Intelligent bounds on modeling uncertainties: applications to sliding mode control of a magnetic levitation system

Robust control techniques such as sliding mode control (SMC) require a dynamic model of the plant and bounds on modeling uncertainties to formulate control laws with guaranteed stability. Although techniques for modeling dynamic systems and estimating model parameters are well established, very few procedures exist for estimating uncertainty bounds. In the case of SMC design, a conservative global bound is usually chosen to ensure closed-loop stability over the entire operating space. The primary drawbacks of this conservative approach are excessive control activity and reduced performance, particularly in regions of the operating space where the model is accurate. In this paper, a novel approach to estimating uncertainty bounds for dynamic systems is introduced. This approach uses a unique artificial neural network (ANN), the 2-sigma network, to bound modeling uncertainties online. This intelligent bounding technique is applied to an industrial SMC problem, magnetic levitation of a ball bearing rotor, where experiments demonstrate improved tracking performance and reduced control activity.