Abstract: Traditional safety monitoring model cannot accurately reflect the nonlinear variation of dam deformation,hence affecting the forecast result. The support vector machine is based on the statistical learning theory and adopts the structural risk minimization principle which has advantages of simple structure,complete theory,good adaptability,global optimization,short training time,and good generalization performance. Least square support vector machine (LS-SVM) was applied to concrete dam safety monitoring,and a corresponding monitoring model was built. Engineering cases prove that the model is of high precision and practicality.

Key words: concrete dam , least square , support vector machine , monitoring model