MUMBAI, India, Feb. 27 -- Intellectual Property India has published a patent application (202641017974 A) filed by G Ashwin Prabhu; Mrs. M. Dharani; Mr. Kannakumar K; Dr. M. Kalaimani; Dr. K. M. Kumar; Dr. A. X. Amal Rebin; Dr. Vidhika Tiwari; Mr. G. V. Dellibabu; and Mr. R B Senthilrajan, Chennai, Tamil Nadu, on Feb. 18, for 'smart robotic system with ai integration for automated inspection and quality control of composite components in mechanical engineering.'
Inventor(s) include Mrs. M. Dharani; Mr. Kannakumar K; Dr. M. Kalaimani; Dr. K. M. Kumar; Dr. A. X. Amal Rebin; Dr. Vidhika Tiwari; Mr. G. V. Dellibabu; and Mr. R B Senthilrajan.
The application for the patent was published on Feb. 27, under issue no. 09/2026.
According to the abstract released by the Intellectual Property India: "The increasing application of fiber-reinforced polymer (FRP) composites in aerospace, automotive, and energy sectors demands high-precision inspection systems to ensure structural integrity and reliability. Conventional non-destructive testing (NDT) methods are often labor-intensive, time-consuming, and dependent on operator expertise, leading to variability in defect detection rates. This study proposes a Smart Robotic System with Artificial Intelligence (AI) Integration for automated inspection and quality control of composite components in mechanical engineering applications. The developed system integrates a 6-axis industrial robotic manipulator with multi-sensor modules, including ultrasonic testing (UT), infrared thermography, and high-resolution machine vision cameras (24 MP). A convolutional neural network (CNN)-based deep learning model was trained on a dataset of over 12,000 labeled composite defect images, including delamination, voids, matrix cracks, and fiber misalignment. The AI model achieved a defect classification accuracy of 96.8%, with a precision of 95.4% and recall of 97.1%, significantly outperforming traditional threshold-based image processing methods (average accuracy 82%). The robotic platform ensures consistent scanning speed of 0.15 m/s and positional accuracy of 0.02 mm, reducing inspection time by approximately 40% compared to manual inspection. Real-time data processing using edge AI computing reduced latency to under 120 ms, enabling immediate defect mapping and automated decision-making. The system also incorporates predictive analytics to estimate defect propagation probability with an error margin below 5%, enhancing preventive maintenance strategies. Experimental validation on carbon fiber reinforced polymer (CFRP) panels demonstrated a 35% reduction in false negatives and a 28% improvement in overall quality assurance efficiency. The integration of AI enables adaptive learning, continuous performance improvement, and scalable deployment in smart manufacturing environments aligned with Industry 4.0 principles. The proposed framework provides a reliable, cost-effective, and intelligent solution for automated composite inspection, ensuring enhanced structural safety, reduced production downtime, and improved manufacturing sustainability."
Disclaimer: Curated by HT Syndication.
