Modified hybrid forecast model considering chaotic residual errors for dam deformation

Abstract

Dam deformation is double effected by the internal and external environments, showing high nonlinear characteristics. Information mining of dam prototype observation data and effective components contained in the residual sequence is limited in conventional dam deformation forecast models. In order to fully explore the complex nonlinear relationship between dam deformation and environmental factors, modified hybrid forecast model considering chaotic residual errors is proposed on the combination of shuffled frog leapfrog algorithm and chaos theory in this study. Hybrid models are established on the basis of dam deformation prototype observation data, and modified hybrid forecast model is established by determining the optimal weight of each hybrid model with shuffled frog leapfrog algorithm. Considering the chaotic characteristics contained in the residual sequence of modified hybrid forecast model, residual sequence is analyzed and forecasted by chaos theory. By superimposing the residual forecast value with the forecast value of modified hybrid forecast model, modified hybrid forecast model considering chaotic residual errors is established. Example shows that, compared with conventional models, the proposed model is better in fitting precision and convergence speed, and forecast capability is significantly improved by considering the effective components contained in the residual sequence, which presents a new method of the deformation forecast for other hydraulic structures.