MUMBAI, India, Feb. 6 -- Intellectual Property India has published a patent application (202641007391 A) filed by JNTUH, Hyderabad, Telangana, on Jan. 25, for 'method and system for multi-hazard structural analysis and risk assessment of compartmental silos using finite element modeling and machine learning.'
Inventor(s) include Mr. V. Purushotham; Dr. B. D. V. Chandra Mohan Rao; and Dr. P. Srinivasa Rao.
The application for the patent was published on Feb. 6, under issue no. 06/2026.
According to the abstract released by the Intellectual Property India: "This invention relates to a method and system for multi-hazard structural analysis and risk assessment of compartmental silo structures used for bulk material storage in industrial applications. Compartmental silos are subjected to complex loading conditions arising from self-weight, material-induced lateral pressures, wind forces, and seismic excitations, which collectively influence their structural performance. Conventional design and analysis approaches often consider these loads independently and rely on simplified assumptions, resulting in limited accuracy in predicting stress distribution, deformation behavior, and potential failure mechanisms in multi-compartment configurations. The invention provides an integrated analytical framework that employs three-dimensional finite element modeling to accurately represent the geometry, boundary conditions, and inter-compartment connectivity of silo structures. Realistic modeling of material pressure distribution is incorporated to capture material-structure interaction effects that dominate silo behavior during operation. The system systematically evaluates individual and combined loading scenarios to identify governing conditions and critical response parameters such as stresses, bending moments, and displacements. In addition to physics-based structural analysis, the invention integrates machine learning techniques for intelligent risk assessment. Structural response data generated from finite element simulations are utilized to train predictive models capable of identifying vulnerability patterns and estimating structural risk under varying hazard intensities. This data-driven capability enhances the reliability of performance evaluation and supports proactive identification of critical structural regions. The invention further incorporates cross-platform validation procedures to ensure consistency and accuracy of analytical results within acceptable engineering tolerances. By combining validated numerical modeling with intelligent predictive analytics, the invention provides a robust decision-support system for structural design, evaluation, and optimization of compartmental silos. The proposed method and system improve confidence in structural safety assessments, support efficient design and retrofitting strategies, and contribute to the development of resilient and reliable bulk material storage infrastructure subjected to multi-hazard environments."
Disclaimer: Curated by HT Syndication.
