خط مشی دسترسیدرباره ما
ثبت نامثبت نام
راهنماراهنما
فارسی
ورودورود
صفحه اصلیصفحه اصلی
جستجوی مدارک
تمام متن
منابع دیجیتالی
رکورد قبلیرکورد بعدی
Document Type : Latin Dissertation
Language of Document : English
Record Number : 149732
Doc. No : ET21524
Main Entry : WEN-TAI YANG
Title Proper : THE CHARACTERIZATION OF SPA= HETEROGENElTY OF PERMEABEJTY: A NEURAL NETWORK APPROACH
Note : This document is digital این مدرک بصورت الکترونیکی می باشد
Abstract : This research project proposes a new neural network approach, using a forward-only counterpropagation network (FCPN), for characterizing the spatial heterogeneity of34imensional permeability on the basis of limited exploration data-The proposed FCPN approach couples with the weighted k-nearest neighbormethod to improve the prediction accuracy of permeability. A set containing k winners(rather than a single winner) with different weights is selected. The weights are based onthe distances from the winners to the point of interest. Therefore, the winners close to thepoint of interest have more influence in the prediction of permeability.Computational results show that the performance of the proposed approach ismore favorable than that of the ordinary kriging method. The average RMS error ofpermeability calculated from the FCPN is 365 md, while the average RMS error ofpermeability calculated fromtested 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 : TL44696.pdf
Title and statement of responsibility and : THE CHARACTERIZATION OF SPA= HETEROGENElTY OF PERMEABEJTY: A NEURAL NETWORK APPROACH [Thesis]
 
 
 
(در صورت عدم وضوح تصویر اینجا را کلیک نمایید)