Computational Technology Resources - CCP

Paper II.4

Prediction of Turbine Performance using Multilayer Feedforward Networks by Reducing Mapping Nonlinearity

H. Lee and P. Hajela

Department of Mechanical Engineering, Aeronautical Engineering & Mechanics, Rensselaer Polytechnic Institute, Troy, New York, United States of America

doi:10.4203/ccp.27.2.4

purchase the full-text of this paper

H. Lee, P. Hajela, "Prediction of Turbine Performance using Multilayer Feedforward Networks by Reducing Mapping Nonlinearity", in B.H.V. Topping, M. Papadrakakis, (Editors), "Artificial Intelligence and Object Oriented Approaches to Structural Engineering", Civil-Comp Press, Edinburgh, UK, pp 99-105, 1994. doi:10.4203/ccp.27.2.4

Abstract

The present paper examines the relationship between the analytical mapping nonlinearity (distribution angle alpha and distribution gradient beta) of training samples and an empirical measure of trainability of MFNs. The model problem is the prediction of turbine efficiency based on the throat distribution of turbine blades. Various normalization schemes are applied to the training samples in order to study how the change of mapping nonlinearity of training samples affects the actual training process. The results of numerical experiments have confirmed that alpha and beta reliably reflect the degree of difficulty of the training process in the context of the model problem.

purchase the full-text of this paper (price £20)

go to the previous paper
go to the next paper
return to the table of contents
return to the book description
purchase this book (price £45 +P&P)

	Computational & Technology Resources an online resource for computational, engineering & technology publications
	not logged in - login
Front Page Browse CCP CSETS CTR IJRT Other Authors Search Purchase Guide FAQ Contact us	Civil-Comp Proceedings ISSN 1759-3433 CCP: 27 ARTIFICIAL INTELLIGENCE AND OBJECT ORIENTED APPROACHES TO STRUCTURAL ENGINEERING Edited by: B.H.V. Topping and M. Papadrakakis Paper II.4 Prediction of Turbine Performance using Multilayer Feedforward Networks by Reducing Mapping Nonlinearity H. Lee and P. Hajela Department of Mechanical Engineering, Aeronautical Engineering & Mechanics, Rensselaer Polytechnic Institute, Troy, New York, United States of America doi:10.4203/ccp.27.2.4 purchase the full-text of this paper Full Bibliographic Reference for this paper H. Lee, P. Hajela, "Prediction of Turbine Performance using Multilayer Feedforward Networks by Reducing Mapping Nonlinearity", in B.H.V. Topping, M. Papadrakakis, (Editors), "Artificial Intelligence and Object Oriented Approaches to Structural Engineering", Civil-Comp Press, Edinburgh, UK, pp 99-105, 1994. doi:10.4203/ccp.27.2.4 Abstract The present paper examines the relationship between the analytical mapping nonlinearity (distribution angle alpha and distribution gradient beta) of training samples and an empirical measure of trainability of MFNs. The model problem is the prediction of turbine efficiency based on the throat distribution of turbine blades. Various normalization schemes are applied to the training samples in order to study how the change of mapping nonlinearity of training samples affects the actual training process. The results of numerical experiments have confirmed that alpha and beta reliably reflect the degree of difficulty of the training process in the context of the model problem. purchase the full-text of this paper (price £20) go to the previous paper go to the next paper return to the table of contents return to the book description purchase this book (price £45 +P&P)
Back to top	©Civil-Comp Limited 2023 - terms & conditions