Adaptive Outlier Detection for Power MOSFETs Based on Gaussian Process Regression

TL;DR

This paper introduces an adaptive outlier detection method for power MOSFETs using Gaussian process regression with Student-t likelihood, effectively capturing spatial trend changes to identify manufacturing anomalies.

Contribution

It presents a novel adaptive outlier detection approach based on GPR with Student-t likelihood, improving detection accuracy for semiconductor device variations.

Findings

Successfully detects outliers with large deviations from the trend

Effective in capturing spatial changes of device characteristics

Validated with experiments on SiC wafers and simulations

Abstract

Outlier detection of semiconductor devices is important since manufacturing variation is inherently inevitable. In order to properly detect outliers, it is necessary to consider the discrepancy from underlying trend. Conventional methods are insufficient as they cannot track spatial changes of the trend}}. This study proposes an adaptive outlier detection using Gaussian process regression (GPR) with Student-t likelihood, which captures a gradual spatial change of characteristic variation. According to the credible interval of the GPR posterior distribution, the devices having excessively large deviations against the underlying trend are detected. The proposed methodology is validated by the experiments using a commercial SiC wafer and simulation.