论文部分内容阅读
推导了多输入多输出Hammerstein模型的矩阵格式,并提出了一种改进的新型神经动力学算法.应用此算法,可同时辨识出Hammerstein模型的多组未知参数,提高了收敛精度和速度.首先,对改进的新型神经动力学算法进行了参数的收敛性分析.之后,推导了基于Hammerstein模型的混合模型,并利用其建立实际模型与机理模型之间的偏差模型,具有很好的补偿效果.由于改进的新型神经动力学方法可以在线调整Hammerstein模型参数,所以混合模型可以准确地模拟复杂过程在大范围内的动态行为.实验表明该方法的合理性和有效性.
The matrix format of multi-input multi-output Hammerstein model is deduced and an improved new neuro-dynamics algorithm is proposed.Using this algorithm, multiple sets of unknown parameters of Hammerstein model can be identified simultaneously to improve the accuracy and speed of convergence.Firstly, After analyzing the convergence of the new improved neuro-dynamics algorithm, a hybrid model based on Hammerstein model is deduced, and the deviation model between the actual model and the mechanism model is established, which has a good compensation effect. The new improved neuro-dynamics method can adjust the Hammerstein model parameters online, so the hybrid model can accurately simulate the dynamic behavior of complex processes in a wide range.The experiments show that the method is reasonable and effective.