A comparative study on the application of various artificial neural networks to simultaneous prediction of rock fragmentation and backbreak
- Authors: Sayadi, Ahmad , Monjezi, Masoud , Talebi, Nemat , Khandelwal, Manoj
- Date: 2013
- Type: Text , Journal article
- Relation: Journal of Rock Mechanics and Geotechnical Engineering Vol. 5, no. 4 (2013), p. 318-324
- Full Text:
- Reviewed:
- Description: In blasting operation, the aim is to achieve proper fragmentation and to avoid undesirable events such as backbreak. Therefore, predicting rock fragmentation and backbreak is very important to arrive at a technically and economically successful outcome. Since many parameters affect the blasting results in a complicated mechanism, employment of robust methods such as artificial neural network may be very useful. In this regard, this paper attends to simultaneous prediction of rock fragmentation and backbreak in the blasting operation of Tehran Cement Company limestone mines in Iran. Back propagation neural network (BPNN) and radial basis function neural network (RBFNN) are adopted for the simulation. Also, regression analysis is performed between independent and dependent variables. For the BPNN modeling, a network with architecture 6-10-2 is found to be optimum whereas for the RBFNN, architecture 6-36-2 with spread factor of 0.79 provides maximum prediction aptitude. Performance comparison of the developed models is fulfilled using value account for (VAF), root mean square error (RMSE), determination coefficient (R2) and maximum relative error (MRE). As such, it is observed that the BPNN model is the most preferable model providing maximum accuracy and minimum error. Also, sensitivity analysis shows that inputs burden and stemming are the most effective parameters on the outputs fragmentation and backbreak, respectively. On the other hand, for both of the outputs, specific charge is the least effective parameter. © 2013 Institute of Rock and Soil Mechanics, Chinese Academy of Sciences.
Optimization of blasting design in open pit limestone mines with the aim of reducing ground vibration using robust techniques
- Authors: Rezaeineshat, Afsaneh , Monjezi, Masoud , Mehrdanesh, Amirhossein , Khandelwal, Manoj
- Date: 2020
- Type: Text , Journal article
- Relation: Geomechanics and Geophysics for Geo-Energy and Geo-Resources Vol. 6, no. 2 (2020), p.
- Full Text:
- Reviewed:
- Description: Blasting operations create significant problems to residential and other structures located in the close proximity of the mines. Blast vibration is one of the most crucial nuisances of blasting, which should be accurately estimated to minimize its effect. In this paper, an attempt has been made to apply various models to predict ground vibrations due to mine blasting. To fulfill this aim, 112 blast operations were precisely measured and collected in one the limestone mines of Iran. These blast operation data were utilized to construct the artificial neural network (ANN) model to predict the peak particle velocity (PPV). The input parameters used in this study were burden, spacing, maximum charge per delay, distance from blast face to monitoring point and rock quality designation and output parameter was the PPV. The conventional empirical predictors and multivariate regression analysis were also performed on the same data sets to study the PPV. Accordingly, it was observed that the ANN model is more accurate as compared to the other employed predictors. Moreover, it was also revealed that the most influential parameters on the ground vibration are distance from the blast and maximum charge per delay, whereas the least effective parameters are burden, spacing and rock quality designation. Finally, in order to minimize PPV, the developed ANN model was used as an objective function for imperialist competitive algorithm (ICA). Eventually, it was found that the ICA algorithm is able to decrease PPV up to 59% by considering burden of 2.9 m, spacing of 4.4 m and charge per delay of 627 Kg. © 2020, Springer Nature Switzerland AG.
