基于RF-NSGA-II的盾构施工地表沉降安全控制多目标优化*

doi:10.16265/j.cnki.issn1003-3033.2022.08.2702

中国安全科学学报 ›› 2022, Vol. 32 ›› Issue (8): 45-51.doi: 10.16265/j.cnki.issn1003-3033.2022.08.2702

基于RF-NSGA-II的盾构施工地表沉降安全控制多目标优化*

吴贤国¹(), 冯宗宝¹, 刘俊¹, 王雷¹^,^**(), 陈虹宇², 李昕懿¹

¹ 华中科技大学土木与水利工程学院,湖北武汉 430074
² 南洋理工大学土木工程与环境学院,新加坡 639798

收稿日期:2022-02-12 修回日期:2022-05-15 出版日期:2022-09-05 发布日期:2023-02-28
通讯作者: 王雷
作者简介:
吴贤国 (1964—),女,湖北武汉人,博士,教授,主要从事数字工程集成建设关键技术及应用、隧道工程施工与运营安全监控等方面的研究。E-mail: wuxg@hust.edu.cn。
基金资助:
国家自然科学基金资助(51778262); 国家自然科学基金资助(71571078); 国家自然科学基金资助(51308240)

Multi-objective optimization of surface settlement safety control during shield construction based on RF-NSGA-II

WU Xianguo¹(), FENG Zongbao¹, LIU Jun¹, WANG Lei¹^,^**(), CHEN Hongyu², LI Xinyi¹

¹ School of Civil and Hydraulic Engineering, Huazhong University of Science and Technology, Wuhan Hubei 430074, China
² School of Civil Engineering and Environment, Nanyang Technological University, Singapore 639798

Received:2022-02-12 Revised:2022-05-15 Online:2022-09-05 Published:2023-02-28
Contact: WANG Lei

摘要/Abstract

摘要：

为有效调整盾构施工参数,指导盾构安全高效施工,建立随机森林(RF)与非支配排序遗传算法(NSGA-II)相结合的多目标优化模型,以主要盾构参数为研究对象,以地表沉降和刀盘磨损为控制目标,优化控制分析施工参数;选取控制地表沉降的9个盾构参数作为RF预测模型的输入指标,得到盾构施工参数与地表沉降的非线性关系,作为NSGA-II适应度函数,选择刀盘磨损作为第2个优化目标,设定施工参数约束范围进行多目标优化;以岩溶地区某地轨道交通项目为例进行验证。结果表明:采用RF算法模拟训练工程实测数据,得到的地表沉降预测模型的精度较高;基于RF-NSGA-II模型智能算法对地表沉降和刀盘磨损的优化效果显著,该模型能够得出相应岩溶地区盾构施工参数控制范围。

关键词: 随机森林(RF), 非支配排序遗传算法(NSGA-II), 盾构施工参数, 地表沉降, 刀盘磨损, 多目标优化

Abstract:

In order to effectively adjust construction parameters of shields, and to achieve safe construction, a multi-objective optimization model based on RF and NSGA-II algorithm was established, in which control analysis of construction parameters were optimized with main shield parameters as research object and ground settlement as control target. Then, nine shield parameters controlling surface settlement were selected as input indexes of RF prediction model, and nonlinear relationship between the parameters and settlement was obtained as NSGA-II fitness function. Then, cutter wear was selected as the second optimization objective, and constraint range of construction parameters was set for multi-objective optimization. Finally, with a rail transit project in karst areas as an example, verification was conducted. The results show that using RF algorithm in training and simulating measured data of the project will result in high prediction accuracy. And the proposed model based on RF-NSGA-II features significant multi-objective optimization effect of ground settlement and cutter head wear, and it can obtain control range of shield construction parameters in karst areas.

Key words: random forest (RF), nondominated sorting genetic algorithm-II (NSGA-II), shield construction parameter, surface settlement, cutter head wear, multi-objective optimization

吴贤国, 冯宗宝, 刘俊, 王雷, 陈虹宇, 李昕懿. 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.

