A Study on UCS of Stabilized Peat with Natural Filler: A Computational Estimation Approach

Ali Dehghanbanadaki, Mahdy Khari, Ali Arefnia, Kamarudin Ahmad, Shervin Motamedi

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

This study applied two feed-forward type computational methods to estimate the Unconfined Compression Strength (UCS) of stabilized peat soil with natural filler and cement. For this purpose, experimental data was obtained via testing of 271 samples at different natural filler and cement mixture dosages. The input parameters for the developed UCS (output) model were: 1) binder dosage, 2) coefficient of compressibility, 3) filler dosage, and 4) curing time. The model estimated the UCS through two types of feed-forward Artificial Neural Network (ANN) models that were trained with Particle Swarm Optimization (ANN-PSO) and Back Propagation (ANN-BP) learning algorithms. As a means to validate the precision of the model two performance indices i.e., coefficient of correlation (R 2 ) and Mean Square Error (MSE) were examined. Sensitivity analyses was also performed to investigate the influence of each input parameters and their contribution on estimating the output. Overall, the results showed that MSE (PSO) < MSE (BP) while R 2 (PSO) > R 2 (BP) ; suggesting that the ANN-PSO model better estimates the UCS compared to ANN-BP. In addition, on the account of sensitivity analysis, it is found that the binder and filler content were the two most influential factors whilst curing period was the least effective factor in predicting UCS.

Original languageEnglish
Pages (from-to)1560–1572
Number of pages13
JournalKSCE Journal of Civil Engineering
Volume23
Issue number4
Early online date18 Jan 2019
DOIs
Publication statusPublished - Apr 2019

Fingerprint

Peat
Particle swarm optimization (PSO)
Fillers
Mean square error
Neural networks
Binders
Curing
Cements
Computational methods
Backpropagation
Compressibility
Learning algorithms
Sensitivity analysis
Soils
Testing

Keywords

  • computation
  • fibrous peat
  • stabilization
  • statistical analysis
  • unconfined compressive strength

ASJC Scopus subject areas

  • Civil and Structural Engineering

Cite this

A Study on UCS of Stabilized Peat with Natural Filler : A Computational Estimation Approach. / Dehghanbanadaki, Ali; Khari, Mahdy; Arefnia, Ali; Ahmad, Kamarudin; Motamedi, Shervin.

In: KSCE Journal of Civil Engineering, Vol. 23, No. 4, 04.2019, p. 1560–1572 .

Research output: Contribution to journalArticle

Dehghanbanadaki, Ali ; Khari, Mahdy ; Arefnia, Ali ; Ahmad, Kamarudin ; Motamedi, Shervin. / A Study on UCS of Stabilized Peat with Natural Filler : A Computational Estimation Approach. In: KSCE Journal of Civil Engineering. 2019 ; Vol. 23, No. 4. pp. 1560–1572 .
@article{37dfc60203dd4705a4771549cb822e86,
title = "A Study on UCS of Stabilized Peat with Natural Filler: A Computational Estimation Approach",
abstract = "This study applied two feed-forward type computational methods to estimate the Unconfined Compression Strength (UCS) of stabilized peat soil with natural filler and cement. For this purpose, experimental data was obtained via testing of 271 samples at different natural filler and cement mixture dosages. The input parameters for the developed UCS (output) model were: 1) binder dosage, 2) coefficient of compressibility, 3) filler dosage, and 4) curing time. The model estimated the UCS through two types of feed-forward Artificial Neural Network (ANN) models that were trained with Particle Swarm Optimization (ANN-PSO) and Back Propagation (ANN-BP) learning algorithms. As a means to validate the precision of the model two performance indices i.e., coefficient of correlation (R 2 ) and Mean Square Error (MSE) were examined. Sensitivity analyses was also performed to investigate the influence of each input parameters and their contribution on estimating the output. Overall, the results showed that MSE (PSO) < MSE (BP) while R 2 (PSO) > R 2 (BP) ; suggesting that the ANN-PSO model better estimates the UCS compared to ANN-BP. In addition, on the account of sensitivity analysis, it is found that the binder and filler content were the two most influential factors whilst curing period was the least effective factor in predicting UCS.",
keywords = "computation, fibrous peat, stabilization, statistical analysis, unconfined compressive strength",
author = "Ali Dehghanbanadaki and Mahdy Khari and Ali Arefnia and Kamarudin Ahmad and Shervin Motamedi",
year = "2019",
month = "4",
doi = "10.1007/s12205-019-0343-4",
language = "English",
volume = "23",
pages = "1560–1572",
journal = "KSCE Journal of Civil Engineering",
issn = "1226-7988",
publisher = "Korean Society of Civil Engineers",
number = "4",