Performance of hybrid SCA-RF and HHO-RF models for predicting backbreak in open-pit mine blasting operations
- Authors: Zhou, Jian , Dai, Yong , Khandelwal, Manoj , Monjezi, Masoud , Yu, Zhi , Qiu, Yingui
- Date: 2021
- Type: Text , Journal article
- Relation: Natural Resources Research Vol. 30, no. 6 (2021), p. 4753-4771
- Full Text:
- Reviewed:
- Description: Backbreak is an adverse phenomenon in blasting operation, which can cause, among others, mine walls instability, falling down of machinery, drilling efficiency reduction and stripping ratio enhancement. Therefore, this research aimed to develop two-hybrid RF (Random Forest) prediction models of random forest, which are optimized by Harris hawks optimizer (HHO) and sine cosine algorithm (SCA), for estimation of the backbreak distance. The HHO and SCA algorithms were adopted to determine two hyper-parameters (mtry and ntree) in the RF models, in which root mean square error (RMSE) was utilized as a fitness function. A database with 234 samples was established, in which six variables [i.e., hole length (L), burden (B), spacing (S), stemming (T), special drilling (SD) and powder factor (PF)] were used as input variables, and backbreak was defined as output variable. Additionally, three classical regression models (i.e., extreme learning machine, radial basis function network and general regression neural network) were adopted to verify the superiority of the hybrid RF prediction models. The predictive reliability of the proposed models was assessed by the combination of mean absolute error (MAE), RMSE, variance accounted for (VAF) and Pearson correlation coefficient (R2). The results revealed that the SCA-RF model outperformed all the other prediction models with MAE of (0.0444 and 0.0470), RMSE of (0.0816 and 0.0996), VAF of (96.82 and 95.88) and R2 of (0.9876 and 0.9829) in training and testing stages, respectively. A Gini index generated internally in the RF model showed that backbreak was significantly more sensitive to L and T than to SD. © 2021, International Association for Mathematical Geosciences.
Six novel hybrid extreme learning machine–swarm intelligence optimization (ELM–SIO) models for predicting backbreak in open-pit blasting
- Authors: Li, Chuanqi , Zhou, Jian , Khandelwal, Manoj , Zhang, Xiliang , Monjezi, Masoud , Qiu, Yingui
- Date: 2022
- Type: Text , Journal article
- Relation: Natural Resources Research Vol. 31, no. 5 (2022), p. 3017-3039
- Full Text:
- Reviewed:
- Description: Backbreak (BB) is one of the serious adverse blasting consequences in open-pit mines, because it frequently reduces economic benefits and seriously affects the safety of mines. Therefore, rapid and accurate prediction of BB is of great significance to mine blasting design and other production activities. For this purpose, six different swarm intelligence optimization (SIO) algorithms were proposed to optimize the extreme learning machine (ELM) model for BB prediction, i.e., ELM-based particle swarm optimization (ELM–PSO), ELM-based fruit fly optimization (ELM–FOA), ELM-based whale optimization algorithm (ELM–WOA), ELM-based lion swarm optimization (ELM–LOA), ELM-based seagull optimization algorithm (ELM–SOA) and ELM-based sparrow search algorithm (ELM–SSA). In total, 234 data records from blasting operations in the Sungun mine in Iran were used in this study, including six input parameters (special drilling, spacing, burden, hole length, stemming, powder factor) and one output parameter (i.e., BB). To evaluate the predictive performance of the different optimization models and initial models, six performance indicators including the root mean square error (RMSE), Pearson correlation coefficient (R), determination coefficient (R2), variance accounted for (VAF), mean absolute error (MAE) and sum of square error (SSE) were used to evaluate the models in the training and testing phases. The results show that the ELM–LSO was the best model to predict BB with RMSE of 0.1129 (R: 0.9991, R2: 0.9981, VAF: 99.8135%, MAE: 0.0706 and SSE: 2.0917) in the training phase and 0.2441 in the testing phase (R: 0.9949, R2: 0.9891, VAF: 98.9806%, MAE: 0.1669 and SSE: 4.1710). Hence, ELM techniques combined with SIO algorithms are an effective method to predict BB. © 2022, The Author(s).
