Advancing 3D-printed fiber-reinforced concrete for sustainable construction: A comparative optimization based study of hybrid machine intelligence models for predicting mechanical strength and CO₂ emissions
Source abstract
Abstract
With the increasing demand for sustainable and resilient marine infrastructure in marine environments, 3D printing technologies offer a promising solution for fabricating customized, durable components under challenging conditions. 3D-printed fiber-reinforced concrete (3DPFRC) presents significant potential for rapid, waste-reducing construction of complex geometries, making it suitable for marine structures such as sea walls, breakwaters, underwater pipelines, and floating platforms. However, optimizing 3DPFRC for mechanical performance and environmental sustainability remains a complex challenge. This study proposes advanced machine learning (ML) models to simultaneously predict compressive strength and CO₂ emissions of 3DPFRC, enabling both mechanical and environmental performance evaluation. A user-friendly graphical user interface (GUI) was also developed to facilitate practical deployment by engineers without programming expertise. Four hybrid ML models were evaluated: CNN-LSTM, RA-PSO, XGBoost-PSO, and SVM-PSO. RA-PSO outperformed others with an R² of 0.9819 (training) and 0.9674 (testing) for compressive strength and 0.97 (training) and 0.94 (testing) for CO₂ emissions, alongside the lowest MSE (48.24 MPa²) and highest F1-score (0.9519). This superior performance is primarily due to RA-PSO’s adaptive parameter tuning and randomized search, which maintain population diversity and prevent premature convergence, enabling the model to capture complex nonlinear interactions in 3DPFRC mix parameters. Sensitivity analysis revealed that water content (34 %), silica fume (30 %), and the water-to-binder ratio (23 %) were the most influential parameters on compressive strength. These findings confirm RA-PSO as a highly reliable tool for optimizing 3DPFRC mix designs while minimizing environmental impact, particularly in Sustainable Marine and Civil Infrastructure Applications.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Innovations in Concrete and Construction Materials · BIM and Construction Integration · Additive Manufacturing and 3D Printing Technologies
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (100+)
Show source-provided references
1. Interpretable machine learning for predicting the strength of 3D printed fiber-reinforced concrete (3DP-FRC)
2. Exploring the fresh and rheology properties of 3D printed concrete with fiber reinforced composites (3DP-FRC): a novel approach using machine learning techniques10.1088/2053-1591/ad9890 ↗
3. Study on printability of 3D printing carbon fiber reinforced eco-friendly concrete: characterized by fluidity and consistency
4. An integrated topology optimization method including manufacturing constraints for 3D printed fiber-reinforced concrete structures10.1016/j.matlet.2023.135442 ↗
5. Casagrande · 3D Concr. Print. a N. Era Constr. Ind. · 2020
6. A novel compressive strength estimation approach for 3D printed fiber-reinforced concrete: integrating machine learning and gene expression programming10.1007/s41939-024-00439-x ↗
7. Prediction of shear behavior of glass FRP bars-reinforced ultra-highperformance concrete I-shaped beams using machine learning10.1007/s10999-023-09675-4 ↗
8. Geopolymer 3D printing: a comprehensive review on rheological and structural performance assessment, printing process parameters, and microstructure10.3389/fmats.2023.1241869 ↗
9. Infrastructure-Oriented efficient materials implemented with fibers10.3390/buildings15040609 ↗
10. Brunjes · Crit. Eval. Constr. Ind. Relat. Addit. Manuf. Res. A Scientometr. Anal. · 2022
11. Hybrid supervised and Self-Supervised learning for 3D printing optimization: a masked supervised bootstrap your own latent approach10.1089/3dp.2024.0211 ↗
12. P. Ni, F. Lei, H. Zheng, J. Song, Z. Zheng, G. Qin, and Z. Yan, Multi-Dimensional Coupled Evaluation and Prediction Of Solar Energy Utilization Indicators on Building Surfaces, Zhuoxin and Qin, Guojin and Yan, Zengfeng, Multi-Dimensional Coupled Evaluation and Prediction Of Solar Energy Utilization Indicators on Building Surfaces.
