Manoj Khandelwal

Correlating P-wave Velocity with the Physico-Mechanical Properties of Different Rocks

In mining and civil engineering projects, physico-mechanical properties of the rock affect both the project design and the construction operation. Determination of various physico-mechanical properties of rocks is expensive and time consuming, and sometimes it is very difficult to get cores to perform direct tests to evaluate the rock mass. The purpose of this work is to investigate the relationships between the different physico-mechanical properties of the various rock types with the P-wave velocity. Measurement of P-wave velocity is relatively cheap, non-destructive and easy to carry out. In this study, representative rock mass samples of igneous, sedimentary, and metamorphic rocks were collected from the different locations of India to obtain an empirical relation between P-wave velocity and uniaxial compressive strength, tensile strength, punch shear, density, slake durability index, Young’s modulus, Poisson’s ratio, impact strength index and Schmidt hammer rebound number. A very strong correlation was found between the P-wave velocity and different physico-mechanical properties of various rock types with very high coefficients of determination. To check the sensitivity of the empirical equations, Students t test was also performed, which confirmed the validity of the proposed correlations.

Prediction of Blast Induced Air Overpressure in Opencast Mine

Blasting is still considered to be the most economical technique for rock excavation and displacement either on the surface or underground. The explosive energy, which fractures the rockmass is not fully utilized and only 20-30% of the energy is utilized in actual breakage of the rockmass, and the rest of the energy is spread in the form of ground vibration, air blast, flying rock, back break, etc. Air blast is considered to be one of the most detrimental side effects due to generation of noise. A generalized equation has been proposed by many researchers but due to its site specific constants, it cannot be used in other geo-mining conditions. In the present paper, an attempt has been made to predict the air blast using a neural network (NN) by incorporating the maximum charge per delay and distance between blast face to monitoring point. To investigate the appropriateness of this approach, the predictions by a NN are also compared with generalized equation of air overpressure and conventional statistical relations. For prediction of air overpressure, the data set has been taken from two different limestone mines for training of the network while validation of the network has been done by Magnesite mine data set. The network is trained by 41 datasets with 50 epochs and tested by 15 dataset. The correlation co-efficient determined by a NN was 0.9574 while correlation co-efficient were 0.3811 and 0.5258 by generalized equation and statistical analysis respectively. The Mean Absolute Percentage Error (MAPE) for a NN was 2.7437, whereas MAPE for generalized equation and statistical analysis were 8.6957 and 6.9179 respectively.

Prediction of Backbreak in Open-Pit Blasting Operations Using the Machine Learning Method

Backbreak is an undesirable phenomenon in blasting operations. It can cause instability of mine walls, falling down of machinery, improper fragmentation, reduced efficiency of drilling, etc. The existence of various effective parameters and their unknown relationships are the main reasons for inaccuracy of the empirical models. Presently, the application of new approaches such as artificial intelligence is highly recommended. In this paper, an attempt has been made to predict backbreak in blasting operations of Soungun iron mine, Iran, incorporating rock properties and blast design parameters using the support vector machine (SVM) method. To investigate the suitability of this approach, the predictions by SVM have been compared with multivariate regression analysis (MVRA). The coefficient of determination (CoD) and the mean absolute error (MAE) were taken as performance measures. It was found that the CoD between measured and predicted backbreak was 0.987 and 0.89 by SVM and MVRA, respectively, whereas the MAE was 0.29 and 1.07 by SVM and MVRA, respectively.

Evaluation and prediction of blast-induced ground vibration using support vector machine

We present the application of Support Vector Machine (SVM) for the prediction of blast induced ground vibration by taking into consideration of maximum charge per delay and distance between blast face to monitoring point. To investigate the suitability of this approach, the predictions by SVM have been compared with conventional predictor equations. Blast vibration study was carried out at Magnesite mine of Pithoragarh, India. Total 170 blast vibrations data sets were recorded at different strate-gic and vulnerable locations in and around to mine. Out of 170 data sets, 150 were used for the training of the SVM network as well as to determine site constants of different conventional predictor equations, whereas, 20 new randomly selected data sets were used to compare the prediction capability of SVM network with conventional predictor equations. Results were compared based on Co-efficient of Determination (CoD) and Mean Absolute Error (MAE) between monitored and predicted values of Peak Particle Veloc-ity (PPV). It was found that SVM gives closer values of predicted PPV as compared to conventional predictor equations. The coef-ficient of determination between measured and predicted PPV by SVM was 0.955, whereas it was 0.262, 0.163, 0.337 and 0.232 by USBM, Langefors-Kihlstrom, Ambraseys-Hendron and Bureau of Indian Standard equations, respectively. The MAE for PPV was 11.13 by SVM, whereas it was 0.973, 1.088, 0.939 and 1.292 by USBM, Langefors-Kihlstrom, Ambraseys-Hendron and Bureau of Indian Standard equations respectively.

Application of soft computing to predict blast-induced ground vibration

In this study, an attempt has been made to evaluate and predict the blast-induced ground vibration by incorporating explosive charge per delay and distance from the blast face to the monitoring point using artificial neural network (ANN) technique. A three-layer feed-forward back-propagation neural network with 2-5-1 architecture was trained and tested using 130 experimental and monitored blast records from the surface coal mines of Singareni Collieries Company Limited, Kothagudem, Andhra Pradesh, India. Twenty new blast data sets were used for the validation and comparison of the peak particle velocity (PPV) by ANN and conventional vibration predictors. Results were compared based on coefficient of determination and mean absolute error between monitored and predicted values of PPV.

