基于改进PSO-ELM算法的混凝土坝变形非线性监控模型

Nonlinear Monitoring Model of Concrete Dam Deformation Based on Improved PSO-ELM Algorithm

针对混凝土坝变形模型高度非线性问题,将极限学习机(ELM)用于混凝土坝变形监控模型的构建中,由于极限学习机的精度受输入权值和隐含层阈值的影响,引入改进的粒子群算法(PSO)进行最优求解,从而建立基于改进PSO-ELM算法的混凝土坝变形非线性监控模型。实例应用结果表明,该模型不仅可行、有效,且具有较强的学习能力和泛化能力。

To solving the highly nonlinear problem of concrete dam deformation model, extreme learning machine （ELM） was used to establish monitoring model of concrete dam deformation. However, the accuracy of the ELM model was affected by the input weight and threshold of the hidden layer. Therefore, improved particle swarm optimization was used to solve the model. Thus, nonlinear monitoring model of concrete dam deformation based improved PSO-ELM was established. The example application shows that the model is not only feasible and effective, but also has strong learning and generalization ability.