13. Large-scale 3D printing concrete technology: current status and future opportunities10.1016/j.cemconcomp.2021.104115 ↗
14. Comprehensive review of 3D printed concrete, life cycle assessment, AI and ML models: materials, engineered properties and techniques for additive manufacturing10.1007/978-981-96-5618-9 ↗
15. Concrete 3D printing technology in sustainable construction: a review on raw materials, concrete types and performances
16. Overview of the development of 3D-printing concrete: a review10.3390/app11219822 ↗
17. Exploring the environmental benefits of 3D printing technology in concrete construction; a review10.1007/s40964-024-00622-z ↗
18. 3D printing concrete structures: state of the art, challenges, and opportunities10.1016/j.conbuildmat.2023.133364 ↗
19. Recent developments on low carbon 3D printing concrete: revolutionizing construction through innovative technology10.1016/j.clema.2024.100251 ↗
20. Technology readiness: a global snapshot of 3D concrete printing and the frontiers for development10.1016/j.cemconres.2022.106774 ↗
21. Effect of concrete surface roughness on shear strength of frozen soil–concrete interface based on 3D printing technology10.1016/j.conbuildmat.2022.130158 ↗
22. Use of industrial waste materials for 3D printing of sustainable concrete: a review10.1016/j.jclepro.2022.130749 ↗
23. Constraints and limitations of concrete 3D printing in architecture
24. Sustainable Non-Conventional concrete 3D Printing—A review10.3390/su151310121 ↗
25. A critical review on reducing the environmental impact of 3D printing concrete: material preparation, construction process and structure level10.1016/j.conbuildmat.2023.133887 ↗
26. Prediction of bending strength in ECC-RC composite beams using machine learning-based models10.1108/IJSI-11-2024-0186 ↗
27. K. ABDALGADER, Machine learning approach for predicting the compressive and flexural strengths of fiber-reinforced concrete mixtures, Materials Research Proceedings, vol. 48.
28. Compressive strength prediction of sustainable concrete incorporating rice husk ash (RHA) using hybrid machine learning algorithms and parametric analyses
29. Quantifying compressive strength in limestone powder incorporated concrete with incorporating various machine learning algorithms with SHAP analysis10.1007/s42107-024-01219-1 ↗
30. Forecasting the strength of preplaced aggregate concrete using interpretable machine learning approaches10.1038/s41598-024-57896-0 ↗
31. Strength prediction of smart cementitious materials using a neural network optimized by particle swarm algorithm10.3390/buildings14072033 ↗
32. Artificial intelligence in materials science and modern concrete technologies: analysis of possibilities and prospects10.1134/S2075113324700783 ↗
33. Trustworthy machine learning-enhanced 3D concrete printing: predicting bond strength and designing reinforcement embedment length10.1016/j.autcon.2024.105754 ↗
34. Performance evaluation of conductive materials in conductive mortar based on machine learning
35. Modified particle packing approach for optimizing waste marble powder as a cement substitute in high-performance concrete10.1016/j.conbuildmat.2023.133845 ↗
36. P. Ni, F. Lei, H. Zheng, J. Song, Z. Zheng, Z. Yan, and G. Qin, Multi-Dimensional Coupled Evaluation and Prediction Of Solar Energy Utilization Indicators on Building Surfaces: A Case Study on Non-Enriched Area, China, Zengfeng and Qin, Guojin, Multi-Dimensional Coupled Evaluation and Prediction Of Solar Energy Utilization Indicators on Building Surfaces: A Case Study on Non-Enriched Area, China.
