Wafer Defect Root Cause Analysis with Partial Trajectory Regression

TL;DR

This paper introduces Partial Trajectory Regression, a novel framework for wafer defect root cause analysis that handles variable process routes and uses new representation learning methods to improve attribution accuracy.

Contribution

The paper proposes a new PTR framework with counterfactual outcome comparison and novel representation learning methods, addressing limitations of traditional models in variable process routes.

Findings

Effective identification of defect root causes demonstrated on real wafer data.

Improved attribution accuracy over conventional regression models.

Framework handles large, heterogeneous process routes.

Abstract

Identifying upstream processes responsible for wafer defects is challenging due to the combinatorial nature of process flows and the inherent variability in processing routes, which arises from factors such as rework operations and random process waiting times. This paper presents a novel framework for wafer defect root cause analysis, called Partial Trajectory Regression (PTR). The proposed framework is carefully designed to address the limitations of conventional vector-based regression models, particularly in handling variable-length processing routes that span a large number of heterogeneous physical processes. To compute the attribution score of each process given a detected high defect density on a specific wafer, we propose a new algorithm that compares two counterfactual outcomes derived from partial process trajectories. This is enabled by new representation learning methods, proc2vec and route2vec. We demonstrate the effectiveness of the proposed framework using real wafer history data from the NY CREATES fab in Albany.