基于机器学习的直角扣件滑移和扭转性能预测方法

doi:10.16183/j.cnki.jsjtu.2022.399

上海交通大学学报 ›› 2024, Vol. 58 ›› Issue (2): 242-252.doi: 10.16183/j.cnki.jsjtu.2022.399

• 船舶海洋与建筑工程 • 上一篇

基于机器学习的直角扣件滑移和扭转性能预测方法

鲍朱杰¹^,², 李祯³, 王斐亮¹^,²^,⁴, 庞博¹^,², 杨健¹^,²()

1.上海交通大学海洋工程国家重点实验室,上海 200240
2.上海市公共建筑和基础设施数字化运维重点实验室,上海 200240
3.广州建筑集团有限公司,广州 510030
4.宁波大学冲击与安全工程教育部重点实验室,浙江宁波 315211

收稿日期:2022-10-12 修回日期:2022-12-07 接受日期:2022-12-14 出版日期:2024-02-28 发布日期:2024-03-04
通讯作者: 杨健,教授,博士生导师;E-mail:j.yang.1@sjtu.edu.cn.
作者简介:鲍朱杰(1998-),硕士生,从事现代结构损伤监测技术研究.
基金资助:
上海市科技创新项目(20dz1201301);上海市科技创新项目(21dz1204704);四川省区域创新合作项目(2022YFQ0048);冲击与安全工程教育重点实验室(宁波大学)开放课题(CJ202106);中国博士后科学基金(2020M682669)

Prediction of Slip and Torsion Performance of Right-Angle Fasteners Based on Machine Learning Methods

BAO Zhujie¹^,², LI Zhen³, WANG Feiliang¹^,²^,⁴, PANG Bo¹^,², YANG Jian¹^,²()

1. State Key Laboratory of Ocean Engineering, Shanghai Jiao Tong University, Shanghai 200240, China
2. Shanghai Key Laboratory for Digital Maintenance of Buildings and Infrastructure, Shanghai 200240, China
3. Guangzhou Municipal Construction Group Co., Ltd., Guangzhou 510030, China
4. Key Laboratory of Impact and Safety Engineering of the Ministry of Education, Ningbo University, Ningbo 315211, Zhejiang, China

Received:2022-10-12 Revised:2022-12-07 Accepted:2022-12-14 Online:2024-02-28 Published:2024-03-04

摘要/Abstract

摘要：

直角扣件初始刚度对模板支架结构承载力有较大影响,但扣件性能的量化设计存在工程量大、计算精确度低等问题.基于一系列扣件抗滑移和扭转试验,建立带直角扣件节点的三维数值模拟并利用试验结果进行验证,通过验证后的数值方法开展大量参数分析揭示多种设计参数对扣件性能的综合影响并建立扣件承载力设计数据库,分别基于随机森林(RF)、支持向量机(SVM)和K最邻近算法(K-NN)提出了扣件刚度预测模型,结合基因表达式编程(GEP)提出了抗滑移模型测点位移和扭转模型刚度预测表达式.研究表明,通过SVM和GEP能够较准确预测直角扣件抗滑移模型位移和扭转模型刚度,对指导工程模板支架结构中扣件的安全设计有着重要意义.

关键词: 直角扣件, 抗滑移性能, 扭转性能, 参数分析, 机器学习

Abstract:

Aiming at the issue of large CPU costs and low calculation accuracy in the design of right-angle fasteners in scaffolding structures, prediction models of fastener anti-slip performance and torsion performance based on machine learning are proposed. A three-dimensional solid model of right-angle fasteners is established using the finite element method, the effectiveness of the numerical simulation method is verified through test results, and the comprehensive influence of various design parameters on the performance of fasteners is revealed by the parametric analysis method. The database is established by combining the test and numerical simulation results, and the fastener stiffness prediction models are proposed based on random forest (RF), support vector machine (SVM) and K-most proximity algorithm (K-NN), respectively. The expressions for the measured point displacement of the anti-slip model and the stiffness prediction of the torsion model are proposed in combination with genetic expression programming. The results indicate that SVM and GEP can predict the displacement and torsional stiffness of right-angle fasteners more accurately, which is important for guiding the safety design of fasteners in engineering scaffolding structures.

