论文信息 - Fast and accurate modeling of embedded passives in multi-layer printed circuits using neural network approach

Fast and accurate modeling of embedded passives in multi-layer printed circuits using neural network approach

In this paper, we present a new approach to modeling of high-frequency effects of embedded passive components in multilayer printed circuits based on artificial neural networks. The training data are generated by electromagnetic simulators, e.g., Ansoft-HFSS and Sonnet-Lite software. The models are trained to learn the S-parameters of the embedded passives versus physical and geometrical parameters. The models are fast and represent the EM based information of the components. They can be used for efficient design of high-frequency circuits and systems.

[1] Giulio Antonini,et al. Gradient evaluation for neural-networks-based electromagnetic optimization procedures , 2000 .

[2] M.C.E. Yagoub,et al. EM Based Optimization of Microwave Circuits by Neural Models and their Application to Power Distribution and Decoupling Optimization , 2001, 2001 31st European Microwave Conference.

[3] Roop L. Mahajan,et al. Applications of knowledge‐based artificial neural network modeling to microwave components , 1999 .

[4] Mankuan Vai,et al. Neural networks in microwave circuit design?beyond black-box models (invited article) , 1999 .

[5] Fang Wang,et al. A hierarchical neural network approach to the development of library of neural models for microwave design , 1998, IMS 1998.

[6] Qi-Jun Zhang,et al. Neural Networks for RF and Microwave Design , 2000 .

[7] Michel Nakhla,et al. A neural network modeling approach to circuit optimization and statistical design , 1995 .