A Type 2 wavelet brain emotional learning network with double recurrent loops based controller for nonlinear systems

Conventional controllers for nonlinear systems often suffer from co-existences of non-linearity and uncertainty. This paper proposes a novel brain emotional neural network to address such challenges. The proposed network integrates a Type 2 wavelet neural network into a conventional brain emotional learning network which is further enhanced by the introduction of a recurrent structure. The proposed network, therefore, combines the advantages of the Type 2 wavelet function, recurrent mechanism, and brain emotional learning system, so as to obtain optimal performance under uncertain environments. The proposed network works with a compensator to mimic an ideal controller, and the parameters of both the network and compensator are updated based on laws derived from the Lyapunov stability analysis theory. The proposed system was applied to a z-axis microelectromechanical system gyroscope. The experimental results demonstrate that the proposed system outperformed other popular neural-network-based control systems, indicating the superiority of the proposed network-based controller.