MUMBAI, India, Sept. 28 -- Intellectual Property India has published a patent application (202641110924 A) filed by Meenakshi Sundararajan Engineering College on September 16, 2026, for Ai-Driven Sustainable Building System Using Recycled Materials And Thermal Sensors For Optimized Energy Performance And Structural Durability.
Inventors include Dr. Ponni. M; Mr. Ravikumar. N; Mr. Vishnuvardhan. S; Mrs. Jothilakshmi; Mrs. Nirmalamabal. U; Dr. S. Aarthi; Mrs. Saranya. P; Mr. Pradeep S B; Mr. Hari Krishna R S; and Mr D. Thinagaran.
The application for the patent was published on September 25, 2026, under issue no. 39/2026.
Abstract: This invention relates to an AI-driven sustainable building system that integrates recycled construction materials, thermal sensing, real-time data acquisition, and artificial-intelligence based predictive analysis to improve building energy performance and structural durability. The proposed system combines sustainable material selection with an intelligent monitoring and decision-support framework in which thermal sensors are positioned at selected building components, including walls, roofs, floors, structural members, and other thermally significant zones, to continuously measure temperature variations and identify changes in thermal behaviour. Sensor and building-operation data are processed using an AI-based analytical module to estimate thermal loads, detect abnormal temperature patterns, predict energy performance trends, and support adaptive operation of building systems. Sensor-based building monitoring and data-driven energy optimization are established approaches in building research, with the U.S. Department of Energy documenting the use of sensor and meter data for energy-efficiency improvement, fault detection, performance tracking, and thermal-comfort assessment. The system further incorporates recycled and recovered construction materials selected according to relevant engineering, thermal, mechanical, and durability requirements, thereby supporting material-resource efficiency while maintaining required building performance. The AI module can correlate thermal measurements with material characteristics, environmental conditions, occupancy-related variations, and building energy behaviour to identify conditions associated with excessive heat transfer, thermal stress, or deterioration. Predictive analytics can subsequently provide early indications of potential performance degradation and recommend appropriate operational or maintenance actions. Whole-building energy modelling can incorporate construction materials, building geometry, HVAC systems, weather conditions, occupancy, and control strategies, providing a recognized technical basis for evaluating building thermal loads and energy use. The invention therefore establishes an integrated feedback loop in which real-time sensor observations are analysed by AI models and converted into performance and maintenance decisions rather than relying solely on periodic inspection or static design assumptions. Existing research also demonstrates the growing application of AI, IoT sensing, predictive analytics, anomaly detection, and adaptive control in smart and sustainable buildings, while identifying the need for greater system-level integration and real-world validation. By combining recycled-material-based construction with continuous thermal monitoring and AI-assisted prediction, the proposed system is configured to reduce unnecessary energy consumption, improve thermal management, support timely identification of abnormal building behaviour, and enhance long-term structural performance. The system may further generate performance indicators, alerts, predictive maintenance recommendations, and optimized operating parameters based on continuously acquired building data. Accordingly, the invention provides a unified technological framework for developing sustainable, energy aware, sensor-enabled, and data-driven buildings while addressing both operational energy performance and durability-related monitoring requirements.
Disclaimer: Curated by HT Syndication.
