论文部分内容阅读
在热工过程模型辨识中,被控对象动态特性往往表现出非线性、慢时变、大迟延和不确定性等特点,这使得难以对其建立比较精确的模型。为了达到精确建模的目的,提出一种基于微分进化算法和径向基函数神经网络的辨识方法。该方法采用基于能量分布正交最小二乘学习算法的径向基函数(radial basis function,RBF)神经网络,通过改进的微分进化算法,对神经网络辨识系统进行参数优化,使RBF神经网络能够更快、更精确地逼近实际系统的输出,达到精确建模的目的。仿真结果表明,在采用改进的RBF网络对热工复杂对象进行辨识时,通过微分进化算法进一步确定其最佳参数,可以取得更好的辨识效果。
In the identification of thermal process model, the dynamic characteristics of the controlled object often show nonlinear, slow time-varying, large delay and uncertainty, which makes it difficult to establish a more accurate model. In order to achieve accurate modeling, a method of identification based on differential evolution algorithm and radial basis function neural network is proposed. In this method, a radial basis function (RBF) neural network based on the energy distribution orthogonal least squares learning algorithm is used to optimize the neural network identification system through the improved differential evolution algorithm to make the RBF neural network more Fast, more accurate approximation of the actual system output, to achieve accurate modeling purposes. The simulation results show that when the improved RBF network is used to identify the thermal complex objects, the optimal parameters can be further determined by the differential evolution algorithm to obtain better identification results.