}

TY - JOUR

T1 - A Study on UCS of Stabilized Peat with Natural Filler

T2 - A Computational Estimation Approach

AU - Dehghanbanadaki, Ali

AU - Khari, Mahdy

AU - Arefnia, Ali

AU - Ahmad, Kamarudin

AU - Motamedi, Shervin

PY - 2019/4

Y1 - 2019/4

N2 - This study applied two feed-forward type computational methods to estimate the Unconfined Compression Strength (UCS) of stabilized peat soil with natural filler and cement. For this purpose, experimental data was obtained via testing of 271 samples at different natural filler and cement mixture dosages. The input parameters for the developed UCS (output) model were: 1) binder dosage, 2) coefficient of compressibility, 3) filler dosage, and 4) curing time. The model estimated the UCS through two types of feed-forward Artificial Neural Network (ANN) models that were trained with Particle Swarm Optimization (ANN-PSO) and Back Propagation (ANN-BP) learning algorithms. As a means to validate the precision of the model two performance indices i.e., coefficient of correlation (R 2 ) and Mean Square Error (MSE) were examined. Sensitivity analyses was also performed to investigate the influence of each input parameters and their contribution on estimating the output. Overall, the results showed that MSE (PSO) < MSE (BP) while R 2 (PSO) > R 2 (BP) ; suggesting that the ANN-PSO model better estimates the UCS compared to ANN-BP. In addition, on the account of sensitivity analysis, it is found that the binder and filler content were the two most influential factors whilst curing period was the least effective factor in predicting UCS.

AB - This study applied two feed-forward type computational methods to estimate the Unconfined Compression Strength (UCS) of stabilized peat soil with natural filler and cement. For this purpose, experimental data was obtained via testing of 271 samples at different natural filler and cement mixture dosages. The input parameters for the developed UCS (output) model were: 1) binder dosage, 2) coefficient of compressibility, 3) filler dosage, and 4) curing time. The model estimated the UCS through two types of feed-forward Artificial Neural Network (ANN) models that were trained with Particle Swarm Optimization (ANN-PSO) and Back Propagation (ANN-BP) learning algorithms. As a means to validate the precision of the model two performance indices i.e., coefficient of correlation (R 2 ) and Mean Square Error (MSE) were examined. Sensitivity analyses was also performed to investigate the influence of each input parameters and their contribution on estimating the output. Overall, the results showed that MSE (PSO) < MSE (BP) while R 2 (PSO) > R 2 (BP) ; suggesting that the ANN-PSO model better estimates the UCS compared to ANN-BP. In addition, on the account of sensitivity analysis, it is found that the binder and filler content were the two most influential factors whilst curing period was the least effective factor in predicting UCS.

KW - computation

KW - fibrous peat

KW - stabilization

KW - statistical analysis

KW - unconfined compressive strength

UR - http://www.scopus.com/inward/record.url?scp=85060097418&partnerID=8YFLogxK

U2 - 10.1007/s12205-019-0343-4

DO - 10.1007/s12205-019-0343-4

M3 - Article

VL - 23

SP - 1560

EP - 1572

JO - KSCE Journal of Civil Engineering

JF - KSCE Journal of Civil Engineering

SN - 1226-7988

IS - 4

ER -