MUMBAI, India, July 7 -- Intellectual Property India has published a patent application (202641079485 A) filed by Madhankumar C; Mr A. Vinoth; Mr Santhosh Kannan G; Ms Chaithra S.; Ms Rathna S.; Mr Mohamed Khalif; and Mr Prince Kumar on June 28, 2026, for Ai-Based Predictive Structural Failure Detection System For High-Rise Reinforced Concrete Buildings.
Inventors include Mr A. Vinoth; Mr Santhosh Kannan G; Ms Chaithra S.; Ms Rathna S.; Mr Mohamed Khalif; and Mr Prince Kumar.
The application for the patent was published on July 03, 2026, under issue no. 27/2026.
Abstract: AI-Based Predictive Structural Failure Detection System for High-Rise Reinforced Concrete Buildings Abstract The rapid growth of urbanization has led to the construction of high-rise reinforced concrete (RC) buildings, making structural safety and timely maintenance increasingly critical. Conventional structural health monitoring (SHM) techniques primarily rely on periodic manual inspections, which are often time-consuming, labor-intensive, and incapable of detecting hidden structural deterioration at an early stage. To address these limitations, this study proposes an AI-Based Predictive Structural Failure Detection System for high-rise reinforced concrete buildings that integrates real-time sensor monitoring with advanced artificial intelligence techniques for early failure prediction. The proposed system employs a network of IoT-enabled sensors, including strain gauges, accelerometers, vibration sensors, crack width sensors, tilt sensors, and environmental sensors, to continuously collect structural and environmental data. The acquired data are transmitted to a cloud-based platform, where preprocessing techniques remove noise and normalize the measurements. A hybrid deep learning framework combining Long Short-Term Memory (LSTM) networks and Gradient Boosting algorithms is utilized to analyze temporal structural behavior, identify abnormal patterns, estimate structural degradation, and predict potential failure risks before critical damage occurs. The system further incorporates an intelligent risk assessment module that categorizes the structural condition into multiple safety levels, enabling automated alerts and maintenance recommendations for engineers and building administrators. A digital dashboard provides real-time visualization of structural health indices, crack progression, load distribution, vibration characteristics, and predicted remaining service life. The proposed framework improves prediction accuracy while minimizing false alarms through continuous model learning and adaptive threshold optimization. Performance evaluation demonstrates that the proposed system achieves high prediction accuracy, reduced failure detection time, improved reliability, and enhanced maintenance planning compared with conventional inspection-based approaches. By enabling predictive maintenance and early warning capabilities, the proposed AI-driven framework significantly enhances the safety, resilience, and operational lifespan of high-rise reinforced concrete buildings while reducing maintenance costs and minimizing the risk of catastrophic structural failures. The proposed solution contributes to the advancement of intelligent infrastructure management and supports the development of safer and more sustainable smart cities.
Disclaimer: Curated by HT Syndication.