Key words: rectangular fasteners, anti-slip performance, torsional performance, parameter analysis, machine learning

中图分类号:

TU731

鲍朱杰, 李祯, 王斐亮, 庞博, 杨健. 基于机器学习的直角扣件滑移和扭转性能预测方法[J]. 上海交通大学学报, 2024, 58(2): 242-252.

BAO Zhujie, LI Zhen, WANG Feiliang, PANG Bo, YANG Jian. Prediction of Slip and Torsion Performance of Right-Angle Fasteners Based on Machine Learning Methods[J]. Journal of Shanghai Jiao Tong University, 2024, 58(2): 242-252.

图/表 16

图1

图2

图3

图4

表1

图5

图6

图7

图8

图9

图10

表2

表3

表4

表5

图11

参考文献 32

[1]	孙世梅, 梁友, 闫伟, 等. 2010-2016年建筑施工脚手架坍塌事故统计分析[J]. 吉林建筑大学学报, 2018, 35(4): 33-36.
	SUN Shimei, LIANG You, YAN Wei, et al. Statistical analysis of scaffolding collapse accidents in building construction 2010-2016[J]. Journal of Jilin Jianzhu University, 2018, 35(4): 33-36.
[2]	HU X P, PENG G, NIU D T, et al. Experimental study on mechanical properties of steel tube-coupler connections in corroded scaffolds[J]. Journal of Constructional Steel Research, 2021, 176: 106383. doi: 10.1016/j.jcsr.2020.106383 URL
[3]	蔡雪峰, 周继忠, 庄金平. 钢管扣件节点抗滑性能研究[J]. 土木工程学报, 2009, 42(3): 60-64.
	CAI Xuefeng, ZHOU Jizhong, ZHUANG Jinping. Joint slip resistance performance of fasteners in steel pipe formwork supports[J]. China Civil Engineering Journal, 2009, 42(3): 60-64.
[4]	宋建学, 史瑞. 脚手架扣件抗滑移试验及分析[J]. 建筑技术, 2011, 42(10): 937-938.
	SONG Jianxue, SHI Rui. Anti-slip test and analysis of scaffold fasteners[J]. Construction Technology, 2011, 42(10): 937-938.
[5]	JIA L, LIU H, CHEN Z, et al. Mechanical properties of right-angle couplers in steel tube-coupler scaffolds[J]. Journal of Constructional Steel Research, 2016, 125: 43-60. doi: 10.1016/j.jcsr.2016.06.005 URL
[6]	CHANG C L, SONG J X. Parameters survey and experiment on steel scaffold components[J]. Advanced Materials Research, 2012, 368: 1513-1516.
[7]	何夕平, 王璜, 赵雪会. 扣件不同紧固力矩对工字钢悬挑钢管外脚手架变形影响分析[J]. 西安建筑科技大学学报, 2018, 50(2): 196-201.
	HE Xiping, WANG Huang, ZHAO Xuehui. Analysis of the deformation influence on the external scaffold of I-steel cantilever steel pipe in different fastening torque[J]. Journal of Xi’an University of Architecture & Technology, 2018, 50(2): 196-201.
[8]	陈志华, 陆征然, 王小盾. 钢管脚手架直角扣件刚度的数值模拟分析及试验研究[J]. 土木工程学报, 2010, 43(9): 100-108.
	CHEN Zhihua, LU Zhengran, WANG Xiaodun. Numerical analysis and experimental study of the stiffness of right-angle couplers in tubular steel scaffolds[J]. China Civil Engineering Journal, 2010, 43(9): 100-108.
[9]	陆征然, 陈志华, 王小盾, 等. 扣件式钢管满堂支撑体系稳定性的有限元分析及试验研究[J]. 土木工程学报, 2012, 45(1): 49-60.
	LU Zhengran, CHEN Zhihua, WANG Xiaodun, et al. Experimental and theoretical study of the bearing capacity of fastener steel tube full-hall formwork support system[J]. China Civil Engineering Journal, 2012, 45(1): 49-60.
