Affiliations: [a] Shenzhen Bureau of Geology, Shenzhen, Guangdong, China
| [b] China Construction First Group the Fifth Construction Co., Ltd. Beijing, China
Correspondence:
[*]
Corresponding author. Jianxun Yang, Shenzhen Bureau of Geology, Shenzhen, Guangdong, 518023, China. E-mail: [email protected].
Abstract: The Pile movement is one of the most crucial matters in designing piles and foundations that need to be estimated for any project failure. Over the variables used in forecasting Pile Settlement, many methods have been introduced to appraise it. However, existing a wide range of theoretical strategies to investigate the pile subsidence, the soil-pile interactions are still ambiguous for academic researchers. Most studies have tried to work out the subsidence rate in piles after loading passing time by artificial intelligence methods. Generally, the Artificial Neural Network (ANN) has drawn attention to show the actual views of pile settlement over the loading phase vertically. This research aims to present the Hybrid Radial Basis Function neural network integrated with the Novel Arithmetic Optimization Algorithm and Biogeography-Based Optimization to calculate the optimal number of neurons embedded in hidden layers. The transportation network of Klang Valley, Mass Rapid Transit in Kuala Lumpur, Malaysia, was chosen to analyze the piles’ settlement and earth features using HRBF-AOA and HRBF-BBO scenarios. Over the prediction process, the R-values of HRBF-AOA and HRBF-BBO were obtained at 0.9825 and 0.9724, respectively. The MAE also shows a similar trend as 0.2837 and 0.323, respectively.
Keywords: Pile in rock, settlement, prediction, radial basis function, biogeography-based optimization, arithmetic optimization algorithm, r-value correlation
