A NEW APPROACH FOR TRAINING AND TESTING ARTIFICIAL NEURAL NETWORKS FOR PERMEABILITY PREDICTION

دانشگاه آزاد اسلامی اصفهان(خوراسگان)

منو

رکورد قبلی

رکورد بعدی

" A NEW APPROACH FOR TRAINING AND TESTING ARTIFICIAL NEURAL NETWORKS FOR PERMEABILITY PREDICTION "

Document Type	:	Latin Dissertation
Language of Document	:	English
Record Number	:	151368
Doc. No	:	ET23160
Main Entry	:	Ademola Akinwumi Oyerokun
Title Proper	:	A NEW APPROACH FOR TRAINING AND TESTING ARTIFICIAL NEURAL NETWORKS FOR PERMEABILITY PREDICTION
Note	:	This document is digital این مدرک بصورت الکترونیکی می باشد
Abstract	:	Although many attempts have been made in the recent years for permeability predictionusing Artificial Neural Network (ANN), none of the approaches has employed prespecifiedtest set instead of a randomly generated test set.The methodology for selecting proper pre-specified test set was presented in chapter fourof this report. The pre-specified test sets were chosen from a plot of log of permeabilityversus density. This approach was explicitly discussed later in the report.In this study, a pre-specified test set approach for training the network for fieldapplicability has been developed using inputs from electric logs and flow unit obtainedfrom geological interpretation of the pay zone. The developed ANN model wassuccessfully applied to the Stringtown Oilfield in West Virginia.The results of this research demonstrated that the embedded powerful abilities of theANN could be utilized to predict permeability among other important petrophysicalparameters provided it was properly trained with the right pre-specified test set for fieldapplicability.....-....,....-...,..tested for theQ1 PC1 bus cardBoth these projects mere sofixare des elopment efforts tonards contributing to dlfferentaspects of Roboucs and lZ1echatronics projects m the Controls and Roboucs Group..
Subject	:	Electericl tess
	:	برق
electronic file name	:	TL46396.pdf
Title and statement of responsibility and	:	A NEW APPROACH FOR TRAINING AND TESTING ARTIFICIAL NEURAL NETWORKS FOR PERMEABILITY PREDICTION [Thesis]