上海交通大学学报(自然版) ›› 2012, Vol. 46 ›› Issue (10): 1675-1679.

• 水利工程 • 上一篇    下一篇

海堤渗压多测点径向基函数监测模型的建立

黄铭1,刘俊2   

  1. (1. 合肥工业大学 土木与水利工程学院, 合肥 230009; 2.上海交通大学 船舶海洋与建筑工程学院, 上海 200240)
  • 收稿日期:2011-03-16 出版日期:2012-10-30 发布日期:2012-10-30
  • 基金资助:

    国家自然科学基金资助项目(50979056)

Establishment of Sea Wall Seepage Pressure Multi-point RBF Monitoring Model

 HUANG  Ming-1, LIU  Jun-2   

  1. (1.School of Civil Engineering, Hefei University of Technology, Hefei 230009, China; 2.School of Naval Architecture, Ocean and Civil Engineering, Shanghai Jiaotong University, Shanghai 200240, China)
  • Received:2011-03-16 Online:2012-10-30 Published:2012-10-30

摘要: 为综合多测点监测信息建立海堤渗压预测模型,揭示其受海洋潮位等因素影响的复杂而特殊的变化规律,以径向基函数(RBF)神经网络为建模工具,采用前期潮位因子、积分型降雨因子、时效因子构建模型输入层,对符合条件的多个渗压测点进行综合训练、预测.同时根据海堤渗压特点,对建模中RBF网络的计算中心选取方法加以探讨,进而结合模糊C均值聚类算法确定计算中心.以浦东海堤实测资料实现了该模型建立的具体过程,取得理想效果,并给出了应用建议.    

关键词: 海堤渗压, 多测点监测模型, 径向基函数, 影响因子, 模糊C均值聚类

Abstract: In order to establish multi-point sea wall seepage pressure monitoring model to describe its rules considering tidewater etc., radial basis function (RBF) artificial neural network was used together with sea wall seepage pressure effect factors analysis. Former tidewater factor, integral rain factor and time effect factor were put into the network as input units, while multiple suitable seepage pressure survey points were taken as output units together. Furthermore, the method to pre-select RBF center considering sea wall seepage pressure character was studied. Then fuzzy C-means algorithm (FCM) was used to adjust and decide them. The instance of Pudong sea wall shows the process of establishing seepage pressure multi-point RBF monitoring model which has good results. Suggestions of application were presented also.

Key words: sea wall seepage pressure, multi-point monitoring model, radial basis function(RBF), effect factor, fuzzy C-means algorithm(FCM)

中图分类号: