Neural Models for Unconfined Compressive Strength of Kaolin Clay Mixed with Pond Ash, Rice Husk Ash and Cement
In this study an Artificial Neural Network (ANN) model was used to predict the Unconfined Compressive Strength (UCS) of Kaolin clay mixed with pond ash, rice husk ash and cement content model under different curing period. The input parameters included percentages of admixtures added along with clay...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Pouyan Press
2020-04-01
|
Series: | Journal of Soft Computing in Civil Engineering |
Subjects: | |
Online Access: | http://www.jsoftcivil.com/article_107849_766ea24c208b78dd6df2cce83c9eedf9.pdf |
id |
doaj-a62f6edfb2da4bd98381e89eefd41aaa |
---|---|
record_format |
Article |
spelling |
doaj-a62f6edfb2da4bd98381e89eefd41aaa2021-01-19T09:47:28ZengPouyan PressJournal of Soft Computing in Civil Engineering2588-28722588-28722020-04-01428510210.22115/scce.2020.223774.1189107849Neural Models for Unconfined Compressive Strength of Kaolin Clay Mixed with Pond Ash, Rice Husk Ash and CementAkash Priyadarshee0Sunayana Chandra1Deepak Gupta2Vikas Kumar3Assistant Professor, Department of Civil Engineering, MIT Muzaffarpur, Bihar, IndiaCSIR-NEERI, Delhi Zonal Centre, IndiaDepartment of Civil Engineering. NIT Jalandhar, IndiaAssistant Professor, Department of Civil Engineering, Central University of Haryana, IndiaIn this study an Artificial Neural Network (ANN) model was used to predict the Unconfined Compressive Strength (UCS) of Kaolin clay mixed with pond ash, rice husk ash and cement content model under different curing period. The input parameters included percentages of admixtures added along with clay content and curing period. The curing Period range was 7, 14 and 28 days considered in neural model. The feedforward back propagated neural model with Levenberg Marqaurdt gradient descent with momentum constant was used to predict the UCS and optimized topology of 5-10-1 was obtained. The sensitivity analysis based on weights of neural model indicated that all admixtures contributed 70% to the UCS of Kaolin clay. The comparison of ANN model with Multiple Regression Analysis (MRA) model indicated that ANN models were performing better than MRA model with values of r as R2 as 0.98 and 0.97 respectively in testing phase of neural model and for MRA model r was 0.94 and R2 as 0.88.http://www.jsoftcivil.com/article_107849_766ea24c208b78dd6df2cce83c9eedf9.pdfkaolin clayartificial neural networkpond ashrice husk ashcement and unconfined compressive strength |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Akash Priyadarshee Sunayana Chandra Deepak Gupta Vikas Kumar |
spellingShingle |
Akash Priyadarshee Sunayana Chandra Deepak Gupta Vikas Kumar Neural Models for Unconfined Compressive Strength of Kaolin Clay Mixed with Pond Ash, Rice Husk Ash and Cement Journal of Soft Computing in Civil Engineering kaolin clay artificial neural network pond ash rice husk ash cement and unconfined compressive strength |
author_facet |
Akash Priyadarshee Sunayana Chandra Deepak Gupta Vikas Kumar |
author_sort |
Akash Priyadarshee |
title |
Neural Models for Unconfined Compressive Strength of Kaolin Clay Mixed with Pond Ash, Rice Husk Ash and Cement |
title_short |
Neural Models for Unconfined Compressive Strength of Kaolin Clay Mixed with Pond Ash, Rice Husk Ash and Cement |
title_full |
Neural Models for Unconfined Compressive Strength of Kaolin Clay Mixed with Pond Ash, Rice Husk Ash and Cement |
title_fullStr |
Neural Models for Unconfined Compressive Strength of Kaolin Clay Mixed with Pond Ash, Rice Husk Ash and Cement |
title_full_unstemmed |
Neural Models for Unconfined Compressive Strength of Kaolin Clay Mixed with Pond Ash, Rice Husk Ash and Cement |
title_sort |
neural models for unconfined compressive strength of kaolin clay mixed with pond ash, rice husk ash and cement |
publisher |
Pouyan Press |
series |
Journal of Soft Computing in Civil Engineering |
issn |
2588-2872 2588-2872 |
publishDate |
2020-04-01 |
description |
In this study an Artificial Neural Network (ANN) model was used to predict the Unconfined Compressive Strength (UCS) of Kaolin clay mixed with pond ash, rice husk ash and cement content model under different curing period. The input parameters included percentages of admixtures added along with clay content and curing period. The curing Period range was 7, 14 and 28 days considered in neural model. The feedforward back propagated neural model with Levenberg Marqaurdt gradient descent with momentum constant was used to predict the UCS and optimized topology of 5-10-1 was obtained. The sensitivity analysis based on weights of neural model indicated that all admixtures contributed 70% to the UCS of Kaolin clay. The comparison of ANN model with Multiple Regression Analysis (MRA) model indicated that ANN models were performing better than MRA model with values of r as R2 as 0.98 and 0.97 respectively in testing phase of neural model and for MRA model r was 0.94 and R2 as 0.88. |
topic |
kaolin clay artificial neural network pond ash rice husk ash cement and unconfined compressive strength |
url |
http://www.jsoftcivil.com/article_107849_766ea24c208b78dd6df2cce83c9eedf9.pdf |
work_keys_str_mv |
AT akashpriyadarshee neuralmodelsforunconfinedcompressivestrengthofkaolinclaymixedwithpondashricehuskashandcement AT sunayanachandra neuralmodelsforunconfinedcompressivestrengthofkaolinclaymixedwithpondashricehuskashandcement AT deepakgupta neuralmodelsforunconfinedcompressivestrengthofkaolinclaymixedwithpondashricehuskashandcement AT vikaskumar neuralmodelsforunconfinedcompressivestrengthofkaolinclaymixedwithpondashricehuskashandcement |
_version_ |
1724331962891501568 |