Prediction of surface heave associated with horizontal drilling using neural networks

Jason S. Lueke, Samuel Ariaratnam

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper presents the implementation of an artificial neural network to predict surface heave resulting from shallow subsurface utility installations conducted with horizontal directional drilling. Data gathered from a full factorial field experimentation examining the effects of drilling techniques is utilized in the network development, with the attempt to understand the relationship between construction techniques and resulting surface heave. The developed model is compared to a multivariate linear regression analysis conducted on the raw data, and a sensitivity analysis utilizing the trained network connection weights is conducted to determine which factor has the greatest effect on surface heave development. Further examination of the behavior of the system is provided through a trend analysis which studied the effect of each drilling factor on the predicted surface heave. The results indicate that a neural network would adequately model the relationship between drilling techniques and the resulting surface heave.

Original languageEnglish (US)
Title of host publicationPipelines 2004, What's on the Horizon - Proceedings of the ASCE Pipeline Division Specialty Congress - Pipeline Engineering and Construction
EditorsJ.J. Galleher, M.T. Stift
Pages1207-1216
Number of pages10
StatePublished - Dec 1 2004
EventASCE Pipeline Division Specialty Congress - Pipeline Engineering and Construction - What's on the Horizon, PIPELINES 2004 - San Diego, CA, United States
Duration: Aug 1 2004Aug 4 2004

Publication series

NameProceedings of the ASCE Pipeline Division Specialty Congress - Pipeline Engineering and Construction

Other

OtherASCE Pipeline Division Specialty Congress - Pipeline Engineering and Construction - What's on the Horizon, PIPELINES 2004
CountryUnited States
CitySan Diego, CA
Period8/1/048/4/04

ASJC Scopus subject areas

  • Engineering(all)

Fingerprint Dive into the research topics of 'Prediction of surface heave associated with horizontal drilling using neural networks'. Together they form a unique fingerprint.

Cite this