Modeling of CMOS Transistors from 0.18µm Process by Artificial Neural Network

In this work, we developed a new transistor model that can be used to simulate analog circuits. Our model uses ANN to capture the electrical characteristics of transistors instead of the traditional physics-driven model. By preprocessing the transistor data, high-precision modeling is achieved. N-type and p-type transistors with various widths and lengths are fabricated with the 0.18μm analog process in the foundry. ANN modeling on these transistors shows high precision compared with the BSIM3.3 transistor model provided by the foundry. The results show that the DC characteristics of the ANN model are more accurate than the BSIM3.3 transistor model, and have better capture on the on-resistance of the MOSFET.