Petroleum Hydrocarbon Quarterly Boiling Range Distribution of Iraqi Crude Oil by Simulated Distillation Method

This study includes analysis of different crude oil stock for various field Iraqi oil by gas chromatography instrument, using simulated distillation technique for determining the initial and final boiling point distribution and specified compound distillation information (normal paraffins) (Recovery W/W) for (nC5 – nC44), ASTM-D5307 becomes the analytical method. This method need tow samples; the first one spiked with internal standard and the second without internal standard. This analysis for quantitative and qualitative oil characterization which is often useful for evaluating the range of hydrocarbons in crude oil using Simulated Distillation. The study was performed using: Quarterly analysis of SIMDIS GC Distillation for three field (East Baghdad, Badra, Amara) Comparison of analyzes of SIMDIS GC Distillation with Different API (light, intermediate, heavy) with Initial boiling point (IBP). Finding experimental relationship between API and Initial boiling point (IBP): The result of this study shows that the boiling point increase as the number of carbon is increase, the values of n-Pentane (nC5) to n- Tetratetracontane (nC44) (w/w) changes from winter and summer (difference in temperatures), Positive correlation between C6 and C5 with API, where their percentages increase with increasing API for crude oil and C6 and C5 are lower in summer than in winter due to the evaporation of light components of the samples in summer. Initial boiling point increase as the API is decrease that mean in crude oil have heavy component increases and light component decrease (inverse relationship).

SimulaD: A Novel Feature Selection Heuristics for Discrete Data

By applying a running average (with a window-size= d), we could transform Discrete data to broad-range, Continuous values. When we have more than 2 columns and one of them is containing data about the tags of classification (Class Column), we could compare and sort the features (Non-class Columns) based on the R2 coefficient of the regression for running averages. The parameters tuning could help us to select the best features (the non-class columns which have the best correlation with the Class Column). “Window size” and “Ordering” could be tuned to achieve the goal. this optimization problem is hard and we need an Algorithm (or Heuristics) for simplifying this tuning. We demonstrate a novel heuristics, Called Simulated Distillation (SimulaD), which could help us to gain a somehow good results with this optimization problem.

SimulaD: A Novel Feature Selection Heuristics For Discrete Data

For discrete big data which have a limited range of values, Conventional machine learning methods cannot be applied because we see clutter and overlapping of classes in such data: many data points from different classes overlap. In this paper we introduce a solution for this problem through a novel heuristics method. By applying a running average (with a window-size= d) we could transform Discrete data to broad-range, Continuous values. When we have more than 2 columns and one of them is containing data about the tags of classification (Class Column), we could compare and sort the features (Non-class Columns) based on the R2 coefficient of the regression for running averages. The parameters tuning could help us to select the best features (the non-class columns which have the best correlation with the Class Column). “Window size” and “Ordering” could be tuned to achieve the goal. This optimization problem is hard and we need an Algorithm (or Heuristics) for simplifying this tuning. We demonstrate a novel heuristics, Called Simulated Distillation (SimulaD), which could help us to gain a somehow good results with this optimization problem.

SimulaD: A Novel Feature Selection Heuristics for Discrete Data

By applying a running average (with a window-size= d), we could transform Discrete data to broad-range, Continuous values. When we have more than 2 columns and one of them is containing data about the tags of classification (Class Column), we could compare and sort the features (Non-class Columns) based on the R2 coefficient of the regression for running averages. The parameters tuning could help us to select the best features (the non-class columns which have the best correlation with the Class Column). “Window size” and “Ordering” could be tuned to achieve the goal. this optimization problem is hard and we need an Algorithm (or Heuristics) for simplifying this tuning. We demonstrate a novel heuristics, Called Simulated Distillation (SimulaD), which could help us to gain a somehow good results with this optimization problem.

SimulaD: A Novel Feature Selection Heuristics for Discrete Data

By applying a running average (with a window-size= d), we could transform Discrete data to broad-range, Continuous values. When we have more than 2 columns and one of them is containing data about the tags of classification (Class Column), we could compare and sort the features (Non-class Columns) based on the R2 coefficient of the regression for running averages. The parameters tuning could help us to select the best features (the non-class columns which have the best correlation with the Class Column). “Window size” and “Ordering” could be tuned to achieve the goal. this optimization problem is hard and we need an Algorithm (or Heuristics) for simplifying this tuning. We demonstrate a novel heuristics, Called Simulated Distillation (SimulaD), which could help us to gain a somehow good results with this optimization problem.