Multi-objective prediction optimization for large-diameter slurry shield tunneling construction based on CatBoost-MOEAD

doi:10.16265/j.cnki.issn1003-3033.2024.06.1734

Abstract

Abstract:

To effectively optimize the shield construction parameters and achieve the goals of safety, efficiency, and energy-saving in the large-diameter slurry shield tunneling process, a hybrid intelligent algorithm combining categorical boosting (CatBoost) and decomposition was proposed based on a multi-objective evolutionary algorithm (MOEAD). The main shield construction parameters were set as the major research objects considering shield construction parameters and geological conditions, and the surface settlement, penetration rate, and tunneling-specific energy were determined as the prediction and control objectives. Moreover, the selected shield construction parameters were optimized, and a line of Wuhan rail transit was used to validate the hybrid algorithm performance. The results showed that the proposed CatBoost algorithm had great prediction performance for large-diameter slurry shields with the fitting accuracy (R²) of the three control objectives more than 0.9. The model's importance rank indicated that the total propulsion force and propulsion speed of the large-diameter slurry shield had significant influences on surface settlement, penetration, and tunneling-specific energy. The proposed CatBoost-MOEAD hybrid intelligent algorithm had an obvious optimization effect on the three control objectives, and the optimization ranges of surface settlement, penetration rate, and tunneling-specific energy reached 12.35%, 7.47%, and 10.70%, respectively. Moreover, the control ranges of corresponding shield construction parameters were presented.

Key words: large-diameter slurry shield, categorical boosting (CatBoost), multi-objective evolutionary algorithm based on decomposition (MOEAD), multi-objective optimization, surface settlement

CLC Number:

X948
U455

WU Xianguo, LIU Jun, SU Feiming, CHEN Hongyu, FENG Zongbao. Multi-objective prediction optimization for large-diameter slurry shield tunneling construction based on CatBoost-MOEAD[J]. China Safety Science Journal, 2024, 34(6): 57-64.

