Performance Prediction of Cement Stabilized Soil Incorporating Solid Waste and Propylene Fiber

Cement stabilized soil (CSS) yields wide application as a routine cementitious material due to cost-effectiveness. However, the mechanical strength of CSS impedes development. This research assesses the feasible combined enhancement of unconfined compressive strength (UCS) and flexural strength (FS)...

Full description

Bibliographic Details
Main Authors: Zhang, G., Ding, Z., Wang, Yufei, Fu, G., Wang, Y., Xie, C., Zhang, Y., Zhao, X., Lu, X., Wang, Xiangyu
Format: Journal Article
Language:English
Published: MDPI 2022
Subjects:
Online Access:http://purl.org/au-research/grants/arc/LP180100222
http://hdl.handle.net/20.500.11937/90924
_version_ 1848765462110797824
author Zhang, G.
Ding, Z.
Wang, Yufei
Fu, G.
Wang, Y.
Xie, C.
Zhang, Y.
Zhao, X.
Lu, X.
Wang, Xiangyu
author_facet Zhang, G.
Ding, Z.
Wang, Yufei
Fu, G.
Wang, Y.
Xie, C.
Zhang, Y.
Zhao, X.
Lu, X.
Wang, Xiangyu
author_sort Zhang, G.
building Curtin Institutional Repository
collection Online Access
description Cement stabilized soil (CSS) yields wide application as a routine cementitious material due to cost-effectiveness. However, the mechanical strength of CSS impedes development. This research assesses the feasible combined enhancement of unconfined compressive strength (UCS) and flexural strength (FS) of construction and demolition (C&D) waste, polypropylene fiber, and sodium sulfate. Moreover, machine learning (ML) techniques including Back Propagation Neural Network (BPNN) and Random Forest (FR) were applied to estimate UCS and FS based on the comprehensive dataset. The laboratory tests were conducted at 7-, 14-, and 28-day curing age, indicating the positive effect of cement, C&D waste, and sodium sulfate. The improvement caused by polypropylene fiber on FS was also evaluated from the 81 experimental results. In addition, the beetle antennae search (BAS) approach and 10-fold cross-validation were employed to automatically tune the hyperparameters, avoiding tedious effort. The consequent correlation coefficients (R) ranged from 0.9295 to 0.9717 for BPNN, and 0.9262 to 0.9877 for RF, respectively, indicating the accuracy and reliability of the prediction. K-Nearest Neighbor (KNN), logistic regression (LR), and multiple linear regression (MLR) were conducted to validate the BPNN and RF algorithms. Furthermore, box and Taylor diagrams proved the BAS-BPNN and BAS-RF as the best-performed model for UCS and FS prediction, respectively. The optimal mixture design was proposed as 30% cement, 20% C&D waste, 4% fiber, and 0.8% sodium sulfate based on the importance score for each variable.
first_indexed 2025-11-14T11:35:38Z
format Journal Article
id curtin-20.500.11937-90924
institution Curtin University Malaysia
institution_category Local University
language English
last_indexed 2025-11-14T11:35:38Z
publishDate 2022
publisher MDPI
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-909242023-05-11T06:57:12Z Performance Prediction of Cement Stabilized Soil Incorporating Solid Waste and Propylene Fiber Zhang, G. Ding, Z. Wang, Yufei Fu, G. Wang, Y. Xie, C. Zhang, Y. Zhao, X. Lu, X. Wang, Xiangyu Science & Technology Physical Sciences Technology Chemistry, Physical Materials Science, Multidisciplinary Metallurgy & Metallurgical Engineering Physics, Applied Physics, Condensed Matter Chemistry Materials Science Physics cement stabilized soil fiber-reinforced soil mechanical strength waste utilization Back Propagation Neural Network Random Forest beetle antennae search COMPRESSIVE STRENGTH CONCRETE REGRESSION HYDRATION BEHAVIOR COLUMNS SULFATE Back Propagation Neural Network Random Forest beetle antennae search cement stabilized soil fiber-reinforced soil mechanical strength waste utilization Cement stabilized soil (CSS) yields wide application as a routine cementitious