Premium
Performance improvement method of support vector machine‐based model monitoring dam safety
Author(s) -
Su Huaizhi,
Chen Zhexin,
Wen Zhiping
Publication year - 2016
Publication title -
structural control and health monitoring
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.587
H-Index - 62
eISSN - 1545-2263
pISSN - 1545-2255
DOI - 10.1002/stc.1767
Subject(s) - support vector machine , safety monitoring , displacement (psychology) , adaptability , process (computing) , engineering , nonlinear system , computer science , data mining , reliability engineering , machine learning , biology , microbiology and biotechnology , psychology , ecology , physics , quantum mechanics , psychotherapist , operating system
Summary Under the comprehensive influence of material and loads, dam structural behavior presents the time‐varying nonlinear characteristics. To forecast the dam structural behavior (displacement, stress, seepage, etc.), the models monitoring dam safety are often built according to the prototype observations on dam safety. However, the modeling process is usually fulfilled with the offline and static pattern. As time goes on, the fitting and forecasting ability of built static model will decline gradually. The article is focused on the support vector machine (SVM)‐based model monitoring dam safety. The methods are studied to advance the adaptability of SVM model and reduce the modeling time. By implementing the impact analysis for SVM parameters and input vector, the optimization method of SVM parameters and input vector is presented to enhance the efficiency of building the SVM‐based static model monitoring dam safety. To describe dynamically the time‐varying mapping relationship between dam structural behavior (effect‐quantity) and its cause (influence‐quantity), the way is developed to update in real time above model by making the most use of new observations. The displacement of one actual dam is taken as an example to verify the modeling efficiency and forecasting ability. Copyright © 2015 John Wiley & Sons, Ltd.