柔性机器人的模糊神经网络控制研究

Study of Neuro-Fuzzy Network Control of a Flexible Robot

对具有未知或变化动力学特性的两连杆柔性机器人的轨迹跟踪问题进行了研究。采用Lagrange-Euler 方程建立了柔性机器人的动力学方程。鉴于柔性机器人的高度非线性和复杂性,用智能控制策略对系统进行控制,其中在系统的反馈控制回路上设计了模糊逻辑控制器,在前馈回路上设计了动态回归神经网络控制器。在三组不同阶跃输入条件下,对模糊逻辑及智能控制器进行了仿真研究。结果证明该方案可使系统性能得到极大的改善。

This paper deals with the tracking control problem of a rigid-flexible manipulator system with unknown and changing dynamics. Lagrange-Euler formulation is used to establish the dynamics of the robotic system. Because of the characteristics of high non-linearity and complexity of the robotic system, intelligent control strategy is proposed to control the system in this study, in which a fuzzy logic controller in the feedback configuration and an efficient dynamic recurrent neural network in the feedforward configuration are developed. Simulations are carried out for both the fuzzy logic controller and the proposed intelligent controller under the condition of three groups of step inputs. Results demonstrate that the performance of the system is greatly improved by using the proposed controller.