کنفرانس مهندسی برق ایران

صفحه اصلی / سی و یکمین کنفرانس بین المللی مهندسی برق

Modeling of a low-noise amplifier with a recurrent neural network

نویسندگان :

Mostafa Noohi¹ Fatemeh Charoosaei² Ali Mirvakili³ Sayed Alireza Sadrossadat⁴

1- دانشگاه صنعتی سهند 2- دانشگاه یزد 3- دانشگاه یزد 4- دانشگاه یزد

کلمات کلیدی :

Computer aided design،Low-noise amplifier،modeling،recurrent neural network

چکیده :

Macromodelling of nonlinear circuits particularly those operating at RF frequencies is of importance and interest specifically in systems where the total simulation time is constrained. Recurrent neural network (RNN) can be considered as a viable approach for generating this modeling. Indeed, with having such a model at hand, the circuit designers have the potential to grasp the system level verification way faster than the conventional simulators. In this paper, a low-noise amplifier (LNA) is used as the nonlinear circuit, and a RNN is designed to generate the model. The LNA is configured in LTSPICE, and its simulation data is used as the input of the RNN model via Python programming. Using RNN, it is possible to train directly using the input-output waveform samples of the main nonlinear circuit without knowing the details. The obtained RNN-based model has the same accuracy compared to the original nonlinear circuit and is also able to extend the dynamic behavior of nonlinear circuits. In addition, models based on recurrent neural networks are much faster than models based on conventional simulation tools such as LTSPICE. It is worth mentioning that this modeling approach can be extended to a variety of applications, including medical, to have a quick prediction of the vital signals.