As the structure of parallel robot is special in general mechanical and electrical systems, its forward kinematics needs to be solved by nonlinear equations. In this paper, for the issue that numerical iterative method requires complex mathematical derivation and programming, and is sensitive to the initial value, a Neuro-fuzzy system is proposed for solving forward kinematics model of parallel robot. Meanwhile, inverse kinematics is used for training database, knowledge representation ability of fuzzy theory and self-learning ability of neural network are combined to overcome the shortcomings that neural network cannot express human language and fuzzy system do not have self-learning ability. In addition, training and generation efficiency of the model can also be improved by reducing the input dimension reasonably. Simulation results have been showed that, in the premise of efficiency, accuracy of forward kinematics model using Neuro-fuzzy system is better than Newton-Raphson iterative method, and has better versatility.
Forward Kinematics Solution of Stewart-Gough using Improved Hybrid Strategy (Neural Network and 3rd-order Newton-Raphson)
