Online Machine Learning Based Controller for Coupled Tanks Systems

摘要

Controlling the behavior of unknown dynamical systems is challenging in the presence of uncertainties and complex nonlinearities. This paper proposes an online machine learning-based methodology to control dynamical systems without a priori knowledge of their dynamical models nor dependency on large-scale datasets. The proposed online controller is based on a class of artificial neural networks, called Radial Basis Function (RBF) network. The learning capability and low computational complexity of the proposed online controller makes it a promising approach to be utilized in real-time control of unknown dynamical systems. The satisfactory performance of the proposed method is validated by applying it to a coupled tanks system.