Using deep learning to automatic inspection system of printed circuit board in manufacturing industry under the internet of things

Industry 4.0 is currently the goal of many factories, promoting manufacturing factories and sustainable operation. Automated Optical Inspection (AOI) a part automation. Products in production line are usually inspected visually by operators. Due to human fatigue inconsistent standards, product inspections still have defects. In this study, sample component assembly printed circuit board (PCB), PCB provided company was tested for surface components. The types defects on include missing parts, multiple wrong parts. At present, using visual inspection operators, components more complex. order reduce labor costs save development time required different boards. proposed method, we use digital image processing, positioning correction algorithm, deep learning YOLO identification, 450 images 10500 samples. result contribution paper shows total recognition rate 92% reaches 99%, they effective. It could light, color backplanes, material numbers, detection compatibility 98%.