Detection of soldering defects in Printed Circuit Boards with Hierarchical Marked Point Processes

Defect Detection in Printed Circuit Boards Using Semi-Supervised Learning

Defect inspection is essential in the semiconductor industry to fabricate printed circuit boards (PCBs) with minimum defect rates. However, conventional inspection systems are labor-intensive and time-consuming. In this study, a semi-supervised learning (SSL)-based model called PCB_SS was developed. It was trained using labeled and unlabeled images under two different augmentations. Training and test PCB images were acquired using automatic final vision inspection systems. The PCB_SS model outperformed a completely supervised model trained using only labeled images (PCB_FS). The performance of the PCB_SS model was more robust than that of the PCB_FS model when the number of labeled data is limited or comprises incorrectly labeled data. In an error-resilience test, the proposed PCB_SS model maintained stable accuracy (error increment of less than 0.5%, compared with 4% for PCB_FS) for noisy training data (with as much as 9.0% of the data labeled incorrectly). The proposed model also showed superior performance when comparing machine-learning and deep-learning classifiers. The unlabeled data utilized in the PCB_SS model helped with the generalization of the deep-learning model and improved its performance for PCB defect detection. Thus, the proposed method alleviates the burden of the manual labeling process and provides a rapid and accurate automatic classifier for PCB inspections.

Convolutional Recurrent Reconstructive Network for Spatiotemporal Anomaly Detection in Solder Paste Inspection

Surface mount technology (SMT) is a process for producing printed-circuit boards. The solder paste printer (SPP), package mounter, and solder reflow oven are used for SMT. The board on which the solder paste is deposited from the SPP is monitored by the solder paste inspector (SPI). If SPP malfunctions due to the printer defects, the SPP produces defective products, and then abnormal patterns are detected by SPI. In this article, we propose a convolutional recurrent reconstructive network (CRRN), which decomposes the anomaly patterns generated by the printer defects, from SPI data. CRRN learns only normal data and detects the anomaly pattern through the reconstruction error. CRRN consists of a spatial encoder (S-Encoder), a spatiotemporal encoder and decoder (ST-Encoder-Decoder), and a spatial decoder (S-Decoder). The ST-Encoder-Decoder consists of multiple convolutional spatiotemporal memories (CSTMs) with a spatiotemporal attention (ST-Attention) mechanism. CSTM is developed to extract spatiotemporal patterns efficiently. In addition, an ST-Attention mechanism is designed to facilitate transmitting information from the spatiotemporal encoder to the spatiotemporal decoder, which can solve the long-term dependency problem. We demonstrate that the proposed CRRN outperforms the other conventional models in anomaly detection. Moreover, we show the discriminative power of the anomaly map decomposed by the proposed CRRN through the printer defect classification.

Chip Appearance Defect Recognition Based on Convolutional Neural Network

To improve the recognition rate of chip appearance defects, an algorithm based on a convolution neural network is proposed to identify chip appearance defects of various shapes and features. Furthermore, to address the problems of long training time and low accuracy caused by redundant input samples, an automatic data sample cleaning algorithm based on prior knowledge is proposed to reduce training and classification time, as well as improve the recognition rate. First, defect positions are determined by performing image processing and region-of-interest extraction. Subsequently, interference samples between chip defects are analyzed for data cleaning. Finally, a chip appearance defect classification model based on a convolutional neural network is constructed. The experimental results show that the recognition miss detection rate of this algorithm is zero, and the accuracy rate exceeds 99.5%, thereby fulfilling industry requirements.