基于RBF神经网络补偿的抑振方法与系统
By using an RBF neural network-based compensation method, a dynamic model considering various nonlinear factors and disturbances was established. Uncertain terms in the dynamic equations were identified and compensated, solving the problem of end-effector vibration in a flexible spatial robotic arm, improving control accuracy and suppressing deformation fluctuations.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- NORTHEASTERN UNIV CHINA
- Filing Date
- 2023-11-13
- Publication Date
- 2026-07-17
AI Technical Summary
Spatial flexible robotic arms are prone to end effector chatter during high-speed movement, which affects control accuracy and the completion of grasping tasks, especially when facing uncertain grasping objects, which increases the difficulty of control.
By employing an RBF neural network-based compensation method, the kinetic and potential energy of the servo system are established by determining the displacement vectors of the robotic arm and the underactuated hand. The dynamic equations are determined in conjunction with external disturbances, and the RBF neural network is used to identify and compensate for uncertain terms in the dynamic equations to establish a dynamic model to suppress vibration.
It improves the control precision of the spatial flexible robotic arm, suppresses deformation fluctuations, reduces chatter, and achieves high-precision grasping tasks.
Smart Images
Figure CN117656057B_ABST