Edy Tonnizam Mohamad

Prediction of the unconfined compressive strength of soft rocks: a PSO-based ANN approach

Many studies have shown that artificial neural networks (ANNs) are useful for predicting the unconfined compressive strength (UCS) of rocks. However, ANNs do have some deficiencies: they can get trapped in local minima and they have a slow learning rate. It is widely accepted that optimization algorithms such as particle swarm optimization (PSO) can improve ANN performance. This study investigated the application of a hybrid PSO-based ANN model to the prediction of rock UCS. To prepare a dataset for the predictive model, extensive laboratory tests (i.e., 160 tests in total) were conducted on 40 soft rock sample sets (mostly shale) presenting various weathering grades that were obtained from different excavation sites in Johor, Malaysia. The laboratory tests included the UCS test and other basic rock index tests (the Brazilian tensile strength test, point load index test, and ultrasonic test). When developing the predictive model of UCS, the results of the basic rock tests as well as the bulk densities of the samples were used as input parameters, while the UCS was set as the output of the predictive model. The value account for (VAF), root mean squared error (RMSE), and adjusted R2 (coefficient of determination) were utilized to check the performances of the predictive models. The high performance indices of the proposed model highlight the superiority of the PSO-based ANN model for UCS prediction.

Estimation of air-overpressure produced by blasting operation through a neuro-genetic technique

Blasting operations usually produce significant environmental problems which may cause severe damage to the nearby areas. Air-overpressure (AOp) is one of the most important environmental impacts of blasting operations which needs to be predicted and subsequently controlled to minimize the potential risk of damage. In order to solve AOp problem in Hulu Langat granite quarry site, Malaysia, three non-linear methods namely empirical, artificial neural network (ANN) and a hybrid model of genetic algorithm (GA)–ANN were developed in this study. To do this, 76 blasting operations were investigated and relevant blasting parameters were measured in the site. The most influential parameters on AOp namely maximum charge per delay and the distance from the blast-face were considered as model inputs or predictors. Using the five randomly selected datasets and considering the modeling procedure of each method, 15 models were constructed for all predictive techniques. Several performance indices including coefficient of determination (R2), root mean square error and variance account for were utilized to check the performance capacity of the predictive methods. Considering these performance indices and using simple ranking method, the best models for AOp prediction were selected. It was found that the GA–ANN technique can provide higher performance capacity in predicting AOp compared to other predictive methods. This is due to the fact that the GA–ANN model can optimize the weights and biases of the network connection for training by ANN. In this study, GA–ANN is introduced as superior model for solving AOp problem in Hulu Langat site.

A combination of the ICA-ANN model to predict air-overpressure resulting from blasting

AbstractBlasting operations usually produce significant environmental problems which may cause severe damage to the nearby areas. Air-overpressure (AOp) is one of the most important environmental impacts of blasting operations which needs to be predicted and subsequently controlled to minimize the potential risk of damage. This paper presents three non-linear methods, namely empirical, artificial neural network (ANN), and imperialist competitive algorithm (ICA)-ANN to predict AOp induced by blasting operations in Shur river dam, Iran. ICA as a global search population-based algorithm can be used to optimize the weights and biases of the network connection for training by ANN. In this study, 70 blasting operations were investigated and relevant blasting parameters were measured. The most influential parameters on AOp, namely maximum charge per delay and the distance from the blast-face, were considered as input parameters or predictors. Using the five randomly selected datasets and considering the modeling procedure of each method, 15 models were constructed for all predictive techniques. Several performance indices including coefficient of determination (R2), root mean square error and value account for were utilized to check the performance capacity of the predictive methods. Considering these performance indices and using simple ranking method, the best models were selected among all constructed models. It was found that the ICA-ANN approach can provide higher performance capacity in predicting AOp compared to other predictive methods.

