Abstract:

GaN HEMTs plays a vital role in high-power and high-frequency electronics. Meeting the demanding performance requirements of these devices without compromising reliability is a challenging endeavor. Field Plates are employed to redistribute the electric field, minimizing the risk of device failure, especially in high-voltage operations. While machine learning has been applied to GaN device design, its application to field plate structures, known for their geometric complexity, is limited. This study introduces a novel approach to streamlining the field plate design process. It transforms complex 2D field plate 2 structures into a concise feature space, reducing data requirements. A machine learning- assisted design framework is proposed to optimize field plate structures and perform inverse design. This approach is not exclusive to the design of GaN HEMTs and can be extended to various semiconductor devices with field plate structures. The framework combines technology computer-aided design (TCAD), machine learning, and optimization, streamlining the design process.