基于神经网络的异步电动机自适应动态面控制

Neural Network-Based Adaptive Dynamic Surface Control for Induction Motors

针对虚拟控制率连续进行高阶求导会引发"计算爆炸"问题,本文结合动态面技术和反步法,给出了考虑铁损异步电动机自适应神经网络位置跟踪控制方法及考虑铁损的异步电机的动态模型;并基于动态面技术,对自适应神经网络控制器进行设计,同时对其稳定性进行分析。为验证本文控制策略的有效性,在Matlab环境下进行仿真分析。仿真结果表明,在负载扰动的情况下,本文提出的方法使考虑铁损的异步电动机系统实现了良好的位置跟踪效果,对电机参数变化和外部负载扰动具有较强的鲁棒性。该方法解决了传统反步法对虚拟控制函数连续微分引发的"计算爆炸"问题,具有一定的理论意义和实际应用价值。

To overcome the problem of'explosion of complexity'inherent in the traditional backstepping design procedure,an adaptive neural networks backstepping dynamic surface control(DSC)approach to position tracking control is developed for induction motors(IMs)with iron losses.Firstly,the dynamic mathematical model of the IMs has been given in the paper.By incorporating the dynamic surface control technique into a fuzzy approximation based neural networks backstepping technique,an adaptive neural networks control approach is developed.Meanwhile,it is proved that the tracking error converges to a small neighborhood of the origin and all the closed-loop signals are bounded.Simulation results illustrate the effectiveness of the proposed approach including elimination of influences from the load disturbance and parameter uncertain.The proposed control method is able to overcome the problem of'explosion of complexity'by introducing first-order low-pass filters.And it has some important value in theory and application.