Control of the Electric Load Simulator Using Fuzzy Multiresolution Wavelet Neural Network with Dynamic Compensation. (11th January 2016)

• Record Type: Journal Article
• Authors: Wang, Chao; Hou, Yuanlong; Liu, Rongzhong; Gao, Qiang; Hou, Runmin
• Other Names: Silberschmidt Vadim V. Academic Editor.
• Is Part Of: Shock and vibration. Volume 2016(2016)
• Publication Date: 2016-01-11
• Subjects: Shock (Mechanics) -- Periodicals; Vibration -- Periodicals; 534.5
• DOI: 10.1155/2016/3574214
• Languages: English
• ISSNs: 1070-9622

Abstract

Abstract : A fuzzy multiresolution wavelet neural network (FMWNN) controller with dynamic compensation (DC) is proposed to address the complexities of the electric load simulator (ELS). The FMWNN acts as a main torque tracking controller, which takes full advantage of the merits of an ideal sliding mode, fuzzy rules, and multiresolution WNN. The fuzzy algorithm is used to dynamically adjust the weights of the WNN and effectively accelerate the convergence rate. In addition, the DC controller is designed to greatly decrease the effect of the approximation error and guarantee the system stability in the sense of the Lyapunov theory. Finally, the proposed algorithms are carried out on the semiphysical simulation platform, the precision and superiority of which are comparatively verified based on the simulation results.