D10.4 Predicting the Analog Integrated Circuit Performance Using Indirect Measurements Based on Simulations
- Event
- SMSI 2021
2021-05-03 - 2021-05-06
digital - Band
- SMSI 2021 - Sensors and Instrumentation
- Chapter
- D10 Advances in Sensor Electronics
- Author(s)
- S. Alraho, Q. Zaman, A. König - TU Kaiserslautern, Kaiserslautern (Germany)
- Pages
- 234 - 235
- DOI
- 10.5162/SMSI2021/D10.4
- ISBN
- 978-3-9819376-4-0
- Price
- free
Abstract
This paper presents a low-cost indirect measurement method to predict the performance of analog integrated circuits (ICs). The method is based on integrating simple sensors near to the main circuit to capture circuit properties under different conditions expected by real fabrication. Monte Carlo with corner simulation results is used to train neural network for modeling and mapping the sensor outputs to the design output performance. The achieved correlation performance metrics is 91.68%. The circuit is designed using AMS 0.35 μm technology and Cadence tools.