MUMBAI, India, July 11 -- Intellectual Property India has published a patent application (202521059689 A) filed by Priyanka V. Deshmukh; Rajesh V. Rajkolhe; and Dr. Sanjay S. Bhagwat, Amravati, Maharashtra, on June 21, for 'adaptive ensemble machine learning framework for predicting acceptance rate in green sand casting processes.'
Inventor(s) include Priyanka V. Deshmukh; Rajesh V. Rajkolhe; and Dr. Sanjay S. Bhagwat.
The application for the patent was published on July 11, under issue no. 28/2025.
According to the abstract released by the Intellectual Property India: "The present invention discloses a Dynamic Adaptive Weighted Ensemble (DAWE) Framework for predicting the acceptance rate of castings in green sand casting processes. This machine learning framework intelligently combines XGBoost, LightGBM, and Random Forest models through an adaptive weighting mechanism that dynamically adjusts model influence based on performance. By analyzing process parameters including mold hardness, moisture content, and permeability, the DAWE Framework predicts the percentage of conforming castings per production batch with enhanced accuracy. The framework incorporates cross-validation and continuous model re-evaluation, demonstrating superior forecasting performance compared to traditional methods. This innovation enables proactive quality optimization and waste reduction in industrial manufacturing."
Disclaimer: Curated by HT Syndication.