WU Xianguo, FENG Zongbao, LIU Jun, WANG Lei, CHEN Hongyu, LI Xinyi. 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.

图/表 6

图1

表1

图2

表2

图3

表3

参考文献 21

[1]	王军武, 胡蝶, 吴寒, 等. 小直径深层排水隧道盾构施工安全风险评价[J]. 中国安全科学学报, 2020, 30(6): 113-120. doi: 10.16265/j.cnki.issn1003-3033.2020.06.017
	WANG Junwu, HU Die, WU Han, et al. Risk assessment in construction of small-diameter deep drainage tunnel[J]. China Safety Science Journal, 2020, 30(6): 113-120. doi: 10.16265/j.cnki.issn1003-3033.2020.06.017
[2]	冯欢欢, 王树英, 杨露伟, 等. 复杂地质条件下TBM刀具失效形式及原因分析与应对措施[J]. 隧道建设:中英文, 2022, 42(1):130-136.
	FENG Huanhuan, WANG Shuying, YANG Luwei, et al. Forms and causes of failure in tunnel boring machine cutters under complex geological conditions and corresponding countermeasures[J]. Tunnel Construction, 2022, 42(1): 130-136.
[3]	OCAK I, SEKER S E. Calculation of surface settlements caused by EPBM tunneling using artificial neural network, SVM, and Gaussian processes[J]. Environmental Earth Sciences, 2013, 70(3): 1 263-1 276.
[4]	CHEN Renpeng, ZHANG Ping, 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): 1363-1 378. doi: 10.1007/s11709-019-0561-3
[5]	王鹏. 基于机器学习的地铁隧道施工扰动控制研究[J]. 现代隧道技术, 2019, 56(增2): 368-373.
	WANG Peng. Control of construction disturbance induced by shield tunnelling based on machine learning[J]. Modern Tunnelling Technology, 2019, 56(S2): 368-373.
[6]	石超, 薛皓文, 丁小彬. 基于BP神经网络的硬岩地层盾构滚刀磨损预测[J]. 现代隧道技术, 2020, 57(增1): 217-225.
	SHI Chao, XUE Haowen, DING Xiaobin. Prediction of cutter wear of shield machine in hard rock stratum based on BP neural network[J]. Modern Tunnelling Technology, 2020, 57(S1): 217-225.
[7]	REN Dongjie, SHEN Shuilong, ARUL A, et al. Prediction model of TBM disc cutter wear during tunnelling in heterogeneous ground[J]. Rock Mechanics and Rock Engineering, 2018, 51(11): 3599-3611. doi: 10.1007/s00603-018-1549-3
[8]	陈焱, 王宇皓, 方勇, 等. 砂性地层土压平衡盾构切刀磨损室内试验研究[J]. 现代隧道技术, 2021, 58(5): 159-166.
	CHEN Yan, WANG Yuhao, FANG Yong, et al. Laboratory experimental study on the wear of EPB shield cutting tools in sandy stratum[J]. Modern Tunnelling Technology, 2021, 58(5):159-166.
[9]	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]. Rallway Standard Design, 2022, 66(2):98-104.
[10]	BREIMAN L. Random forests[J]. Machine Learning, 2001, 45(1): 5-32. doi: 10.1023/A:1010933404324
[11]	张新生, 蔡宝泉. 基于改进随机森林模型的海底管道腐蚀预测[J]. 中国安全科学学报, 2021, 31(8): 69-74. doi: 10.16265/j.cnki.issn1003-3033.2021.08.010
