Study On Prediction Of Prestressed Concrete Pipe Pile Quality Based On BP Neural Network

The prestressed concrete pipe pile are widely used in pile foundation, how to get quality of the single pile is one of the most important problems at present. Therefore, this thesis, based on the knowledge of quality forecast of the prestressed concrete pipe pile and the mechanism of the neural network, proposes the neural network model on the prediction of the prestressed concrete pipe pile, and it will solve how to forecast quality of the prestressed concrete pipe.Firstly, this thesis describes the load bearing mechanism of the prestressed concrete pipe pile, analysis all factors with regard to quality of the single pile from five respects that bearing stratum, pile body, construction machinery, time and spatial effect, meanwhile, meanwhile, the influence factor of quality index system is built. Then, it introduces the basic concept and fundamental principle of neural network, the relevant characteristics of BP net work, and the thesis focuses on the feasibility and superiority of the neural network model in solving the problem. on the basis of previous work, it establishes the 3-level BP network with 7 factors involving pile, field operation and soil perform as neuron of input level and vertical bearing capacity along with pile integrity as neuron of output level. Finally, the thesis applies the neural network model to the prestressed concrete pipe pile in Handan.Compares the predictive result with the results of measured value, verifying the accuracy and reliability. this thesis provides a new prediction method for quality of the prestressed concrete pipe pile.