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

Zi-Qi Wang, Li-jiang Li, Fei Chao, Chih-Min Lin, Longzhi Yang, Changle Zhou, Xiang Chang, Changjing Shang, Qiang Shen

Research output: Contribution to journalArticlepeer-review

Abstract

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 -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.
Original languageEnglish
Article number109274
Number of pages10
JournalKnowledge-Based Systems
Volume251
Early online date27 Jun 2022
DOIs
Publication statusPublished - 5 Sep 2022

Fingerprint

Dive into the research topics of 'A Type 2 wavelet brain emotional learning network with double recurrent loops based controller for nonlinear systems'. Together they form a unique fingerprint.

Cite this