Using multiple neural networks to estimate the screening effect of surface waves by in-filled trenches

Chang Chi Hung, Sheng-Huoo Ni

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

Trenching is an economical and effective method to reduce surface vibrations and isolate structures from shaking. Previous reports on vibration screening concentrated on either experimental work or analytical study. Due to the construction of more complex structures in the last two decades, presenting more complicated boundary conditions, a variety of numerical methods have been used. Complexity of formulation, the large number of parameters involved, and the difficulty and time required to analyze an effective vibration screening makes the direct numerical approach impractical. The purpose of this paper is to explore the use of an artificial neural network to estimate the effectiveness of a vibration screening trench. Three artificial neural networks, BPN, GRNN, and RBF, are used to evaluate the performance of a chosen physical model. The results show that all three models can be used to evaluate effectiveness of screening trenches with varying accuracy, with GRNN having the highest accuracy. There is much stronger agreement with data of numerically calculated results for neural networks than for empirical multi-variate regression methods.

Original languageEnglish
Pages (from-to)397-409
Number of pages13
JournalComputers and Geotechnics
Volume34
Issue number5
DOIs
Publication statusPublished - 2007 Sep 1

Fingerprint

Surface waves
surface wave
trench
vibration
Screening
Neural networks
artificial neural network
Trenching
numerical method
Numerical methods
boundary condition
Boundary conditions
screening
effect
method

All Science Journal Classification (ASJC) codes

  • Geotechnical Engineering and Engineering Geology
  • Computer Science Applications

Cite this

@article{83e61da23d9243828300b56324b363ec,
title = "Using multiple neural networks to estimate the screening effect of surface waves by in-filled trenches",
abstract = "Trenching is an economical and effective method to reduce surface vibrations and isolate structures from shaking. Previous reports on vibration screening concentrated on either experimental work or analytical study. Due to the construction of more complex structures in the last two decades, presenting more complicated boundary conditions, a variety of numerical methods have been used. Complexity of formulation, the large number of parameters involved, and the difficulty and time required to analyze an effective vibration screening makes the direct numerical approach impractical. The purpose of this paper is to explore the use of an artificial neural network to estimate the effectiveness of a vibration screening trench. Three artificial neural networks, BPN, GRNN, and RBF, are used to evaluate the performance of a chosen physical model. The results show that all three models can be used to evaluate effectiveness of screening trenches with varying accuracy, with GRNN having the highest accuracy. There is much stronger agreement with data of numerically calculated results for neural networks than for empirical multi-variate regression methods.",
author = "Hung, {Chang Chi} and Sheng-Huoo Ni",
year = "2007",
month = "9",
day = "1",
doi = "10.1016/j.compgeo.2007.06.005",
language = "English",
volume = "34",
pages = "397--409",
journal = "Computers and Geotechnics",
issn = "0266-352X",
publisher = "Elsevier BV",
number = "5",

}

Using multiple neural networks to estimate the screening effect of surface waves by in-filled trenches. / Hung, Chang Chi; Ni, Sheng-Huoo.

In: Computers and Geotechnics, Vol. 34, No. 5, 01.09.2007, p. 397-409.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Using multiple neural networks to estimate the screening effect of surface waves by in-filled trenches

AU - Hung, Chang Chi

AU - Ni, Sheng-Huoo

PY - 2007/9/1

Y1 - 2007/9/1

N2 - Trenching is an economical and effective method to reduce surface vibrations and isolate structures from shaking. Previous reports on vibration screening concentrated on either experimental work or analytical study. Due to the construction of more complex structures in the last two decades, presenting more complicated boundary conditions, a variety of numerical methods have been used. Complexity of formulation, the large number of parameters involved, and the difficulty and time required to analyze an effective vibration screening makes the direct numerical approach impractical. The purpose of this paper is to explore the use of an artificial neural network to estimate the effectiveness of a vibration screening trench. Three artificial neural networks, BPN, GRNN, and RBF, are used to evaluate the performance of a chosen physical model. The results show that all three models can be used to evaluate effectiveness of screening trenches with varying accuracy, with GRNN having the highest accuracy. There is much stronger agreement with data of numerically calculated results for neural networks than for empirical multi-variate regression methods.

AB - Trenching is an economical and effective method to reduce surface vibrations and isolate structures from shaking. Previous reports on vibration screening concentrated on either experimental work or analytical study. Due to the construction of more complex structures in the last two decades, presenting more complicated boundary conditions, a variety of numerical methods have been used. Complexity of formulation, the large number of parameters involved, and the difficulty and time required to analyze an effective vibration screening makes the direct numerical approach impractical. The purpose of this paper is to explore the use of an artificial neural network to estimate the effectiveness of a vibration screening trench. Three artificial neural networks, BPN, GRNN, and RBF, are used to evaluate the performance of a chosen physical model. The results show that all three models can be used to evaluate effectiveness of screening trenches with varying accuracy, with GRNN having the highest accuracy. There is much stronger agreement with data of numerically calculated results for neural networks than for empirical multi-variate regression methods.

UR - http://www.scopus.com/inward/record.url?scp=34848867291&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34848867291&partnerID=8YFLogxK

U2 - 10.1016/j.compgeo.2007.06.005

DO - 10.1016/j.compgeo.2007.06.005

M3 - Article

AN - SCOPUS:34848867291

VL - 34

SP - 397

EP - 409

JO - Computers and Geotechnics

JF - Computers and Geotechnics

SN - 0266-352X

IS - 5

ER -