF values for the training set are 0.8355, 0.00138 and 80.98, respectively, whereas 0.8353, 0.00348 and 82.41, respectively for the testing set. Finally, sensitivity analysis is performed to understand the influence of input parameters on MFS. It shows that the most sensitive factor in blasting MFS is the uniaxial compressive strength.

Effect of heat treatment on the emission rate of radon from red sandstone.

High temperature and pore structure are important factors affecting the emission rate of radon in rocks. This study mainly focused on the correlation between radon emission rate and temperature in red sandstone. The results showed that in the temperature range of 25-400 °C, as the temperature increased, the connectivity of the internal pores of the sample became better, resulting in a significantly increased radon emission rate. The radon emission rate at 400 °C was 2.86 times the original. To explain the changes that occurred in the internal structure of the samples, the porosity characteristics of the samples after heat treatment were studied by nuclear magnetic resonance (NMR). It was found that the pore structure was also an important factor affecting the rate of radon emission. The smaller pore size of the micropores (r < 0.1 μm) inhibited the emission of radon in the sandstone. These results helped in understanding the mechanism of radon emission rate and provide an important basis for predicting rock fragmentation and coal fire.

A new auto-tuning model for predicting the rock fragmentation: a cat swarm optimization algorithm

The main focus of the present work is to offer an auto-tuning model, called cat swarm optimization (CSO), to predict rock fragmentation. This population-based method has a stochastic formation involving exploration and exploitation phases. CSO is a robust and powerful meta-heuristic algorithm inspired by the behaviors of cats; it is composed of two search modes: seeking and tracing, which can be joined by mixture ratio parameter. CSO is applied to large-scale optimization problems like rock fragmentation to have good forecasting parameters in D80 formulas (D80 is a common descriptor that evaluates rock fragmentation). To evaluate the efficiency of the proposed CSO model, its obtained results were compared to those of the particle swarm optimization (PSO) algorithm. In the modeling, two forms of CSO and PSO models, including power and linear forms, were developed. The comparative results showed that CSO models outperformed the rival in terms of the task defined. The precision of the proposed models was computed using statistical evaluation criteria. Comparison results concluded that CSO-power model with the root mean square error (RMSE) of 0.847 was more computationally efficient with better predictive ability compared to CSO-linear, PSO-linear and PSO-power models with the RMSE of 1.314, 1.545 and 2.307, respectively. Furthermore, the sensitivity analysis revealed the effect of the stemming parameter upon D80 in comparison with other input parameters.

Experimental Study of the Mechanism of TBM Disk Cutter Penetration in Mixed-Faced Grounds under Confining Pressure

Abstract In this article, the effects of tunnel boring machine (TBM) disk cutter penetrations on rock fragmentation are experimentally investigated. In these tests, the tested sample is composed of Beishan granite and Chongqing sandstone. The effects of five sets of TBM disk cutter penetrations are investigated under confining pressure of 10 MPa, and 3-D forces acting on the rolling cutter and the forming rock chips are analyzed. It is found from the experimental results that in the mixed-faced ground, for granite, the boreability of the TBM disk cutter increases slowly with increasing penetration, while for sandstone, the boreability of the TBM disk cutter almost linearly decreases. At the same penetration, the average normal force and rolling force in granite are larger than those in sandstone, and cutter vibration becomes obvious when the disk cutter rolls through the interface of the composite rocks. Moreover, the optimizing penetration, which is equal to 2 mm in the mixed-faced ground composed of granite and sandstone under confining stress of 10 MPa, is provided to guide the TBM operation and to predict rock fragmentation in TBM tunneling.

A fresh view on particle swarm optimization to develop a precise model for predicting rock fragmentation

Purpose The purpose of this paper is to propose a gauge for the convergence of the deterministic particle swarm optimization (PSO) algorithm to obtain an optimum upper bound for PSO algorithm and also developing a precise equation for predicting the rock fragmentation, as important aims in surface mines. Design/methodology/approach In this study, a database including 80 sets of data was collected from 80 blasting events in Shur river dam region, in Iran. The values of maximum charge per delay (W), burden (B), spacing (S), stemming (ST), powder factor (PF), rock mass rating (RMR) and D80, as a standard for evaluating the fragmentation, were measured. To check the performance of the proposed PSO models, artificial neural network was also developed. Accuracy of the developed models was evaluated using several statistical evaluation criteria, such as variance account for, R-square (R2) and root mean square error. Findings Finding the upper bounds for the difference between the position and the best position of particles in PSO algorithm and also developing a precise equation for predicting the rock fragmentation, as important aims in surface mines. Originality/value For the first time, the convergence of the deterministic PSO is studied in this study without using the stagnation or the weak chaotic assumption. The authors also studied application of PSO inpredicting rock fragmentation.