A Novel Approach for Blast-Induced Flyrock Prediction Based on Imperialist Competitive Algorithm and Artificial Neural Network

Flyrock is one of the major disturbances induced by blasting which may cause severe damage to nearby structures. This phenomenon has to be precisely predicted and subsequently controlled through the changing in the blast design to minimize potential risk of blasting. The scope of this study is to predict flyrock induced by blasting through a novel approach based on the combination of imperialist competitive algorithm (ICA) and artificial neural network (ANN). For this purpose, the parameters of 113 blasting operations were accurately recorded and flyrock distances were measured for each operation. By applying the sensitivity analysis, maximum charge per delay and powder factor were determined as the most influential parameters on flyrock. In the light of this analysis, two new empirical predictors were developed to predict flyrock distance. For a comparison purpose, a predeveloped backpropagation (BP) ANN was developed and the results were compared with those of the proposed ICA-ANN model and empirical predictors. The results clearly showed the superiority of the proposed ICA-ANN model in comparison with the proposed BP-ANN model and empirical approaches.

Blast-induced air and ground vibration prediction: a particle swarm optimization-based artificial neural network approach

Mines, quarries, and construction sites face environmental damages due to blasting environmental impacts such as ground vibration and air overpressure. These phenomena may cause damage to structures, groundwater, and ecology of the nearby area. Several empirical predictors have been proposed by various scholars to estimate ground vibration and air overpressure, but these methods are inapplicable in many conditions. However, prediction of ground vibration and air overpressure is complicated as a consequence of the fact that a large number of influential parameters are involved. In this study, a hybrid model of an artificial neural network and a particle swarm optimization algorithm was implemented to predict ground vibration and air overpressure induced by blasting. To develop this model, 88 datasets including the parameters with the greatest influence on ground vibration and air overpressure were collected from a granite quarry site in Malaysia. The results obtained by the proposed model were compared with the measured values as well as with the results of empirical predictors. The results indicate that the proposed model is an applicable and accurate tool to predict ground vibration and air overpressure induced by blasting.

Application of several non-linear prediction tools for estimating uniaxial compressive strength of granitic rocks and comparison of their performances

Uniaxial compressive strength (UCS) of rock is crucial for any type of projects constructed in/on rock mass. The test that is conducted to measure the UCS of rock is expensive, time consuming and having sample restriction. For this reason, the UCS of rock may be estimated using simple rock tests such as point load index (Is(50)), Schmidt hammer (Rn) and p-wave velocity (Vp) tests. To estimate the UCS of granitic rock as a function of relevant rock properties like Rn, p-wave and Is(50), the rock cores were collected from the face of the Pahang–Selangor fresh water tunnel in Malaysia. Afterwards, 124 samples are prepared and tested in accordance with relevant standards and the dataset is obtained. Further an established dataset is used for estimating the UCS of rock via three-nonlinear prediction tools, namely non-linear multiple regression (NLMR), artificial neural network (ANN) and adaptive neuro-fuzzy inference system (ANFIS). After conducting the mentioned models, considering several performance indices including coefficient of determination (R2), variance account for and root mean squared error and also using simple ranking procedure, the models were examined and the best prediction model was selected. It is concluded that the R2 equal to 0.951 for testing dataset suggests the superiority of the ANFIS model, while these values are 0.651 and 0.886 for NLMR and ANN techniques, respectively. The results pointed out that the ANFIS model can be used for predicting UCS of rocks with higher capacity in comparison with others. However, the developed model may be useful at a preliminary stage of design; it should be used with caution and only for the specified rock types.

Application of two intelligent systems in predicting environmental impacts of quarry blasting

Blasting, as the most frequently used method for hard rock fragmentation, is a hazardous aspect in mining industries. These operations produce several undesirable environmental impacts such as ground vibration, air-overpressure (AOp), and flyrock in the nearby environments. These environmental impacts may cause injury to human and damage to structures, groundwater, and ecology of the nearby area. This paper is aimed to predict the blasting environmental impacts in granite quarry sites through two intelligent systems, namely artificial neural network (ANN) and adaptive neuro-fuzzy inference system (ANFIS). For this purpose, 166 blasting operations at four granite quarry sites in Malaysia were investigated and the values of peak particle velocity (PPV), AOp, and flyrock were precisely recorded in each blasting operation. Considering some model performance indices including coefficient of determination (R2), value account for (VAF), and root mean square error (RMSE), and also using simple ranking procedure, the best models for prediction of PPV, AOp, and flyrock were selected. The results demonstrated that the ANFIS models yield higher performance capacity compared to ANN models. In the case of testing datasets, the R2 values of 0.939, 0.947, and 0.959 for prediction of PPV, AOp, and flyrock, respectively, suggest the superiority of the ANFIS technique, while in predicting PPV, AOp, and flyrock using ANN technique, these values are 0.771, 0.864, and 0.834, respectively.

