基于微粒群算法的海堤渗压RBF神经网络监测模型

发布时间：2018-11-12 13:19

【摘要】：为提高海堤安全监控能力,从渗压实测数据以及潮位因子和降雨因子入手,使用影响因子的合理形式,利用径向基函数(RBF)神经网络建立渗压监测模型,推导微分进化微粒群优化算法(DPSO)速度和位移进化的数值计算方程,以此确定渗压RBF神经网络模型的聚类中心,并由此对渗压进行拟合和预测。以120组实测样本对模型进行训练拟合,并对后期60组渗压进行预测,得到拟合段平均相对误差为0.83%,相应预测段为1.71%。实际应用表明,经微分进化微粒群算法优化后,渗压RBF神经网络模型可以有效反映及预测渗压变化。
[Abstract]:In order to improve the safety monitoring ability of seawall, starting from the measured data of seepage pressure, tidal level factor and rainfall factor, and using the reasonable form of influence factor, the radial basis function (RBF) neural network is used to establish the seepage pressure monitoring model. The (DPSO) velocity and displacement evolution equations of differential evolution particle swarm optimization algorithm are derived to determine the clustering center of the RBF neural network model of osmotic pressure and to fit and predict the osmotic pressure. The model was trained and fitted with 120 groups of measured samples, and 60 groups of osmotic pressure were predicted in the later stage. The average relative error of fitting section was 0.83 and the corresponding prediction section was 1.71. The practical application shows that the RBF neural network model of osmotic pressure can effectively reflect and predict the change of osmotic pressure after the differential evolution particle swarm optimization.
【作者单位】：合肥工业大学土木与水利工程学院;三峡库区地质灾害教育部重点实验室(三峡大学);
【基金】：三峡库区地质灾害教育部重点实验室(三峡大学)开放研究基金项目(2015KDZ03) 水利部公益性行业科研专项经费资助项目(201401063-02)
【分类号】：U656.314

【相似文献】