改进的Elman网络在系统辨识中的应用

Application of Improved Elman Network in System Identification

介绍了E lm an网络在非线性动力学模型辨识中的应用原理,采用改进的E lm an动态递归网络实现对某平整机液压自动厚控系统(HAGC)的模型辨识。实验表明,E lm an网络利用内部状态反馈来描述系统的非线性动力学行为,提高了学习速度,适合于动态系统的实时辨识。

The principle of Elman network to identify nonlinear dynamic systems is introduced. An approach based on improved Elman dynamical recursive neural network to identify a hydraulic AGC dynamic model of temper mill is presented. The experiments show that it uses internal state feedback to describe the nonlinear dynamic rules of system, so that its learning speed is improved and it is suitable for real-time identification of dynamic systems.