【摘要】 结合主元分析(PCA)和径向基函数(RBF)神经网络,建立了地下水动态模拟与软测量预测模型。通过主元分析法提取主要成分,实现数据预处理;将选取的主要成分作为RBF神经网络的输入;采用k均值聚类算法确定RBF网络隐含层参数,并用递进最小二乘法确定输出层权值。仿真结果表明,该模型优化了网络结构,提高了预测精度。更多还原

【Abstract】 This paper uses Principal Component Analysis(PCA) and Radial Basis Function(RBF) neural network,and establishes a forecasting model for dynamic simulation of groundwater and soft measurement.Through principal component analysis method to extract the main components and realize the data preprocessing.The main components are selected as the input of RBF neural network.Using K means clustering algorithm to determine the RBF hidden layer of network parameters,and determine the output layer weights using progressive method of least squares.更多还原