中文摘要：

研究目的是建立考虑摩擦影响的复杂机构非线性运动参数辨识模型。复杂机构的动态响应为高度非线性，考虑摩擦的影响使机构运动的不确定性增大，机构控制的难度较大。应用动态神经网络技术，建立机构运动参数动态参数辨识模型，对柔性机构的运动参数进行辨识和预测。通过机构实例的验证，该方法计算速度较快，精度较高，为实现复杂大系统的辨识提供了一种有效可行的方法。

英文摘要：

The aim of the research is to setup motive parameters prediction model of complicated mechanism nonlinear motion. The dynamic response of the complicated mechanism is high nonlinear. The motion of the mechanism is very difficult to be controlled because of the uncertain friction. Via dynamic ANN method, establish prediction and identification model of mechanism dynamic parameters. The results of prediction and identification prove that the training speed and precision are high. This method provided an available way for prediction of complicated mechanism.