混沌神经网络模型参考自适应控制器设计

研究了非线性的神经网络模型参考自适应控制器设计问题。将混沌机制引入常规BP算法,利用混沌机制固有的全局游动,逃出权值优化过程中存在的局部极小点,解决了网络训练易陷入局部极小点的问题。通过训练神经网络模型参考自应用控制器和辨识器,完成了对一类复杂离散非线性系统的控制。给出了具体的算法步骤。仿真结果表明了混沌BP算法优于常规BP算法。有效地提高了控制精度和适时性。

Design of adaptive controller for the chaotic neural network model reference

The design of adaptive controller for the chaotic neural network model reference is studied. Chaotic mechanism is introduced to normal BP algorithm, and the problem of local limit value for network is solved using global moving characteristic of chaotic mechanism is weight optimization. By training the adaptive controller and identifier for neural network model reference the control problem of complex nonlinear discrete system is completed. The steps of the algorithm are given. The simulation results show that the chaotic BP algorithm is more effective than the normal BP algorithm. The control precision and instantaneity are improved effectively.