Study On The Selection Of Piles With Artificial Neural Network

The selection of piles for building is a complex work which involves wide. It needs various knowledge and professional experience for the structural design. It's no proceeding well theories about it at current domestic and international. A way concerned about the selection of piles is put forward based on artificial neural network in this paper. The qualities of the ANN, high-nonlinear, high-permissibility of error and high-robustness, self-adaptability, online work, and so on, are adequately used in the research. From the research we know that the method based on ANN can solve the problem on selection of piles for building.In this paper, the main principle of BP neural network and the artificial neural network toolbox of Matlab6.5 is described briefly. When the math model of artificial neural network about the selection of piles is established based on the artificial neural network toolbox of Matlab6.5, first of all, the main characters of piles are analyzed, and the main affecting elements that can dominate selection of piles are picked out. Then, the question on how to choose the numbers of the hidden-layer and neuron is discussed, and the identification model of neural network about the selection of piles is established based on the neural network toolbox of Matlab6.5. Analyzing and solving the problem on selection of piles for building through adopting several ameliorate BP arithmetic by the decided BP network construction, and selecting the best BP arithmetic (Fletcher-Powell arithmetic) for the model. Based on the above work, a model based on neural network toolbox of Matlab6.5 is designed. The model can help designers to easily select an appropriate pile for building and make the progress of selection sample and clear.Inputting the geology data of typical project items, training network, optimizing the network model. By testing, the trained model can help designers to select an appropriate kind of piles. The demonstration shows that this method has an important practical significance and a referential worth in the design of piles.