基于RBF神经网络的烧结终点预测模型

本文提出一种基于径向基函数（RBF）神经网络的烧结终点预测模型。该模型首先采用改进的最近邻聚类算法确定径向基函数中心，接着应用递推最小二乘法训练网络的权值。通过现场采集数据对该模型进行仿真，其实验结果表明，该模型具有较好的学习能力和泛化能力，为烧结终点的预测提供了一种新的解决方法。

Burning through Point Prediction Model Based on RBF Neural Network

In this paper,a burning through point prediction model based on RBF neural network is presented. The model uses an improved nearest - neighbor clustering algorithm to select the RBF center, and a recursive least square algorithm to train weights of the RBF neural network. The simulation results show that the network has excellent learning capacities and generalization ability. Therefore the model is a new effective approach for BTP prediction.