Intellectual Property India Publishes Patent Application for System And Method For Concrete Mix Design Optimization Using Machine Learning-Based Strength Prediction And Particle Swarm Optimization

MUMBAI, India, July 30 -- Intellectual Property India has published a patent application (202641086878 A) filed by Vellore Institute Of Technology on July 16, 2026, for System And Method For Concrete Mix Design Optimization Using Machine Learning-Based Strength Prediction And Particle Swarm Optimization.

Inventors include Abdul Rahim A; and Madhumitha S K.

The application for the patent was published on July 24, 2026, under issue no. 30/2026.

Abstract: A computer-implemented system (100) for concrete mix design optimization is provided. The system (100) includes a processor (102), a memory (104), an input unit (106), a feature engineering unit (108), a machine learning-based prediction unit (110), a Particle Swarm Optimization (PSO) unit (112), and a result management unit (114). The input unit (106) receives user-defined material constraints comprising minimum and maximum allowable values of concrete constituent materials and a target compressive strength range. The feature engineering unit (108) computes derived mix parameters including water-to-cement ratio and material proportion ratios. The prediction unit (110) predicts compressive strength values for candidate concrete mix combinations using a trained Extreme Gradient Boosting (XGBoost) regression model. The PSO unit (112) optimizes proportions of the concrete constituent materials based on the predicted compressive strength values and the target compressive strength range. The result management unit (114) stores optimized concrete mix designs and corresponding predicted performance values in a consolidated dataset. FIG. 1

Disclaimer: Curated by HT Syndication.