Prediction of the strength and elasticity modulus of granite through an expert artificial neural network

The uniaxial compressive strength (UCS) and Young’s modulus (E) are important parameters in designing solutions to rock engineering problems. However, determination of these properties in the laboratory is expensive and time consuming. Therefore, many attempts have been made to estimate these properties indirectly by defining various correlations. These correlations often relate UCS and E to some basic rock index tests. Nevertheless, in this study, using an artificial neural network (ANN) enhanced with the imperialist competitive algorithm (ICA), a hybrid model is developed for predicting the UCS and E of granite samples. The samples used in this study were taken from the face of the Pahang–Selangor raw water transfer tunnel in Malaysia. To train the aforementioned model, the results of the laboratory tests, including porosity (n), P wave velocity (VP), point load strength index (Is(50)) and the Schmidt hammer rebound number (Rn), were used as model inputs. For the sake of comparison, the performance of the hybrid model was checked against a conventional ANN predictive model with similar architecture. Value account for (VAF), root mean square error (RMSE) and coefficient of determination (R2) were used to control the capacity performance of the predictive models. The performance indices obtained using the ICA-ANN approach show that the proposed model can predict UCS and E with a high degree of accuracy. The results of sensitivity analysis reveal that VP is the most influential parameter, compared to the other input parameters, on UCS and E.

Neuro-fuzzy technique to predict air-overpressure induced by blasting

In addition to all benefits of blasting in mining and civil engineering applications, blasting has some undesirable impacts on surrounding areas. Blast-induced air-overpressure (AOp) is one of the most important environmental impacts of blasting operation which may cause severe damage to nearby residents and structures. Hence, it is a major concern to predict and subsequently control the AOp due to blasting. This paper presents an adaptive neuro-fuzzy inference system (ANFIS) model for prediction of blast-induced AOp in quarry blasting sites. For this purpose, 128 blasting operations were monitored in three quarry sites, Malaysia. Several models were constructed to obtain the optimum model in which each model involved five inputs and one output. Values of maximum charge per delay, powder factor, burden to spacing ratio, stemming length, and distance between monitoring station and blast face were set as input parameters to predict AOp. For comparison purposes, considering the same data, AOp values were predicted through the pre-developed artificial neural network (ANN) model and multiple regression (MR) technique. The results demonstrated the superiority of the ANFIS model to predict AOp compared to other methods. Moreover, results of sensitivity analysis indicated that the maximum charge per delay and powder factor and distance from the blast face are the most influential parameters on AOp.

An optimized ANN model based on genetic algorithm for predicting ripping production

Due to the environmental constraints and the limitations on blasting, ripping as a ground loosening and breaking method has become more popular in both mining and civil engineering applications. As a result, a more applicable rippability model is required to predict ripping production (Q) before conducting such tests. In this research, a hybrid genetic algorithm (GA) optimized by artificial neural network (ANN) was developed to predict ripping production results obtained from three sites in Johor state, Malaysia. It should be noted that the mentioned hybrid model was first time applied in this field. In this regard, 74 ripping tests were investigated in the studied areas and the relevant parameters were also measured. A series of GA–ANN models were conducted in order to propose a hybrid model with a higher accuracy level. To demonstrate the performance capacity of the hybrid GA–ANN model, a pre-developed ANN model was also proposed and results of predictive models were compared using several performance indices. The results revealed higher accuracy of the proposed hybrid GA–ANN model in estimating Q compared to ANN technique. As an example, root-mean-square error values of 0.092 and 0.131 for testing datasets of GA–ANN and ANN techniques, respectively, express the superiority of the newly developed model in predicting ripping production.