en.Wedoany.com Reported - The Korea Institute of Machinery and Materials (KIMM) has, for the first time, developed a technology capable of analyzing and controlling two-dimensional semiconductors at the atomic layer level (1 to 2 nanometers) using artificial intelligence (AI). This technology aims to significantly enhance process reproducibility and productivity.
On the 17th, KIMM announced that a research team from the Semiconductor Equipment Research Center, led by Senior Researcher Kim Hyung-woo, has developed synthesis and etching processes for 6-inch next-generation two-dimensional semiconductors (MoS₂, WS₂) using low-temperature plasma-based PECVD (Plasma-Enhanced Chemical Vapor Deposition) and RIE (Reactive Ion Etching) equipment, and has successfully integrated these processes into an AI-based intelligent system.
During the process, the research team measured real-time changes in generated light and gas mass, and analyzed them using machine learning to predict process conditions. The team also utilized various real-time diagnostic equipment (OES, ToF-MS, QMS, etc.) to acquire time-series multimodal data, which was applied to machine learning models, successfully achieving atomic-level precise prediction of semiconductor thickness.
This technology is designed based on low-temperature plasma processes, ensuring effective compatibility with existing mass production equipment. It achieves atomic layer etching through a single process while maintaining process efficiency and productivity. Senior Researcher Kim Hyung-woo stated that achieving atomic-level control of a 6-inch wafer-scale two-dimensional semiconductor process under low-temperature conditions is significant. He plans to further develop this technology into a core solution for the automation and intelligentization of next-generation semiconductor manufacturing processes.
This article is compiled by Wedoany. All AI citations must indicate the source as "Wedoany". If there is any infringement or other issues, please notify us promptly, and we will modify or delete it accordingly. Email: news@wedoany.com
