ANFIS modelling of the strength properties of natural rubber latex modified concrete

The increasing demand for sustainable construction materials has driven research into innovative modifications to enhance concrete performance while reducing environmental impact. This study investigates the optimization of Natural Rubber Latex Modified Concrete (NRLMC) using an Adaptive Neuro-Fuzzy...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Discover applied sciences Jg. 7; H. 5; S. 472 - 37
Hauptverfasser: Nyah, Efiok Etim, Onwuka, David Ogbonna, Arimanwa, Joan Ijeoma, Alaneme, George Uwadiegwu, Nakkeeran, G., Onwuka, Ulari Sylvia, Okere, Chinenye Elizabeth
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Cham Springer International Publishing 09.05.2025
Springer Nature B.V
Springer
Schlagworte:
Accuracy
Adaptive systems
Algorithms
Aluminum
Applied and Technical Physics
Artificial intelligence
Calcium sulfate
Cement
Chemistry/Food Science
Compressive strength
Concrete mixing
Concrete structures
Construction
Destabilization
Durability
Earth Sciences
Engineering
Environment
Environmental impact
Fuzzy logic
Green infrastructure
Latex
Machine learning
Materials Science
Mechanical properties
Microstructural analysis
Natural rubber
Natural rubber latex
Neural networks
Neuro-fuzzy models
Optimization
Porosity
Regression analysis
Renewable resources
Research methodology
Resource utilization
Rubber
Scanning electron microscopy
Splitting
Sustainability
Sustainable concrete
Sustainable development
Sustainable materials
Tensile properties
Tensile strength
X-ray spectroscopy
Artificial intelligence
Neuro-fuzzy models
Natural rubber latex
Sustainable concrete
ISSN:3004-9261, 2523-3963, 3004-9261, 2523-3971
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:The increasing demand for sustainable construction materials has driven research into innovative modifications to enhance concrete performance while reducing environmental impact. This study investigates the optimization of Natural Rubber Latex Modified Concrete (NRLMC) using an Adaptive Neuro-Fuzzy Inference System (ANFIS), a hybrid AI model that integrates fuzzy logic and neural networks for precise property prediction. The justification for this study stems from the need for an eco-friendly, high-performance alternative to conventional concrete, leveraging renewable natural rubber latex (NRL) to improve mechanical properties and durability. Laboratory experiments were conducted to evaluate the effects of varying NRL and calcium sulfate (CaSO 4 ) contents on compressive, flexural, and splitting tensile strength. Results showed that an optimal mix of 10% NRL and 2% CaSO 4 achieved a compressive strength of 44.27 MPa, while 9% NRL and 1.8% CaSO 4 yielded peak flexural and splitting tensile strengths of 12.33 MPa and 5.1 MPa, respectively. Beyond these thresholds, mechanical properties declined due to matrix destabilization. Microstructural analysis using Scanning Electron Microscopy and Energy Dispersive X-ray Spectroscopy confirmed NRL’s role in reducing porosity and enhancing matrix uniformity. The ANFIS model demonstrated exceptional accuracy, with low RMSE and MAPE values and a strong R 2 correlation, offering a superior predictive framework compared to traditional modeling techniques. Furthermore, SHAP analysis reveals that OPC (%) and NRL (%) are the primary contributors to compressive and tensile strength, while CaSO4 (%) has a moderate impact, particularly on flexural and tensile properties, providing valuable insights for optimizing material composition in construction applications. This research holds significant implications for sustainable infrastructure development, promoting renewable resource utilization while enhancing the durability and resilience of concrete structures. Future studies should explore hybrid AI models, long-term field performance, and additional material combinations to further optimize NRLMC’s applicability in various structural environments. Article Highlights The study optimizes Natural Rubber Latex Modified Concrete (NRLMC) using ANFIS, demonstrating improved mechanical properties with an optimal mix of 10% NRL and 2% CaSO 4 . Microstructural analysis (SEM/EDS) confirms reduced porosity and enhanced matrix uniformity, while SHAP analysis identifies OPC and NRL as key contributors to strength. The ANFIS model shows high predictive accuracy, supporting AI-driven material optimization for sustainable and durable concrete applications.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:3004-9261
2523-3963
3004-9261
2523-3971
DOI:10.1007/s42452-025-07040-y