Journal of Science and Transport Technology

Metaheuristic-Enhanced Machine Learning for Accurate Shear Strength Assessment of RC Deep Beams

2025-09-18T09:39:31+00:00

Extensive testing required by traditional structural engineering methods can be time-consuming and costly due to the complexity of the procedures involved. This work presents a novel machine learning approach for predicting the shear strength of reinforced concrete (RC) deep beams. It employs a Gradient Boosting (GB) algorithm, optimized using metaheuristic techniques, specifically the Golden Jackal Optimization (GJO) and Honey Badger Algorithm (HBA). To develop this approach, a comprehensive dataset of 314 experimentally tested RC deep beams with web openings was compiled from peer-reviewed literature. The dataset includes key features governing the shear strength. The GB model's hyperparameters were fine-tuned using GJO and HBA, with the GJO-optimized model (GB_06) showing superior performance. It achieved a coefficient of determination (R²) of 0.9664 and a root mean squared error (RMSE) of 70.258 kN on the test dataset. Feature importance analysis using SHAP values identified the shear span-to-depth ratio, horizontal web reinforcement ratio, and vertical web reinforcement ratio as the key factors influencing shear strength. The proposed model offers significant improvements in accuracy and reliability, providing structural engineers with an efficient tool for design optimization and safety assessment of RC deep beams.

Forensic Geotechnical Evaluation of Challenges in Constructing the Flood Protection Infrastructure (Wall) at Kadana Powerhouse, Gujarat, India

2025-10-05T17:06:10+00:00

This paper presents a forensic geotechnical evaluation of the construction challenges and long-term stability of a 34-meter-high flood protection (FP) infrastructure (wall) at the Kadana Powerhouse, Gujarat, India, built within a geologically complex terrain. Following a critical design shift from underground draft tube tunnels to a cut-and-cover system necessitated by construction delays and adverse rock mass conditions previously confined slopes were exposed, revealing weak fault and foliation planes dipping unfavorably toward the excavation face. Emergency stabilization measures, including pre-stressed anchors and Perfo-bolts, were deployed to arrest progressive instability during construction. Nearly four decades later, a back-analysis incorporating 2D stability modeling, based on historical performance data was conducted to evaluate the long-term efficacy of these interventions. The analysis confirmed a notable improvement in the Factor of Safety (FOS) from 1.099 to 1.578 for sliding and from 3.053 to 4.048 for overturning, validating the adequacy of the original design response. The novelty of this study lies in its integration of retrospective analysis and performance monitoring to assess legacy infrastructure a rarely documented forensic geotechnical case of FP wall from India. The findings underscore the importance of integrating geological insight with adaptive engineering during both the design and construction phases and offer valuable guidance for future infrastructure development in weak or structurally disturbed rock masses.

Laboratory assessment of fly ash in compressive strength, abrasion-resistant and low-carbon concrete for slope erosion control

2025-10-09T09:30:07+00:00

Concrete is essential for landslide prevention and slope stabilization, requiring high durability and abrasion resistance. This study evaluates fly ash as a cement replacement to improve abrasion resistance, maintain M35 (35 MPa) strength, and reduce carbon emissions for sustainable construction. The methodology includes material characterization and testing of concrete properties such as compressive strength, abrasion resistance, and water permeability. Experimental results show that the 90-day compressive strength meets the M35 standard, ranging from 39.9 to 41.1 MPa. Water permeability resistance improves from 10 to 12 atm with fly ash addition. The lowest abrasion loss (4.6%) and minimal wear depth (0.5 cm) occur at 30% fly ash replacement after six test cycles (72 hours). Carbon emissions are reduced by 9.5% to 46.8%, depending on the replacement level. The study identifies the optimal mix as 30% fly ash replacement (F30P1.1), which achieves M35-grade concrete, the best abrasion resistance, and a significant 28.4% reduction in CO₂ emissions compared to concrete without fly ash. These findings have practical implications for the construction industry, particularly in the context of sustainable materials and environmental benefits.