[10]	贾莉, 刘红波, 陈志华, 等. 扣件式钢管满堂脚手架整体稳定试验与有限元分析[J]. 建筑结构学报, 2017, 38(6): 114-122.
	JIA Li, LIU Hongbo, CHEN Zhihua, et al. Experimental research and FEA on bearing capacity of full hall steel tube and coupler scaffold support system[J]. Journal of Building Structures, 2017, 38(6): 114-122.
[11]	中国建筑科学院. 建筑施工扣件式钢管脚手架安全技术规范: JGJ 130—2011[S]. 北京: 中国建筑工业出版社, 2011.
	China Academy of Building Research. Technical code for safety of steel tubular scaffold with couplers in construction: JGJ 130—2011[S]. Beijing: China Construction Industry Press, 2011.
[12]	SU L Y, FU L P. Analysis on the stability of double-fastener type tubular scaffold[C]// International Conference on Advances in Civil Engineering. UK: IOP Publishing, 2019, 330: 022083.
[13]	中华人民共和国国家质量监督检验检疫总局. 钢管脚手架扣件: GB 15831—2006[S]. 北京: 中国建筑金属结构, 2006.
	General Administration of Quality Supervision, Inspection and Quarantine of the People’s Republic of China. Steel tube scaffold couplers: GB 15831—2006[S]. Beijing: China Construction Metal Structure Association, 2006.
[14]	中国建筑一局有限公司. 建筑施工临时支撑结构技术规范: JGJ 300—2013[S]. 北京: 中国建筑工业出版社, 2013.
	China Construction First Group Corporation Limited. Technical specifications for temporary support structures for building construction: JGJ 300—2013[S]. Beijing: China Construction Industry Press, 2013.
[15]	全国铸造标准化技术委员会. 可锻铸铁件: GB/T 9440—2010[S]. 北京: 中华人民共和国国家质量监督检验检疫总局, 2010.
	National Technical Committee for Standardization of Foundry. Forged iron castings: GB/T 9440—2010[S]. Beijing: General Administration of Quality Supervision, Inspection and Quarantine of the People’s Republic of China, 2010.
[16]	全国钢标准化技术委员会. 低压流体输送用焊接钢管: GB/T 3091—2015[S]. 北京: 中华人民共和国国家质量监督检验检疫总局, 2015.
	National Technical Committee for Standardization of Steel. Welded steel pipes for low-pressure fluid transportation: GB/T 3091—2015[S]. Beijing: General Administration of Quality Supervision, Inspection and Quarantine of the People’s Republic of China, 2015.
[17]	张洪, 刘彬彬. 应用深度学习识别法兰螺栓连接状态[J]. 应用声学, 2021, 40(3): 350-357.
	ZHANG Hong, LIU Binbin. The recognition of flange bolt connection state based on deep learning[J]. Journal of Applied Acoustics, 2021, 40(3): 350-357.
[18]	ZHANG Z, DU F, ZHANG L, et al. Monitoring of piezoelectric impedance for bolt loosening using general regression neural network[J]. Mechanical Science and Technology for Aerospace Engineering, 2022, 41(4): 639-645.
[19]	NA W S. Bolt loosening detection using impedance based non-destructive method and probabilistic neural network technique with minimal training data[J]. Engineering Structures, 2021, 226: 111228. doi: 10.1016/j.engstruct.2020.111228 URL
