In this study, the effect of applying the tilted ion implantation process of a 1.2 kV SiC trench MOSFET on the electrical characteristics of the devices was investigated. P-shielding with tilted ion implantation protects both the sidewall and bottom of the trench from an electric field, enabling stable high-voltage operation, and the cell pitch can be reduced by using only one channel. Moreover, the tilted ion implantation process has the advantage of not requiring additional masks. For a comparative analysis, the tilt angle for ion implantation into the trench was changed in a TCAD simulation. A high breakdown voltage of 1617 V was achieved under an optimized tilt angle of 18.2°, and a low on-resistance of 2.9 mΩ-cm2 was obtained via structural optimization.

No abstract

No abstract

In the learned machine learning, the performance of machine learning degrades at the same time as drift occurs in terms of learning models and learning data over time. As a solution to this problem, I would like to propose the concept and evaluation method of ML drift to determine the re-learning period of machine learning. An XAI test and an XAI test of an apple image were performed according to strawberry and clarity. In the case of strawberries, the change in the XAI analysis of ML models according to the clarity value was insignificant, and in the case of XAI of apple image, apples normally classified objects and heat map areas, but in the case of apple flowers and buds, the results were insignificant compared to strawberries and apples. This is expected to be caused by the lack of learning images of apple flowers and buds, and more apple flowers and buds will be studied and tested in the future.

No abstract