Title of article :
Jiangsu Province Key Laboratory of Aerospace Power Systems, College of Energy and Power Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China
Author/Authors :
Wang, Chao School of Mechanical Engineering - Nanjing University of Science and Technology, China , Hou, Yuanlong School of Mechanical Engineering - Nanjing University of Science and Technology, China , Liu, Rongzhong School of Mechanical Engineering - Nanjing University of Science and Technology, China , Gao, Qiang School of Mechanical Engineering - Nanjing University of Science and Technology, China , Hou, Runmin School of Mechanical Engineering - Nanjing University of Science and Technology, China
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.
Keywords :
Dynamic Compensation , Neural Network , Fuzzy Multiresolution Wavelet , Control , Electric Load Simulator
Journal title :
Shock and Vibration
