Prediction and controlling of flyrock in blasting operation using artificial neural network

Flyrock is one of the most hazardous events in blasting operation of surface mines. There are several empirical methods to predict flyrock. Low performance of such models is due to complexity of flyrock analysis. Existence of various effective parameters and their unknown relationships are the main reasons for inaccuracy of the empirical models. Presently, application of new approaches such as artificial intelligence is highly recommended. In this paper, an attempt has been made to predict and control flyrock in blasting operation of Sangan iron mine, Iran incorporating rock properties and blast design parameters using artificial neural network (ANN) method. A three-layer feedforward back-propagation neural network having 13 hidden neurons with nine input parameters and one output parameter were trained using 192 experimental blast datasets. It was also observed that in ascending order, blastability index, charge per delay, hole diameter, stemming length, powder factor are the most effective parameters on the flyrock. Reducing charge per delay caused significant reduction in the flyrock from 165 to 25 m in the Sangan iron mine.     

Identification of hazardous waste landfill site: a case study from Zanjan province, Iran

The study of landfill sites is one of the most important studies in landfill engineering, and the landfill site selection involves combination of engineering, science, and politics. This paper describes a comprehensive hazardous waste landfill site selection methodology with the combined utilization of geographic information system and multiple criteria analysis methods, as applied to the Zanjan province in Iran. The six main data categories that were used are geological/engineering geological, geomorphological, hydrological/hydrogeological, climatological, pedological, and social/economical criteria, which included 31 input layers in total. A suitability map for hazardous waste landfilling was prepared for study area with five classes from most suitable to completely unsuitable. Finally, out of the three sites, one site was selected which was chosen by the local authorities. Our work offers a comprehensive methodology and provides essential support for decision-makers in the assessment of hazardous waste management problems in Zanjan province in I.R. Iran and other developing cities in other countries.     

Evaluating the efficacy of SVMs,BNs, ANNs and ANFIS in wave height prediction

Wave Height (WH) is one of the most important factors in design and operation of maritime projects. Different methods such as semi-empirical, numerical and soft computing-based approaches have been developed for WH forecasting. The soft computing-based methods have the ability to approximate nonlinear wind–wave and wave–wave interactions without a prior knowledge about them. In the present study, several soft computing-based models, namely Support Vector Machines (SVMs), Bayesian Networks (BNs), Artificial Neural Networks (ANNs) and Adaptive Neuro-Fuzzy Inference System (ANFIS) are used for mapping wind data to wave height. The data set used for training and testing the simulation models comprises the WH and wind data gathered by National Data Buoy Center (NDBC) in Lake Superior, USA. Several statistical indices are used to evaluate the efficacy of the aforementioned methods. The results show that the ANN, ANFIS and SVM can provide acceptable predictions for wave heights, while the BNs results are unreliable.     

Stochastic Modeling Approach for the Evaluation of Backbreak due to Blasting Operations in Open Pit Mines

Backbreak is an undesirable side effect of bench blasting operations in open pit mines. A large number of parameters affect backbreak, including controllable parameters (such as blast design parameters and explosive characteristics) and uncontrollable parameters (such as rock and discontinuities properties). The complexity of the backbreak phenomenon and the uncertainty in terms of the impact of various parameters makes its prediction very difficult. The aim of this paper is to determine the suitability of the stochastic modeling approach for the prediction of backbreak and to assess the influence of controllable parameters on the phenomenon. To achieve this, a database containing actual measured backbreak occurrences and the major effective controllable parameters on backbreak (i.e., burden, spacing, stemming length, powder factor, and geometric stiffness ratio) was created from 175 blasting events in the Sungun copper mine, Iran. From this database, first, a new site-specific empirical equation for predicting backbreak was developed using multiple regression analysis. Then, the backbreak phenomenon was simulated by the Monte Carlo (MC) method. The results reveal that stochastic modeling is a good means of modeling and evaluating the effects of the variability of blasting parameters on backbreak. Thus, the developed model is suitable for practical use in the Sungun copper mine. Finally, a sensitivity analysis showed that stemming length is the most important parameter in controlling backbreak.     

Prediction of the Rock Mass Diggability Index by Using Fuzzy Clustering-Based,ANN and Multiple Regression Methods

Rock mass classification systems are one of the most common ways of determining rock mass excavatability and related equipment assessment. However, the strength and weak points of such rating-based classifications have always been questionable. Such classification systems assign quantifiable values to predefined classified geotechnical parameters of rock mass. This causes particular ambiguities, leading to the misuse of such classifications in practical applications. Recently, intelligence system approaches such as artificial neural networks (ANNs) and neuro-fuzzy methods, along with multiple regression models, have been used successfully to overcome such uncertainties. The purpose of the present study is the construction of several models by using an adaptive neuro-fuzzy inference system (ANFIS) method with two data clustering approaches, including fuzzy c-means (FCM) clustering and subtractive clustering, an ANN and non-linear multiple regression to estimate the basic rock mass diggability index. A set of data from several case studies was used to obtain the real rock mass diggability index and compared to the predicted values by the constructed models. In conclusion, it was observed that ANFIS based on the FCM model shows higher accuracy and correlation with actual data compared to that of the ANN and multiple regression. As a result, one can use the assimilation of ANNs with fuzzy clustering-based models to construct such rigorous predictor tools.     

