Scholarlink

<p>This study aims at proposing a more efficient control system for uncertain nonlinear systems. A novel and efficient neural network model, termed as Self-organizing Takagi–Sugeno–Kang fuzzy elliptic type-2 cerebellar model articulation controller (SO-TSK-FT2C), is proposed, which uses a self-organizing mechanism to adjust the network layers for achieving efficient structure. The learning laws for system parameters are derived based on the gradient descent algorithm, aimed at minimizing the cost function across all rules of the proposed structure. For control applications, the SO-TSK-FT2C serves as the main controller, supplemented by a robust compensator that addresses residual errors. The stability of the control system is ensured through Lyapunov stability theory. Two examples, a robot manipulator and a chaotic system, are demonstrated to illustrate the effectiveness of the proposed algorithm. Some simulation results, including comparisons with other models, have confirmed the superiority in control performance for the proposed control system.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Self-Organizing Takagi–Sugeno–Kang Fuzzy Elliptic Type-2 CMAC for Nonlinear Systems with Uncertainty

  • 期刊论文

  • 发表日期：

    2025年5月20日

查看全文
  • Duc-Hung Pham,
  • Chih-Min Lin,
  • Van-Nam Giap,
  • Van-Trung Nguyen,
  • Ngoc-Thang Pham

摘要

This study aims at proposing a more efficient control system for uncertain nonlinear systems. A novel and efficient neural network model, termed as Self-organizing Takagi–Sugeno–Kang fuzzy elliptic type-2 cerebellar model articulation controller (SO-TSK-FT2C), is proposed, which uses a self-organizing mechanism to adjust the network layers for achieving efficient structure. The learning laws for system parameters are derived based on the gradient descent algorithm, aimed at minimizing the cost function across all rules of the proposed structure. For control applications, the SO-TSK-FT2C serves as the main controller, supplemented by a robust compensator that addresses residual errors. The stability of the control system is ensured through Lyapunov stability theory. Two examples, a robot manipulator and a chaotic system, are demonstrated to illustrate the effectiveness of the proposed algorithm. Some simulation results, including comparisons with other models, have confirmed the superiority in control performance for the proposed control system.