Journal of Northeastern University(Natural Science) ›› 2024, Vol. 45 ›› Issue (12): 1769-1777.DOI: 10.12068/j.issn.1005-3026.2024.12.012
• Resources & Civil Engineering • Previous Articles
Xiu-mei CAO1, Wen ZHAO1(), Zhi-guo WANG1, Peng HE2
Received:
2023-07-12
Online:
2024-12-10
Published:
2025-03-18
Contact:
Wen ZHAO
CLC Number:
Xiu-mei CAO, Wen ZHAO, Zhi-guo WANG, Peng HE. Prediction of Soil Conditioners for Sandy Soil Shield Based on Optuna-XGBoost[J]. Journal of Northeastern University(Natural Science), 2024, 45(12): 1769-1777.
地层 | 标准贯入击数 | 动弹性模量 | 动剪切模量 | 天然密度 | 黏聚力 | 内摩擦角 | 渗透系数 | 变形模量 |
---|---|---|---|---|---|---|---|---|
Ed/MPa | Gd/MPa | ρ0/(g·cm-3) | C/kPa | φ/(°) | K/(m·d-1) | E0/MPa | ||
圆砾 | 31.3 | 675.7 | 229.4 | 2.00 | 0 | 35 | 90 | 35 |
砾砂 | 27.4 | 723.0 | 250.0 | 2.00 | 0 | 32 | 65 | 32 |
中粗砂 | 25.1 | 579.0 | 198.0 | 1.99 | 0 | 31 | 30 | 26 |
粉细砂 | 23.1 | 283.1 | 102.2 | 2.00 | 0 | 28 | 6 | 15 |
粉质黏土 | 8.5 | 273.7 | 92.0 | 1.94 | 21 | 16 | 0.02 | 16 |
Table 1 Different geological properties
地层 | 标准贯入击数 | 动弹性模量 | 动剪切模量 | 天然密度 | 黏聚力 | 内摩擦角 | 渗透系数 | 变形模量 |
---|---|---|---|---|---|---|---|---|
Ed/MPa | Gd/MPa | ρ0/(g·cm-3) | C/kPa | φ/(°) | K/(m·d-1) | E0/MPa | ||
圆砾 | 31.3 | 675.7 | 229.4 | 2.00 | 0 | 35 | 90 | 35 |
砾砂 | 27.4 | 723.0 | 250.0 | 2.00 | 0 | 32 | 65 | 32 |
中粗砂 | 25.1 | 579.0 | 198.0 | 1.99 | 0 | 31 | 30 | 26 |
粉细砂 | 23.1 | 283.1 | 102.2 | 2.00 | 0 | 28 | 6 | 15 |
粉质黏土 | 8.5 | 273.7 | 92.0 | 1.94 | 21 | 16 | 0.02 | 16 |
参数 | 值 |
---|---|
开挖直径/m | 6.28 |
刀盘转速/(r·min-1) | 0~3.7 |
刀盘最大扭矩/(kN·m) | 7 200 |
刀盘开口率/% | 55 |
功率/kW | 1 799 |
Table 2 Shield machine equipment parameters
参数 | 值 |
---|---|
开挖直径/m | 6.28 |
刀盘转速/(r·min-1) | 0~3.7 |
刀盘最大扭矩/(kN·m) | 7 200 |
刀盘开口率/% | 55 |
功率/kW | 1 799 |
环号 | 记录时刻 | 刀盘扭矩 | 刀盘转速 | 总推力 | 推进速度 | 螺旋输送机扭矩 | 螺旋输送机转速 | 土舱压力 |
---|---|---|---|---|---|---|---|---|
kN·m | r·min-1 | kN | mm·min-1 | kN·m | r·min-1 | bar | ||
1 | 15∶45∶00 | 1 020.251 | 1.174 | 2 290.500 | 0.318 | 0 | 0.090 | 1.16 |
1 | 15∶45∶10 | 964.438 | 1.176 | 2 579.734 | 1.591 | 0 | 0.090 | 1.17 |
1 | 15∶45∶20 | 1 016.740 | 1.175 | 4 023.811 | 11.140 | 0 | 0.009 | 1.24 |
1 | 15∶45∶30 | 995.710 | 1.172 | 5 367.500 | 14.004 | 5.608 | 5.608 | 1.29 |
︙ | ︙ | ︙ | ︙ | ︙ | ︙ | ︙ | ︙ | ︙ |
1 396 | 6∶30∶10 | 3 184.901 | 1.179 | 12 252.636 | 95.487 | 33.701 | 13.012 | 1.84 |
1 396 | 6∶30∶20 | 3 412.209 | 1.175 | 12 148.345 | 97.714 | 35.439 | 13.064 | 1.89 |
1 396 | 6∶30∶30 | 3 681.826 | 1.153 | 12 279.574 | 91.985 | 34.129 | 13.125 | 1.86 |
1 396 | 6∶30∶40 | 3 857.941 | 1.144 | 12 409.705 | 93.257 | 34.746 | 13.030 | 1.85 |
Table 3 Tunneling data of 1~1 396 ring
环号 | 记录时刻 | 刀盘扭矩 | 刀盘转速 | 总推力 | 推进速度 | 螺旋输送机扭矩 | 螺旋输送机转速 | 土舱压力 |
---|---|---|---|---|---|---|---|---|
kN·m | r·min-1 | kN | mm·min-1 | kN·m | r·min-1 | bar | ||
1 | 15∶45∶00 | 1 020.251 | 1.174 | 2 290.500 | 0.318 | 0 | 0.090 | 1.16 |