Figures/Tables 9

Table 1

Table 2

Table 3

Fig.1

Fig.2

Table 4

Fig.3

Table 5

Table 6

References 25

[1]	DING Zhi, ZHANG Mobao, ZHANG Xiao, et al. Theoretical analysis on the deformation of existing tunnel caused by under-crossing of large-diameter slurry shield considering construction factors[J]. Tunnelling and Underground Space Technology, 2023, 133: DOI: 10.1016/j.tust.2022.104913.
[2]	叶万军, 成炜康, 陈笑楠, 等. 砂卵石地层大直径盾构工程地表沉降深度学习预测[J]. 中国安全生产科学技术, 2023, 19(8):124-129.
	YE Wanjun, CHENG Weikang, CHEN Xiaonan, et al. Deep learning and prediction on surface subsidence of large-diameter shield project in sandy cobble stratum[J]. Journal of Safety Science and Technology, 2023, 19(8):124-129.
[3]	翟淑芳, 杜红坤, 岳奇超, 等. 基于特征粒径的盘形滚刀破岩最优贯入度分析[J]. 现代隧道技术, 2023, 60(4):147-152,162.
	ZHAI Shufang, DU Hongkun, YUE Qichao, et al. Analysis of the optimal penetration of disc cutter in rock breaking based on Characteristic particle size[J]. Modern Tunnelling Technology, 2023, 60(4):147-152,162.
[4]	张仁贤. 泥水盾构掘进功率自适应控制技术研究[D]. 杭州: 浙江大学, 2019.
	ZHANG Renxian. Research on power adaptive control technology of slurry shield driving head[D]. Hangzhou: Zhejiang University, 2019.
[5]	朱才辉, 李宁. 地铁施工诱发地表最大沉降量估算及规律分析[J]. 岩石力学与工程学报, 2017, 36(增1):3543-3560.
	ZHU Caihui, LI Ning. Estimation and regularity analysis of maximal surface settlement induced by subway construction[J]. Chinese Journal of Rock Mechanics and Engineering, 2017, 36(S1):3543-3560.
[6]	王超, 刘红中, 王乐乎, 等. 基于线性回归法的TBM滚刀贯入度预测研究[J]. 隧道建设:中英文, 2021, 41(增1):207-215.
	WANG Chao, LIU Hongzhong, WANG Lehu, et al. Penetration prediction of disc cutter of tunnel boring machine based on linear regression method[J]. Tunnel Construction, 2021, 41(S1):207-215.
[7]	张垚. 土压平衡盾构机掘进系统能耗优化控制[D]. 抚顺: 辽宁石油化工大学, 2020.
	ZHANG Yao. Optimization control of energy consumption in tunneling system of earth pressure balance shield tunneling machine[D]. Fushun: Liaoning Petrochemical University, 2020.
[8]	PECK R B. Deep excavations and tunnelling in soft ground[C]. The 7^th International Conference on Soil Mechanics and Foundation Engineering, 1969:225-290.
[9]	LIU Xinrong, SULIMAN Lojain, ZHOU Xiaohan, et al. Settlement characteristic due to excavate parallel tunnels in a fill-rock slope: model test and numerical analysis[J]. Rock Mechanics and Rock Engineering, 2022, 55(11):7125-7143.
[10]	LI Liping, SUN Shanggu, WANG Jing, et al. Development of compound EPB shield model test system for studying the water inrushes in karst regions[J]. Tunnelling and Underground Space Technology, 2020, 101: DOI: 10.1016/j.tust.2020.103404.
[11]	GUO Kai, ZHANG Limao. Data-driven optimization for mitigating tunnel-induced damages[J]. Applied Soft Computing, 2022, 115: DOI: 10.1016/j.asoc.2021.108128.
[12]	方诗圣, 苏一恒, 林彤彤, 等. 基于机器学习的盾构掘进地表沉降回归预测模型[J]. 合肥工业大学学报:自然科学版, 2023, 46(9):1224-1229.
	FANG Shisheng, SU Yiheng, LIN Tongtong, et al. Regression prediction model of shield tunneling-induced ground settlement based on machine learning algorithms[J]. Journal of Hefei University of Technology:Natural Science, 2023, 46(9):1224-1229.
[13]	SHAN Feng, HE Xuzhan, ARMAGHANI D J, et al. Success and challenges in predicting TBM penetration rate using recurrent neural networks[J]. Tunnelling and Underground Space Technology, 2022, 130: DOI: 10.1016/j.tust.2022.104728.
[14]	ELBAZ K, YAN Tao, ZHOU Annan, et al. Deep learning analysis for energy consumption of shield tunneling machine drive system[J]. Tunnelling and Underground Space Technology, 2022, 123: DOI: 10.1016/j.tust.2022.104405.
[15]	吴贤国, 冯宗宝, 刘俊, 等. 基于RF-NSGA-Ⅱ的盾构施工地表沉降安全控制多目标优化[J]. 中国安全科学学报, 2022, 32(8):45-51. doi: 10.16265/j.cnki.issn1003-3033.2022.08.2702
	WU Xianguo, FENG Zongbao, LIU Jun, et al. Multi-objective optimization of surface settlement safety control during shield construction based on RF-NSGA-Ⅱ[J]. China Safety Science Journal, 2022, 32(8):45-51. doi: 10.16265/j.cnki.issn1003-3033.2022.08.2702
[16]	曾铁梅, 王金峰, 吴贤国, 等. 盾构下穿既有隧道位移控制施工参数多目标优化[J]. 铁道标准设计, 2022, 66(2):98-104.
	ZENG Tiemei, WANG Jinfeng, WU Xianguo, et al. Multi-objective optimization of displacement of shield tunneling underpass existing tunnel based on GA-LSSVM combining NSGA-II[J]. Railway Standard Design, 2022, 66(2):98-104.
[17]	鲁宇明, 史册, 黎明, 等. 基于改进MOEAD算法的零件加工布局优化研究[J]. 机械设计, 2021, 38(5):49-56.
	LU Yuming, SHI Ce, LI Ming, et al. Research on optimization of parts processing layout based on the improved MEAD algorithm[J]. Journal of Machine Design, 2021, 38(5):49-56.
[18]	PROKHORENKOVA L, GUSEV G, VOROBEV A, et al. CatBoost: unbiased boosting with categorical features[C]. The 32^nd International Conference on Neural Information Processing Systems, 2018:6639-6649.
[19]	ZHANG Qingfu, LI Hui. MOEA/D: a multiobjective evolutionary algorithm based on decomposition[J]. IEEE Transactions on Evolutionary Computation, 2007, 11(6):712-731.
[20]	刘茜. 基于智能方法的盾构施工参数预测和优化控制[D]. 武汉: 华中科技大学, 2022.
	LIU Xi. Prediction and optimal control of shield construction parameters based on intelligent methods[D]. Wuhan: Huazhong University of Science and Technology, 2022.
[21]	KIM D K, KWON K, PHAM K, et al. Surface settlement prediction for urban tunneling using machine learning algorithms with Bayesian optimization[J]. Automation in Construction, 2022, 140:DOI: 10.1016/j.autcon.2022.104331.
[22]	CHEN Renpeng, ZHANG Pin, WU Huaina, et al. Prediction of shield tunneling-induced ground settlement using machine learning techniques[J]. Frontiers of Structural and Civil Engineering, 2019, 13(6):1363-1378. doi: 10.1007/s11709-019-0561-3
[23]	张品. 基于机器学习算法的盾构掘进地表沉降预测及控制[D]. 长沙: 湖南大学, 2019.
	ZHANG Pin. Prediction and control of tunneling-induced settlement using machine learning algorithms[D]. Changsha: Hunan University, 2019.
[24]	TANG Libin, NA Seonhong. Comparison of machine learning methods for ground settlement prediction with different tunneling datasets[J]. Journal of Rock Mechanics and Geotechnical Engineering, 2021, 13(6):1274-89.
[25]	阮顺领, 韩思淼, 张宁宁, 等. 基于CNN-aGRU融合模型的尾矿坝浸润线预测方法[J]. 中国安全科学学报, 2023, 33(增1):119-127.
	RUAN Shunling, HAN Simiao, ZHANG Ningning, et al. Prediction method of saturation line of tailings dam based on CNN-aGRU fusion model[J]. China Safety Science Journal, 2023, 33(S1):119-127. doi: 10.16265/j.cnki.issn1003-3033.2023.S1.2481

