Scholarlink

<p>In practical application, the external disturbances and parameter uncertainties have a significant impact on the control performance of robot manipulator especially when the disturbance frequencies are unknown. Moreover, the absence of actuator dynamics in the robot manipulator dynamics may affect the model accuracy and generate unmodeled disturbances. In this paper, a novel internal model-based neural network controller is proposed to solve the position tracking problem of robot manipulator driven by permanent magnet synchronous motors subject to external disturbances and parameter uncertainties. In particular, the controller design takes into account both the mechanical and electrical subsystems. For the mechanical subsystem, the internal model method is applied to compensate for the disturbances and realize position tracking. For the electrical subsystem, the neural network method is applied to approximate the unknown dynamics and realize current tracking. Finally, experimental results are given to demonstrate the superior performance of the proposed controller.</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

Internal Model-Based Neural Network Control for Robot Manipulator Including Actuator Dynamics

  • 期刊论文

  • 发表日期：

    2026年4月8日

查看全文
  • Zhaowu Ping,
  • Yuqian He,
  • Chengtao Xu,
  • Yunzhi Huang,
  • Jun-Guo Lu,
  • Hai Wang

摘要

In practical application, the external disturbances and parameter uncertainties have a significant impact on the control performance of robot manipulator especially when the disturbance frequencies are unknown. Moreover, the absence of actuator dynamics in the robot manipulator dynamics may affect the model accuracy and generate unmodeled disturbances. In this paper, a novel internal model-based neural network controller is proposed to solve the position tracking problem of robot manipulator driven by permanent magnet synchronous motors subject to external disturbances and parameter uncertainties. In particular, the controller design takes into account both the mechanical and electrical subsystems. For the mechanical subsystem, the internal model method is applied to compensate for the disturbances and realize position tracking. For the electrical subsystem, the neural network method is applied to approximate the unknown dynamics and realize current tracking. Finally, experimental results are given to demonstrate the superior performance of the proposed controller.