大坝变形蚁群聚类径向基函数神经网络安全监控预测模型

Ant Colony Clustering Radial Basis Function Neural Network Model for Safety Monitoring of Dam Deformation

本文研究了蚁群聚类法和径向基函数神经网络的基本原理,结合大坝变形安全监控的要求,探讨了大坝变形监测数据聚类处理方法,构建了径向基神经网络隐层基函数,由此表征了大坝变形规律的影响因素与变形之间的非线性映射关系.通过上述研究,建立了大坝变形蚁群聚类径向基函数神经网络(ACC-RBF)安全监控模型.实例分析表明,所提出的模型比传统的径向基神经网络模型预测精度更高.

This paper studies the basic principle of ant colony clustering algorithm and radial basis function neural network. Combined with the safety requirements of dam deformation monitoring, the clustering meth- od for the monitoring data of dam deformation is explored~ the basis function in the hidden layer of radial basis function neural network is built~ and then the nonlinear mapping relationship between the factors which affect the deformation law of the dam and deformation, is shown. Through the above research, an ant colony cluste- ring radial basis function neural network model is established for safety monitoring of dam deformation. The case study shows that the prediction accuracy of the proposed model is higher than that of the traditional radial basis function neural network model.