Evolutionary Neuro-Space Mapping Technique for Modeling of Nonlinear Microwave Devices

Abstract

Abstract-This paper presents a new advance in Neuro-space mapping (Neuro-SM) techniques for modeling nonlinear microwave devices. Suppose that existing device models (namely, coarse models) cannot match the behavior of a new device (referred to as the fine model). By neural network mapping of the voltage and current signals from the coarse to the fine models, Neuro-SM can modify the behavior of the coarse model to match that of the fine model. However, the efficiency of mapping depends on both the mapping structure and the coarse model. In this paper, a structural optimization technique is presented to achieve optimal combinations of mapping structure and coarse model. An aggressive optimization formulation exploring detailed structural variations in both the mapping and the coarse model is proposed, where the internal branches of coarse models and separate mappings for the voltage and current at gate and drain are used as basic topology variables. The formulation of such a structural optimization by an evolutionary optimization algorithm is proposed. Numerical examples of metal-semiconductor field-effect transistor and high electron-mobility transistor modeling demonstrate that, by using the proposed algorithm, optimal combinations of space mapping and coarse model structures can be achieved leading to the best modeling accuracy with the simplest mapping function.Index Terms-Genetic algorithms, knowledge-based modeling, nonlinear device modeling, space mapping.

An advanced analytical neuro–space mapping technique with sensitivity analysis for transistor modeling

“…Our proposed neuro‐SM is a further advance over the previous techniques in other works , , , . Compared with the work of Zhang et al where only voltage mappings were considered, our proposed technique considers separate mappings for voltage and current.…”

“…Moreover, obvious accuracy improvement using the proposed neuro‐SM over the traditional neuro‐SM presented by Zhang et al can be observed. The proposed neuro‐SM model is more accurate than the resulting model built by the DC and small‐signal training methods of Gorissen et al and Zhu et al owing to the inclusion of large‐signal HB data for both voltage and current mapping neural network training.…”

“…When the existing model is poor or when the nonlinearity of the modeling transistor is high, there is no guarantee that only voltage mappings are sufficient to get the desired accuracy. D. Gorissen's work considered not only the voltage mappings but also the current mappings in the neuro‐SM . However, its focus was mainly on how to obtain the optimal combination of the existing model and the mappings so that the overall neuro‐SM model can produce the best accuracy.…”

“…D. Gorissen's work considered not only the voltage mappings but also the current mappings in the neuro-SM. 16 However, its focus was mainly on how to obtain the optimal combination of the existing model and the mappings so that the overall neuro-SM model can produce the best accuracy. The analytical relationships between the neuro-SM model and the existing model were not presented.…”

Accurate large-signal modeling using neuro-space mapping for power transistors

“…This technique uses neural networks to map the voltage or current signals of the existing device model into that of the device data. The Neuro-SM method can be applied to not only the simple DC and S-parameters modeling of nonlinear devices, but also the complex large-signal modeling [6,7,8]. In [9], a dynamic neural network is used as the mapping network for the Neuro-SM model of power transistors.…”