MUMBAI, India, Sept. 14 -- Intellectual Property India has published a patent application (202641108137 A) filed by Pragati Engineering College on September 09, 2026, for Ai-Enabled Predictive Quality Assessment Of Additively Manufactured Components Using Electrical Signals.
Inventors include Dr. Kola Satyanarayana; Mrs. P. Sandhya; Mr. D Prakasa Rao; and Mr. Venkatadurgaprasad Kante.
The application for the patent was published on September 11, 2026, under issue no. 37/2026.
Abstract: To overcome these limitations, the invention provides an integrated AI-driven adaptive material testing system in which an additively manufactured specimen is subjected to one or more material tests while a multi-modal sensing network captures real-time response data. The captured data are processed by an intelligence engine that performs preprocessing, feature extraction, anomaly detection, defect classification, material-property prediction, uncertainty estimation, and response-state assessment during the active test rather than only after test completion. Based on these inferences, an adaptive controller automatically or semi-automatically modifies one or more test parameters, such as load rate, strain rate, dwell interval, sampling density, thermal profile, imaging frequency, or test sequence, thereby creating a closed-loop testing architecture tailored to the actual specimen behavior. In preferred embodiments, the system further incorporates specimen metadata, additive manufacturing process history, digital twin support, and optional distributed or federated learning so that test decisions are informed both by live observations and prior knowledge accumulated across specimens, builds, or sites. For inventive-step arguments, the strongest technical advantages are the ones that flow from the closed-loop adaptive test architecture rather than from AI in general. The literature shows that AI already supports prediction, optimization, defect detection, and digital-twin-style analysis in additive manufacturing, so your argument should emphasize the new interaction between real-time sensing, inference, and test modification.
Disclaimer: Curated by HT Syndication.
