Prediction of the Settlement of High Embankments by Back Propagation Neural Network

Abstract

Abstract: The post construction settlement of high embankments of T1 to T5 alignments in Kunming new airport project site is predicted using a multilayer (two hide layers) neural network method. The observed settlement values indicate that the maximum post construction settlements are related to areas with highest fills. The settlement pattern indicates that the post construction settlements have a rapid settlement rate initially and then gradually change to the steady settlement. It is predicted that the maximum post construction settlement at T1 is 52.7 mm and the observed value in August 2011 was 55.6 mm. It is concluded that the two hide layer Back Propagation (BP) neural network model can have an accurate prediction on the post construction settlement.

Key words: High embankments, Post Construction Settlement, BP Neural Network, Settlement Prediction

MA Lihui，HAN Wenxi, LI Yang. Prediction of the Settlement of High Embankments by Back Propagation Neural Network[J]. , 2013, 27(1): 14-16.

[1]	LI Yingxiao, LIU Yuanming, ZHENG Tao, ZHOU Yuhang, TENG Zhaolei. Prediction Model of Surface Subsidence after the Construction of Guiyang Metro Tunnel [J]. Soil Engineering and Foundation, 2024, 38(4): 706-709.
[2]	OUYANG Lei, DENG Xiping, HE Lijun, LIU Jiayin, CHEN Peng. Prediction of Soil Compression Coefficient by Genetic Algorithm Optimized BP Neural Network [J]. Soil Engineering and Foundation, 2022, 36(6): 907-910.
[3]	ZHU Fanghai, HU Shenggang. Influencing Factors of Preloading Method in the Soil Improvement in Zouma Lake Project [J]. Soil Engineering and Foundation, 2022, 36(2): 122-126.
[4]	WU Qitai. Optimization of Design Parameters of Dynamic Compaction and Replacement Method in High Fill Soils [J]. Soil Engineering and Foundation, 2021, 35(2): 106-110.
[5]	ZHAN Hongzhi, LIN Jianfeng. Application of BP Neural Network in Prediction Collapsibility Coefficient of Loess [J]. Soil Engineering and Foundation, 2020, 34(4): 493-496.
[6]	GAO Defeng, ZHOU Ao, FENG Yateng, WANG Haixiao, XIA Wenjun. Deformation Monitoring and Back Analysis of Soil Parameters in the Cut and Cover Installation of Taihu Tunnel [J]. Soil Engineering and Foundation, 2020, 34(3): 385-390.
[7]	ZHANG Jie1, SHI Li2. A Prediction Method Using GA-BP Neural Network for the Frictional Resistance of PHC Piles [J]. , 2019, 33(3): 304-307.
[8]	LI Hongtao, LIU Sijia, HU Tongxu, WANG Wen. Application of Exponential Function Model in the Settlement Prediction of Pile Supported Bridge Foundations [J]. , 2019, 33(3): 343-346.
[9]	SUN Xiwang1, LI Liangji2, YANG Guoyue2, XU Yunlong2. Rheological Properties of the Compacted Red Clay in Kunming Region [J]. , 2018, 32(1): 50-54.
[10]	HU Xiyan, PENG Huanyun, LI Jianzhong. Prediction of Dam Settlement Using Empirical and Exponential Creep Models [J]. , 2017, 31(2): 193-196.
[11]	YANG Laihua1, JIN Chun2, XU Bangshu2, DENG Wen1. Settlement Prediction in the Chengde Airport Construction [J]. , 2016, 30(5): 566-568.
[12]	SHI Li, HUANG Tao . Industrial Building Deformation Predictions by BP Neural Network [J]. , 2016, 30(2): 223-226.
[13]	MING Qianjun, YAO Yueliang, ZHANG Jie. Evaluation of the Borehole Quality in the Geotechnical Investigation by BP Neural Network Process [J]. , 2015, 29(6): 63-66.
[14]	LIU Xiaopeng，LIU Lin. Design Parameters for Dayaowan Northern Shore Container Terminal Soft Soil Improvement [J]. , 2015, 29(3): 44-47.
[15]	LEI Gang. Vertical Shaft Dimension Optimization Using Modified BP Neural Network [J]. , 2014, 28(6): 64-66.

Prediction of the Settlement of High Embankments by Back Propagation Neural Network

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 15

Recommended Articles

Metrics

Comments