Study On Safety Monitor Model And Its Application Of Arch-dam's Deformation

Arch dam deformation is effected by multi-factors, and their relations, high nonlinear mapping relation, are very complex. Conventional method can only approximately describe the relationship of the deformation and its impacting factors. However, Integer Analysis model and Blur Neural Net Work method can effectively solve it.On the basis of systematic analysis the impact factors of arch dam deformation, the characteristics of water level, temperature and time effect of dam are analyzed by adopt the Stepwise regress analysis method. By studying the stepwise regress model, some limit and scarcity can be get: 1. General stepwise regress model needs synchronous environmental observation data, however, to many structure, there is a lack of the corresponding environmental data and it can not model; 2. As a kind of single model, stepwise regress model is not suit to the unitary structure such as arch dam and its workload is large, so it needs to be improve.In this paper, some improved methods are extracted to modify the shortage of the general model, that is to build model directly by the deformation data and forecasting. By building Blur Neural Net Work model and Integer Analysis model successfully, satisfied results can be get so that suitable model can be build to monitor structure and every sensitive factor can be known.The study resolution shows that Integer Analysis model is an effective analysis method in analyzing prototype measurement of dam, and that Blur Neural Net Work can effectively realize complex and high nonlinear mapping relationship between deformation and each impact factor through recessive description way. Therefore, Integer Analysis model and Blur Neural Net Work method will find its way in analyzing prototype measurement of dam, worthy of propagation in hydraulic engineering practice.