ANFIS modelling of the strength properties of natural rubber latex modified concrete
Abstract 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 Ne...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Springer
2025-05-01
|
| Series: | Discover Applied Sciences |
| Subjects: | |
| Online Access: | https://doi.org/10.1007/s42452-025-07040-y |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Abstract 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 (CaSO4) contents on compressive, flexural, and splitting tensile strength. Results showed that an optimal mix of 10% NRL and 2% CaSO4 achieved a compressive strength of 44.27 MPa, while 9% NRL and 1.8% CaSO4 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 R2 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. |
|---|---|
| ISSN: | 3004-9261 |