MUMBAI, India, Jan. 9 -- Intellectual Property India has published a patent application (202511114267 A) filed by IMS Engineering College, Ghaziabad, Uttar Pradesh, on Nov. 18, 2025, for 'artificial intelligence-based system and method for numerical solution of ordinary differential equations.'
Inventor(s) include Anil Kumar; Ram Bharat Singh; and Sanjay Kumar Tiwari.
The application for the patent was published on Jan. 9, under issue no. 02/2026.
According to the abstract released by the Intellectual Property India: "The present invention discloses an artificial intelligence-based system and method for obtaining accurate and efficient numerical solutions of ordinary differential equations (ODEs). The invention employs a hybrid computational framework that integrates physics-informed neural networks (PINNs), reinforcement learning, and genetic algorithms to approximate solutions without explicit discretization. The system dynamically learns the functional behavior of ODEs under given initial or boundary conditions while minimizing residual differential errors through adaptive optimization. A self-learning error estimator continuously evaluates convergence and refines model parameters to enhance accuracy and stability. The invention is applicable to linear, nonlinear, stiff, and high-dimensional ODEs across scientific and engineering domains, providing superior performance compared to conventional numerical solvers."
Disclaimer: Curated by HT Syndication.