1 | 15∶45∶10 | 964.438 | 1.176 | 2 579.734 | 1.591 | 0 | 0.090 | 1.17 |
1 | 15∶45∶20 | 1 016.740 | 1.175 | 4 023.811 | 11.140 | 0 | 0.009 | 1.24 |
1 | 15∶45∶30 | 995.710 | 1.172 | 5 367.500 | 14.004 | 5.608 | 5.608 | 1.29 |
︙ | ︙ | ︙ | ︙ | ︙ | ︙ | ︙ | ︙ | ︙ |
1 396 | 6∶30∶10 | 3 184.901 | 1.179 | 12 252.636 | 95.487 | 33.701 | 13.012 | 1.84 |
1 396 | 6∶30∶20 | 3 412.209 | 1.175 | 12 148.345 | 97.714 | 35.439 | 13.064 | 1.89 |
1 396 | 6∶30∶30 | 3 681.826 | 1.153 | 12 279.574 | 91.985 | 34.129 | 13.125 | 1.86 |
1 396 | 6∶30∶40 | 3 857.941 | 1.144 | 12 409.705 | 93.257 | 34.746 | 13.030 | 1.85 |
环数 | 地层 | TPI | FPI |
---|---|---|---|
0~442 | 砾砂、中粗砂、圆砾、粉质黏土 | 1 781.78 S-0.81 | 3 635.77 S-0.65 |
443~976 | 砾砂、中粗砂、圆砾 | 11 249.88 S-1.27 | 933 821.73 S-1.9 |
977~1 396 | 砾砂、中粗砂、粉质黏土 | 1 229.02 S-0.74 | 64 252.37 S-1.36 |
环数 | 地层 | TPI | FPI |
---|---|---|---|
0~442 | 砾砂、中粗砂、圆砾、粉质黏土 | 1 781.78 S-0.81 | 3 635.77 S-0.65 |
443~976 | 砾砂、中粗砂、圆砾 | 11 249.88 S-1.27 | 933 821.73 S-1.9 |
977~1 396 | 砾砂、中粗砂、粉质黏土 | 1 229.02 S-0.74 | 64 252.37 S-1.36 |
超参数 | 含义 | 取值范围 | 泡沫原液用量 | 泡沫剂体积比 | 膨润土泥浆用量 |
---|---|---|---|---|---|
max depth | 树的最大深度 | [ | 13 | 15 | 15 |
min child weight | 最小叶子权重 | (1,15) | 5 | 9 | 5 |
learning rate | 学习率 | (0.01,0.2) | 0.076 3 | 0.166 8 | 0.146 5 |
gamma | 复杂度的惩罚项 | [0.1,1.0] | 0.8 | 0.1 | 0.2 |
alpha | L1正则项的参数 | (0.01,10.0) | 1.112 7 | 0.032 2 | 0.072 9 |
lambda | L2正则项的参数 | (0.01,10.0) | 0.046 5 | 0.001 8 | 4.476 2 |
subsample | 随机抽取样本比例 | [0.1,1.0] | 0.8 | 1 | 0.7 |
Table 5 Search space hyperparameters of XGBoost and optimal Optuna results
超参数 | 含义 | 取值范围 | 泡沫原液用量 | 泡沫剂体积比 | 膨润土泥浆用量 |
---|---|---|---|---|---|
max depth | 树的最大深度 | [ | 13 | 15 | 15 |
min child weight | 最小叶子权重 | (1,15) | 5 | 9 | 5 |
learning rate | 学习率 | (0.01,0.2) | 0.076 3 | 0.166 8 | 0.146 5 |
gamma | 复杂度的惩罚项 | [0.1,1.0] | 0.8 | 0.1 | 0.2 |
alpha | L1正则项的参数 | (0.01,10.0) | 1.112 7 | 0.032 2 | 0.072 9 |
lambda | L2正则项的参数 | (0.01,10.0) | 0.046 5 | 0.001 8 | 4.476 2 |
subsample | 随机抽取样本比例 | [0.1,1.0] | 0.8 | 1 | 0.7 |
优化算法 | 泡沫原液用量 | 泡沫剂体积比 | 膨润土泥浆用量 | |||||
---|---|---|---|---|---|---|---|---|
R2 | MAE | R2 | MAE | R2 | MAE | |||
Optuna | 0.951 3 | 2.338 1 | 0.948 1 | 0.027 7 | 0.924 7 | 5.753 6 | ||
BO | 0.912 3 | 2.862 9 | 0.921 3 | 0.057 9 | 0.902 1 | 6.878 5 | ||
GS | 0.922 7 | 3.130 0 | 0.917 4 | 0.024 5 | 0.876 5 | 7.614 5 | ||
PSO | 0.933 6 | 2.870 0 | 0.925 5 | 6.324 0 | 0.920 0 | 6.324 4 |
Table 6 Comparison of hyperparameter optimization algorithms
优化算法 | 泡沫原液用量 | 泡沫剂体积比 | 膨润土泥浆用量 | |||||
---|---|---|---|---|---|---|---|---|
R2 | MAE | R2 | MAE | R2 | MAE | |||
Optuna | 0.951 3 | 2.338 1 | 0.948 1 | 0.027 7 | 0.924 7 | 5.753 6 | ||
BO | 0.912 3 | 2.862 9 | 0.921 3 | 0.057 9 | 0.902 1 | 6.878 5 | ||
GS | 0.922 7 | 3.130 0 | 0.917 4 | 0.024 5 | 0.876 5 | 7.614 5 | ||