[20]	SUN W C, GUAN Z Q, ZENG Y, et al. Bolt loosening detection of rocket connection structure based on variational modal decomposition and support vector machines[J]. Applied Sciences-Basel, 2022, 12(12): 6266.
[21]	WANG F R, CHEN Z, SONG G B. Monitoring of multi-bolt connection looseness using entropy-based active sensing and genetic algorithm-based least square support vector machine[J]. Mechanical Systems and Signal Processing, 2020, 136: 106507. doi: 10.1016/j.ymssp.2019.106507 URL
[22]	ERALIEV O, LEE K H, LEE C H. Vibration-based loosening detection of a multi-bolt structure using machine learning algorithms[J]. Sensors, 2022, 22(3): 1210. doi: 10.3390/s22031210 URL
[23]	KHAN N, SALEEM M R, LEE D, et al. Utilizing safety rule correlation for mobile scaffolds monitoring leveraging deep convolution neural networks[J]. Computers in Industry, 2021, 129: 103448. doi: 10.1016/j.compind.2021.103448 URL
[24]	SAROTHI S Z, AHMED K S, KHAN N I, et al. Machine learning-based failure mode identification of double shear bolted connections in structural steel[J]. Engineering Failure Analysis, 2022, 139: 106471. doi: 10.1016/j.engfailanal.2022.106471 URL
[25]	SAKHAKARMI S, ARTEAGA C, CHO C, et al. Scaffold safety analysis: Focusing on deep learning[C]// Construction Research Congress 2020:Computer Applications. New York, USA: Amer Soc Civil Engineers, 2020: 218-225.
[26]	赵平, 吴昊, 贾建国. 插销式脚手架在异形结构中的安全性能研究[J]. 工业建筑, 2015, 45(2): 101-106.
	ZHAO Ping, WU Hao, JIA Jianguo. Study of safety performance of plug-in scaffold for special-shaped structure[J]. Industrial Construction, 2015, 45(2): 101-106.
[27]	CHO C, KIM K, PARK J, et al. Data-driven monitoring system for preventing the collapse of scaffolding structures[J]. Journal of Construction Engineering and Management, 2018, 144(8): 4018077-1-13.
[28]	LUO S X, QIAO A M, TANG Q G. Fault diagnosis method for attached lifting scaffold based on support vector machine[J]. Journal of Engineering, 2020, 2020(13): 495-498.
[29]	PANG B, WANG F, YANG J, et al. Evaluation on the progressive collapse resistance of infilled reinforced concrete frames based on numerical and semi-analytical methods[J]. Engineering Structures, 2022, 267: 114684. doi: 10.1016/j.engstruct.2022.114684 URL
[30]	AZIM I, YANG J, IQBAL M F, et al. Prediction of catenary action capacity of RC beam-column substructures under a missing column scenario using evolutionary algorithm[J]. KSCE Journal of Civil Engineering, 2021, 25(3): 891-905. doi: 10.1007/s12205-021-0431-0
[31]	秦大同, 谢里阳. 现代机械设计手册[M]. 第2版. 北京: 化学工业出版社, 2011.
	QIN Datong, XIE Liyang. Modern mechanical design manual[M]. 2nd ed. Beijing: Chemical Industry Press, 2011.
[32]	FERREIRA C. Gene expression programming: A new adaptive algorithm for solving problems[J]. Complex Systems, 2001, 13(2): 87-129.