Probabilistic and sensitivity analyses of effective geotechnical parameters on rock slope stability: a case study of an urban area in northeast Iran

Despite the development of cities, risk assessment of rock slope stability in urban areas seems not to be growing at the same time. Mashhad is a developed city in northeast of Iran with a population of over 2.4 million. Given the closeness of the southern part of Mashhad to the Binaloud mountain ridge, the stability of the residential complexes that are being constructed in this area is a critical issue. Based on the fundamental roles of discontinuity properties and geo-mechanical parameters of rock mass, in this study we evaluated the most influential parameters of the rock slope stability and the failure probability of the slope near the Negin residential complex built on this ridge. According to the deterministic and probabilistic analyses, the north trench that was excavated for this residential complex could potentially cause plane failure. Moreover, the relationship between effective parameters on instability and their impact on safety factors were determined by sensitivity analysis. Therefore, slope dip, pore water pressure, and joint set dip were highly influential on the safety factor. There was also a nonlinear relationship between different parameters and safety in the studied area. This study presents an approach for risk assessment of rock slope stability in urban areas.     

Kinematic evolution of thrusts wedge and erratic line length balancing: insights from deformed sandbox models

Kinematic evolution of fold-thrust structures has been investigated by analogue models that include syntectonic sedimentation. Different decollement dips and basement thicknesses produced different wedge geometries and propagating characteristics. A model with one decollement level was characterized by a closely spaced thrust system during early stages of shortening as compared to the late stages. The frequency of fault nucleation was rapid during the early stages of deformation. Conversely, the frequency of fault nucleation was low and thrust spacing was significantly wider in a model with two decollement levels. Individual faults became locked at steep dips and deformation stepped forward as a new fault nucleated in-sequence in front of the older locked structure. Once the thrust system was established up to 27 % overall shortening, an overlying bed was introduced to simulate syntectonic deformation. Model sand wedge did not grow self similarly but rather its length and height increased episodically with deformation. Restoration of deformed models show that layer parallel shortening accommodated for approximately half of the total model shortening across the multilayers. Calculated error in apparent layer shortening from the restored layers revealed a direct relation with depth of the layers in the models. The experimental results are comparable to a natural example from the Northern Apennines fold-and-thrust belts.     

Accuracy of dynamic disk-based DDA with respect to a single sliding disk cluster

Disk clusters are developed to represent the shape of granular materials more precisely (compared to circular particles) and to minimise excessive rolling. Investigating the behaviour of dynamic disk-based discontinuous deformation analysis (DDA) with disk clusters is very important to evaluate the applicability of disk-based DDA to dynamic problems in geomechanics. In this paper, the accuracy of disk-based DDA under dynamic conditions is studied by a comprehensive sensitivity analysis. The results obtained by disk-based DDA are compared with the analytical solutions of a disk cluster on an incline subjected to gravitational force only, and three different accelerations of increasing complexity with sinusoidal input functions as well as gravitational load. In this research, the effects of time step size and interface friction angles on the results are studied. Overall, most of the error for both velocity and displacement occurs at the beginning of the solution. With increasing friction angle, the initial perturbation of the solution increases in the case of sliding under gravitational force only, and decreases in the case of sliding under dynamic loads. This study shows that disk-based DDA predicts accurately the velocities and displacements derived with respect to the frictional resistance offered by the inclines.     

Facies analysis and depositional environments of the OligoceneeMiocene Asmari Formation,Zagros Basin,Iran

The Asmari Formation(a giant hydrocarbon reservoir)is a thick carbonate sequence of the Oligocenee Miocene in the Zagros Basin,southwest of Iran.This formation is exposed at Tang-e-Lendeh in the Fars interior zone with a thickness of 190 m comprising medium and thick to massive bedded carbonates.The age of the Asmari Formation in the study area is the late Oligocene(Chattian)eearly Miocene(Burdigalian).Ten microfacies are defned,characterizing a gradual shallowing upward trend;the related environments are as follows:open marine(MF 8e10),restricted lagoon(MF 6e7),shoal(MF 3e5),lagoon(MF 2),and tidal fat(MF 1).Based on the environmental interpretations,a homoclinal ramp consisting of inner and middle parts prevails.MF 3e7 are characterized by the occurrence of large and small porcelaneous benthic foraminifera representing a shallow-water setting of an inner ramp,infuenced by wave and tidal processes.MF 8e10,with large particles of coral and algae,represent a deeper fair weather wave base of a middle ramp setting.