Detecting Defective Wafers Via Modular Networks

TL;DR

This paper introduces a modular network approach for detecting defective wafers in semiconductor manufacturing by modeling process stages, improving generalizability and interpretability in fault detection across diverse wafer types.

Contribution

The paper presents a novel modular network architecture that captures process stage correlations, enhancing fault detection accuracy and generalizability in semiconductor wafer quality prediction.

Findings

Improved fault detection accuracy across different wafer types.

Enhanced interpretability of the manufacturing process model.

Demonstrated effectiveness through extensive experiments.

Abstract

The growing availability of sensors within semiconductor manufacturing processes makes it feasible to detect defective wafers with data-driven models. Without directly measuring the quality of semiconductor devices, they capture the modalities between diverse sensor readings and can be used to predict key quality indicators (KQI, \textit{e.g.}, roughness, resistance) to detect faulty products, significantly reducing the capital and human cost in maintaining physical metrology steps. Nevertheless, existing models pay little attention to the correlations among different processes for diverse wafer products and commonly struggle with generalizability issues. To enable generic fault detection, in this work, we propose a modular network (MN) trained using time series stage-wise datasets that embodies the structure of the manufacturing process. It decomposes KQI prediction as a combination of stage modules to simulate compositional semiconductor manufacturing, universally enhancing faulty wafer detection among different wafer types and manufacturing processes. Extensive experiments demonstrate the usefulness of our approach, and shed light on how the compositional design provides an interpretable interface for more practical applications.