Airplane parts need thorough inspections, and AI can help — but only if data is up to snuff
Safran uses Loopr AI to streamline defect inspections. The software creates synthetic data to improve AI algorithm training.
Safran, an aviation manufacturer, has partnered with Loopr AI to enhance defect detection processes in their parts manufacturing. Loopr AI utilizes synthetic data to improve inspection accuracy and efficiency, reducing inspection time and costly defect recalls. Previously, inspectors at Safran spent 20 to 30 minutes examining a single toilet lid, searching for consistent colors, smooth surfaces, and other defects.
However, fatigue can affect detection rates. AI can streamline these processes, but requires sufficient data for training. When companies lack data, they can use synthetic data to address the issue. Loopr AI generates synthetic data from computer-generated images, 3D models, and simulation tools. Safran conducted pilot projects with Loopr AI to test the effectiveness of AI in defect identification.
With the AI system, inspection time for a toilet seat reduced from 20 to 30 minutes to five to 10 minutes, including an automatically created defect and inspection sheet. The Loopr AI inspection process can be automated or hybrid, allowing human review and confirmation of the AI's findings. Safran is now expanding the use of Loopr AI technology to its facilities in Washington and California.
Written by urgent.news from Business Insider's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
