Iterative Cluster Harvesting for Wafer Map Defect Patterns
This work addresses the problem of automated defect pattern analysis in semiconductor manufacturing, offering an incremental improvement to support manual labeling efforts.
The paper tackles the challenge of unsupervised clustering for wafer map defect patterns, which vary significantly in shape, location, density, and rotation. It presents an iterative harvesting approach that filters clusters based on silhouette scores, showing improved clustering performance on a real-world industrial dataset compared to related methods.
Unsupervised clustering of wafer map defect patterns is challenging because the appearance of certain defect patterns varies significantly. This includes changing shape, location, density, and rotation of the defect area on the wafer. We present a harvesting approach, which can cluster even challenging defect patterns of wafer maps well. Our approach makes use of a well-known, three-step procedure: feature extraction, dimension reduction, and clustering. The novelty in our approach lies in repeating dimensionality reduction and clustering iteratively while filtering out one cluster per iteration according to its silhouette score. This method leads to an improvement of clustering performance in general and is especially useful for difficult defect patterns. The low computational effort allows for a quick assessment of large datasets and can be used to support manual labeling efforts. We benchmark against related approaches from the literature and show improved results on a real-world industrial dataset.