AI-Powered Industrial Quality Control

NanoAL needed a vision system to automatically classify materials and detect their exact position on a moving conveyor belt - critical for triggering a PLC reject mechanism at the right moment. The system had to process two camera feeds at 14+ FPS simultaneously, exceed 95% detection accuracy, and operate 24/7 under industrial dust and vibration without human intervention.

Challenge

• Exact material position on the belt had to be detected - not just classified - to trigger PLC rejection accurately
• Dual-camera setup required sustained 14+ FPS throughput per camera simultaneously
• Industrial environment (dust, vibration, variable lighting) demanded model robustness around the clock
• System had to integrate with the existing PLC reject mechanism without hardware replacement

Solution

• YOLO-based detection with position localization to pinpoint material coordinates on the conveyor belt
• TensorRT-optimized inference sustaining 14+ FPS across two simultaneous camera feeds
• Direct PLC integration triggering the existing reject mechanism based on real-time detection output
• Edge GPU deployment hardened for 24/7 continuous operation in an industrial environment

Architecture

Outcome

• Exceeded the 95% detection accuracy requirement under real industrial conditions
• 14+ FPS sustained across both camera feeds with sub-100ms detection-to-PLC signal latency
• Integrated with existing PLC reject mechanism with no hardware replacement required
• System runs 24/7 in production with no operator intervention required

Tech Stack

• AI/ML: Python, TensorRT, YOLO
• Infrastructure: Edge GPU, PLC Integration