Parameter Identification and Refinement for Parallel PCB Inspection in Cyber–Physical–Social Systems

Replacing manual inspection, automated optical inspection (AOI) equipment is widely used in printed circuit board (PCB) factories for automatic PCB defect segmentation. However, parameter refinement of AOI devices has gradually become an efficiency bottleneck in AOI usage, posing a highly challenging task. Since a large number of AOI parameters and different types of inspected objects make timely proper parameter refinement for clear images quite difficult. Considering this, we propose the concept of parallel PCB inspection in cyber–physical–social systems (CPSSs). Based on artificial systems, computational experiments, and parallel execution (ACP) theory with automatic parameter identification and refinement, we perform descriptive intelligence to build an artificial imaging system, obtain knowledge about the mapping relationships of parameter settings and imaging results, and realize automatic parameter identification given image input; conduct predictive intelligence to obtain image quality assessment results and maximize quality score for refinement strategies; and carry out prescriptive intelligence to guide parameter refinement for better imaging. This system could guide engineers proactively with constructive suggestions on parameter refinement when imaging failures occur, greatly reducing the training cost of engineers while improving work efficiency and work quality. To validate that our parallel PCB inspection could perform automatic AOI results evaluation without human participation, we evaluate it on distortion-free and different distortion images and confirm image quality score is positively associated with segmentation accuracy.