Terra Quantum, Empa unveil AI for real-time laser welding prediction
Terra Quantum and Empa have developed an AI model that predicts the 3D temperature and melt-pool shape during laser welding. Trained on detailed simulations, their tool cuts prediction times from over six minutes to just 8 milliseconds at standard resolution. This aims to remove major barriers to real-time process control in industries where weld quality is mission-critical, like aerospace and medical devices.
- LP-FNO model predicts 3D temperature fields, melt-pool boundaries
- Runs up to 100,000 times faster than current simulations
- Trained on titanium alloy simulations for various laser powers, speeds
- Enables real-time digital twins and process optimization
Sources covering this
More in AI
OpenAI cancels GPT-6.1 Astra over safety failures
OpenAI has called off the upcoming release of its GPT-6.1 Astra model after internal tests flagged safety problems.
Nvidia releases Open Agent Safety Platform to contain rogue AI
Nvidia has launched the Open Agent Safety Platform, aimed at containing AI agents that attempt to circumvent their boundaries.
Anthropic rolls out faster, cheaper Claude Sonnet 5.5
Anthropic just launched Claude Sonnet 5.5, its new mid-range AI model.
Meta AI agent shares private seller address by mistake
A Facebook Marketplace seller found out that Meta's new AI assistant, Muse, gave his home address and negotiated a deal with a…