An investigation of pile design utilizing advanced data analytics

Nikolaos P. Machairas, Magued Iskander

Research output: Contribution to journalConference article

Abstract

This study explores the use of state-of-the-art data analytics techniques for predicting the axial load capacity of piles. A support vector machine algorithm was developed. About 213 load tests obtained from FHWA's deep foundation load test database (DFLTD) version 2 were used to evaluate the performance of the developed approach against the FHWA design method. The scope was limited to impact-driven, un-tapered, steel, and concrete piles, loaded in compression, using a static load test. The results of the predictive analysis show an improvement over the capacities obtained by the FHWA pile design method. Perhaps more remarkably, the predictive model outperformed the FHWA pile design method by relying only on seven readily available features as compared to a laborious and error-prone design methodology. This study demonstrates the potential of machine learning in geotechnical engineering as an alternative to conventional design approaches. The methodology is also demonstrated with an online capacity computation tool.

Original languageEnglish (US)
Pages (from-to)132-141
Number of pages10
JournalGeotechnical Special Publication
Volume2018-March
Issue numberGSP 294
DOIs
StatePublished - Jan 1 2018
Event3rd International Foundations Congress and Equipment Expo 2018: Installation, Testing, and Analysis of Deep Foundations, IFCEE 2018 - Orlando, United States
Duration: Mar 5 2018Mar 10 2018

Fingerprint

Piles
pile
design method
methodology
geotechnical engineering
Geotechnical engineering
Axial loads
Concrete construction
steel
compression
Support vector machines
Learning systems
Steel
test

ASJC Scopus subject areas

  • Civil and Structural Engineering
  • Architecture
  • Building and Construction
  • Geotechnical Engineering and Engineering Geology

Cite this

An investigation of pile design utilizing advanced data analytics. / Machairas, Nikolaos P.; Iskander, Magued.

In: Geotechnical Special Publication, Vol. 2018-March, No. GSP 294, 01.01.2018, p. 132-141.

Research output: Contribution to journalConference article

Machairas, Nikolaos P. ; Iskander, Magued. / An investigation of pile design utilizing advanced data analytics. In: Geotechnical Special Publication. 2018 ; Vol. 2018-March, No. GSP 294. pp. 132-141.
@article{79a3448258cf4fb089d0945de468709c,
title = "An investigation of pile design utilizing advanced data analytics",
abstract = "This study explores the use of state-of-the-art data analytics techniques for predicting the axial load capacity of piles. A support vector machine algorithm was developed. About 213 load tests obtained from FHWA's deep foundation load test database (DFLTD) version 2 were used to evaluate the performance of the developed approach against the FHWA design method. The scope was limited to impact-driven, un-tapered, steel, and concrete piles, loaded in compression, using a static load test. The results of the predictive analysis show an improvement over the capacities obtained by the FHWA pile design method. Perhaps more remarkably, the predictive model outperformed the FHWA pile design method by relying only on seven readily available features as compared to a laborious and error-prone design methodology. This study demonstrates the potential of machine learning in geotechnical engineering as an alternative to conventional design approaches. The methodology is also demonstrated with an online capacity computation tool.",
author = "Machairas, {Nikolaos P.} and Magued Iskander",
year = "2018",
month = "1",
day = "1",
doi = "10.1061/9780784481578.014",
language = "English (US)",
volume = "2018-March",
pages = "132--141",
journal = "Geotechnical Special Publication",
issn = "0895-0563",
publisher = "American Society of Civil Engineers (ASCE)",
number = "GSP 294",

}

TY - JOUR

T1 - An investigation of pile design utilizing advanced data analytics

AU - Machairas, Nikolaos P.

AU - Iskander, Magued

PY - 2018/1/1

Y1 - 2018/1/1

N2 - This study explores the use of state-of-the-art data analytics techniques for predicting the axial load capacity of piles. A support vector machine algorithm was developed. About 213 load tests obtained from FHWA's deep foundation load test database (DFLTD) version 2 were used to evaluate the performance of the developed approach against the FHWA design method. The scope was limited to impact-driven, un-tapered, steel, and concrete piles, loaded in compression, using a static load test. The results of the predictive analysis show an improvement over the capacities obtained by the FHWA pile design method. Perhaps more remarkably, the predictive model outperformed the FHWA pile design method by relying only on seven readily available features as compared to a laborious and error-prone design methodology. This study demonstrates the potential of machine learning in geotechnical engineering as an alternative to conventional design approaches. The methodology is also demonstrated with an online capacity computation tool.

AB - This study explores the use of state-of-the-art data analytics techniques for predicting the axial load capacity of piles. A support vector machine algorithm was developed. About 213 load tests obtained from FHWA's deep foundation load test database (DFLTD) version 2 were used to evaluate the performance of the developed approach against the FHWA design method. The scope was limited to impact-driven, un-tapered, steel, and concrete piles, loaded in compression, using a static load test. The results of the predictive analysis show an improvement over the capacities obtained by the FHWA pile design method. Perhaps more remarkably, the predictive model outperformed the FHWA pile design method by relying only on seven readily available features as compared to a laborious and error-prone design methodology. This study demonstrates the potential of machine learning in geotechnical engineering as an alternative to conventional design approaches. The methodology is also demonstrated with an online capacity computation tool.

UR - http://www.scopus.com/inward/record.url?scp=85048885301&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85048885301&partnerID=8YFLogxK

U2 - 10.1061/9780784481578.014

DO - 10.1061/9780784481578.014

M3 - Conference article

VL - 2018-March

SP - 132

EP - 141

JO - Geotechnical Special Publication

JF - Geotechnical Special Publication

SN - 0895-0563

IS - GSP 294

ER -