Non Destructive Evaluation of Friction Stir Welds using Machine Learning

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: 35864

Start date and planned duration: March 2024, 36 months

Objective

The project seeks to drive research and development in non-destructive testing and process control specific to friction stir welding. By harnessing these technologies, industries can elevate the quality, efficiency, and safety of their products.

Project Outline

This project addresses the Smart Manufacturing research stream within the TWI core research programme. The project will develop qualification assistance tools for Friction Stir Welding by to assessing the likelihood or probability that a manufactured product or component meets certain quality standards or specifications. Instead of a binary pass/fail evaluation, a machine-learning approach will generate a probabilistic qualification which takes into account the inherent variability in the welding process and the fact that defects may not always be absolute or easily detectable. The machine learning qualification will be compared to both existing NDT techniques (PAUT, Eddy Current, and X-Ray CT) and new NDT techniques such as hybrid laser ultrasonic to detect a range of flaws including hard-to-detect flaws such as joint line remnants in lap joints and lack-of-penetration root flaws in butt joints.

Industry Sectors

- Automotive Sector
- Aerospace Sector
- All Sectors

Benefits to Industry

The key industrial drivers for development of non-destructive evaluation techniques in FSW are:

Reduced manufacturing costs by minimising post-weld NDT requirements
Improved weld quality by iterative process optimisation
Improved weld repeatability by detecting anomalies and root-causes
Pre-defect detection of process instability and in-process correction, reducing scrap rates
Ability to weld complex geometries with consistent properties through process feedback control.