Research On The Bearing Capacity Of Drilled Grouting Pile

Drilled grouting pile is one of the widely used types of the deep foundation. In the recent years, the number of the drilled grouting pile used in china exceeds 1000 000 per year. The depth of the pile under the earth is being up to 104 meter. In research of the characteristic of the bearing capacity of the piles, how to specify the bearing capacity and the settlement is the key. Because of lots of factors is instable, how to specify the bearing capacity of the piles properly and make good economic efficiency is the concerned problem for the designer.Artificial Neural Network is one of the efficient information processing method i n studying t he s ophisticated sy stems. It n eed n o mathematical model, but can deal with non-liner fuzzy problems. It is often used in predicting, classification and so on. In recent years, ANN has been used in engineering fields. Back Propagation neural network is one of the most widely used networks. The practice algorithm is similar to delta rule. With long period developing, BPN has been improved. In this paper ,the improved ANN has been used, it can adopt to adjust the most fitness studying according to the curvature changing of different area in the curved surface.When using the ANN model to predict the specify bearing capacity of drilled grouting pile, we can think of the factors of effecting specify the bearing capacity and build ANN model. The ANN model has superiority that other pure mathematical models do not have because it may not only think every factors of effecting specify the bearing capacity but also objectively simulate the practical forces conditions of pile. Moreover, it has theoretic and practical merits to certain extent because avoiding deriving the complex mathematical formula.The paper introduce simply the research condition of specify the bearing capacity and point the value of using the ANN in pile engineering.Five factors of effecting specify the bearing capacity of drilled grouting pile (engineering properties of soil, structural dimension of pile, stiffness of pile, time) have been concluded through introducing the transmission of load mechanism of drilled grouting pile. At the same time, the effecting parameter has been collected. The paper build the ANN model in predicting ultimate bearing capacity of drilled grouting pile and discuss in detail the extraction of inputting nodes information when quoting the fundamental principle of ANN model and introducing research process of the improved BNN. According to them, the ANN model in predicting the ultimate bearing capacity is created. Based on engineering examples, numerical analysis has been executed. The analysis shows that: the ANN method to predict bearing capacity of piles is useful and effective, and could be used in pile analysis.