Daily Archives: September 22, 2026

Authors: Vishal Sahu, Sandeep Choudhary

Abstract: Reinforced Cement Concrete (RCC) buildings with floating columns are increasingly adopted in modern urban construction to achieve architectural flexibility, open parking spaces, and large column-free areas. However, the discontinuity introduced by floating columns significantly alters the load transfer mechanism and may adversely affect the structural durability and long-term performance of buildings, particularly under seismic and environmental loading conditions. Recent advances in Artificial Intelligence (AI) provide an opportunity to predict the durability and service life of such complex structural systems more accurately than conventional empirical methods. This review paper presents a comprehensive analysis of AI-based durability prediction techniques for RCC buildings incorporating floating columns, with structural behavior evaluated using STAAD.Pro. The review summarizes the influence of floating column configurations on stress distribution, deflection, drift, and load-carrying capacity, while examining AI approaches such as Artificial Neural Networks (ANN), Machine Learning (ML), Deep Learning (DL), Support Vector Machines (SVM), Random Forest (RF), and ensemble models for predicting durability indicators including crack development, corrosion potential, service life, and structural degradation. The paper also discusses the integration of finite element analysis results obtained from STAAD.Pro with AI algorithms to improve prediction accuracy and facilitate intelligent structural health assessment. Furthermore, existing research gaps, challenges, and future opportunities in AI-assisted durability evaluation are highlighted. The review concludes that the combination of STAAD.Pro-based structural analysis and AI-driven predictive models offers a reliable and efficient framework for enhancing the safety, durability, maintenance planning, and sustainable design of RCC buildings with floating columns. This integrated approach supports data-driven decision-making and contributes to the development of resilient and smart infrastructure.

Published by: vikaspatanker

Authors: Girish Prasad, Professor Vinay Deulkar, Assistant Professor Piyush Mahajan

Abstract: Ultra-High-Performance Concrete (UHPC) is increasingly recognized as an advanced construction material for high-traffic highway pavements because of its outstanding mechanical performance, durability, and extended service life. This review provides a comprehensive assessment of UHPC, covering its development, constituent materials, mix-design principles, mechanical characteristics, durability performance, and recent developments in pavement applications. Particular attention is given to its superior compressive and flexural strength, very low permeability, high abrasion resistance, and enhanced resistance to freeze–thaw cycles and chemical deterioration. These properties make UHPC particularly suitable for pavements subjected to heavy traffic and demanding environmental conditions. Despite these benefits, its wider adoption is constrained by factors such as relatively high initial cost, limited availability of specialized materials, and challenges associated with large-scale construction and implementation. Overall, the reviewed research indicates that UHPC offers considerable potential for improving pavement performance, extending service life, reducing maintenance requirements, and supporting the development of more durable and sustainable highway infrastructure.

 

 

Published by: vikaspatanker

Authors: Krishna Kumar Singh, Professor Vinay W. Deulkar, Professor Piyush Mahajan

Abstract: The rapid growth of freight transportation has increased the need for efficient traffic load scheduling in integrated rail-road freight corridors. Conventional scheduling methods often suffer from poor coordination, traffic congestion, delivery delays, and inefficient resource utilization. This research proposes an Artificial Intelligence (AI)-based Coordinated Traffic Load Scheduling Framework using an Artificial Neural Network (ANN) to predict traffic conditions, freight demand, travel time, and scheduling performance. Historical and simulated transportation data are used to train and validate the ANN model, and the predicted outputs are integrated into a traffic scheduling simulation for intelligent freight allocation and route optimization. The performance of the proposed framework is evaluated using key indicators such as transportation cost, travel time, delivery delay, vehicle utilization, rail utilization, fuel consumption, carbon emissions, and scheduling efficiency. The results demonstrate that the ANN-based approach improves prediction accuracy, optimizes multimodal freight scheduling, reduces operational costs and congestion, and enhances the overall efficiency of rail-road freight transportation. The proposed framework provides an effective and intelligent solution for sustainable freight corridor management and future smart logistics systems.

Published by: vikaspatanker