Feasibility of ANFIS model for prediction of ground vibrations resulting from quarry blasting

One of the most significant environmental issues of blasting operations is ground vibration, which can cause damage to the surrounding residents and structures. Hence, it is a major concern to predict and subsequently control the ground vibration due to blasting. This paper presents two artificial intelligence techniques, namely, adaptive neuro-fuzzy inference system (ANFIS) and artificial neural network for the prediction of ground vibration in quarry blasting site. For this purpose, blasting parameters as well as ground vibrations of 109 blasting operations were measured in ISB granite quarry, Johor, Malaysia. Moreover, an empirical equation was also proposed based on the measured data. Several AI-based models were trained and tested using the measured data to determine the optimum models. Each model involved two inputs (maximum charge per delay and distance from the blast-face) and one output (ground vibration). To control capacity performances of the predictive models, the values of root mean squared error (RMSE), value account for (VAF), and coefficient of determination (R2) were computed for each model. It was found that the ANFIS model can provide better performance capacity in predicting ground vibration in comparison with other predictive techniques. The values of 0.973, 0.987 and 97.345 for R2, RMSE and VAF, respectively, reveal that the ANFIS model is capable to predict ground vibration with high degree of accuracy.

Prediction of Drillability of Rocks with Strength Properties Using a Hybrid GA-ANN Technique

The purpose of this paper is to provide a proper, practical and convenient drilling rate index (DRI) prediction model based on rock material properties. In order to obtain this purpose, 47 DRI tests were used. In addition, the relevant strength properties i.e. uniaxial compressive strength and Brazilian tensile strength were also used and selected as input parameters to predict DRI. Examined simple regression analysis showed that the relationships between the DRI and predictors are statistically meaningful but not good enough for DRI estimation in practice. Moreover, multiple regression, artificial neural network (ANN) and hybrid genetic algorithm (GA)-ANN models were constructed to estimate DRI. Several performance indices i.e. coefficient of determination (R2), root mean square error and variance account for were used for evaluation of performance prediction the proposed methods. Based on these results and the use of simple ranking procedure, the best models were chosen. It was found that the hybrid GA-ANN technique can performed better in predicting DRI compared to other developed models. This is because of the fact that the proposed hybrid model can update the biases and weights of the network connection to train by ANN.

Blast-induced ground vibration prediction using support vector machine

Ground vibrations induced by blasting are one of the fundamental problems in the mining industry and may cause severe damage to structures and plants nearby. Therefore, a vibration control study plays an important role in the minimization of environmental effects of blasting in mines. In this paper, an attempt has been made to predict the peak particle velocity using support vector machine (SVM) by taking into consideration of maximum charge per delay and distance between blast face to monitoring point. To investigate the suitability of this approach, the predictions by SVM have been compared with conventional vibration predictor equations. Coefficient of determination (CoD) and mean absolute error were taken as a performance measure.

Evaluation of effect of blast design parameters on flyrock using artificial neural networks

Flyrock, the propelled rock fragments beyond a specific limit, can be considered as one of the most crucial and hazardous events in the open pit blasting operations. Involvement of various effective parameters has made the problem so complicated, and the available empirical methods are not proficient to predict the flyrock. To achieve more accurate results, employment of new approaches, such as artificial neural network (ANN) can be very helpful. In this paper, an attempt has been made to apply the ANN method to predict the flyrock in the blasting operations of Sungun copper mine, Iran. Number of ANN models was tried using various permutation and combinations, and it was observed that a model trained with back-propagation algorithm having 9-5-2-1 architecture is the best optimum. Flyrock were also computed from various available empirical models suggested by Lundborg. Statistical modeling has also been done to compare the prediction capability of ANN over other methods. Comparison of the results showed absolute superiority of the ANN modeling over the empirical as well as statistical models. Sensitivity analysis was also performed to identify the most influential inputs on the output results. It was observed that powder factor, hole diameter, stemming and charge per delay are the most effective parameters on the flyrock.

Prediction and analysis of blast parameters using artificial neural network

In this study an attempt is made to predict the ratio of muck pile profile before and after the blast, fly rock and total explosive used, based on simple field tests as well blast design parameters. Prediction is done by making three different artificial neural network (ANN) models. Comparative statistical analysis is made among these three networks to ensure their performance suitability. Models of ANN were based on Feed Forward Back Propagation network with training functions – Resilient Backpropagation, One Step Secant and Powell-Beale Restarts. Total numbers of datasets chosen were 92 among which 17 were chosen for testing and validation and the rest were used for the training of networks. Statistical analysis is also made for these datasets. Considering performance for all the outputs, the best results are predicted by Powell-Beale Restarts, with an average percentage error of 5.871% for the ratio of muck pile before and after the blast, 5.335% for fly rocks and 5.775% for total explosive used. These parameters are predicted by number of holes to be blasted, hole diameter, pattern (spacing (m) X burden (m)), total volume of rock in a blast, average depth and total drill depth.