We have combined our expertise in semiconductor technologies with machine learning and data analysis to develop an artificial intelligence-based solution named Fab Technology Co-Optimization™, or FTCO™, for wafer-level fabrication facilities. FTCO™ uses manufacturing data to perform statistical and physics-based machine learning software simulations to create a computer model or “digital twin” of a wafer that can be used to simulate the fabrication process. As a virtual representation of the manufacturing process and the wafer, this “digital twin” serves as a platform through which fab and process engineers can run experiments and tests to understand the impact on the yield of a wafer due to variations in the parameters of the manufacturing process, predict the yield for further research on new products, and reduce the time to market for products, with fewer number of wafer runs, which can be time-consuming and expensive.
AI-Driven FTCO™ Solution Platform Flow Diagram
Silvaco’s FTCO™ Solution
Silvaco’s FTCO™ Platform leverages artificial intelligence (AI) and machine learning (ML) to generate a Digital Twin which is a physics based digital counterpart that mirrors the form, fit and function of the physical world.
- A Digital Twin is a virtual representation of complex real system
- Components, devices, or full fab process
- Designed to model and be indistinguishable from the real-world system
- Provides insight into how the behavior of the real system will change with variation in design
- A Digital Twin can start to form prior to the real system, and can allow for virtual prototyping
- Once formed, the digital twin allows engineers to ask the digital twin “what-if” scenarios
With FTCO™, Silvaco provides the designer with an interactive visualization of the process step under investigation. Users can adjust the inputs of these fabrication steps to interactively see how the structure will change.
FTCO™ Platform Solution
