Artificial Neural Network as a Tool for Backbreak Prediction

Backbreak is one of the destructive side effects of the blasting operation. Reducing of this event is very important for economic of a mining project. Involvement of various parameters has made the backbreak analyzing difficult. Currently there is no any specific method to predict or control the phenomenon considering all the effective parameters. In this paper, artificial neural network (ANN) as a powerful tool for solving such complicated problems is used to predict backbreak in blasting operation of the Sangan iron mine, Iran. Network training was fulfilled using a collected database of the practiced operation including blast design details and rock condition. Trying various types of the networks, a network with two hidden layers was found to be optimum. Performance of the ANN model was compared with statistical analysis using datasets which were kept apart from the original database. According to the obtained results, for the ANN model there existed a higher correlation (R² = 0.868) and lesser error (RMSE = 0.495) between the predicted and measured backbreak as compared to the regression model. Also, sensitivity analysis revealed that the inputs rock factor and number of rows are the most and the least sensitive parameters on the output backbreak, respectively.     

Saqqar: A 34 km diameter impact structure in Saudi Arabia

Here we present the first proof of an impact origin for the Saqqar circular structure in northwestern Saudi Arabia (Neville et al. 2014 ), with an apparent diameter of 34 km, centered at 29°35′N, 38°42′E. The structure is formed in Cambrian–Devonian siliciclastics and is unconformably overlain by undeformed Cretaceous and Paleogene sediments. The age of impact is not well constrained and lies somewhere between 410 and 70 Ma. The subsurface structure is constrained by 2‐D reflection seismic profiles and six drilled wells. First‐order structural features are a central uplift that rises approximately 2 km above regional datums, surrounded by a ring syncline. The crater rim is defined by circumferential normal faults. The central uplift and ring syncline correspond to a Bouguer gravity high and an annular ring‐like low, respectively. The wells were drilled within the central uplift, the deepest among them exceed 2 km depth. Sandstone core samples from these wells show abundant indicators of a shock metamorphic overprint. Planar deformation features (PDFs) were measured with orientations along (0001), {103}, and less frequently along {101} and {104}. Planar fractures (PFs) predominantly occur along (0001) and {101}, and are locally associated with feather features (FFs). In addition, some shocked feldspar grains and strongly deformed mica flakes were found. The recorded shock pressure ranges between 5 and 15 GPa. The preserved level of shock and the absence of an allochthonous crater fill suggest that Saqqar was eroded by 1–2 km between the Devonian and Maastrichtian. The documentation of unequivocal shock features proves the formation of the Saqqar structure by a hypervelocity impact event.     

Baseline metals pollution profile of tropical estuaries and coastal waters of the Straits of Malacca

The status report on metal pollution in tropical estuaries and coastal waters is important to understand potential environmental health hazards. Detailed baseline measurements were made on physicochemical parameters (pH, temperature, redox potential, electrical conductivity, salinity, dissolved oxygen, total dissolved solid), major ions (Na, Ca, Mg, K, HCO₃, Cl, SO₄ and NO₃) and metals concentrations (²⁷Al, ⁷⁵As, ¹³⁸Ba, ⁹Be, ¹¹¹Cd, ⁵⁹Co, ⁶³Cu, ⁵²Cr, ⁵⁷Fe, ⁵⁵Mn, ⁶⁰Ni, ²⁰⁸Pb, ⁸⁰Se, ⁶⁶Zn) at estuaries and coastal waters along the Straits of Malacca. Principal component analysis (PCA) was employed to reveal potential pollution sources. Seven principal components were extracted with relation to pollution contribution from minerals-related parameters, natural and anthropogenic sources. The output from this study will generate a profound understanding on the metal pollution status and pollution risk of the estuaries and coastal system.     

