Research On Dam Displacement Forecasting Model Based On Support Vector Machine

Our country has become a country which has the most dams in the world with the rapid development of water power engineering construction.In order to safeguard the security and master the circulate state of the dam ,it has important real-time meaning to forecast the aftertime deformation quantity according to known monitoring data.Because the deformation of dam system is nonlinear,fuzzy and uncertainty,conventional precise mathematic model has relatively large difference to the practical situation since it is under so many assumptions,and its results of forecast are not as good as request.Support Vector Machine(SVM)is a new kind of machine leanring algorithm proposed recently which is based on VC Dimension Theory and Structural Risk Minimization of Statistical Learning Theory. SVM can obtain the optimum resultfrom the gained information which is not the optimum result only when the samples are infinite.SVM has much stronger theory foundation and better generalization than Neural Network which is based on Empirical Risk Minimization. This research introduce SVM into dam deformation forecasting analysis, and buide forecast modle apply to forecasting displacement data.Firstly,this aticle analysis the deformate characteristic of the dam,and eliminate the "abnormal data"in the histrial deformate data use statistical method. Then it use cross validation method to ensure the SVM parameter. At last,using the chosen eigenvector and kernel function build dam deformation forecasting model.We forecast the deformate problem in one dam in Anhui province using the model which has been build.The result show that the forecast result is very close to real monitoring data.At the same time,we compare the SVM model forecasting result with the regression model and BP network model forecasting result,it show that the SVM model forecasting effect is credible. The forecasted results showed that this model has perfect estimate capabilities.