MUMBAI, India, Sept. 28 -- Intellectual Property India has published a patent application (202641112728 A) filed by Ranjith Kumar P; Sivaadithyan N; Sankarapandian G; and Dr. M. Karpagam on September 20, 2026, for Deep Convolution Neural Network Based Cnc Machine Fault Detection System Using Sound.
Inventors include Ranjith Kumar P; Sivaadithyan N; Sankarapandian G; and Dr. M. Karpagam.
The application for the patent was published on September 25, 2026, under issue no. 39/2026.
Abstract: The present invention relates to a Deep Convolutional Neural Network (DCNN) based CNC Machine Fault Detection System Using Sound for automated monitoring of Computer Numerical Control (CNC) machines. The system acquires acoustic signals generated by the CNC machine during operation and performs signal preprocessing to obtain suitable sound representations. The processed acoustic signals are converted into Mel-spectrograms, which are provided as input to a trained Deep Convolutional Neural Network for automatic extraction of acoustic features and classification of machine operating conditions. The system is configured to identify conditions including normal operation, heavy-load condition, and machine-fault condition. The classified condition is provided through an output interface for real-time monitoring and fault indication. The proposed system provides a non-invasive and automated approach for CNC machine condition monitoring and facilitates early detection of abnormal operating conditions, thereby supporting timely maintenance, reduction of machine downtime, and improved operational efficiency
Disclaimer: Curated by HT Syndication.
