A Contactless PCBA Defect Detection Method: Convolutional Neural Networks with Thermographic Images

Abstract

IEEEIn the mass production of electronic products, in-circuit-test and printed circuit board assembly (PCBA) quality tests are performed. In-circuit-test (ICT) measures resistance values and capacitance, but not only does it require the use of a fixture, that is expensive and requires frequent replacement, but also the fixture’s needles may cause PCBA defects. To overcome these limitations, various researches tried to replace ICT using visual inspection methods, however visual inspection methods cannot be applied to chip resistor and chip capacitors, that do not have externally visible characteristics. In this paper, we propose a contactless inspection method that can detect PCBA defects without the use of the fixture and ICT by using the comparison of thermal images and deep learning analysis. We review existing contactless inspection methods and compare them with our proposed thermal image analysis method. We analyzed thermal images by applying structural similarity index map as a rule-based object detection method, we used convolutional neural networks (CNN), regions with CNN features, and an autoencoder as deep learning analysis methods. As a result, we achieved highly accurate defective component detection and location in real-time.