The modeling of cracks and identification of dam behavior changes are difficult issues in dam health monitoring research. In this\npaper, a time-varying identificationmodel for crackmonitoring data is built using support vector regression (SVR) and the Bayesian\nevidence framework (BEF). First, the SVR method is adopted for better modeling of the nonlinear relationship between the crack\nopening displacement (COD) and its influencing factors. Second, the BEF approach is applied to determine the optimal SVR\nmodeling parameters, including the penalty coefficient, the loss coefficient, and the width coefficient of the radial kernel function,\nunder the principle that the prediction errors between the monitored and the model forecasted values are as small as possible.\nThen, considering the predicted COD, the historical maximum COD, and the time-dependent component, forewarning criteria\nare proposed for identifying the time-varying behavior of cracks and the degree of abnormality of dam health. Finally, an example\nof modeling and forewarning analysis is presented using two monitoring subsequences froma real structural crack in the Chencun\nconcrete arch-gravity dam. The findings indicate that the proposed time-varyingmodel can provide predicted results that aremore\naccurately nonlinearity fitted and is suitable for use in evaluating the behavior of cracks in dams.
Loading....