	ZHANG Xinsheng, CAI Baoquan. Corrosion prediction of submarine pipelines based on improved random forest model[J]. China Safety Science Journal, 2021, 31(8):69-74. doi: 10.16265/j.cnki.issn1003-3033.2021.08.010
[12]	SRINIVAS N, DEB K, ROY P K, et al. Comparative study of vector evaluated GA and NSGA applied to multiobjective optimization[C]. Proceedings of the Symposium on Genetic Algorithms, 1995: 83-90.
[13]	DEB K, AGRAWAL S, PRATAP A, et al. A fast elitist non-dominated sorting genetic algorithm for multi-objective optimization: NSGA-II[C]. International Conference on Parallel Problem Solving From Nature, 2000: 849-858.
[14]	LIU Xuxuan, XU Sheng, HUANG Yueyang. Optimal control for earth pressure balance of shield machine based on action-dependent heuristic dynamic programming[J]. ISA Transactions, 2019, 94: 28-35. doi: 10.1016/j.isatra.2019.04.007
[15]	BOUAYAD D, TUNNELLING F E J, TECHNOLOGY U S. Modeling the relationship between ground surface settlements induced by shield tunneling and the operational and geological parameters based on the hybrid PCA/ANFIS method[J]. Tunnelling and Underground Space Technology, 2017, 68: 142-152. doi: 10.1016/j.tust.2017.03.011
[16]	邓立营, 刘春光, 党军锋. 盾构机刀盘扭矩及盾体推力计算方法研究[J]. 矿山机械, 2010, 38(17): 13-16.
	DENG Liying, LIU Chunguang, DANG Junfeng. Research on method of calculating torque of cutter head of shield machine and thrust of shield[J]. Mining Machine, 2010, 38(17): 13-16.
[17]	KIM D, PHAM K, PARK S, et al. Determination of effective parameters on surface settlement during shield TBM[J]. Geomechanics and Engineering, 2020, 21(2): 153-164.
[18]	吕乾乾. 地铁盾构隧道同步注浆施工对地层沉降影响的预测分析[D]. 天津: 天津大学, 2012.
	LYU Qianqian. Prediction and analysis of influence on stratum settlement of subway shield tunnel construction with synchronous grouting[D]. Tianjin: Tianjin University, 2012.
[19]	陶冶. 基于SVM的盾构刀盘能耗预测分析[D]. 武汉: 华中科技大学, 2017.
	TAO Ye. Prediction and analysis of energy consumption of shield cutter based on SVM[D]. Wuhan: Huazhong University of Science and Technology, 2017.
[20]	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, 2019.
	ZHANG Yao. Optimization control of energy consumption in tunneling system of earth pressure balance shield tunneling machine[D]. Fushun: Liaoning University of Petrochemical Technology, 2019.
[21]	GAO Minyu, ZHANG Ning, SHEN Shuilong, et al. Real-time dynamic earth-pressure regulation model for shield tunneling by integrating gru deep learning method with ga optimization[J]. Ieee Access, 2020, 8: 64 310-64 323.

