Classification and Prediction of Chip Diameter in High-Power Semiconductor Devices Through Electrical Parameters Using Machine Learning

The applications of machine learning (ML) are rapidly expanding across various fields to reduce their complexity and improve efficiency. In power electronics, where design tasks require complex analytical computations and accurate predictions, ML techniques are becoming increasingly important for reliable device design and robust manufacturing. With the growing demand of power density of high-power semiconductor devices, such as diodes and thyristors, the electrical parameters critically influence the physical dimensions and geometry of the chip. In this article, a comprehensive survey of high-power thyristors is conducted, analyzing the influence of chip diameter and thickness on both electrical and thermal performance. Moreover, a dedicated dataset is developed by extracting electrical parameters from the leading semiconductor manufacturer’s datasheet of multiple models. Furthermore, multiple machine learning algorithms, including Artificial Neural Networks (ANNs), Support Vector Machines (SVMs), and Ensemble methods, are implemented and compared. The developed models provide manufacturers with efficient predictive tools to determine optimal chip dimensions for specific power ratings, thereby supporting efficient and reliable device design.