Prediction of the PVT Data using Neural Network Computing Theory

Abstract

Artificial neural networks theory creates, with other theories and algorithms, a new science. This science deals with the human body as an excellent source, through which it can simulate some biological basics and systems, to be used in solving many scientific, and engineering problems. Neural networks are tested successfully in so many fields as pattern recognition or intelligent classifier, prediction, and correlation development. Recently, Neural network has gained popularity in petroleum applications. In this paper we applied this technique in PVT parameters determinations. The application interests in the estimation of the bubble point pressure through a designed neural network. As this value well estimated, it then used with other variables in a second network to determine oil FVF at this value of bubble point pressure. A comparison study between the performance of neural network and other published correlations has shown an excellent response with smallest absolute relative average error, and highest correlation coefficient for the designed networks among all correlations. Introduction PVT properties always determined experimentally from calculation based on samples collected from either well bore or at the surface. Such samples may be very expensive to obtain. Hence, in case of the absence of the experimental measured PVT properties, it is necessary to use the empirically derived correlation to predict the PVT data.1 Many correlation already exist in the oil and gas industry such as: Standing correlation, Glaso correlation, Beggs and Vasquez correlation,....etc. Many investigators recognize that the neural network can serve the petroleum industry to create more accurate predication PVT correlations. So, there is a number of papers in this area. R. B. Gharbi, and A. M. El- Sharkawy2,3, in 1997, published two papers in this field. The first paper use the neural system to estimate the PVT data for middle east crude oil reservoirs28, while the next one was interest in developing a universal neural network for predicting PVT properties for any oil reservoir3.

Efficient Algorithm for the Prediction of Pressure–Volume–Temperature Properties of Crude Oils Using the Perturbed-Chain Statistical Associating Fluid Theory Equation of State

“…More recently, advanced regression techniques have been implemented to obtain a more accurate correlation for the crude oil properties through the use of artificial neural networks (ANNs). − Neural networks are highly adaptive information-processing systems that can be trained to match a set of inputs to a set of outputs. Despite being more accurate than empirical equations, ANNs generally depend on the data set used for the training process, which can lead to significant deviations in the predictions if not implemented with care.…”

Accurate model based on artificial intelligence for prediction of carbon dioxide solubility in aqueous tetra‐n‐butylammonium bromide solutions

“…Artificial neural networks (ANNs) are algorithms that can be trained and even improved by experience, which means less statistical training processes. These networks are also flexible to adapt themselves to environmental changes, which make them applicable in many different areas . Pattern recognition, identification, classification, speech, vision, control systems, and simulation are the most important uses of artificial neural networks (ANNs).…”

Practical Implementation of Knowledge-Based Approaches for SAGD Production Analysis

“…ANN has achieved significant popularity in areas such as production prediction , reservoir characterization or properties prediction (An et al 1993, Goda et al 2003, Tang et al 2011, history matching (Ramgulam 2006), classification (Stundner et al 2001), proxy for prediction of recovery performance (Lechner et al 2005, Awoleke et al 2011, production operation optimization and well design (Stoisits et al 1999, Yeten et al 2002, Ayala H et al 2007). In recent years, the neural network has also been utilized to evaluate enhanced oil recovery (EOR) projects (Zerafat et al 2011, Parada et al 2012, predict heavy oil recoveries (Ahmadloo et al 2010, Popa et al 2012, and assess CO 2 sequestration process (Mohammadpoor et al 2012).…”