Displacement back analysis for still basin at left bank slope of Nuozhadu hydropower plant

A displacement back analysis, named as CACA-SVM, was proposed by combining the Support Vector Machines(SVM) and the Continuous Ant Colony Algorithm(CACA). The model used both the nonlinear characteristics of the Support Vector Machines to reduce numerical calculation and the global optimization performance of the Continuous Ant Colony Algorithm to avoid trapping in local optimum. The model was applied to displacement back analysis of rock mechanic parameters for still basin at the left bank slope of Nuozhadu hydropower plant and those parameters were used to forecast displacement of the monitoring points. Forecasting trend was in good agreement with the measured trend, which indicated that the model was suitable for solving the geotechnical engineering problem of nonlinearity and uncertainty and could well be applied to displacement back analysis.