A High-accuracy Calibration Method of Transient TSEPs for Power Semiconductor Devices

TL;DR

This paper introduces a high-accuracy calibration method for transient TSEPs in power semiconductor devices, significantly improving temperature monitoring accuracy without extra hardware costs.

Contribution

It proposes a novel calibration approach that accounts for load-induced temperature differences and stray parameters, utilizing neural networks for improved junction temperature prediction.

Findings

Mean absolute error reduced by over 30%

Effective temperature compensation strategy implemented

Method shows good generalization without extra hardware

Abstract

The thermal sensitive electrical parameter (TSEP) method is crucial for enhancing the reliability of power devices through junction temperature monitoring. The TSEP method comprises three key processes: calibration, regression, and application. While significant efforts have been devoted to improving regression algorithms and increasing TSEP sensitivity to enhance junction temperature monitoring accuracy, these approaches have reached a bottleneck. In reality, the calibration method significantly influences monitoring accuracy, an aspect often overlooked in conventional TSEP methods. To address this issue, we propose a high-accuracy calibration method for transient TSEPs. First, a temperature compensation strategy based on thermal analysis is introduced to mitigate the temperature difference caused by load current during dual pulse tests. Second, the impact of stray parameters is analyzed to identify coupled parameters, which are typically neglected in existing methods. Third, it is observed that random errors follow a logarithm Gaussian distribution, covering a hidden variable. A neural network is used to obtain the junction temperature predictive model. The proposed calibration method is experimental validated in threshold voltage as an example. Compared with conventional calibration methods, the mean absolute error is reduced by over 30%. Moreover, this method does not require additional hardware cost and has good generalization.