Rock and Soil Mechanics ›› 2023, Vol. 44 ›› Issue (6): 1789-1799.doi: 10.16285/j.rsm.2022.1683

• Geotechnical Engineering • Previous Articles     Next Articles

Sinking state prediction and optimal sensor placement of super large open caissons based on LightGBM

DONG Xue-chao1, 2, GUO Ming-wei1, 2, WANG Shui-lin1, 2   

  1. 1. State Key Laboratory of Geomechanics and Geotechnical Engineering, Institute of Rock and Soil Mechanics, Chinese Academy of Sciences, Wuhan, Hubei 430071, China; 2. University of Chinese Academy of Sciences, Beijing 100049, China
  • Received:2022-10-26 Accepted:2022-12-09 Online:2023-06-14 Published:2023-06-17
  • Supported by:
    This work was supported by the Scientific and Technological Key Projects in Transportation Industry 2019(2019-MS1-011).

Abstract: The sinking state prediction and optimal sensor placement are conducive to ensuring safe and steady sinking of open caissons and reducing monitoring costs. Based on LightGBM, a framework in the field of machine learning, a sinking state prediction model of super large open caisson is established. By using the monitoring data of the stress sensors at the bottom of the open caisson, the sinking speed of the open caisson, the height difference in the transverse direction and the height difference along the bridge direction are accurately predicted. Through the analysis of the sensor importance, the optimal sensor placement scheme that can meet the sinking state prediction accuracy is determined. The proposed sinking state prediction model and the optimal sensor placement method were applied to the super large open caisson sinking project of the main tower of Changtai Yangtze River Bridge. The results show that the model has high accuracy in predicting the sinking state of the open caisson, and the R2 of the three prediction indexes is greater than 0.94. The important sensors for predicting the sinking state are mainly concentrated in the outer circle of the open caisson and the area near the transverse and longitudinal axes. Under the condition of satisfying the prediction accuracy of sinking state, the optimal sensor placement scheme can reduce the number of sensors by 45.5%. When the numbers of sensors in the optimal sensor placement schemes are same, the proposed optimization scheme is better than the scheme based on the correlation analysis of characteristic variables in terms of overall accuracy of sinking state prediction.

Key words: super large open caisson, sinking state prediction, optimal sensor placement, LightGBM, machine learning, feature importance

CLC Number: 

  • U446.2
[1] ZHANG Wen-gang, GU Xin, LIU Han-long, ZHANG Qing, WANG Lin, WANG Lu-qi, . Probabilistic back analysis of soil parameters and displacement prediction of unsaturated slopes using Bayesian updating [J]. Rock and Soil Mechanics, 2022, 43(4): 1112-1122.
[2] SU Guo-shao, ZHANG Ke-shi, Lü Hai-bo. A cooperative optimization method based on particle swarm optimization and Gaussian process for displacement back analysis [J]. , 2011, 32(2): 510-515.
[3] XU Chong,LIU Bao-guo,LIU Kai-yun,GUO Jia-qi. Slope angle intelligent design based on Gaussian process with combinatorial kernel function [J]. , 2010, 31(3): 821-826.
[4] SU Guo-shao, SONG Yong-chun, YAN Liu-bin. Application of Gaussian process machine learning to slope stability evaluation [J]. , 2009, 30(3): 675-679.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
[1] YAO Yang-ping, HOU Wei. Basic mechanical behavior of soils and their elastoplastic modeling[J]. , 2009, 30(10): 2881 -2902 .
[2] XU Jin-ming, QIANG Pei, ZHANG Peng-fei. Texture analysis of photographs of silty clay[J]. , 2009, 30(10): 2903 -2907 .
[3] XIANG Tian-bing, FENG Xia-ting, CHEN Bing-rui, JIANG Quan, ZHANG Chuan-qing. Rock failure mechanism and true triaxial experimental study of specimens with single structural plane under three-dimensional stress[J]. , 2009, 30(10): 2908 -2916 .
[4] SHI Yu-ling, MEN Yu-ming, PENG Jian-bing, HUANG Qiang-bing, LIU Hong-jia. Damage test study of different types structures of bridge decks by ground-fissure[J]. , 2009, 30(10): 2917 -2922 .
[5] XIA Dong-zhou, HE Yi-bin, LIU Jian-hua. Study of damping property and seismic action effect for soil-structure dynamic interaction system[J]. , 2009, 30(10): 2923 -2928 .
[6] XU Su-chao, FENG Xia-ting, CHEN Bing-rui. Experimental study of skarn under uniaxial cyclic loading and unloading test and acoustic emission characteristics[J]. , 2009, 30(10): 2929 -2934 .
[7] ZHANG Li-ting, QI Qing-lan, WEI Jing HUO Qian, ZHOU Guo-bin. Variation of void ratio in course of consolidation of warping clay[J]. , 2009, 30(10): 2935 -2939 .
[8] ZHANG Qi-yi. Study of failure patterns of foundation under combined loading[J]. , 2009, 30(10): 2940 -2944 .
[9] YI Jun, JIANG Yong-dong, XUAN Xue-fu, LUO Yun, ZHANG Yu. A liquid-solid dynamic coupling modelof ultrasound enhanced coalbed gas desorption and flow[J]. , 2009, 30(10): 2945 -2949 .
[10] TAO Gan-qiang, YANG Shi-jiao, REN Feng-yu. Experimental research on granular flow characters of caved ore and rock[J]. , 2009, 30(10): 2950 -2954 .