参数类型	变量	数据(221组)
	变量	最小值	最大值
	土压力X₁/ MPa	0.05	0.18
	刀盘转速X₂/(rad·min^-1)	1.3	2.3
	总推力X₃/kN	8 000	15 000
	刀盘扭矩X₄/(kN·m)	1 208	3 050
	掘进速度X₅/ (mm·min^-1)	12.96	28.17
	注浆压力X₆/MPa	0.093	0.286
	注浆量X₇/ m³	4.4	11.8
	渣土量X₈/ m³	38	80
	泡沫剂X₉/ L	22.22	44.44
输出	地表沉降f₁/ mm	0.22	8.55

输入参数	参数范围	输入参数	参数范围
X₁/MPa	[0,0.3]	X₆/MPa	[0,0.5]
X₂/(rad·min^-1)	[0,3]	X₇/ m³	[0,20]
X₃/kN	[0,25000]	X₈/ m³	[0,150]
X₄/(kN·m)	[0,4000]	X₉/L	[0,100]

变量	优化结果			盾构施工实际数据			控制范围
变量	最小值	最大值	平均值	最小值	最大值	平均值	控制范围
X₁/MPa	0.06	0.11	0.08	0.05	0.18	0.13	0.06~0.11
X₂/(rad·min^-1)	1.3	1.3	1.3	1.3	2.3	1.6	1.3
X₃/kN	8 616	13 949	10 791	8 000	15 000	11 929	8 600~14 000
X₄/(kN·m)	1 904	3 001	2 786	1 208	3 050	2 000	1 900~3 000
X₅/(mm·min^-1)	13.6	27.8	22.1	13.0	28.2	22.7	14~28
X₆/MPa	0.13	0.28	0.18	0.09	0.29	0.21	0.1~0.3
X₇/m³	4.4	5.2	4.9	4.4	11.8	5.6	4~5
X₈/m³	39	75	50	39	80	51	39~75
X₉/L	33.4	40.0	35.5	22.2	44.4	35.2	33~40
f₁/mm	0.45	3.27	2.23	0.22	8.55	2.87	—
f₂/mm	0.13	0.13	0.13	0.13	0.23	0.17	—

基于RF-NSGA-II的盾构施工地表沉降安全控制多目标优化*

Multi-objective optimization of surface settlement safety control during shield construction based on RF-NSGA-II

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 6

参考文献 21

相关文章 15

编辑推荐

Metrics

本文评价

[1]	杨文臣, 周燕宁, 田毕江, 郭凤香, 胡澄宇. 基于聚类分析和SVM的二级公路交通事故严重度预测[J]. 中国安全科学学报, 2022, 32(5): 163-169.
[2]	洪亮, 刘刚, 葛如海, 李梁, 李思远. 混杂工况下校车常开式安全气囊的多目标优化[J]. 中国安全科学学报, 2022, 32(4): 72-79.
[3]	丁茜, 赵晓东, 吴鑫俊, 张泰丽, 徐振涛. 基于RBF核的多分类SVM滑塌易发性评价模型[J]. 中国安全科学学报, 2022, 32(3): 194-200.
[4]	戢晓峰, 杨春丽, 郝京京, 覃文文. 国内外应急物流研究热点对比与展望^*[J]. 中国安全科学学报, 2021, 31(12): 144-152.
[5]	杨晓强, 林湘漪, 蒋澜. 使用困难报告数据驱动的民用航空器安全状态评价^*[J]. 中国安全科学学报, 2021, 31(11): 85-92.
[6]	吴仁彪, 何宇翔, 贾云飞. 基于改进层次分析法的重点人员风险评价方法^*[J]. 中国安全科学学报, 2021, 31(10): 112-118.
[7]	田睿, 孟海东, 陈世江, 王创业, 石磊. RF-AHP-云模型下岩爆烈度分级预测模型[J]. 中国安全科学学报, 2020, 30(7): 166-172.
[8]	赵建强, 熊彦铭, 张佑建. 隔离-失能竞争失效机制下安全系统多目标优化设计[J]. 中国安全科学学报, 2020, 30(6): 1-7.
[9]	杜修力, 曹秀秀, 钟紫蓝, 侯本伟, 王威. 考虑多失效模式的桩-土结构体系稳健性设计[J]. 中国安全科学学报, 2020, 30(6): 23-30.
[10]	张忠义, 宋英华, 王喆, 刘丹. 多层级防汛应急物资储备库公私协同LAP模型[J]. 中国安全科学学报, 2020, 30(5): 177-183.
[11]	马辉, 张文静, 董美红. 装配式建筑吊装施工空间冲突分析与多目标优化[J]. 中国安全科学学报, 2020, 30(2): 28-34.
[12]	宋英华, 苏贝贝, 霍非舟, 宁晶婧, 方丹辉. 考虑动态需求的应急物资配送中心快速选址研究[J]. 中国安全科学学报, 2019, 29(8): 172-177.
[13]	柴超君, 凌永生, 岳琪, 贾文宝. 维数约简用于BPNN的核事故源项估算方法[J]. 中国安全科学学报, 2018, 28(9): 122-127.
[14]	师建国, 高广财, 滕睿. 采煤机滚筒参数优化及其对摇臂安全使用性能影响[J]. 中国安全科学学报, 2018, 28(8): 55-60.
[15]	宋叶, 宋英华, 刘丹, 王喆. 基于时间满意度和胜任能力的地震应急救援队伍指派模型[J]. 中国安全科学学报, 2018, 28(8): 180-185.