MUMBAI, India, Jan. 2 -- Intellectual Property India has published a patent application (202541122245 A) filed by Vellore Institute Of Technology, Vellore, Tamil Nadu, on Dec. 4, 2025, for 'hybrid cnn-bilstm system for aircraft engine failure prediction system.'
Inventor(s) include Dr Perepi Rajarajeswari; Dereddy Maheswararedd Y; Kanala Chanikya Reddy; and Chandra Vignan.
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 system for aircraft engine failure prediction comprising a data acquisition module configured to collect multivariate time-series sensor data from aircraft engines, a hybrid deep learning model comprising a convolutional neural network module configured to extract spatial features and a bidirectional long short-term memory network module configured to capture temporal dependencies, and a prediction output module configured to generate failure predictions. The system processes sensor data from twenty-one sensors monitoring temperature, pressure, vibration, and rotational speed through data preprocessing including cleaning, feature scaling, and time-series segmentation to generate preprocessed sequences of fifty timesteps with twenty-five features per timestep. The convolutional neural network module applies sixty-four convolutional filters with kernel size of three followed by max pooling, while the bidirectional long short-term memory network module comprises two layers with sixty-four units each."
Disclaimer: Curated by HT Syndication.
