Prith Bannerjee

Prith Banerjee is Chief Technology Officer at ANSYS and is responsible for driving the long term technology strategy of the company. Prior to that, he was CTO of Schneider Electric, CTO of ABB, Managing Director at Accenture, and Director of HP Labs.

Previously, he spent 20 years in academia as Professor, Chairman and Dean at the University of Illinois and Northwestern University. In addition, Prith has founded two EDA software companies, Accelchip and Binachip.

He has served on the Board of Directors of Cray, CUBIC, and Turntide. He is a Fellow of the AAAS, ACM and IEEE. He received a B.Tech. in electronics engineering from the Indian Institute of Technology, Kharagpur, and an M.S. and Ph.D. in electrical engineering from the University of Illinois, Urbana.

Presentation Title

AI Driven Digital Twins for Semiconductor Manufacturing FABS

Abstract

Semiconductor fabrication fabs consist of clean rooms with extremely sophisticated equipment that can support physico chemical processes such as chemical vapor deposition, epitaxial growth, ion implantation, and etching using which semiconductor circuits are created on wafers.

There is a large push to completely au tom ate the production of semiconductor chips using IOT, sensors, automation and robotics. In this talk I will discuss the use of Digital Twins in semiconductor manufacturing fabs to drive higher yields, faster throughput, lower cost, and higher operating equipment efficiency.

Digital twins have a physical asset, a virtual model, and a two way information flow between the physical and virtual worlds using an IOT platform. One approach to build digital twins is to use data based analytics and AI/machine learning but this requires lots of training data and the accuracy is limited to the observed data. A second approach to build digital twins is to use physics based simulation which are very accurate, but they require long computation times to deploy.

In this talk I will discuss AI Driven Digital twins on the Industrial Metaverse that combine AI/ML based analytics and physics based simulation to build digital twins that are very accurate, require less training data, and drive high operational efficiency.

We will discuss how to build digital twins for semiconductor manufacturing equipment, digital twins for semiconductor manufacturing processes, and digital twins for the complete semiconductor manufacturing fab plant.