Industrial Consultancy & Sponsored Research (IC&SR) , IIT Madras
Method for Simulation Assisted Data Generation and Deep Learning Intelligence Creation in Nondestructive Evaluation Systems
Categories for this Invention
Technology: Method for simulation assisted data generation for NDE system;
Industry: NDE/NDT, Artificial Intelligence, Deep learning Industries with Instrumentation fault finding; Applications: NDE/NDT Systems.
Market: The global Non-Destructive Testing (NDT) Software Market is projected to grow at a CAGR of 11.10% during the period (2024-29).
Image Gallery
Problem Statement
- Generally, NDE/NDT plays a vital role in improving the manufacturing productivity and quality. There are a few NDT/NDE inspection techniques such as feature-based classification, artificial neural networks & adaptive filtering which have been developed to perform automatic radiographic inspections of the objects.
- However, application of these techniques is restricted due to lack of sufficient training data to train the NDE/NDT system to perform defect identification, which leads to inefficient implementation of said NDT/NDE techniques.
- Present invention addresses above issues in efficient manner.
Technology
- Present invention describes a system and method for automatically identifying one or more anomalies in the objects.
- The system receives experimental data of the object and applies a probability density function (PDF) upon one or more variables associated with the experimental data to determine corresponding one or more PDF estimates.
- Further generates simulated data associated with the object based on at least one of the one or more PDF estimates and priori data associated with the testing of the object.
- The simulated data comprises one or more new anomalies unknown in the experimental data along with the one or more anomalies of the experimental data.
- Furthermore, the system trains a learning model based on the one or more new anomalies and the one or more anomalies of the experimental data.
- The learning model is applied for detecting any anomaly in an object.
Key Features / Value Proposition
Technical Perspective:
Efficient Techniques:
- The claimed invention enhances the automation of detecting anomalies in an object using a Non-destructive Testing/Evaluation (NDE/NDT).
Using AI Network for generating large & relevant data:
- The claimed subject matter further provides techniques for generating large and relevant data for training artificial intelligence networks (such as Deep Learning and/or Machine Learning) for the NDE/NDT system.
Improved Performance:
- The claimed patent facilitates improved the accuracy and efficiency of the NDE/NDT system
Industrial Perspective:
Utility:
- Applicable in the industry such as NDT/NDE Industry, automation Industry and flaw detection industries, Instrumentation, Oil & gas industries.
Questions about this Technology?
Contact For Licensing
sm-marketing@imail.iitm.ac.in
ipoffice2@iitm.ac.in
Research Lab
Prof. Krishnan Balasubramaniam
Department of Mechanical Engineering.
Intellectual Property
- IITM IDF Ref. 1898;
- IN Patent No. 481776 (Granted)
Technology Readiness Level
TRL-4
Proof of Concept ready, tested and validated in Laboratory