Iterative Cluster Harvesting for Wafer Map Defect Patterns

TL;DR

This paper introduces an iterative clustering method for wafer map defect patterns that improves clustering accuracy, especially for challenging patterns, with low computational effort, aiding large dataset analysis and manual labeling.

Contribution

The novel iterative dimensionality reduction and clustering approach enhances defect pattern clustering accuracy over existing methods.

Findings

Improved clustering performance on real-world wafer defect data.

Effective handling of challenging defect patterns with varied shapes and orientations.

Low computational cost enables quick analysis of large datasets.

Abstract

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.