Small signal behavioral modeling technique of GaN high electron mobility transistor using artificial neural network: An accurate, fast, and reliable approach

Abstract

This article reports a comparative study of two artificial neural network structures and associated variants used to describe and predict the behavior of 2 × 200 μm2 GaN high electron mobility transistors (HEMTs), utilizing radiofrequency characterization. Two architectures namely multilayer perceptron and cascade feedforward, have been investigated in this work to develop the behavioral model. A study is conducted utilizing the two architectures, all trained using Levenberg‐Marquardt, in terms of accuracy, convergence rate, and generalization capability to develop the behavioral model of GaN HEMT. However, to ensure the robustness of the model, accuracy, convergence rate, time elapsed, and generalization capability of the proposed model is also tested under couple of training algorithms, activation functions, number of hidden layers and neuron embedded inside it, methods for initialization of weights and bias and certain other vital parameters playing vital role in influencing the model accuracy and effectiveness. An excellent agreement found between measured S‐parameters and the proposed model proves the effectiveness of the proposed approach and excellent prediction ability for a sweeping multibias set and broad frequency range of 1 to 18 GHz. Moreover, a very good generalization capability is also recorded under variation of crucial parameters of GaN HEMT‐based neural model.

A Generic and Efficient Globalized Kernel Mapping-Based Small-Signal Behavioral Modeling for GaN HEMT

“…Finally, the proposed small signal modeling approach of GaN HEMT is also compared with the conventional smallsignal behavioral model approach for GaN HEMT developed using Artificial Neural Network (ANN). Similar to the work in [29] - [31], the ANN based small-signal behavioral model is developed for the same set of predictors and responses discussed in Section III-B. The desired responses are scaled using the expression in (14).…”

“…The desired responses are scaled using the expression in (14). In this context, a feed-forward three layer Multi-Layer Perceptron (MLP) based ANN model is trained using Levenberg-Marquardt algorithm with 15 neurons, tan-sigmoid as an activation function, and initialization of weights and bias, as discussed in [31], with the same objective function defined in (15) and (16). The objective function tends to minimize the objective function for optimal set of weights and biases.…”

Genetic algorithm initialized artificial neural network based temperature dependent small‐signal modeling technique for GaN high electron mobility transistors

“…Therefore, the alternative machine learning (ML) based modeling techniques seem very promising owing to their quick turn‐around with very good accuracy 24‐30 . One of the exciting features of the ML is its ability to predict the outcome in real‐time very quickly and this could be quite attractive for device modeling at high frequencies where the inter‐dependence of various device parameters on each other is huge 30 .…”

“…One of the exciting features of the ML is its ability to predict the outcome in real‐time very quickly and this could be quite attractive for device modeling at high frequencies where the inter‐dependence of various device parameters on each other is huge 30 . Furthermore, the ML based modeling discards the need to solve simultaneous complex equations involved in conventional methods and this reduces computational time with enhanced yield 26 . In this context, artificial neural networks (ANNs) and support vector regression are being frequently explored for modeling of GaN HEMTs 24‐31 .…”

Experimental insight into the temperature effects on DC and microwave characteristics for a GaAs pHEMT in multilayer 3‐D MMIC technology

“…In addition, a small-signal equivalent circuit model is extracted from the S-parameter measurements by using the well-known "cold" approach (V ds = 0 V). [27][28][29][30] Compared to the behavioral models like for instance those using artificial neural networks (ANNs), [31][32][33] the equivalent-circuit-based approach allows achieving a physically sound model that is more helpful as feedback for technologists. It is worth underlying that the small-signal equivalent circuit can be used as cornerstone for building both large-signal and noise microwave models.…”