Neural Networks Based Internal Model Adaptive Tracking Control System for Structural Testing Machine
He Yubin, Liu Yanqiu, Yan Guirong, Xu Jianxue
(Xi'an Jiaotong University, Xi'an Shaanxi, 710049£©

Abstract: A nonlinear internal model adaptive control method based on neural networks, with respect of the complex nonlinearities and uncertainties in electrohydraulic se rvo structural testing system, is presented and an internal model adaptive loadi ng control system for the structural testing machine is designed in this paper. A feedforward neural network is defined to learn timevarying system dynamics as the internal model, which can be modified onª²line. The controller can be design ed with little priori information required about the controlled plant and regula ted onª²line by using the measured input/output data with the neural network lea rning method derived from the BP algorithm. The effectiveness of the tracking co ntrol system is verified by experimental results.
Keywords: structural testing system, neural ne twork, neural internal model, adaptive control
                        robustness.