material due to cost-effectiveness. However, the mechanical strength of CSS impedes development. This research assesses the feasible combined enhancement of unconfined compressive strength (UCS) and flexural strength (FS) of construction and demolition (C&D) waste, polypropylene fiber, and sodium sulfate. Moreover, machine learning (ML) techniques including Back Propagation Neural Network (BPNN) and Random Forest (FR) were applied to estimate UCS and FS based on the comprehensive dataset. The laboratory tests were conducted at 7-, 14-, and 28-day curing age, indicating the positive effect of cement, C&D waste, and sodium sulfate. The improvement caused by polypropylene fiber on FS was also evaluated from the 81 experimental results. In addition, the beetle antennae search (BAS) approach and 10-fold cross-validation were employed to automatically tune the hyperparameters, avoiding tedious effort. The consequent correlation coefficients (R) ranged from 0.9295 to 0.9717 for BPNN, and 0.9262 to 0.9877 for RF, respectively, indicating the accuracy and reliability of the prediction. K-Nearest Neighbor (KNN), logistic regression (LR), and multiple linear regression (MLR) were conducted to validate the BPNN and RF algorithms. Furthermore, box and Taylor diagrams proved the BAS-BPNN and BAS-RF as the best-performed model for UCS and FS prediction, respectively. The optimal mixture design was proposed as 30% cement, 20% C&D waste, 4% fiber, and 0.8% sodium sulfate based on the importance score for each variable. 2022 Journal Article http://hdl.handle.net/20.500.11937/90924 10.3390/ma15124250 English http://purl.org/au-research/grants/arc/LP180100222 http://creativecommons.org/licenses/by/4.0/ MDPI fulltext
spellingShingle Science & Technology
Physical Sciences
Technology
Chemistry, Physical
Materials Science, Multidisciplinary
Metallurgy & Metallurgical Engineering
Physics, Applied
Physics, Condensed Matter
Chemistry
Materials Science
Physics
cement stabilized soil
fiber-reinforced soil
mechanical strength
waste utilization
Back Propagation Neural Network
Random Forest
beetle antennae search
COMPRESSIVE STRENGTH
CONCRETE
REGRESSION
HYDRATION
BEHAVIOR
COLUMNS
SULFATE
Back Propagation Neural Network
Random Forest
beetle antennae search
cement stabilized soil
fiber-reinforced soil
mechanical strength
waste utilization
Zhang, G.
Ding, Z.
Wang, Yufei
Fu, G.
Wang, Y.
Xie, C.
Zhang, Y.
Zhao, X.
Lu, X.
Wang, Xiangyu
Performance Prediction of Cement Stabilized Soil Incorporating Solid Waste and Propylene Fiber
title Performance Prediction of Cement Stabilized Soil Incorporating Solid Waste and Propylene Fiber
title_full Performance Prediction of Cement Stabilized Soil Incorporating Solid Waste and Propylene Fiber
title_fullStr Performance Prediction of Cement Stabilized Soil Incorporating Solid Waste and Propylene Fiber
title_full_unstemmed Performance Prediction of Cement Stabilized Soil Incorporating Solid Waste and Propylene Fiber
title_short Performance Prediction of Cement Stabilized Soil Incorporating Solid Waste and Propylene Fiber
title_sort performance prediction of cement stabilized soil incorporating solid waste and propylene fiber
topic Science & Technology
Physical Sciences
Technology
Chemistry, Physical
Materials Science, Multidisciplinary
Metallurgy & Metallurgical Engineering
Physics, Applied
Physics, Condensed Matter
Chemistry
Materials Science
Physics
cement stabilized soil
fiber-reinforced soil
mechanical strength
waste utilization
Back Propagation Neural Network
Random Forest
beetle antennae search
COMPRESSIVE STRENGTH
CONCRETE
REGRESSION
HYDRATION
BEHAVIOR
COLUMNS
SULFATE
Back Propagation Neural Network
Random Forest
beetle antennae search
cement stabilized soil
fiber-reinforced soil
mechanical strength
waste utilization
url http://purl.org/au-research/grants/arc/LP180100222
http://hdl.handle.net/20.500.11937/90924