Computational Technology Resources - CCP

J.N. Watson, C.A. Fairfield, C. Wan, A. Sibbald, "The Use of Artificial Neural Networks in Pile Integrity Testing", in B.H.V. Topping, (Editor), "Developments in Neural Networks and Evolutionary Computing for Civil and Structural Engineering", Civil-Comp Press, Edinburgh, UK, pp 7-13, 1995. doi:10.4203/ccp.34.1.2

Abstract

The interpretation of a frequency response spectrum in the non-destructive testing of concrete foundation piles is essentially a pattern recognition problem. This paper examines the possibility of using a feed-forward, multilayer, artificial neural network (ANN) to identify and locate changes in the pile's cross section so automating some of the duties more usually undertaken by an expert analyst. The network is trained through the Back Propagation (BP) learning algorithm to detect a fault's length and position from the difference in its spectral components to a sound pile of identical dimensions. The phase information from the suspect pile is later included to enable the network to differentiate between types of fault; namely necking and overbreak. A full study of the network architecture and learning parameters' effect on eventual system performance is presented and samples of the network response are given.

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 £55 +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: 34 DEVELOPMENTS IN NEURAL NETWORKS AND EVOLUTIONARY COMPUTING FOR CIVIL AND STRUCTURAL ENGINEERING Edited by: B.H.V. Topping Paper I.2 The Use of Artificial Neural Networks in Pile Integrity Testing J.N. Watson, C.A. Fairfield, C. Wan and A. Sibbald Department of Civil and Transportation Engineering, Napier University, Edinburgh, UK doi:10.4203/ccp.34.1.2 purchase the full-text of this paper Full Bibliographic Reference for this paper J.N. Watson, C.A. Fairfield, C. Wan, A. Sibbald, "The Use of Artificial Neural Networks in Pile Integrity Testing", in B.H.V. Topping, (Editor), "Developments in Neural Networks and Evolutionary Computing for Civil and Structural Engineering", Civil-Comp Press, Edinburgh, UK, pp 7-13, 1995. doi:10.4203/ccp.34.1.2 Abstract The interpretation of a frequency response spectrum in the non-destructive testing of concrete foundation piles is essentially a pattern recognition problem. This paper examines the possibility of using a feed-forward, multilayer, artificial neural network (ANN) to identify and locate changes in the pile's cross section so automating some of the duties more usually undertaken by an expert analyst. The network is trained through the Back Propagation (BP) learning algorithm to detect a fault's length and position from the difference in its spectral components to a sound pile of identical dimensions. The phase information from the suspect pile is later included to enable the network to differentiate between types of fault; namely necking and overbreak. A full study of the network architecture and learning parameters' effect on eventual system performance is presented and samples of the network response are given. 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 £55 +P&P)
Back to top	©Civil-Comp Limited 2023 - terms & conditions