基于径向基函数的海堤监控模型及预测置信度判别

黄铭; 刘俊

doi:10.13204/j.gyjz201309016

基于径向基函数的海堤监控模型及预测置信度判别

doi: 10.13204/j.gyjz201309016

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.
2. 上海交通大学船舶海洋与建筑工程学院,上海200240

基金项目:

国家自然科学基金项目(50979056)

详细信息

作者简介:
第一作者:黄铭，男，1972 年出生，博士，教授，博士生导师。email：Lsxhuangm@ hotmail.com

中图分类号: U656.2
计量
- 文章访问数: 70
- HTML全文浏览量: 1
- PDF下载量: 84
- 被引次数: 0
出版历程
- 收稿日期: 2012-10-15
- 刊出日期: 2013-09-20

SEA WALL MONITORING MODEL BASED ON RADIAL BASIS FUNCTION AND DISTINGUISHABILITY ON ITS FORECAST CONFIDENCE LEVEL

Huang Ming¹,
Liu Jun²

1.
1. School of Civil Engineering,Hefei University of Technology,Hefei 230009,China;
2.
2． School of Naval Architecture,Ocean and Civil Engineering,Shanghai Jiaotong University,Shanghai 200240,China

摘要

摘要: 为对土石材料修筑的海堤运行状态实施有效分析和预测，在因果关系分析基础上，选取前期潮位因子、积分型降雨因子和时效因子，以径向基函数(ＲBF)神经网络为建模工具，结合实测序列特点，采用模糊C 均值聚类算法比较确定计算中心，建立海堤安全监控ＲBF 模型，实现海堤状态量的预测；在对模型误差序列的大小、趋势和分布特征分析基础上，提出基于置信度的预测效果的假设检验方法，并在给定置信水平下对不同预测时长的稳定性予以比较；以实例建立模型并对其训练及预测效果加以分析判别。
- 海堤安全监控 /
- ＲBF 模型 /
- 预测误差 /
- 置信度 /
- 假设检验
Abstract: To analyze and forecast sea wall working state，a sea wall monitoring model was established by thefollowing steps: selecting former tidewater factor，integral rain factor and time effect factor based on causality study，using radial basis function ( ＲBF ) artificial neural network as modeling tool， considering monitoring datacharacteristics，and using fuzzy C-mean algorithm(FCM) to confirm ＲBF centers． And then，the forecast of sea wallworking state was realized by the methods below: errors of the model were studied，including error values，trend anddistribution，based on these，a hypothesis testing method was presented to evaluate forecast results consideringconfidence level，and stabilities of different forecast length was compared on a same confidence level，finally theinstance model were set up，the training and forecast effects were analyzed．
- sea wall safety monitoring /
- ＲBF model /
- forecast error /
- confidence level /
- hypothesis testing

HTML全文

参考文献(14)

Huang Ming, Liu Jun.Monitoring and Analysis of ShanghaiPudong Seawall Performance [J].Journal of Performance ofConstructed Facilities,2009,23(6):399-405.

[2] 黄铭.数学模型与工程安全监测[M].上海:上海交通大学出版社,2008.

[3] 李珍照.大坝安全监测[M].北京:中国电力出版社,1997.

[4] 吴中如,沈长松,阮焕祥.水工建筑物安全监控理论及其应用[M].南京:河海大学出版社,1990.

[5] Kim Dongwon, Huh Sung-Hoe, Seo Sam-Jun, et al.Self-Organizing Radial Basis Function Network Modeling for RobotManipulator[J].Lecture Notes in Computer Science,2005,35(33): 579-587.

[6] 王维斌,赵新华.基于RBF 神经网络的活性污泥模型的应用[J].南开大学学报:自然科学版,2008,41(2):91-97.

[7] 张秀玲,陈丽杰,季颖,等.基于径向基函数神经网络的板形模式识别研究[J].工业仪表与自动化装置,2009(3):7-9.

[8] Huang Ming,Liu Jun,Wang Ning.Foundation Pit Multi-PointDisplacement RBF Monitoring Model and Application Key Points[C]// 2010 International Conference on Mechanic Automationand Control Engineering, MACE2010.Piscataway: IEEEComputer Society,2010. 4562-4565.

[9] 黄铭,刘俊.堆载预压作用下路基沉降的多测点监测模型[J].上海交通大学学报,2011,45(5): 753-756.

[10] 刘笛,朱学峰,苏彩红.一种新型的模糊C 均值聚类初始化方法[J].计算机仿真,2004,21(11):148-151.

[11] 张新波.两阶段模糊C-均值聚类算法[J].电路域系统学报,2005,10(2):117-120.

[12] Pal N R,Bezdek J C.On Clusters Validity for the Fuzzy C-MeansMode [J].IEEE Trans.on Fuzzy Systems,1995,28(3): 370-379.

[13] Huang M,Liu J,Huang W,et al.Analysis of Sea Wall OsmosisPressures Influencing Factors and Monitoring Models[C]//Advances in Earth Structures: Research to Practice,Proceedingsof Sessions of Geoshanghai.ASCE,2006: 310-316.

[14] Everitt B S.The Cambridge Dictionary of Statistical[M].2nd ed.Cambridge: Press Syndicate of the University of Cambridge,2002.

施引文献

资源附件(0)

访问统计