PSO | 0.933 6 | 2.870 0 | 0.925 5 | 6.324 0 | 0.920 0 | 6.324 4 |
模型 | 泡沫原液用量 | 泡沫剂体积比 | 膨润土泥浆用量 | |||||
---|---|---|---|---|---|---|---|---|
R2 | MAE | R2 | MAE | R2 | MAE | |||
XGBoost | 0.918 1 | 4.669 1 | 0.857 7 | 0.079 4 | 0.895 4 | 8.213 6 | ||
SVR | 0.915 6 | 4.603 6 | 0.851 9 | 0.081 1 | 0.885 9 | 7.276 9 | ||
RF | 0.901 1 | 2.796 7 | 0.837 1 | 0.080 7 | 0.860 3 | 7.938 9 | ||
Optuna-XGBoost | 0.951 3 | 2.338 1 | 0.948 1 | 0.027 7 | 0.924 7 | 5.753 6 | ||
Optuna-SVR | 0.922 7 | 2.882 9 | 0.889 5 | 0.066 8 | 0.900 8 | 6.438 5 | ||
Optuna-RF | 0.943 3 | 2.057 9 | 0.901 2 | 0.057 9 | 0.919 9 | 6.267 5 |
Table 7 The analysis results of the fitting accuracy for 6 models
模型 | 泡沫原液用量 | 泡沫剂体积比 | 膨润土泥浆用量 | |||||
---|---|---|---|---|---|---|---|---|
R2 | MAE | R2 | MAE | R2 | MAE | |||
XGBoost | 0.918 1 | 4.669 1 | 0.857 7 | 0.079 4 | 0.895 4 | 8.213 6 | ||
SVR | 0.915 6 | 4.603 6 | 0.851 9 | 0.081 1 | 0.885 9 | 7.276 9 | ||
RF | 0.901 1 | 2.796 7 | 0.837 1 | 0.080 7 | 0.860 3 | 7.938 9 | ||
Optuna-XGBoost | 0.951 3 | 2.338 1 | 0.948 1 | 0.027 7 | 0.924 7 | 5.753 6 | ||
Optuna-SVR | 0.922 7 | 2.882 9 | 0.889 5 | 0.066 8 | 0.900 8 | 6.438 5 | ||
Optuna-RF | 0.943 3 | 2.057 9 | 0.901 2 | 0.057 9 | 0.919 9 | 6.267 5 |
1 | 魏康林.土压平衡式盾构施工中“理想状态土体”的探讨[J].城市轨道交通研究,2007(1):67-70. |
Wei Kang‑lin.On the “Ideal Soil” in the earth pressure balanced shield tunneling[J].Urban Mass Transit,2007(1):67-70. | |
2 | Messerklinger S, Zumsteg R, Puzrin A M.A new pressurized vane shear apparatus[J].Geotechnical Testing Journal,2011,34(2):112-121. |
3 | Vinai R, Oggeri C, Peila D.Soil conditioning of sand for EPB applications:a laboratory research[J].Tunnelling and Underground Space Technology,2008,23(3):308-317. |
4 | Thewes M, Budach C.Soil conditioning with foam during EPB tunnelling[J].Geomechanik Und Tunnelbau,2010,3(3):256-267. |
5 | 魏康林.土压平衡盾构施工中泡沫和膨润土改良土体的微观机理分析[J].现代隧道技术,2007(1):73-77. |
Wei Kang‑lin.Micro‑mechanism analysis for the soil improvement by foam and bentonite in EPB shield tunneling[J].Modern Tunnelling Technology,2007(1):73-77. | |
6 | 王树英,刘朋飞,胡钦鑫,等.盾构隧道渣土改良理论与技术研究综述[J].中国公路学报,2020,33(5):8-34. |
Wang Shu‑ying, Liu Peng‑fei, Hu Qin‑xin,et al.State‑of‑the‑art on theories and technologies of soil conditioning for shield tunneling[J].China Journal of Highway and Transport,2020,33(5):8-34. | |
7 | Li S C, Wan Z E, Zhao S S,et al.Soil conditioning tests on sandy soil for earth pressure balance shield tunneling and field applications[J].Tunnelling and Underground Space Technology,2022,120:104271. |
8 | Cheng C H, Liao S M, Huo X B,et al.Experimental study on the soil conditioning materials for EPB shield tunneling in silty sand[J].Advances in Civil Engineering,2020,2020:8856569. |
9 | Zhen Z, Ge X S, Zhang J.Soil conditioning tests on sandy and cobbly soil for shield tunneling[J].KSCE Journal of Civil Engineering,2021,25(4):1229-1238. |
