Using the FA-NAR Dynamic Neural Network Model and Big Data to Monitor Dam Safety

In view of the dynamics dam safety monitoring data, sensitivity to time and space, nonlinearity, it has been proposed use firefly algorithm search determine delay order number hidden layer units combine them with nonlinear autoregressive algorithms. The algorithms are combined obtain FA-NAR deformation prediction model, which is compared traditional BP results, Xiaolangdi data for prediction, predicted by dynamic neural network have a better convergence effect more accurate result. It provides certain reference basis perfecting monitoring.