Using Graph Attention Network to Reversely Design GaN MIS-HEMTs Based on Hand-Drawn Characteristics

Authors:
Open Access
Publisher website
Google Scholar
Abstract
In this work, the methodology using Graph Attention Network (GAT) for the reserve design in GaN power MIS-HEMTs based on hand-drawn characteristics is demonstrated for the first-time. The hand-drawn I D -V G characteristic is constructed by Ramer-Douglas-Peucker algorithm. Then, the extracted information is sent to the Graph Attention Network to receive the corresponding device design variables, including t AiGaN , recessed depth, Al%, L g , L gd , and L gs . Less than 30 seconds is consumed to generate the design variables and less than 8% of the differences in the key extracted parameters, such as threshold voltage (V th ), On-state current (I on ), and subthreshold slope (SS), can be achieved by comparing hand-drawn I D -V G and simulated I D -V G characteristic based on the design variables from GAT model. Therefore, the developed GAT approach is promising for the reverse design of GaN power MIS-HEMTs, which can provide users with efficient and valuable design suggestions to optimize the devices toward the targeting performance.
Funding Information
  • “Center for the Semiconductor Technology Research” from the Featured Areas Research Center Program within the Framework of the Higher Education Sprout Project
  • Ministry of Education (MoE), Taiwan
  • National Science and Technology Council (NSTC), Taiwan (111-2634-F-A49-008, 111-2622-8-A49-018-SB, 111-2221-E-492-022, 110-2221-E-492-012)
  • Young Scholar Fellowship Program (112-2636-E-A49-005)

This publication has 17 references indexed in Scilit: