Intelligent System For Crude Oil Prediction

Abstract

Since the earliest ages, petroleum belongs to the minerals that have been used by humanity, earlier than metals and coal, and for numerous different purposes. Petroleum is a mixture of naturally occurring hydrocarbons that may exist in the solid, rocks, liquid or gaseous states, depending upon the conditions of pressure and temperature to which it is subjected. Petroleum Engineers combine technology, chemistry, mathematics, crude oil properties, physics and geology with engineering methods to enhanced petroleum industry. They are concerned with finding deposits of oil and gas in quantities suitable for commercial use and with the economic extraction of these materials from the ground. In this thesis, an intelligent prediction system based on computational intelligence technique (fuzzy) has been designed as Intelligent Petroleum Prediction System (IPPS). Multiple processes are used to achieve an accurate result. The required data for evaluation has been chosen from distinct and specialized sources of oilfields. The proposed system utilizes a huge amount of petroleum dataset using fuzzy technique to apply prediction function on Daqing oilfield and other oilfields in Yemen. Another goal of the proposed system is to share petroleum knowledge among Chief Executive Manager and engineers to make drilling decision on oil wells or nullity. More than one module applied on the prediction system; such as petroleum dataset acquisition, classification, data mining, prediction, knowledge validation and other processes. Recently, using artificial intelligence techniques for prediction is highly usage in prediction domain, precision is the criterion. The proposed work reviewing engineering’s experiences, analysis oil wells dataset, reordering memberships, forming an intelligent system to utilize crude oil knowledge