10 | Wang S Y, Liu P F, Gong Z Y,et al.Auxiliary air pressure balance mode for EPB shield tunneling in water‑rich gravelly sand strata:feasibility and soil conditioning[J].Case Studies in Construction Materials,2022,16:e00799. |
11 | 展超.基于BP神经网络的富水砂层渣土改良试验效果预测[J].隧道建设(中英文),2020,40(7):988-996. |
Zhan Chao.Experimental effect prediction of ground conditioning of water‑rich sandy stratum based on BP neural network[J].Tunnel Construction,2020,40(7):988-996. | |
12 | Lin L, Guo H, Lyu Y C,et al.A machine learning method for soil conditioning automated decision‑making of EPBM:hybrid GBDT and random forest algorithm[J].Maintenance and Reliability,2022,24(2):237-247. |
13 | 李琛,骆汉宾,刘文黎,等.基于改进Faster R-CNN法的盾构渣土流塑性自动识别研究[J].隧道建设(中英文),2022,42(2):268-274. |
Li Chen, Luo Han‑bin, Liu Wen‑li,et al.Automatic recognition of flow plasticity of conditioned soil based on improved faster R-CNN[J].Tunnel Construction,2022,42(2):268-274. | |
14 | Lin S S, Shen S L, Zhang N,et al.Modelling the performance of EPB shield tunnelling using machine and deep learning algorithms[J].Geoscience Frontiers,2021,12(5):101177. |
15 | Mokhtari S, Mooney M A.Predicting EPBM advance rate performance using support vector regression modeling[J].Tunnelling and Underground Space Technology,2020,104:103520. |
16 | Kong X X, Ling X Z, Tang L,et al.Random forest‑based predictors for driving forces of earth pressure balance(EPB) shield tunnel boring machine(TBM)[J].Tunnelling and Underground Space Technology,2022,122:104373. |
17 | Qu T M, Wang S Y, Hu Q X.Coupled discrete element‑finite difference method for analysing effects of cohesionless soil conditioning on tunneling behaviour of EPB shield[J].KSCE Journal of Civil Engineering,2019,23(10):4538-4552. |
18 | 刘明阳,余宏淦,陶建峰,等.基于盾构机运行参数的局部切空间排列与XGBoost融合的地质类型识别[J].中南大学学报(自然科学版),2022,53(6):2080-2091. |
Liu Ming‑yang, Yu Hong‑gan, Tao Jian‑feng,et al.Geological‑type identification with LTSA and XGBoost algorithm based on EPB shield operating data[J].Journal of Central South University(Science and Technology),2022,53(6):2080-2091. | |
19 | 杨果林,张沛然,陈亚军,等.长沙典型地层土压平衡盾构掘进参数及表现预测[J].中南大学学报(自然科学版),2020,51(8):2069-2080. |
Yang Guo‑lin, Zhang Pei‑ran, Chen Ya‑jun,et al.Excavation parameters and performance prediction of earth pressure balance shield in typical strata of Changsha[J].Journal of Central South University(Science and Technology),2020,51(8):2069-2080. | |
20 | Xu Q W, Zhang L Y, Zhu H H,et al.Laboratory tests on conditioning the sandy cobble soil for EPB shield tunnelling and its field application[J].Tunnelling and Underground Space Technology,2020,105:103512. |
21 | Chen T Q, Guestrin C.XGBoost:a scalable tree boosting system[C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. San Francisco,2016:785-794. |