37. A review of machine learning (ML) and explainable artificial intelligence (XAI) methods in additive manufacturing (3D printing)10.1016/j.mtcomm.2024.110294 ↗
38. Artificial intelligence in 3D printing
39. Machine learning in 3D printing
40. Research status and prospect of machine learning in construction 3D printing
41. Accelerating 3D printing of pharmaceutical products using machine learning
42. A data-driven machine learning approach for the 3D printing process optimisation10.1080/17452759.2022.2068446 ↗
43. Data-driven models for predicting compressive strength of 3D-printed fiber-reinforced concrete using interpretable machine learning algorithms
44. Effects of binder component and curing regime on compressive strength, capillary water absorption, shrinkage and pore structure of geopolymer mortars10.1016/j.conbuildmat.2024.137707 ↗
45. A systematic research on foamed concrete: the effects of foam content, Fly ash, slag, silica fume and water-to-binder ratio10.1016/j.conbuildmat.2022.127683 ↗
46. Bioadhesive behaviors of HPMC E5: comparative analysis of various techniques, histological and human radiological evidence10.1038/s41598-024-52144-x ↗
47. Influence of fibers on the mechanical properties and durability of ultra-high-performance concrete: a review
48. Influence of graded coarse aggregate content and specific surface area on the fracture properties of asphalt mixtures based on discrete element simulations and indoor tests10.1016/j.conbuildmat.2021.123942 ↗
49. Combination of support vector machine and K-Fold cross validation to predict compressive strength of concrete in marine environment10.1016/j.conbuildmat.2019.02.071 ↗
50. Back-propagation neural network optimized by K-fold cross-validation for prediction of torsional strength of reinforced concrete beam10.3390/ma15041477 ↗
51. Geopolymer concrete compressive strength via artificial neural network, adaptive neuro fuzzy interface system, and gene expression programming with K-fold cross validation10.3389/fmats.2021.621163 ↗
52. Predictive model for erosion rate of concrete under wind gravel flow based on K-Fold Cross-Validation combined with support vector machine10.3390/buildings15040614 ↗
53. Predictive analysis of foam concrete compressive strength: a comparative study of OLS and SVR with K-fold validation10.1007/s42107-023-00931-8 ↗
54. Smaller is better? Unduly nice accuracy assessments in roof detection using remote sensing data with machine learning and k-fold cross-validation10.1016/j.heliyon.2023.e14045 ↗
55. Evolutionary optimization of machine learning algorithm hyperparameters for strength prediction of high-performance concrete10.1007/s42107-023-00698-y ↗
56. Predicting concrete compressive strength using hybrid ensembling of surrogate machine learning models10.1016/j.cemconres.2021.106449 ↗
57. A comparative investigation using machine learning methods for concrete compressive strength estimation
58. Machine learning in concrete science: applications, challenges, and best practices10.1038/s41524-022-00810-x ↗
59. Machine learning in concrete technology: a review of current researches, trends, and applications10.3389/fbuil.2023.1145591 ↗
60. Machine learning techniques in concrete mix design10.3390/ma12081256 ↗
61. Efficient machine learning models for prediction of concrete strengths10.1016/j.conbuildmat.2020.120950 ↗
62. A hybrid model based on convolution neural network and long short-term memory for qualitative assessment of permeable and porous concrete
63. A deep hybrid learning model to detect unsafe behavior: integrating convolution neural networks and long short-term memory10.1016/j.autcon.2017.11.002 ↗
64. Compressive strength prediction of high-strength concrete using long short-term memory and machine learning algorithms10.3390/buildings12030302 ↗
65. Application of novel hybrid deep learning architectures combining convolutional neural networks (CNN) and recurrent neural networks (RNN): construction duration estimates prediction considering preconstruction uncertainties10.1088/2631-8695/ad6ca7 ↗
66. High-speed railway seismic response prediction using CNN-LSTM hybrid neural network10.1007/s13349-023-00758-6 ↗
67. Attention-based hybrid convolutional-long short-term memory network for bridge pier hysteresis and backbone curves prediction
68. A prediction of precipitation data based on support vector machine and particle swarm optimization (PSO-SVM) algorithms10.3390/a10020057 ↗
