MUMBAI, India, Jan. 2 -- Intellectual Property India has published a patent application (202541122804 A) filed by Vellore Institute Of Technology, Vellore, Tamil Nadu, on Dec. 5, 2025, for 'hybrid machine learning model for predictive maintenance of vehicle engines.'
Inventor(s) include Dr. N. Sangeetha; and Manimaran R.
The application for the patent was published on Jan. 2, under issue no. 01/2026.
According to the abstract released by the Intellectual Property India: "The present disclosure provides a computer-implemented method (100) for predictive maintenance of vehicle engines. The method includes collecting engine sensor data (102) from sensors monitoring engine parameters, preprocessing the data (104) including handling class imbalance between normal and fault conditions, training base machine learning models in parallel (116, 122) on preprocessed data, combining predictions using a meta-classifier (120, 126) to form a stacking ensemble architecture, and generating an engine condition prediction (124, 128) based on combined predictions. The base models comprise gradient boosting, random forest, adaptive boosting, extreme gradient boosting, support vector machine, categorical boosting, light gradient boosting machine, and extra trees classifiers with meta-classifiers including support vector classifier, logistic regression, and multi-layer perceptron classifier."
Disclaimer: Curated by HT Syndication.
