基于RBF神经网络的机械臂运动控制算法及应用研究-控制理论与控制工程专业论文.docxVIP

基于 RBF 神经网络的机械臂运动控制算法及应用研究 兰州交通大学硕士学位论文 万方数据 万方数据 类方法相比，基于EC-RBF学习算法的RBFNN在机械臂轨迹跟踪控制中跟踪效果更好。 关键词：径向基函数神经网络；熵聚类；模型参考自适应控制；机械臂；轨迹跟踪 论文类型：应用基础研究 - II -  Abstract Trajectory tracking control of robot manipulator is the important part in its motion control. Control system of robot manipulator is a multi-variable, strong coupling, and highly nonlinear uncertain systems, trajectory tracking requires the robot manipulator to move according to a desired trajectory that has been given. Model reference adaptive control (MARC) based on radial basis function neural networks (RBFNN) not only has strong capability of dynamic approximation and adaptive by RBFNN, but also could improve the control real-time and immunity interference immunity, thus it has been used in nonlinear control widely. But the traditional learning algorithm of RBFNN, based on K-means clustering, is very sensitive to algorithm initial value, and it also demands that the number of all input samples and RBF should be given in advance. For this sensitivity problem of initial value, the thesis improves the learning algorithm of RBFNN based on K-means clustering, and uses a learning algorithm based on entropy clustering-radial basis function (EC-RBF) to train the RBFNN. Through adopting this new method, neural Networks solution of robot manipulator inverse kinematics is achieved. Using this method to train the two RBFNN that the neural Networks model reference adaptive control system of robot manipulator includes, the dynamic model identification and trajectory tracking control of unknown robot manipulator are implemented. Comparing with the traditional K-means clustering algorithm, the simulation result indicates that this improvement algorithm is more effective and superior. The main contents are below: To study the basic theory and structure of RBFNN, and study the 1improvement learning algorithm EC-RBF, which is based on entropy clustering of RBFNN. Using the entropy clustering, the initial value of traditiona