69. A hybrid detection model for acute lymphocytic leukemia using support vector machine and particle swarm optimization (SVM-PSO)10.1038/s41598-024-74889-1 ↗
70. Comparison of debris flow susceptibility assessment methods: support vector machine, particle swarm optimization, and feature selection techniques10.1007/s11629-023-8395-9 ↗
71. New cardiovascular disease prediction approach using support vector machine and quantum-behaved particle swarm optimization10.1007/s11042-023-16194-z ↗
72. Hybrid of jellyfish and particle swarm optimization algorithm-based support vector machine for stock market trend prediction10.1016/j.asoc.2024.111394 ↗
73. A comprehensive survey of evolutionary algorithms and metaheuristics in brain EEG-based applications10.1088/1741-2552/ad7f8e ↗
74. Kinematic optimization of a robotic arm for automation tasks with human demonstration
75. Exploring the potential of machine learning in stochastic reliability modelling for reinforced soil foundations10.3390/buildings14040954 ↗
76. PRECISE-RA: predicting remission and StratifyingRisk in rheumatoid arthritis patients treated withbDMARDs—A
77. Compressive strength of bentonite concrete using state-of-the-art optimised XGBoost models
78. Predicting bentonite swelling pressure: optimized XGBoost versus neural networks10.1038/s41598-024-68038-x ↗
79. Developing two robust hybrid models for predicting tunnel deformation in squeezing prone grounds10.1016/j.trgeo.2024.101231 ↗
80. M. Ghadamyari, Advancing Energy Forecasting: Integrating Data Mining and Hybrid Machine Learning Techniques for Enhanced Peak Load and Demand Prediction, Available at SSRN 4764479.
81. Enhancing rock fragmentation assessment in mine blasting through machine learning algorithms: a practical approach10.1007/s42452-024-05888-0 ↗
82. A feature restoration for machine learning on anti-corrosion materials10.1016/j.cscee.2024.100902 ↗
83. A novel data-driven machine learning techniques to predict compressive strength of Fly ash and recycled coarse aggregates based self-compacting concrete
84. Leveraging a hybrid machine learning approach for compressive strength estimation of Roller-Compacted concrete with recycled aggregates10.3390/math12162542 ↗
85. Prediction of ultimate strength and strain in FRP wrapped oval shaped concrete columns using machine learning10.1038/s41598-025-95272-8 ↗
86. Developing machine learning models to predict the Fly ash concrete compressive strength10.1007/s42107-024-01125-6 ↗
87. Modelling the mechanical properties of concrete produced with polycarbonate waste ash by machine learning10.1038/s41598-024-62412-5 ↗
88. Optimized machine learning models for predicting the tensile strength of high-performance concrete
89. Machine learning based models for predicting compressive strength of geopolymer concrete10.1007/s11709-024-1039-5 ↗
90. Prediction of compressive strength and portland cement composition using cross-validation and feature ranking techniques10.1016/j.conbuildmat.2019.07.224 ↗
91. Prediction of concrete compressive strength using non-destructive test results
92. Development of the new prediction models for the compressive strength of nanomodified concrete using novel machine learning techniques10.3390/buildings12122160 ↗
93. Different machine learning approaches to predict the compressive strength of composite cement concrete
94. Concrete compressive strength classification using hybrid machine learning models and interactive GUI10.1007/s41062-025-01983-2 ↗
95. Classification of concrete compressive strength using machine learning methods
96. Performance of Fine-Tuning techniques for multilabel classification of surface defects in reinforced concrete bridges10.3390/app15094725 ↗
97. Machine Learning-Based rapid prediction method of failure mode for reinforced concrete column10.5000/EESK.2024.28.2.113 ↗
98. Advanced predictive modeling of concrete compressive strength and slump characteristics: a comparative evaluation of BPNN, SVM, and RF models optimized via PSO10.3390/ma17194791 ↗
99. Cement-based grouting material development and prediction of material properties using PSO-RBF machine learning10.1016/j.conbuildmat.2024.135328 ↗
100. Investigation of optimized machine learning models with PSO for forecasting the shear capacity of steel fiber-reinforced SCC beams with/out stirrups