Passivity enforcement for passive component modeling subject to variations of geometrical parameters using neural networks

@article{Guo2012PassivityEF,
  title={Passivity enforcement for passive component modeling subject to variations of geometrical parameters using neural networks},
  author={Zhiyu Guo and Jianjun Gao and Yazi Cao and Qijun Zhang},
  journal={2012 IEEE/MTT-S International Microwave Symposium Digest},
  year={2012},
  pages={1-3}
}
A novel passivity enforcement technique for passive component modeling subject to variations of geometrical parameters is proposed using combined neural networks and rational functions. A constrained neural network training process to enforce passivity of Y-parameters is introduced. Eigenvalues of Hamiltonian matrix for parametric model at many geometrical samples are used simultaneously as constraints for neural network training. Furthermore, a new passivity conditioning parameter e is… CONTINUE READING

References

Publications referenced by this paper.
Showing 1-5 of 5 references

Rational approximation of frequency domain responses by vector fitting

  • A. Semlyen
  • IEEE Trans . Power Delivery .
  • 1999

Similar Papers

Loading similar papers…