Deep open-set recognition for silicon wafer production monitoring. (April 2022)

• Record Type: Journal Article
• Authors: Frittoli, Luca; Carrera, Diego; Rossi, Beatrice; Fragneto, Pasqualina; Boracchi, Giacomo
• Is Part Of: Pattern recognition. Volume 124(2022)
• Publication Date: 2022-04
• Subjects: Pattern classification -- Open-set recognition -- Sparse convolutions -- Quality inspection -- Wafer monitoring; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2021.108488
• Languages: English
• ISSNs: 0031-3203

Abstract

Highlights: A novel solution to monitor the production of silicon wafers by Deep Learning models. A crucial problem for semiconductor industry, challenging due to the huge input size. We accurately address wafer monitoring as an open-set recognition problem. Our network can process huge inputs as lists of defects, without loss of information. We employ latent representation of our deep model to identify novel patterns. Abstract: The chips contained in any electronic device are manufactured over circular silicon wafers, which are monitored by inspection machines at different production stages. Inspection machines detect and locate any defect within the wafer and return a Wafer Defect Map (WDM), i.e., a list of the coordinates where defects lie, which can be considered a huge, sparse, and binary image. In normal conditions, wafers exhibit a small number of randomly distributed defects, while defects grouped in specific patterns might indicate known or novel categories of failures in the production line. Needless to say, a primary concern of semiconductor industries is to identify these patterns and intervene as soon as possible to restore normal production conditions. Here we address WDM monitoring as an open-set recognition problem, where the aim is to classify WDM in known categories and promptly detect novel patterns. In particular, we propose a comprehensive pipeline for wafer monitoring based on a Submanifold Sparse Convolutional Network, a deep architecture designed to process sparse data at an arbitrary resolution, which is trained on the known classes. To detect novelties, we define an outlier detector based on a Gaussian Mixture Model fitted on the latent representation of the classifier. Our experiments on a real dataset of WDMs show that directly processing full-resolution WDMs by Submanifold Sparse Convolutions yields superior classification performance on known classes than traditional Convolutional Neural Networks, which require a preliminary binning to reduce the size of the binary images representing WDMs. Moreover, our solution outperforms state-of-the-art open-set recognition solutions in novelty detection.