Copyright © 2025 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{184411,
        author = {Mr. BABUL RAJ},
        title = {Deep Learning Approach for Predicting Microstructural Behavior of Concrete Structures Incorporating Waste Glass and Optical Fibers},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {4},
        pages = {1566-1574},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=184411},
        abstract = {The sustainable development of construction materials requires innovative solutions that utilize industrial by-products and recycled resources. This study investigates the application of waste glass aggregates and synthetic fibers in concrete bricks and employs a deep learning approach to predict their microstructural behavior and mechanical performance. An experimental program was conducted by preparing concrete bricks with varying proportions of glass and fiber, followed by scanning electron microscopy (SEM) and image-based microstructural analysis to evaluate porosity, interfacial transition zone (ITZ), and crack propagation patterns. The extracted datasets were used to train and validate convolutional neural networks (CNNs) and hybrid deep learning models. Results showed that the proposed framework achieved high prediction accuracy (R² = 0.96) compared to conventional regression methods, effectively capturing the correlation between microstructure and compressive strength. Sensitivity analysis revealed that fiber content significantly influenced crack bridging and ductility, while glass aggregates contributed to pore refinement and densification. The outcomes demonstrate the potential of artificial intelligence (AI)-driven models in optimizing mix design, improving durability performance, and supporting sustainable construction practices through the circular utilization of waste materials.},
        keywords = {Deep learning, Concrete bricks, Waste glass aggregates, Fiber reinforcement, Microstructural behavior, CNN, SEM analysis, Sustainable construction, AI prediction, Circular economy},
        month = {September},
        }