Damage Model and Numerical Experiment of High-Voltage Electro Pulse Boring in Granite

High-voltage electro pulse boring (EPB) has the advantages of high rock-breaking efficiency and good wall quality, and is a new and efficient potential method of rock breaking. The EPB process is defined as random because it is affected by many factors. At present, there is no suitable physical and mathematical model to describe the process and results of rock breakage in EPB, and the conclusions reached regarding rock-breakage mechanisms are not uniform. In this study, a complete damage model of high voltage EPB in granite is established, which includes a shock wave model and a damage model of high voltage EPB in granite. The damage model is based on the Particle Flow Code two-dimensional program. Use of a damage model of EPB accommodates the complete process of high voltage EPB, from discharge to production of a shock wave, and so rock-breaking via electro pulse can be simulated and calculated. The time-varying waveforms of shock waves with different electrical parameters are simulated and calculated on the basis of the model. Different shock wave forms are loaded into the surface and internal rock in the damage geometric model of EPB granite. Then, the breakage process of the rock surface and internally, and the mechanism of rock breakage using EPB are analyzed. This study provides a scientific basis for the quantitative expression and prediction of rock fragmentation in EPB in order to improve the drilling efficiency and reduction of energy loss in the process of EPB.

Rock Fragmentation Prediction through a New Hybrid Model Based on Imperial Competitive Algorithm and Neural Network

Reliable estimation of rock fragmentation is an important issue in the blasting operations in order to predict quality of the production. Since rock fragmentation is affected by various parameters such as blast pattern and rock mass characteristics, it is very difficult to have an appreciate prediction of it. This paper describes a new hybrid imperialism competitive algorithm (ICA)-artificial neural network (ANN) in order to solve shortcomings of ANN itself for prediction of rock fragmentation. In fact, the influence of ICA on ANN results was studied in this research. By investigating the related studies, the most important parameters of ICA were identified and a series of parametric studies for their determination were conducted. All models were built using 8 inputs and one output which is rock fragmentation. To have a fair comparison and show the capability of the new hybrid model, a pre-developed ANN model was also considered and constructed. Evaluation of the obtained results demonstrated that a higher ability of rock fragmentation prediction is received developing a hybrid ICA-ANN model. Coefficient of determination (R2) values of (0.949 and 0.813) and (0.941 and 0.819) were obtained for training and testing of ICA-ANN and ANN models, respectively which indicated that the proposed ICA-ANN model can be implemented better in improving performance capacity of ANN model in estimating rock fragmentation.

Rock Fragmentation Prediction through a New Hybrid Model Based on Imperial Competitive Algorithm and Neural Network

Reliable estimation of rock fragmentation is an important issue in the blasting operations in order to predict quality of the production. Since rock fragmentation is affected by various parameters such as blast pattern and rock mass characteristics, it is very difficult to have an appreciate prediction of it. This paper describes a new hybrid imperialism competitive algorithm (ICA)-artificial neural network (ANN) in order to solve shortcomings of ANN itself for prediction of rock fragmentation. In fact, the influence of ICA on ANN results was studied in this research. By investigating the related studies, the most important parameters of ICA were identified and a series of parametric studies for their determination were conducted. All models were built using 8 inputs and one output which is rock fragmentation. To have a fair comparison and show the capability of the new hybrid model, a pre-developed ANN model was also considered and constructed. Evaluation of the obtained results demonstrated that a higher ability of rock fragmentation prediction is received developing a hybrid ICA-ANN model. Coefficient of determination (R2) values of (0.949 and 0.813) and (0.941 and 0.819) were obtained for training and testing of ICA-ANN and ANN models, respectively which indicated that the proposed ICA-ANN model can be implemented better in improving performance capacity of ANN model in estimating rock fragmentation.

Prediction of fragmentation due to blasting using mutual information and rock engineering system; case study: Meydook copper mine

One of the key outcomes of blasting in mines is found to be rock fragmentation which profoundly affects downstream expenses. In fact, size prediction of rock fragmentation is the first leap towards the optimization of blasting design parameters. This paper makes an attempt to present a model to predict rock fragmentation using Mutual Information (MI) in Meydook copper mine. Ten parameters are considered to influence fragmentation. On the other hand, Rock Engineering System (RES) is employed for sake of comparison between different methods. To validate the results, six blasting scenarios are selected out and compared with results of both models. The coefficients R2, RMSE and MAE were used in an attempt to assess the performance of presented models. The values of the coefficients R2, RMSE and MAE considering two methods of MI and RES for 30 blasting cycles are calculated as (0.81, 10.7, and 9.02) and (0.75, 11.87, and 9.61), respectively, implying the better capability of MI model to predict fragmentation.