22 | Srinivas P, Katarya R.hyOPTXg:OPTUNA hyper‑parameter optimization framework for predicting cardiovascular disease using XGBoost[J].Biomedical Signal Processing and Control,2022,73:103456. |
[1] | Meng CHEN, Yu HONG. Test Study on Drying Shrinkage Properties of Engineered Cementitious Composites with RTP‐PVA Hybrid Fibre [J]. Journal of Northeastern University(Natural Science), 2024, 45(3): 407-414. |
[2] | Guang-lei XIA, Zhao-xia WU, Meng-yuan LIU, Yu-shan JIANG. Prediction of Sinter Chemical Indexes Based on GMM-KNN-LSTM [J]. Journal of Northeastern University(Natural Science), 2024, 45(3): 314-322. |
[3] | Meng-yuan LIU, Zhao-xia WU, Jin-yang WANG, Guang-lei XIA. Air Permeability Prediction of Sinter Layer Based on TST-LSTM Model [J]. Journal of Northeastern University(Natural Science), 2024, 45(10): 1379-1385. |
[4] | LIU Ke-qi, DU Dian-chun, ZHAO Wen, DING Wan-tao. Machine Learning-Based Prediction and Optimization of Slurry Shield’s Key Tunneling Parameters [J]. Journal of Northeastern University(Natural Science), 2023, 44(11): 1621-1630. |
[5] | JIAO Zhi-jie, WANG Zhi-qiang, LUO Jun-yi, XU Zhi-peng. Study on Plate Angular Rolling Process Using Pattern Prediction Model [J]. Journal of Northeastern University(Natural Science), 2022, 43(6): 815-820. |
[6] | CHEN Bing, HAN Jin-yang, TANG Xiao-lei, XIA Bo-ran. Prediction Model for Elongation of Tension Leveling Based on Machine Learning Algorithm and Numerical Analysis [J]. Journal of Northeastern University(Natural Science), 2022, 43(2): 236-242. |
[7] | GONG Qi, CHEN Bing-zhi, LI Yong-hua, XIA Qing. Fault Analysis of Metro Power Supply Module and Prediction Method [J]. Journal of Northeastern University(Natural Science), 2022, 43(1): 8-16. |
[8] | GUO Yong-chun, ZHENG Hai-yan, HU Xin-guang, SHENG Feng-man. Prediction Model of Al2O3 Activity in CaO-SiO2-Al2O3-MgO Quaternary Slag System [J]. Journal of Northeastern University(Natural Science), 2021, 42(5): 652-657. |
[9] | ZHU Zi-zong, XIE Yang-yang, WU Qiang, SHI Guo-jing. Coke-Making with Modified Xinjiang Kubai Coals and Prediction the Cold Strength of Coke [J]. Journal of Northeastern University Natural Science, 2017, 38(12): 1726-1730. |
[10] | LI Xiao-peng, WANG Xue, YUN Hai-meng, AN Lian-chui. Static Friction Coefficient Fractal Model of Joint Surfaces with Elastic-Plastic Beformation Considered [J]. Journal of Northeastern University Natural Science, 2016, 37(5): 673-677. |
[11] | LIU Qing, YUAN Wei, WANG Bao, PENG Liang-zhen. Concentrate Grade Prediction of Gold Ore Based on GA-BP Neural Network [J]. Journal of Northeastern University Natural Science, 2015, 36(2): 237-240. |
[12] | LYU Wu, MAO Zhizhong, YUAN Ping, JIA Mingxing. Ladle Furnace End Point Sulphur Content Prediction Model Based on Model Migration Method〓 [J]. Journal of Northeastern University Natural Science, 2014, 35(3): 314-317. |
Viewed | ||||||
Full text |
|
|||||
Abstract |
|
|||||