改进递归最小二乘RBF神经网络溶解氧预测

为提高溶解氧预测的准确性，将基于改进型递归最小二乘算法优化的径向基函数（ RBF）神经网络方法应用于溶解氧预测。利用K均值聚类算法进行隐层单元中心选择；利用改进型递归最小二乘算法优化RBF神经网络隐含层到输出层的权值。仿真结果表明：该方法对溶解氧的预测具有较好的非线性拟合能力，预测精度优于RBF神经网络和递归最小二乘算法优化的RBF神经网络。

Dissolved oxygen prediction based on improved recursive least square RBF neural network

In order to improve accuracy of dissolved oxygen prediction,radial basis function( RBF)neural network based on improved recursive least square algorithm is applied to predict the dissolved oxygen. Using K means clustering algorithm to choose the center of hidden layer units and improved recursive least square algorithm is used to optimize the weights of hidden layer to output layer of RBF neural network. Simulation results show that the proposed method has good nonlinear fitting ability and its prediction precision is higher than RBF neural network and RBF neural network based on recusive least square algorithm.