Horizontal wells have revolutionized hydrocarbon production by enhancing recovery efficiency and reducing environmental impact. This paper presents an enhanced Black Oil Model simulator, written in Visual Basic, for three-dimensional two-phase (oil and water) flow through porous media. Unlike most existing tools, this simulator is customized for horizontal well modeling and calibrated using extensive historical data from the South Rumaila Oilfield, Iraq. The simulator first achieves a strong match with historical pressure data (1954–2004) using vertical wells, with an average deviation of less than 5% from observed pressures, and is then applied to forecast the performance of hypothetical horizontal wells (2008–2011). The result

Various theories have been proposed since in last century to predict the first sighting of a new crescent moon. None of them uses the concept of machine and deep learning to process, interpret and simulate patterns hidden in databases. Many of these theories use interpolation and extrapolation techniques to identify sighting regions through such data. In this study, a pattern recognizer artificial neural network was trained to distinguish between visibility regions. Essential parameters of crescent moon sighting were collected from moon sight datasets and used to build an intelligent system of pattern recognition to predict the crescent sight conditions. The proposed ANN learned the datasets with an accuracy of more than 72% in comp

The consumption of fossil fuels has caused many challenges, including environmental and climate damage, global warming, and rising energy costs, which has prompted seeking to substitute other alternative sources. The current study explored the microwave pyrolysis of Albizia branches to assess its potential to produce all forms of fuel (solid, liquid, gas), time savings, and effective thermal heat transfer. The impact of the critical parameters on the quantity and quality of the biofuel generation, including time, power levels, biomass weight, and particle size, were investigated. The results revealed that the best bio-oil production was 76% at a power level of 450 W and 20 g of biomass. Additionally, low power levels led to enhanced

 In this work, plasma parameters such as (electron temperature (Te), electron density (ne), plasma frequency (fp) and Debye length (λD)) were studied using spectral analysis techniques. The spectrum of the plasma was recorded with different energy values, SnO2 and ZnO anesthetized at a different ratio (X = 0.2, 0.4 and 0.6) were recorded. Spectral study of this mixing in the air. The results showed electron density and electron temperature increase in zinc oxide: tin oxide alloy targets. It was located  that  The intensity of the lines increases in different laser peak powers when the laser peak power increases and then decreases when the force continues to increase.

In order to promote sustainable steel-concrete composite structures, special shear connectors that can facilitate deconstruction are needed. A lockbolt demountable shear connector (LB-DSC), including a grout-filled steel tube embedded in the concrete slab and fastened to a geometrically compatible partial-thread bolt, which is bolted on the steel section's top flange of a composite beam, was proposed. The main drawback of previous similar demountable bolts is the sudden slip of the bolt inside its hole. This bolt has a locked conical seat lug that is secured inside a predrilled compatible counter-sunk hole in the steel section's flange to provide a non-slip bolt-flange connection. Deconstruction is achieved by demounting the tube from the t

     Deep learning (DL) plays a significant role in several tasks, especially classification and prediction. Classification tasks can be efficiently achieved via convolutional neural networks (CNN) with a huge dataset, while recurrent neural networks (RNN) can perform prediction tasks due to their ability to remember time series data. In this paper, three models have been proposed to certify the evaluation track for classification and prediction tasks associated with four datasets (two for each task). These models are CNN and RNN, which include two models (Long Short Term Memory (LSTM)) and GRU (Gated Recurrent Unit). Each model is employed to work consequently over the two mentioned tasks to draw a road map of deep learning mod