In some cases, the difference of DC responses between the coarse model and devices is large, however the nonlinear responses are similar. Concerning the complex modeling process, an improved Neuro-Space Mapping (Neuro-SM) structure was proposed. The capacitors and inductors were added on the traditional Neuro-SM model to constitute a new Neuro-SM model. The DC component of the input signal was adjusted by the mapping network,but the AC component is independent on the mapping network. The new model can improve the DC feature without changing AC characteristic and match the device with a few optimization variables and simple mapping relationship. The simulation experimental results demonstrate that the enhanced Neuro-SM model can make full use of the similar nonlinear responses between the coarse model and devices, maintaining the accuracy of the model as well as simplifying the modeling process.
闫淑霞 张齐军. 神经网络空间映射结构的研究与改进[J]. 计算机应用, 2014, 34(12): 3621-3623.
YAN Shuxia ZHANG Qijun. Research and improvement of neuro-space mapping structure. Journal of Computer Applications, 2014, 34(12): 3621-3623.
［1］ZHANG Q J, GUPTA K C. Neural networks for RF and microwave design ［M］. Boston: Artech House, 2000:3-4.
［2］KABIR H, ZHANG L, YU M, et al. Smart modeling of microwave devices ［J］. IEEE Microwave Magazine, 2010, 11(3): 105-118.
［3］TIAN Y, ZHANG Q. Knowledge-based neural networks for modeling of radio-frequency/microwave components ［J］. Journal of University of Electronic Science and Technology of China, 2011, 40(6): 815-824. (田毅贞,张齐军. 知识型神经网络的射频/微波器件建模方法［J］. 电子科技大学学报,2011, 40(6): 815-824.)
［4］KABIR H, WANG Y, YU M, et al. Neural network inverse modeling and applications to microwave filter design ［J］. IEEE Transactions on Microwave Theory and Techniques, 2008, 56(4): 867-879.
［5］GARCIA J P, PEREIRA F Q, REBENAQUE D C, et al. A neural-network method for the analysis of multilayered shielded microwave circuits ［J］. IEEE Transactions on Microwave Theory and Techniques, 2006, 54(1): 309-320.
［6］O’BRIEN B, DOOLEY J, BRAZIL T J. RF power amplifier behavioral modeling using a globally recurrent neural network［C］// Proceedings of the 2006 IEEE Microwave Symposium Digest. Piscataway: IEEE, 2006: 1089-1092.
［7］ZHANG C. Behavioral modeling of power amplifier using recurrent neural networks ［D］. Tianjin: Tianjin University, 2014.(张川.递归神经网络对功率放大器的行为级建模［D］. 天津:天津大学,2014.)
［8］ZHANG L, XU J, YAGOUB M, et al. Efficient analytical formulation and sensitivity analysis of neuro-space mapping for nonlinear microwave device modeling［J］. IEEE Transactions on Microwave Theory and Techniques, 2005, 53(9): 2752-2767.
［9］GORISSEN D, ZHANG L, ZHANG Q, et al. Evolutionary neuro-space mapping technique for modeling of nonlinear microwave devices［J］. IEEE Transactions on Microwave Theory and Techniques, 2011, 59(2): 213-229.
［10］ZHANG L, ZHANG Q, WOOD J. Statistical neuro-space mapping technique for large-signal modeling of nonlinear device［J］. IEEE Transactions on Microwave Theory and Techniques, 2008, 54(11): 2453-2467.
［11］ZHANG L, XU J, YAGOUB M, et al. Neuro-space mapping technique for nonlinear device modeling and large-signal simulation［C］// Proceedings of the 2003 IEEE Microwave Symposium Digest. Piscataway: IEEE, 2003: 173-176.
［12］Advanced Design System (ADS): Ver. 2013[CP/OL].[2013-10-10].http://www.keysight.com/zh-CN/pc-1297113/advanced-design-system-ads?nid=-34346.0&cc=CN&lc=chi
2014, Vol. 34 
