[8p-B11-1~16] 8.2 Plasma deposition of thin film, plasma etching and surface treatment

6:00 PM - 6:15 PM JST(9:00 AM - 9:15 AM UTC)

[8p-B11-15] Surrogate Learning and Optimization for Low-Pressure ICP Coil Design Based on Structural Feature

〇Daiki Kawahito¹, Koki Hayashi¹, Yukiya Saito¹, Hironori Moki¹ (1.Tokyo Electron Ltd.)

Keywords:

machine learning,low pressure plasma

We developed a surrogate model for an inductively coupled plasma (ICP) in which RF coil configurations are represented as spatial structural features, and a deep learning is used to predict two-dimensional plasma field distributions. The model is designed to capture the relationship between coil geometry and plasma behavior more directly than conventional parameter-based representations. We also applied the trained model to explore candidate coil designs that achieve both improved electron density uniformity and maintained plasma density. In this presentation, we report the modeling approach and the results of this design exploration.