Defect Detection of Semiconductor Wafer EB-SEM Images Based on Convolutional Neural Networks

When problems arise during the production of semiconductors, wafer maps help engineers determine what went wrong. Improving the semiconductor production process, product performance, and cost-effectiveness may be achieved by efficient pattern detection of wafer map failures. Hence, through a deep learning-based convolutional neural network (DCNN), this article presents a precise model for the autonomous identification of kinds of wafer map failures. Dataset TT, an open-source real-time wafer map dataset with nine failure classes' worth of wafer map (SEM) pictures, is used for this investigation. This is a condensed version of our study. We begin by extracting the pictures using the augmentation procedures of the data augmentation model, namely the Conditional GAN model. We next suggest an optimization technique based on spider monkeys to train a deep convolutional neural network to provide a model for various classes. Finally, we assess the suggested prediction model's efficacy by contrasting it with a number of prominent deep learning models, including VGGNet, ResNet, and EfficientNet, as well as three additional notable machine learning-based models: random forest, logistical regression, as well as gradient boosted decision trees. As a result, the suggested DCNN EfficientNet-B4 model performed better than other well-known prediction models based on machine learning as well as deep learning, according to the thorough investigation.