Efficient Sensitivity Analysis of Dynamic Neuro-space Mapping for Transistor Modeling
In this paper, an enhanced dynamic Neuro-space mapping (Neuro-SM) method is proposed with emphasis on transistor modeling. By modifying the dynamic voltage relationships in an existing nonlinear model, the proposed Neuro-SM produces a new and more accurate model than the nonlinear model as well as the static Neuro-SM. Compared to the existing dynamic Neuro-SM, a new sensitivity analysis technique is derived to speed up the training of the proposed model with dc, small- and large-signal data. The validity and efficiency of the proposed Neuro-SM method are demonstrated by modeling examples of a GaAs high-electron-mobility transistor (HEMT). Suitable value of time delay parameter which is equal to one divided by 3 or 5 times of the largest frequency considered in simulation is suggested and demonstrated by the modeling example.
KeywordsNeural networks Neuro-SM Transistor modeling Optimization Simulation
This work is supported by Scientific Research Plan Project by Tianjin Education Commission (No. 2016CJ13).
- 1.Zhang, L., Xu, J., Yagoub, M., et al.: Neuro-space mapping technique for nonlinear device modeling and large-signal simulation. IEEE MIT-S Int. Microw. Symp. Philadelphia, PA, Jun. 2003, pp. 173–176Google Scholar
- 2.Zhu, L., Liu, K., Zhang, Q., et al.: An enhanced analytical neuro-space mapping method for large-signal microwave device modeling. IEEE MIT-S Int. Microw. Symp. Dig. Montreal, QC, Jun. 2012, pp. 1–3Google Scholar
- 6.Zhang, L., Xu, J., Yagoub, M.C., et al.: Efficient analytical formulation and sensitivity analysis of neuro-space mapping for nonlinear microwave device modeling. IEEE Trans. Microw. Theory Tech. 53(9), 2752–2767 (2005)Google Scholar
- 8.Medici 2013 I-2013.12-0. Synopsys Inc., Mountain View, CA, 2013Google Scholar