Application of Eddy Current Array for Digitalisation of Manufacturing Data

In this section

Back to Core Research Programme AMorph – 4D Printing for Field Morphing Structures Automation of Composite and Hybrid Joining Process Coaxial Wire Additive Manufacturing Processes and In-Line Monitoring Tools Development of Coded Excitation Technique for Non-Metallic Pipes Inspection Development of Digital Twin technology as a demonstrator for real-time integrity assessment of crack growth in tensile specimens Development of Friction Stir Welding (FSW) for Hydrogen Fuel Storage Tanks Development of Leak-Before-Break Hydrogen Storage Composite Pressure Vessels With Polymeric Liner Establishing Assessment Methods for Determining Safe Service Limits of High-Temperature Materials in Extreme Environments Fracture toughness in aggressive environments: effect of crack monitoring techniques on test results In-process detection and non-destructive testing of electron beam weld imperfections Internal Bore Coatings for Applications in Corrosion and Hydrogen Environment Joining of Additively Manufactured Materials Long term behaviour of polymeric liner materials/coatings in hydrogen service Techniques for High Temperature Ultrasonic Inspection of Arc Welding Ultimate Leverage Fund

Project Code: 35921

Start date and planned duration: April 2024, 33 months

Objective

Identify and test suitable pre-processing, post-processing and ML techniques for automated ECAT data analysis and defect classification.
Develop automated algorithms that will enhance images by optimising the parameters of ECAT impedance data with altered phase angles at multiple excitation frequencies.
Develop automated algorithms that will detect and classify defects by ML using augmented ECAT data sets.Cross-validate of ECAT with MT and PT methods.
Evaluation and comparison of test results from three inspection methods.

Project Outline

This project intends to manufacture welded test samples, in order to compile a body of evidence which can be submitted to the ASME committee for the application to include a code case for use of ECAT in lieu of MT and PT. These welded samples containing representative flaws, will be tested by ECAT, MT and PT to demonstrate that ECAT performance is equivalent to, or better than conventional methods in terms of detection capability. Furthermore, the samples will be analysed by proposed automated analysis and signal processing algorithms. Signal processing algorithms will be developed in order to permit automated data post-processing to analyse the generated impedance images with different frequencies and altered phase angles. Machine learning (ML) algorithms will be developed to automatically classify defects. Data augmentation technology utilising virtual defects will be used to generate sufficient representative defective ECAT data from limited sets of test samples. This proposed project will present, for the first time, the application of ML to automated defect detection and classification using augmented ECAT data sets.

Industry Sectors

- Power, Nuclear

-Manufacturing industry

Benefits to Industry

The knowledge gained from the work proposed and the software developed during the project will help TWI Industrial Members advance their NDE practices.