MUMBAI, India, Jan. 9 -- Intellectual Property India has published a patent application (202541134662 A) filed by Indian Institute Of Technology, Hyderabad, Telangana, on Dec. 31, 2025, for 'system and method for real-time prediction of corrosion-fatigue crack growth rate in metallic structures.'
Inventor(s) include Deepak Joshi; Prasannata Bhange; Sunil Pandu; Kamal Mankari; Swati Ghosh Acharyya; and Amit Acharyya.
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 present disclosure discloses a method and a system for real-time prediction of corrosion-fatigue crack growth rate (CGR) in metallic structures. The system comprises an acoustic emission (AE) sensing module (102) for capturing AE waveforms generated in metallic structure during crack propagation under corrosion-fatigue conditions. Further, a data synchronization module (104) time-aligns metadata associated with the AE waveforms with a fatigue log data. Further, a preprocessing module (106) segments the AE waveforms into fixed-length patches to generate segmented AE waveform data. Further, a neural network module (108) predicts a continuous CGR value associated with each segment of a plurality of segments in the segmented AE waveform data. The neural network module (108) employs multi-head self-attention and positional encoding to capture long-range temporal dependencies. Further, an output interface (110) displays real-time CGR prediction results for use in structural health monitoring of operational assets."
Disclaimer: Curated by HT Syndication.
