Transformation of Neural State Space Models into LFT Models for Robust Control Design
暂无分享,去创建一个
This paper considers the extraction of linear state space models and uncertainty models from neural networks trained as state estimators with direct application to robust control. A new method for writing a neural state space model in a linear fractional transformation form in a non-conservative way is proposed, and it is demonstrated how a standard robust control law can be designed for a system described by means of a multi layer perceptron.
[1] Johan A. K. Suykens,et al. Lur'e systems with multilayer perceptron and recurrent neural networks: absolute stability and dissipativity , 1999, IEEE Trans. Autom. Control..
[2] J. Doyle,et al. Robust and optimal control , 1995, Proceedings of 35th IEEE Conference on Decision and Control.
[3] J. Suykens,et al. Nonlinear system identification using neural state space models, applicable to robust control design , 1995 .