New AI Platform From Euler Analyzes Sensor Data to Improve Metal Print Quality

Key Takeaways

• Euler's AI predicts defects up to a dozen layers ahead
• Real‑time alerts enable operators to intervene before failures
• Free remote viewer simplifies layer‑by‑layer inspection
• Centralized comment system streamlines large‑shop collaboration
• Savings on powder and machine time offset tool cost

Pulse Analysis

Laser powder bed fusion (LPBF) has become the workhorse of metal additive manufacturing, delivering high‑strength parts for aerospace, automotive, and medical applications. Unlike prototyping, production‑grade prints must meet strict tolerances, prompting manufacturers to equip printers with an array of sensors—thermal cameras, melt‑pool monitors, and high‑resolution imaging of each layer. Historically, this data is archived and examined only after a build completes, leaving a gap in immediate quality control. The industry therefore faces costly scrap, long downtime, and limited insight into the root causes of defects.

Euler, a spin‑off from the Danish Technical University, tackles that gap with an AI‑driven platform that ingests the visual sensor stream in real time. Trained on thousands of historic builds, its machine‑learning models can flag anomalies as they emerge and even forecast potential failures several layers ahead. Operators receive instant alerts through an intuitive dashboard, allowing corrective actions such as parameter tweaks or early job termination. A complimentary remote viewer lets engineers examine layer images without being on the shop floor, while a built‑in comment hub captures collaborative notes across shifts.

The impact on manufacturers is immediate: reducing scrap rates translates into direct savings on expensive metal powders, which can cost $150‑$300 per kilogram, and preserving machine uptime improves throughput. By converting raw sensor data into actionable intelligence, Euler’s solution lowers the barrier for small and medium‑size enterprises to adopt production‑grade metal printing. As AI‑enhanced quality assurance becomes standard, the broader additive‑manufacturing ecosystem is likely to see accelerated scale‑up, tighter supply‑chain integration, and stronger competitive positioning against traditional subtractive processes.