Paper Infomation
Study on Prediction of Settlement of Foundation Based on Artificial Neural Network
Full Text(PDF, 560KB)
Author: Xiaobo Xiong, Liduo Zhou
Abstract: When constructing the highway, we encounter series of engineering difficult problems, such as deep soft foundation. The keys of the engineering are to control the final deformation of the foundation. As we all know, Marine sediment clay has higher creep characteristic. When carrying through the soft soil drainage consolidation deformation, shear rheological deformation is the source of soil deformation, that is, the soil particles occur lateral extrusion. At the same time, the creep deformation is the main and the consolidation deformation is secondary. The principle and application of neural network were introduced. Through improving the algorithm of neural network, the NNT prediction model was built. The author have taken the eight parameters including (as input values): ground treatment methods, the thickness of soft soil, compression modulus of soft soil, the thickness of the hard soil, compression modulus of hard soil, height of embankment, construction time, settlement when engineering completed. The results also proved BP neural network prediction model has high accuracy and stability, can be used in similar projects.
Keywords: Artificial Neural Network; Foundation; Settlement; Prediction
References:
[1] Xiaobo Xiong, Liduo Zhou, Yan Chen, et al. ANN based creep constitutive model for marine sediment clay in coastal zone. Global view of engineering geology and the environment. (Wu & Qi eds), pp: 449-455. (2013)
[2] Ziad Ramadana, Philip K. Hopkea, Mara J. Johnsonb, et al. Application of PLS and Back-Propagation Neural Networks for the estimation of soil properties. Chemometrics and Intelligent Laboratory Systems 75: 23-30. (2005)
[3] Hyun Il Park, Seung Rae Lee. Evaluation of the compression index of soils using an artificial neural network. Computers and Geotechnics. 38: 472-481. (2011)
[4] Antonio Fernandez-Caballero, Jose Mira, Gustavo Deco. 50 Years of Artificial Intelligence: a Neuronal Approach, Neurocomputing，Volume 71, Issues 4-6, January, Pages 667-669. (2008)
[5] Jonathan R. Whitlock, Arnold J. Heynen, Marshall G. Shuler, et al. Learning Induces Long-Term Potentiation in the Hippocampus, Science. Aug 25; 313(5790):1093-7. (2006)
[6] Tian Yubo. Hybrid neural network technology. Science Press, Beijing. (2009)
[7] Martin T. Hagan, Howard B. Demuth, Mark H. Beale. Neural network design. 1996 by PWS Publishing Company. China Machine Press. (2002)
[8] SUN Jun, ZHAO Qi-hua, XIONG Xiao-bo. Intelligent prediction on deformations in the construction of anchor block-abutment foundation of an extremely long-span suspension bridge (Runyang Bridge over Yangzi River)—a case history study. Rock and Soil Mechanics. Vol.24 Supp: 1-7. (2003)
[9] Xiong Xiaobo, Sun Jun, Zhao Qihua, et al. Application on settlement forecast of soft foundation based on BP neural network, STUDY ON INTELLIGENT FORECAST AND CONTROL OF CONSTRUCTION DEFORMATION OF DEEP FOUNDATION PIT OF NORTH ANCHORAGE OF RUNYANG BRIDGE(I). Chinese Journal of Rock Mechanics and Engineering. 22(12): 1966-1970. (2003)
[10] Xiong Xiaobo. Research on intelligent prediction and control of deep & large excavation work, PhD dissertation, Tongji University, Shanghai, China. (2003)
[11] Li Yuhua, HUang Lin. Application on settlement forecast of soft foundation based on BP neural network, GEOTECHNICAL ENGINEERING WORLD, 10, (5): 30-32. (2008)
[12] SUN Yan, LI Shi-jun. Settlement Forecast of A Typical Soft Soil Based on Artificial Neural Network. Communications Standardization, (21): 193-195. (2009)
[13] XU Bing-wei,JIANG Xin-liang. DIAPHRAGM WALL'S DEFORMATION FORECASTING BASED ON BP-RBF NEURAL NETWORKS. ENGINEERING MECHANICS. 26(Sup.I): 163-166. (2009)
[14] Chen Shangrong, Zhao Shengfeng. Application of BP neural network forecast for the deformation of foundation. Shanghai Geology. (1): 29-31+41. (2010)
[15] Wei Jian, Hu jiping, Tan Qulin, et al. Application of BP artificial neural network to predict the settlement of tall buildings, Beijing Surveying and Mapping, (2): 25-27+33. (2013)