MUMBAI, India, Jan. 9 -- Intellectual Property India has published a patent application (202511115711 A) filed by Thapar Institute Of Engineering And Technology, Patiala, Punjab, on Nov. 22, 2025, for 'a system and method for machine learning-based predictive analysis and multi-objective process optimization in natural fiber reinforced polymer composite manufacturing.'
Inventor(s) include Dr. Rohit Ahuja; Dr. Ratnesh Kumar Raj Singh; Sonali; Archana Singh; and Vijay Chouhan.
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 invention relates to composite manufacturing, integrating a composite fabrication module comprising a fiber pre-processing submodule (employing ball milling using 10 mm balls), a polymer blending submodule, and an extrusion submodule for producing a continuous filament via additive manufacturing. It further encompasses a mechanical testing module for evaluating tensile strength, flexural strength, Young's modulus, and elongation of composite specimens, alongside a data acquisition module capturing input parameters such as fiber type, fiber proportion, resin-hardener ratio, and curing conditions. A synthetic data augmentation module generates validated synthetic data through autoencoder-based latent space perturbation, while a multi-output regression engine-using ensemble stacking of machine learning models including Random Forest, Support Vector Regression, Gaussian Process Regression, and Stepwise Linear Regression with meta-learners like XGBoost-predicts mechanical properties. An explainability module employing SHAP analysis quantifies the influence of input parameters on the predicted outcomes."
Disclaimer: Curated by HT Syndication.