岩土编号	岩土名称	黏聚力/ kPa	内摩擦角/(°)	压缩模量/MPa
1-1	杂填土	14.8	9.3	2.84
2-4	粉质黏土	18.8	9.2	10.43
3-2	粉质黏土	14.4	6.0	4.40
3-2b	粉砂	29.4	36.9	15.19
4-21	粉细砂	21.3	37.1	11.31

参数	最大值	最小值	平均值
x₁/(mm·min^-1)	36.17	24.21	29.32
x₂/(rad·min^-1)	1.28	1.16	1.23
x₃/kN	61 140.00	43 313.37	54 309.21
x₄/(kN·m)	4 014.84	1 780.01.	2 575.85
x₅/MPa	0.018	0.012	0.015 6
x₆MPa	0.516	0.032	0.316 0
x₇/m³	3 013.00	2 248.64	2 663.10
x₈/m³	3 110.35	2 313.33	2 795.98
x₉/MPa	0.380	0.283	0.338
x₁₀/MPa	0.368	0.294	0.311
x₁₁/(°)	4.13	-10.07	-4.22
x₁₂/(°)	14.08	7.44	10.77
x₁₃/kPa	25.35	13.67	19.49
x₁₄/MPa	10.77	6.92	8.21
x₁₅/m	18.60	17.61	18.11
y₁/mm	2.37	-11.33	-1.62
y₂/mm	26.95	17.72	24.96
y₃/(kJ·m^-3)	522.22	420.50	455.12

超参数	搜索范围	优化结果
超参数	搜索范围	地表沉降	贯入度	掘进比能
max_depth	(4, 8)	4	4	4
l2_leaf_reg	(3, 9)	9	3	3
learning rate	(0.01, 0.5)	0.01	0.1	0.03

输入参数	参数范围	输入参数	参数范围
x₁/(mm·min^-1)	[0,80]	x₄/(kN·m)	[0,8 000]
x₂/(rad·min^-1)	[0,7.6]	x₁₀/MPa	[0,0.6]
x₃/(kN)	[0,90 000]	x₁₁/(°)	[-8,8]

数据	地表沉降/mm	贯入度/ mm	掘进比能/ (kJ·m^-3)
原始数据平均值	-1.62	24.96	455.12
优化结果平均值	-1.42 (12.35%)	26.82 (7.47%)	406.39 (10.71%)
理想点取值	-1.33 (17.90%)	25.99 (4.13%)	404.70 (11.08%)