Hybridizing five neural-metaheuristic paradigms to predict the pillar stress in bord and pillar method
- Authors: Zhou, Jian , Chen, Yuxin , Chen, Hui , Khandelwal, Manoj , Monjezi, Masoud , Peng, Kang
- Date: 2023
- Type: Text , Journal article
- Relation: Frontiers in Public Health Vol. 11, no. (2023), p.
- Full Text:
- Reviewed:
- Description: Pillar stability is an important condition for safe work in room-and-pillar mines. The instability of pillars will lead to large-scale collapse hazards, and the accurate estimation of induced stresses at different positions in the pillar is helpful for pillar design and guaranteeing pillar stability. There are many modeling methods to design pillars and evaluate their stability, including empirical and numerical method. However, empirical methods are difficult to be applied to places other than the original environmental characteristics, and numerical methods often simplify the boundary conditions and material properties, which cannot guarantee the stability of the design. Currently, machine learning (ML) algorithms have been successfully applied to pillar stability assessment with higher accuracy. Thus, the study adopted a back-propagation neural network (BPNN) and five elements including the sparrow search algorithm (SSA), gray wolf optimizer (GWO), butterfly optimization algorithm (BOA), tunicate swarm algorithm (TSA), and multi-verse optimizer (MVO). Combining metaheuristic algorithms, five hybrid models were developed to predict the induced stress within the pillar. The weight and threshold of the BPNN model are optimized by metaheuristic algorithms, in which the mean absolute error (MAE) is utilized as the fitness function. A database containing 149 data samples was established, where the input variables were the angle of goafline (A), depth of the working coal seam (H), specific gravity (G), distance of the point from the center of the pillar (C), and distance of the point from goafline (D), and the output variable was the induced stress. Furthermore, the predictive performance of the proposed model is evaluated by five metrics, namely coefficient of determination (R2), root mean squared error (RMSE), variance accounted for (VAF), mean absolute error (MAE), and mean absolute percentage error (MAPE). The results showed that the five hybrid models developed have good prediction performance, especially the GWO-BPNN model performed the best (Training set: R2 = 0.9991, RMSE = 0.1535, VAF = 99.91, MAE = 0.0884, MAPE = 0.6107; Test set: R2 = 0.9983, RMSE = 0.1783, VAF = 99.83, MAE = 0.1230, MAPE = 0.9253). Copyright © 2023 Zhou, Chen, Chen, Khandelwal, Monjezi and Peng.
Application of various robust techniques to study and evaluate the role of effective parameters on rock fragmentation
- Authors: Mehrdanesh, Amirhossein , Monjezi, Masoud , Khandelwal, Manoj , Bayat, Parichehr
- Date: 2023
- Type: Text , Journal article
- Relation: Engineering with Computers Vol. 39, no. 2 (2023), p. 1317-1327
- Full Text:
- Reviewed:
- Description: In this paper, an attempt has been made to implement various robust techniques to predict rock fragmentation due to blasting in open pit mines using effective parameters. As rock fragmentation prediction is very complex and complicated, and due to that various artificial intelligence-based techniques, such as artificial neural network (ANN), classification and regression tree and support vector machines were selected for the modeling. To validate and compare the prediction results, conventional multivariate regression analysis was also utilized on the same data sets. Since accuracy and generality of the modeling is dependent on the number of inputs, it was tried to collect enough required information from four different open pit mines of Iran. According to the obtained results, it was revealed that ANN with a determination coefficient of 0.986 is the most precise method of modeling as compared to the other applied techniques. Also, based on the performed sensitivity analysis, it was observed that the most prevailing parameters on the rock fragmentation are rock quality designation, Schmidt hardness value, mean in-situ block size and the minimum effective ones are hole diameter, burden and spacing. The advantage of back propagation neural network technique for using in this study compared to other soft computing methods is that they are able to describe complex and nonlinear multivariable problems in a transparent way. Furthermore, ANN can be used as a first approach, where much knowledge about the influencing parameters are missing. © 2021, The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature.