Machine Learning-Assisted Sustainable Mix Design of Waste Glass Powder Concrete with Strength–Cost–CO<sub>2</sub> Emissions Trade-Offs

Glass powder, a non-degradable waste material, offers significant potential to reduce cement consumption and carbon emissions in concrete production. However, existing mix design methods for glass powder concrete (GPC) fail to systematically balance economic efficiency, environmental sustainability,...

Full description

Saved in:
Bibliographic Details
Main Authors: Yuzhuo Zhang, Jiale Peng, Zi Wang, Meng Xi, Jinlong Liu, Lei Xu
Format: Article
Language:English
Published: MDPI AG 2025-07-01
Series:Buildings
Subjects:
Online Access:https://www.mdpi.com/2075-5309/15/15/2640
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849770696925773824
author Yuzhuo Zhang
Jiale Peng
Zi Wang
Meng Xi
Jinlong Liu
Lei Xu
author_facet Yuzhuo Zhang
Jiale Peng
Zi Wang
Meng Xi
Jinlong Liu
Lei Xu
author_sort Yuzhuo Zhang
collection DOAJ
description Glass powder, a non-degradable waste material, offers significant potential to reduce cement consumption and carbon emissions in concrete production. However, existing mix design methods for glass powder concrete (GPC) fail to systematically balance economic efficiency, environmental sustainability, and mechanical performance. To address this gap, this study proposes an AI-assisted framework integrating machine learning (ML) and Multi-Objective Optimization (MOO) to achieve a sustainable GPC design. A robust database of 1154 experimental records was developed, focusing on five key predictors: cement content, water-to-binder ratio, aggregate composition, glass powder content, and curing age. Seven ML models were optimized via Bayesian tuning, with the Ensemble Tree model achieving superior accuracy (R<sup>2</sup> = 0.959 on test data). SHapley Additive exPlanations (SHAP) analysis further elucidated the contribution mechanisms and underlying interactions of material components on GPC compressive strength. Subsequently, a MOO framework minimized unit cost and CO<sub>2</sub> emissions while meeting compressive strength targets (15–70 MPa), solved using the NSGA-II algorithm for Pareto solutions and TOPSIS for decision-making. The Pareto-optimal solutions provide actionable guidelines for engineers to align GPC design with circular economy principles and low-carbon policies. This work advances sustainable construction practices by bridging AI-driven innovation with building materials, directly supporting global goals for waste valorization and carbon neutrality.
format Article
id doaj-art-5c6db2e6f9194a7ba9a839aa87ff853e
institution DOAJ
issn 2075-5309
language English
publishDate 2025-07-01
publisher MDPI AG
record_format Article
series Buildings
spelling doaj-art-5c6db2e6f9194a7ba9a839aa87ff853e2025-08-20T03:02:55ZengMDPI AGBuildings2075-53092025-07-011515264010.3390/buildings15152640Machine Learning-Assisted Sustainable Mix Design of Waste Glass Powder Concrete with Strength–Cost–CO<sub>2</sub> Emissions Trade-OffsYuzhuo Zhang0Jiale Peng1Zi Wang2Meng Xi3Jinlong Liu4Lei Xu5School of Management, Shenyang Jianzhu University, Shenyang 110168, ChinaSchool of Management, Shenyang Jianzhu University, Shenyang 110168, ChinaSchool of Architecture and Urban Planning, Shenyang Jianzhu University, Shenyang 110168, ChinaSchool of Management, Shenyang Jianzhu University, Shenyang 110168, ChinaSchool of Civil Engineering, Southeast University, Nanjing 211189, ChinaLaboratory of Construction Materials, Ecole Polytechnique Fédérale de Lausanne, 1015 Lausanne, SwitzerlandGlass powder, a non-degradable waste material, offers significant potential to reduce cement consumption and carbon emissions in concrete production. However, existing mix design methods for glass powder concrete (GPC) fail to systematically balance economic efficiency, environmental sustainability, and mechanical performance. To address this gap, this study proposes an AI-assisted framework integrating machine learning (ML) and Multi-Objective Optimization (MOO) to achieve a sustainable GPC design. A robust database of 1154 experimental records was developed, focusing on five key predictors: cement content, water-to-binder ratio, aggregate composition, glass powder content, and curing age. Seven ML models were optimized via Bayesian tuning, with the Ensemble Tree model achieving superior accuracy (R<sup>2</sup> = 0.959 on test data). SHapley Additive exPlanations (SHAP) analysis further elucidated the contribution mechanisms and underlying interactions of material components on GPC compressive strength. Subsequently, a MOO framework minimized unit cost and CO<sub>2</sub> emissions while meeting compressive strength targets (15–70 MPa), solved using the NSGA-II algorithm for Pareto solutions and TOPSIS for decision-making. The Pareto-optimal solutions provide actionable guidelines for engineers to align GPC design with circular economy principles and low-carbon policies. This work advances sustainable construction practices by bridging AI-driven innovation with building materials, directly supporting global goals for waste valorization and carbon neutrality.https://www.mdpi.com/2075-5309/15/15/2640sustainable construction materialswaste glasscarbon footprint reductionmulti-objective optimizationmachine learning
spellingShingle Yuzhuo Zhang
Jiale Peng
Zi Wang
Meng Xi
Jinlong Liu
Lei Xu
Machine Learning-Assisted Sustainable Mix Design of Waste Glass Powder Concrete with Strength–Cost–CO<sub>2</sub> Emissions Trade-Offs
Buildings
sustainable construction materials
waste glass
carbon footprint reduction
multi-objective optimization
machine learning
title Machine Learning-Assisted Sustainable Mix Design of Waste Glass Powder Concrete with Strength–Cost–CO<sub>2</sub> Emissions Trade-Offs
title_full Machine Learning-Assisted Sustainable Mix Design of Waste Glass Powder Concrete with Strength–Cost–CO<sub>2</sub> Emissions Trade-Offs
title_fullStr Machine Learning-Assisted Sustainable Mix Design of Waste Glass Powder Concrete with Strength–Cost–CO<sub>2</sub> Emissions Trade-Offs
title_full_unstemmed Machine Learning-Assisted Sustainable Mix Design of Waste Glass Powder Concrete with Strength–Cost–CO<sub>2</sub> Emissions Trade-Offs
title_short Machine Learning-Assisted Sustainable Mix Design of Waste Glass Powder Concrete with Strength–Cost–CO<sub>2</sub> Emissions Trade-Offs
title_sort machine learning assisted sustainable mix design of waste glass powder concrete with strength cost co sub 2 sub emissions trade offs
topic sustainable construction materials
waste glass
carbon footprint reduction
multi-objective optimization
machine learning
url https://www.mdpi.com/2075-5309/15/15/2640
work_keys_str_mv AT yuzhuozhang machinelearningassistedsustainablemixdesignofwasteglasspowderconcretewithstrengthcostcosub2subemissionstradeoffs
AT jialepeng machinelearningassistedsustainablemixdesignofwasteglasspowderconcretewithstrengthcostcosub2subemissionstradeoffs
AT ziwang machinelearningassistedsustainablemixdesignofwasteglasspowderconcretewithstrengthcostcosub2subemissionstradeoffs
AT mengxi machinelearningassistedsustainablemixdesignofwasteglasspowderconcretewithstrengthcostcosub2subemissionstradeoffs
AT jinlongliu machinelearningassistedsustainablemixdesignofwasteglasspowderconcretewithstrengthcostcosub2subemissionstradeoffs
AT leixu machinelearningassistedsustainablemixdesignofwasteglasspowderconcretewithstrengthcostcosub2subemissionstradeoffs