螺栓拧紧力矩/(N·m)	螺栓预紧力/kN
20	11.11
30	16.67
40	22.22
50	27.78
60	33.33

算法	模型超参数	滑移模型优化值	扭转模型优化值
RF	树的数量	100	99
	最大深度	7	7
SVM	正则化常数,c	2 070	7 000
	核函数类型	径向基核函数	径向基核函数
	核函数系数,γ	1	0.3
K-NN	邻域数	2	2

模型	训练集					测试集
模型	R²	RMSE	MAE	Mean	COV	R²	RMSE	MAE	Mean	COV
RF	1.00	3.39	1.34	1.05	0	0.99	0.89	0.23	0.98	0.04
SVM	0.99	0.65	0.33	0.99	0.24	0.98	0.29	0.10	0.99	0.08
K-NN	0.88	0.86	0.35	1.08	0.17	0.74	0.24	0.06	1.00	0.12

模型	训练集					测试集
模型	R²	RMSE	MAE	Mean	COV	R²	RMSE	MAE	Mean	COV
RF	0.97	416.47	311.78	0.97	0.28	0.90	217.19	169.43	1.00	0.08
SVM	0.95	335.53	236.37	1.00	0.23	0.90	231.72	148.35	0.98	0.07
K-NN	0.97	406.41	339.70	1.04	0.10	0.94	264.78	211.11	0.97	0.16

参数类型	优化值
染色体	30
基因	3
头部长度	10
基因连接运算符	+
函数集	+,-, *, /, ^2
变异概率	0.013 8
反转率	0.005 46
IS转座概率	0.005 46
RIS转座概率	0.005 46

基于机器学习的直角扣件滑移和扭转性能预测方法

Prediction of Slip and Torsion Performance of Right-Angle Fasteners Based on Machine Learning Methods

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 16

参考文献 32

相关文章 15

编辑推荐

Metrics

本文评价

[1]	孙乾洋, 周利, 丁仕风, 刘仁伟, 丁一. 基于人工神经网络的极地船舶冰阻力预报方法[J]. 上海交通大学学报, 2024, 58(2): 156-165.
[2]	李明爱1,2,3，许冬芹1. 综述：运动想像脑机接口中的迁移学习[J]. J Shanghai Jiaotong Univ Sci, 2024, 29(1): 37-59.
[3]	苏泓嘉, 罗宇成, 刘飞. 装备体系效能评估及支撑技术综述[J]. 空天防御, 2023, 6(3): 29-38.
[4]	黄俊, 李少杰, 康庄. 大管径海底管道J型铺设分析[J]. 海洋工程装备与技术, 2023, 10(2): 145-151.
[5]	孙婕, 李子昊, 张书宇. 机器学习在化学合成及表征中的应用[J]. 上海交通大学学报, 2023, 57(10): 1231-1244.
[6]	甘娥忠, 刘焱, 王海荣, 王承光. 基于机器学习性能度量理论的保障资源指标综合权衡研究[J]. 空天防御, 2023, 6(1): 38-44.
[7]	贾岛, 陈磊, 朱志鹏, 余曜, 迟德建. 机器学习在引战系统设计中的应用研究[J]. 空天防御, 2022, 5(2): 27-31.
[8]	王卓鑫, 赵海涛, 谢月涵, 任翰韬, 袁明清, 张博明, 陈吉安. 反向传播神经网络联合遗传算法对复合材料模量的预测[J]. 上海交通大学学报, 2022, 56(10): 1341-1348.
[9]	李川, 聂熠文, 刘军伟, 孟凡钦, 沈晓静. 基于机器学习的多算法融合航迹稳健起始方法[J]. 空天防御, 2022, 5(1): 20-24.
[10]	周毅, 秦康平, 孙近文, 范栋琦, 郑义明. 台风气象环境电网设备风险量化预警及其N-m故障处置预案在线生成方法[J]. 上海交通大学学报, 2021, 55(S2): 22-30.
[11]	何夏维, 蔡云泽, 严玲玲. 一种合成残差式的反作用轮故障检测方法[J]. 上海交通大学学报, 2021, 55(6): 716-728.
[12]	祝颂, 钱晓超, 陆营波, 刘飞. 基于XGBoost的装备体系效能预测方法[J]. 空天防御, 2021, 4(2): 1-.
[13]	包清临, 柴华奇, 赵嵩正, 王吉林. 采用机器学习算法的技术机会挖掘模型及应用[J]. 上海交通大学学报, 2020, 54(7): 705-717.
[14]	张东明, 张晓云, 杨小波, 侯心一. 基于正交实验和多项式回归分析方法的非典型接触状态车人碰撞事故参数分析[J]. 上海交通大学学报, 2019, 53(1): 55-61.
[15]	屠恩美，杨杰. 半监督学习理论及其研究进展概述[J]. 上海交通大学学报（自然版）, 2018, 52(10): 1280-1291.