Leachability of radium-226 from industrial phosphogypsum waste using some simulated natural environmental solutions

This study investigated the leaching of radium-226 from phosphogypsum (PG) waste produced from the fertilizer industry by synthetic solutions that replicate water that may contact the waste in natural conditions. The results indicated that the activity concentration of Ra-226 in the PG was 461 ± 12 Bq kg^?1 and compared with other studies carried out worldwide. The leached percentage of Ra-226 represents the exchangeable fraction loosely bounded in the matrix of the PG waste. The leached fraction of Ra-226 was 6.5 ± 0.6 and 9.0 ± 0.5% when the waste was exposed to rainwater and saline solution, respectively. It is also found that the leaching fraction increased 10–12 ± 0.4% when the waste was exposed to the admixture of saline solution containing Sr²⁺ or Ba²⁺ cations, whereas it was lowered to 4–5 ± 0.5% in the presence of carbonate or sulfate anions. When the PG is used as an economic fertilizer, the irrigation water can leach 7.8 ± 0.6% of Ra-226 that could contribute to plant uptake, thereby to animal and/or human consumption. The primary tests of the drinking water (well and tap resources) consumed by the populations surround the PG facility showed that the activity concentration of Ra-226 was below the minimum detectable activity.     

Exploring thermocline and water masses variability in southern South China Sea from the World Ocean Database (WOD)

Study about water characteristics(temperature and salinity) from the World Ocean Database(WOD) was conducted in the area of southern South China Sea(SSCS), covering the area of 0°–10°N, 100°–117°E. From interannual analysis, upper layer(10 m) and deep water temperature(50 m) increased from 1951 until 2014. Monthly averaged show that May recorded the highest upper layer temperature while January recorded the lowest. It was different for the deep water which recorded the highest value in September and lowest in February. Contour plot for upper layer temperature in the study area shows presence of thermal front of cold water at southern part of Vietnam tip especially during peak northeast season(December–January). The appearances of warm water were obviously seen during generating southwest monsoon(May–June). Thermocline study revealed the deepest isothermal layer depth(ILD) during peak northeast and southwest monsoon. Temperature threshold at shallow area reach more than 0.8°C during the transitional period. Water mass study described T-S profile based on particular region. Water mass during the southwest monsoon is typically well mixed compared to other seasons while strong separation according to location is very clear. During transitional period between northeast monsoon to southwest monsoon, the increasing of water temperature can be seen at Continental Shelf Water(CSW) which tend to be higher than 29°C and vice versa condition during transitional period between southwest monsoon to northeast monsoon. Dispersion of T-S profile can be seen during southwest monsoon inside Tropical Surface Water(TSW) where the salinity and temperature become higher than during northeast monsoon.     

Modelling the mechanical behaviour of unsaturated soils using a genetic algorithm-based neural network

Modelling the mechanical behaviour of unsaturated soils has been the subject of many research works in the past few decades. A number of constitutive models have been developed to describe the complex behaviour of unsaturated soils. Despite the significant advances in the constitutive theories for unsaturated soils, none of the existing models can completely describe the various aspects of the real behaviour of unsaturated soils. In this paper, a new unified approach is presented, based on the integration of a neural network and a genetic algorithm, for the modelling of unsaturated soils. In the proposed approach, a genetic algorithm was used to optimise the weights of the neural network. A three-layer sequential architecture was chosen for the neural network. The network had eight input neurons, five neurons in the hidden layer and three neurons in the output layer. The eight input neurons represented the initial gravimetric water content, initial dry density, degree of saturation, net mean stress with respect to pore-air pressure, axial strain, deviatoric stress, soil suction and volumetric strain, and the three neurons in the output layer represented the deviatoric stress, suction and volumetric strain at the end of each increment. The network was trained and tested using a database that included results from a comprehensive set of triaxial tests on unsaturated soils from the literature. The predictions of the proposed model were compared with the experimental results. The comparison of the results indicates that the proposed approach was accurate and robust in representing the mechanical behaviour of unsaturated soils.