The majority of the environmental outputs from gas refineries are oily wastewater. This research reveals a novel combination of response surface methodology and artificial neural network to optimize and model oil content concentration in the oily wastewater. Response surface methodology based on central composite design shows a highly significant linear model with P value <0.0001 and determination coefficient R2 equal to 0.747, R adjusted was 0.706, and R predicted 0.643. In addition from analysis of variance flow highly effective parameters from other and optimization results verification revealed minimum oily content with 8.5 ± 0.7 ppm when initial oil content 991 ppm, temperature 46.4 °C, pressure 21 Mpa, and flowrate 27,000 m3/day which is nearly closed to suggested oily content 8.5 ppm. An artificial neural network (ANN) technique was employed in this study to estimate the oil content in the treatment process. An artificial neural network model was remarkably accurate at simulating the process under investigation. A low mean squared error (MSE) and relative error (RE) equal to 1.55 × 10−7 and 2.5, respectively, were obtained during the training phase, whilst the testing results demonstrated a high coefficient of determination (R2) equal to 0.99.
This study is concerned with making comparison in using different geostatistical methods for porosity distribution of upper shale member - Zubair formation in Luhais oil field which was chosen to study.
Kriging, Gaussian random function simulation and sequential Gaussian simulation geostatistical methods were adopted in this study. After preparing all needed data which are contour map, well heads of 12 wells, well tops and porosity from CPI log. Petrel software 2009 was used for porosity distribution of mentioned formation in methods that are showed above. Comparisons were made among these three methods in order to choose the best one, the comparing cri
Problem of water scarcity is becoming common in many parts of the world. Thus to overcome this problem proper management of water and an efficient irrigation systems are needed. Irrigation with buried vertical ceramic pipe is known as a very effective in management of irrigation water. The two- dimensional transient flow of water from a buried vertical ceramic pipe through homogenous porous media is simulated numerically using the software HYDRUS/2D to predict empirical formulas that describe the predicted results accurately. Different values of pipe lengths and hydraulic conductivity were selected. In addition, different values of initial volumetric soil water content were assumed in this simulation a
... Show MoreAn investigation was conducted effect of addition co- solvent on solvent extraction process for two types of a lubricating oil fraction (spindle) and (SAE-30) obtained from vacuum distillation unit of lube oil plant of Daura Refinery. In this study two types of co-solvents ( formamide and N-methyl, 2, pyrrolidone) were blended with furfural to extract aromatic hydrocarbons which are the undesirable materials in raw lubricating oil, in order to improve the viscosity index, viscosity and yield of produced lubricating oil. The studied operating condition are extraction temperature range from 70 to 110 °C for formamide and 80 to 120 °C for N-methyl, 2, pyrrolidone, solvent to oil ratio range from 1:1 to 2:1 (wt./wt.) for furfural with form
... Show MoreIn the present work advanced oxidation process, photo-Fenton (UV/H2O2/Fe+2) system, for the treatment of wastewater contaminated with oil was investigated. The reaction was influenced by the input concentration of hydrogen peroxide H2O2, the initial amount of the iron catalyst Fe+2, pH, temperature and the concentration of oil in the wastewater. The removal efficiency for the system UV/ H2O2/Fe+2 at the optimal conditions and dosage (H2O2 = 400mg/L, Fe+2 = 40mg/L, pH=3, temperature =30o C) for 1000mg/L load was found to be 72%.
This search has introduced the techniques of multi-wavelet transform and neural network for recognition 3-D object from 2-D image using patches. The proposed techniques were tested on database of different patches features and the high energy subband of discrete multi-wavelet transform DMWT (gp) of the patches. The test set has two groups, group (1) which contains images, their (gp) patches and patches features of the same images as a part of that in the data set beside other images, (gp) patches and features, and group (2) which contains the (gp) patches and patches features the same as a part of that in the database but after modification such as rotation, scaling and translation. Recognition by back propagation (BP) neural network as
... Show MoreRegarding to the computer system security, the intrusion detection systems are fundamental components for discriminating attacks at the early stage. They monitor and analyze network traffics, looking for abnormal behaviors or attack signatures to detect intrusions in early time. However, many challenges arise while developing flexible and efficient network intrusion detection system (NIDS) for unforeseen attacks with high detection rate. In this paper, deep neural network (DNN) approach was proposed for anomaly detection NIDS. Dropout is the regularized technique used with DNN model to reduce the overfitting. The experimental results applied on NSL_KDD dataset. SoftMax output layer has been used with cross entropy loss funct
... Show MoreThis search has introduced the techniques of multi-wavelet transform and neural network for recognition 3-D object from 2-D image using patches. The proposed techniques were tested on database of different patches features and the high energy subband of discrete multi-wavelet transform DMWT (gp) of the patches. The test set has two groups, group (1) which contains images, their (gp) patches and patches features of the same images as a part of that in the data set beside other images, (gp) patches and features, and group (2) which contains the (gp) patches and patches features the same as a part of that in the database but after modification such as rotation, scaling and translation. Recognition by back propagation (BP) neural network as com
... Show More