Volume 87 Issue 07
Research article, Type: Subscription; Page: 01-17;
Received: 28 February 2026 / Revised: 25 April 2026 / Accepted: 20 June 2026 / Published: 05 July 2026
Title: AI-Driven Compressive Strength Prediction and Environmental Optimization of Ultra-High-Performance Concrete (UHPC) Incorporating Recycled
Author: Juntem Yam, Tuijun Wang, Zinran Dong, Lenhao Zhou, Ivan Matnez-Vatuena & Dugge Yang
Abstract: The construction industry faces immense pressure to mitigate carbon emissions while simultaneously enhancing infrastructural resilience. Ultra-High-Performance Concrete (UHPC) offers superior mechanical strength and durability, but its extensive cement content results in a heavy environmental footprint. This study presents an innovative, data-driven approach to optimize eco-friendly UHPC mixtures by replacing conventional fine aggregates with recycled industrial by-products and construction waste. Leveraging Machine Learning (ML) algorithms—specifically Gradient Boosting and Random Forest architectures—a predictive model was developed using a dataset of 1,200 mix designs to forecast 28-day compressive strength with an accuracy exceeding 94%. The experimental results validate that optimizing particle packing density offsets the typical strength degradation associated with recycled aggregates. Furthermore, the lifecycle assessment confirms a 35% reduction in embodied carbon compared to standard UHPC formulations, positioning this material as a viable candidate for sustainable, high-load.………….. [For more click here]
Keywords: Ultra-High-Performance Concrete (UHPC), Machine Learning, Recycled Aggregates, Embodied Carbon, Compressive Strength Prediction, Sustainable Infrastructure
Research article, Type: Subscription; Page: 17-30;
Received: 05 March 2026 / Revised: 26 April 2026 / Accepted: 25 June 2026 / Published: 13 July 2026
Title: Sustainable Ultra-High-Performance Concrete Using Recycled Glass Cullet and Volcanic Ash
Author: Roushan Kumar & Manjeet Kashyap
Abstract: Cement production contributes significantly to global carbon dioxide emissions. This study investigates the development of eco-friendly Ultra-High-Performance Concrete (UHPC) by replacing conventional silica flour and a portion of Ordinary Portland Cement (OPC) with recycled glass cullet and natural volcanic ash. Standard UHPC mixes rely heavily on fine quartz powders, which pose respiratory health risks during processing and carry high environmental costs. In this research, finely crushed recycled waste glass entirely replaces silica flour, acting as a micro-filler. Simultaneously, volcanic ash replaces up to 30% of OPC by weight to exploit its natural pozzolanic properties. Experimental testing evaluates compressive strength, flexural strength, and microstructure development at 7, 28, and 90 days. Durability performance is assessed through chloride permeability and water absorption tests..………….. [For more click here]
Keywords: Recycled glass cullet, Volcanic ash, Pozzolanic reaction, Sustainable construction materials, Microstructure analysis
Research article, Type: Subscription; Page: 31-51;
Received: 31 March 2026 / Revised: 16 May 2026 / Accepted: 18 June 2026 / Published: 20 July 2026
Title: Autonomous Structural Health Monitoring of Aging Bridges Using UAV Swarms and Deep Learning
Author: Nilesh Choudhary & Asish Thakur
Abstract: Aging transportation infrastructure requires frequent, high-precision inspections to prevent catastrophic failures. Traditional manual inspection methods are labor-intensive, subjective, and dangerous for personnel. This research presents an automated framework for structural health monitoring (SHM) using a cooperative swarm of Unmanned Aerial Vehicles (UAVs) integrated with deep learning algorithms. The proposed system deploys multiple small UAVs equipped with high-resolution optical and thermal cameras to dynamically map concrete bridge structures. A decentralized flocking algorithm ensures collision-free, optimal coverage of the bridge components. The captured imagery is processed in real-time using a customized Convolutional Neural Network (CNN) optimized for pixel-level segmentation of structural defects, including fatigue cracks, concrete spalling, and rebar corrosion. Field testing on a decommissioned reinforced concrete girder bridge demonstrates that the UAV swarm reduces inspection time by 65% compared to single-drone operations. The deep learning model achieves a 94.2% Intersection over Union (IoU) score in detecting sub-millimeter surface cracks…………….. [For more click here]
Keywords: Structural Health Monitoring, UAV swarms, Deep learning, Crack segmentation, Bridge inspection, Computer vision