Bp Neural Network Applied Research In Long-span Cable-stayed Bridge Construction Control

In this paper, the basic theory of nerve network is studied. The application of the neural network method in the construction control of cable-stayed bridge is demonstrated possible in theory.In this paper, the influencing factors in the construction control of cable-stayed bridge are analyzed thanks to the related data collected. Taking BP nerve network basic theory as its theoretical basis, a prediction model of construction control is established. The application is verified feasible in the construction control of cable-stayed bridge by analyzing an actual bridge and comparing its result with the predication result of the gray system theory. A reasonable normalization method is made certain by the normalization principle and the data of construction. This method increases the learning efficiency and the rate of convergence of the network. A deflection-predicting program is designed by the use of MATLAB programming language. It realizes network control and attains a good result.