印刷电路板
稳健性(进化)
计算机科学
焊接
人工智能
材料科学
生物化学
化学
复合材料
基因
操作系统
出处
期刊:Journal of physics
[IOP Publishing]
日期:2023-08-01
卷期号:2562 (1): 012030-012030
标识
DOI:10.1088/1742-6596/2562/1/012030
摘要
Abstract Printed circuit board (PCB) has a wide range of applications, and its automated quality inspection is a vital part of economic production. The time overhead of the current PCB defect detection method will increase with the increase in the number of detection targets. To ensure the stability of detection performance, this paper proposes a novel PCB detection method based on color threshold segmentation. Experiments show that this method can effectively detect and analyse various information about solder pads and solder pastes, among which the detection accuracy rate of solder pads is 99.4%, the missed detection rate is 0.4%, and the detection accuracy rate of solder paste is 99.3%, The missed detection rate is 0.03%. At the same time, the method in this paper has better robustness and stability than other PCB defect detection methods, and can better meet the needs of industrial production.
科研通智能强力驱动
Strongly Powered by AbleSci AI