基于径向基函数神经网络迟滞非线性自适应控制

The Adaptive Control for Hysteresis Nonlinear Systems via Neural Networks

提出了一种新的动态迟滞非线性模型.将一定数量不同死区宽度的back lash模型并行相加,作为一个动态系统以仿真执行器中的迟滞特性.利用该模型,采用伪控制方法设计了一套具有未知迟滞特性非线性系统的神经网络自适应控制方案,通过自适应算法来调整干扰项的上限.采用Lyapunov稳定性理论进行了严格证明,仿真试验验证了所提方案的有效性.

A novel class of hysteresis models was proposed. A certain number of different deadband width backlash models are superposed, which represents a dynamics to mimic hysteresis in the actuator. With the model proposed, an radial basis function neural network （RBFN）-based adaptive control scheme for nonlinear systems with unknown hysteresis nonlinearity was developed. The control scheme adopts the design method of pseudo-control. Without the assumption of boundedness of disturbance term, it is tuned through adaptive algorithm. The stability is rigidly proved via Lyapunov theory and the effectiveness of the proposed control scheme is illustrated through simulation.