变结构神经网络自校正控制器的设计与研究

The Design and Research for Self-tune Controller via Variable Structure Neural Network

提出了一种变结构神经网络自校正控制器的设计方法，采用变结构神经网络ＢＰ优化算法设计控制器来控制实际对象，动态地修改神经网络的权值作为自校正方法，使系统较好地适应负荷和外扰的变化，获得满意的控制质量。

This paper presents a new self-tune controller design metho d based on the variable structure neural network.The variable structur e BP Optimization algorithm is used to design controller to control an actual system and the dynamic modification of the weighting value of a neural network. serves as a self-tune method. Hence the system can a dapt itself better to the variations in load and external interference , which has yielded a satisfied control quality.