An Enhanced Dynamic Neuro-Space Mapping Technique for Nonlinear Device Modeling
Accurate modeling of nonlinear microwave devices is critical for reliable design of microwave circuit and system. In this paper, a more general Neuro-SM method, i.e., an enhanced dynamic neuro-space mapping (Neuro-SM) is proposed to fulfill the needs of the increased modeling complexity. The proposed technique retains the ability of the existing dynamic Neuro-SM in modifying the dynamic voltage relationship between the coarse model and the desired model. The proposed Neuro-SM also considers output/current mapping besides input/voltage mappings. In this way, the enhanced dynamic Neuro-SM can produce a more accurate model of microwave devices with more dynamics and nonlinearity. The validity and efficiency of the enhanced dynamic Neuro-SM method are demonstrated through a high-electron mobility transistor (HEMT) modeling example.
KeywordsArtificial network Space mapping Neuro-SM Nonlinear device modeling
This work is supported by the Key project of Tianjin Natural Science Foundation (No. 16JCZDJC38600).
- 1.Zhang, L., Xu, J., Yagoub, M., et al.: Neuro-space mapping technique for nonlinear device modeling and large-signal simulation. In: IEEE MIT-S International Microwave Symposium, Philadelphia, PA, pp. 173–176, June 2003Google Scholar
- 4.Zhu, L., Liu, K., Zhang, Q., et al.: An enhanced analytical neuro-space mapping method for large-signal microwave device modeling. In: IEEE MIT-S International Microwave Symposium Digest, Montreal, QC, pp. 1–3, June 2012Google Scholar