Authors

José Cesáreo, Raimúndez Álvarez

Abstract

Evolution Strategies (ES) are stochastic optimization techniques obeying an evolutionist paradigm, that can be used to find global optima over a response hypersurface. The current investigation focuses on Port Controlled Hamiltonian (PCH) systems stabilization, using the unsupervised learning capabilities of ES’s inherited from their evolutionist paradigm. The training process intends to build a complementary Energy Function ( H _ a ) which guarantees local asymptotic stability at the desired equilibrium point.

Keywords

Evolution Strategy; Attraction Basin; Evolution Strategy; Exogenous Parameter; Local Asymptotic Stability

Citation

BibTeX

@inbook{Ces_reo,
  title={{Port Controller Hamiltonian Synthesis Using Evolution Strategies}},
  ISBN={9783540428909},
  DOI={10.1007/3-540-45606-6_11},
  booktitle={{Dynamics, Bifurcations, and Control}},
  publisher={Springer Berlin Heidelberg},
  author={Cesáreo, José and Álvarez, Raimúndez},
  pages={159--172}
}

Download the bib file

References

  • H.-P. Schwefel, Advances in Artificial Life. Third International Conference on Artificial Life (1995)
  • Putting energy back in control. IEEE Control Syst. 21, 18–33 (2001) – 10.1109/37.915398
  • R. Ortega, Proceedings of Lagrangian and Hamiltonian Methods for Nonlinear Control (2000)
  • Hauser, J., Sastry, S. & Kokotovic, P. Nonlinear control via approximate input-output linearization: the ball and beam example. IEEE Trans. Automat. Contr. 37, 392–398 (1992) – 10.1109/9.119645
  • A.J. Schaft van der, L 2 Gain and Passivity Techniques in Nonlinear Control (1996)
  • Back, T., Hammel, U. & Schwefel, H.-P. Evolutionary computation: comments on the history and current state. IEEE Trans. Evol. Computat. 1, 3–17 (1997) – 10.1109/4235.585888
  • Sjöberg, J. & Ljung, L. Overtraining, Regularization, and Searching for Minimum in Neural Networks. IFAC Proceedings Volumes 25, 73–78 (1992) – 10.1016/s1474-6670(17)50715-6