Defect Detection on Semiconductor Wafers by Distribution Analysis

TL;DR

This paper introduces a fast, distribution-based classification method for defect detection on semiconductor wafers, demonstrating high accuracy on large real-world datasets from wafer fabrication.

Contribution

It proposes a novel distribution analysis-based classification algorithm, integrating feature selection and unification with existing classifiers, optimized for low-dimensional search space.

Findings

Achieved high detection accuracy on real wafer data

Algorithm is fast with quasi-linear complexity

Effective in classifying multiple product types

Abstract

A method for object classification that is based on distribution analysis is proposed. In addition, a method for finding relevant features and the unification of this algorithm with another classification algorithm is proposed. The presented classification algorithm has been applied successfully to real-world measurement data from wafer fabrication of close to hundred thousand chips of several product types. The presented algorithm prefers finding the best rater in a low-dimensional search space over finding a good rater in a high-dimensional search space. Our approach is interesting in that it is fast (quasi-linear) and reached good to excellent prediction or detection quality for real-world wafer data.