AI-vision based real-time in-situ monitoring of the metallic deposition in μ-plasma transferred arc directed energy deposition process

Key Points

• This research aims to develop a real-time monitoring framework for metallic deposition in directed energy processes using AI vision and image analysis techniques.
• Implemented AI vision using HDR imaging and advanced image segmentation technologies.
• Utilized arc-robust segmentation to isolate melt pool and deposition regions under various conditions.
• Tracked deposition height using calibrated pixel-to-millimetre mapping, validated experimentally.
• Achieved reliable isolation of melt pool and deposition regions, even under challenging glare conditions.
• Successfully tracked deposition height in real-time, contributing to process optimization.
• Established rapid classification of deposition quality, making it suitable for closed-loop monitoring systems.