SEMI project eyes AI, ML to streamline chip manufacturing
The organization has teamed up with Cornell University, which, under the agreement, will optimize and accelerate two critical process steps – lithography and plasma etch. The project, says the organization, aims to help accelerate the adoption of data-driven AI methodologies to streamline microelectronics operations and lay the foundation for SEMI to establish data transfer and management standards crucial to the trusted exchange of trade secrets, IP, and other sensitive information.
“Streamlining manufacturing processes across the microelectronics supply chain to address the rising complexity of technology development is key for the industry to keep pace with market demand and drive growth,” says Ajit Manocha, SEMI president and CEO. “The microelectronics industry has been slow to adopt ML and AI due, in part, to IP and data security concerns that impede data sharing. SEMI’s agreement with Cornell, supported by the U.S. Army Research Laboratory (ARL), is an important step in using ML and AI techniques to tackle this and other issues and bring new technologies to market faster.”
The project is designed to address the complexity of semiconductor manufacturing, which is affected by the intricate interdependencies among various processes, environments, tools, and materials. This complexity deepens with the rise of new technologies and makes existing analytical approaches such as statistical process control (SPC) and design of experiments (DOE) more challenging, says the organization.
In addition, analyzing clean room data is now harder because of varying formats and lack of physical models for categorizing the data. Consequently, identifying root causes of manufacturing problems is much more difficult, slowing the development of new technologies.
Tools and materials from several SEMI members will be used for the project at Cornell University’s NanoScale Science & Technology Facility (CNF). The budget for the year-long project is provided by an ARL grant, SEMI, and through in-kind contributions from companies in the form of materials and testing services.
Related articles:
TSMC, Purdue partner on secured microelectronics ecosystem
Chip manufacturing equipment market goes into reverse
IC Insights, SEMI far apart on significance of Chinese IC production
If you enjoyed this article, you will like the following ones: don't miss them by subscribing to :
