基于双路神经网络的TBM实时性能预测研究

doi:10.3901/JME.2024.16.043

机械工程学报 ›› 2024, Vol. 60 ›› Issue (16): 43-53.doi: 10.3901/JME.2024.16.043

扫码分享

基于双路神经网络的TBM实时性能预测研究

刘建琴^1,2, 胡桂菘¹, 乔金丽³, 郭晓¹

1. 天津大学机械工程学院天津 300072;
2. 天津大学机构理论与装备设计教育部重点实验室天津 300072;
3. 河北工业大学土木与交通学院天津 300401

收稿日期:2023-11-28 修回日期:2024-04-18 出版日期:2024-08-20 发布日期:2024-10-21
作者简介:刘建琴,女,1972年出生,博士,副教授。主要从事隧道掘进机器人设计,机构动力学及振动控制,数字化设计与制造方面的研究。E-mail:liujianqin@tju.edu.cn
乔金丽(通信作者),女,1978年出生,博士,副教授。主要从事地下结构,结构材料等方面的研究。E-mail:qiaojinli@hebut.edu.cn
基金资助:
国家自然科学基金资助项目(52075370)。

Research on Real-time Performance Prediction of TBM Based on Dual Neural Networks

LIU Jianqin^1,2, HU Guisong¹, QIAO Jinli³, GUO Xiao¹

1. College of Mechanical Engineering, Tianjin University, Tianjin 300072;
2. Key Laboratory of Mechanism Theory and Equipment Design of Ministry of Education, Tianjin University, Tianjin 300072;
3. School of Civil Engineering and Transportation, Hebei University of Technology, Tianjin 300401

Received:2023-11-28 Revised:2024-04-18 Online:2024-08-20 Published:2024-10-21

摘要/Abstract

摘要： 为了通过施工中易于获取的数据，实时预测岩石掘进机(Tunnel boring machine，TBM)性能从而为掘进参数的选择提供参考，依托广东某输水隧洞的地勘资料和掘进数据，分析主要掘进参数和场切深指数在不同类型围岩中的分布规律，在围岩类型由II类变为V类的过程中，刀盘扭矩、刀盘推力、贯入度等参数均存在着均值和标准差同时减小的趋势；除刀盘驱动系统外，支护系统和排渣系统中的参数的均值和标准差与场切深指数存在显著相关性。利用隐马尔可夫模型计算隧洞沿程各类围岩的概率分布，将其作为预测模型特征可提高预测精度但会增加过拟合风险。提出将掘进参数和围岩信息分别输入的双路神经网络模型，模型可对TBM施工前方一环的平均掘进性能进行预测，并将其与经典机器学习模型进行比较。结果表明，所提出的性能预测模型可以保证预测精度优于经典机器学习模型的同时拥有良好的泛化能力。

关键词: 岩石掘进机, 性能预测, 隐马尔可夫模型, 人工神经网络, 机器学习

Abstract: With the goal of predicting tunnel boring machine(TBM) performance in real time through data that is easy to obtain during construction, relying on the geological survey data and excavation data of a water conveyance tunnel in Guangdong, the distribution of the main boring parameters and field depth index in different types of surrounding rock is analyzed. The hidden Markov model (HMM) is used to calculate the probability distribution of various surrounding rocks along the tunnel, and using it as a prediction model feature can improve the prediction accuracy but increase the risk of overfitting. A two-way neural network model is proposed, which predicts the average advance performance of the first ring in TBM construction and compares it with classical machine learning models. The results show that the proposed performance prediction model can ensure that the prediction accuracy is better than that of the classical machine learning model and has good generalization ability.

Key words: TBM, performance prediction, hidden Markov model(HMM), artificial neural networks, machine learning

中图分类号:

U455

刘建琴, 胡桂菘, 乔金丽, 郭晓. 基于双路神经网络的TBM实时性能预测研究[J]. 机械工程学报, 2024, 60(16): 43-53.

LIU Jianqin, HU Guisong, QIAO Jinli, GUO Xiao. Research on Real-time Performance Prediction of TBM Based on Dual Neural Networks[J]. Journal of Mechanical Engineering, 2024, 60(16): 43-53.

参考文献

[1] WEI Jing,SUN Qinchao,SUN Wei,et al. Load-sharing characteristic of multiple pinions driving in tunneling boring machine[J]. Chinese Journal of Mechanical Engineering,2013,26(3):532-540.
[2] OZDEMIR L. Development of theoretical equation for predicting tunnel boreability[D]. Golden:Colorado School of Mines,1977.
[3] ROSTAMI J,OZDEMIR L. A new model for performance prediction of hard rock TBMs[C]//Proceedings of the Rapid Excavation and Tunneling Conference,June 13-17,1993,Colorado School of Mines,Golden. Boston:Society For Mining,Metallogy & Exploration,1993:793-793.
[4] YAGIZ S. A model for the prediction of tunnel boring machine performance[C]//Proceedings of the 10th IAEG Conference on Engineering Geology for Tomorrow's Cities,Substructures and Underground Space,Nottingham. UK:The Geological Society of London,2006:383.
[5] ARMAGHANI D J,YAGIZ S,MOHAMAD E T,et al. Prediction of TBM performance in fresh through weathered granite using empirical and statistical approaches[J]. Tunnelling and Underground Space Technology,2021,118:104183.1-104183.26.
[6] 王湘怡,周小雄,卢建炜,等. 基于机器学习的TBM隧道掘进岩爆预测[J]. 施工技术,2022,51(20):1-7. WANG Xiangyi,ZHOU Xiaoxiong,LU Jianwei,et al. Prediction of rock burst in tbm tunnel excavation based on machine learning[J]. Construction Technology,2022,51(20):1-7.
[7] ARMAGHANI D J,Mohamad E T,NARAYANASAMY M S,et al. Development of hybrid intelligent models for predicting TBM penetration rate in hard rock condition[J]. Tunnelling and Underground Space Technology,2017(63):29-43.
[8] CHEN Xu,LIU Xiaoli,WANG Enzhi,et al. Prediction of tunnel boring machine operating parameters using various machine learning algorithms[J]. Tunnelling and Underground Space Technology,2021,109:103699.
[9] JING Liujie,LI Jianbin,ZHANG Na,et al. A TBM advance rate prediction method considering the effects of operating factors[J]. Tunnelling and Underground Space Technology,2021,107:103620.
[10] 姜兴宇,高超,高伟贤,等. 基于库仑-莫尔准则的盘形滚刀破岩力预测研究[J]. 机械工程学报,2016,52(20):126-136. JIANG Xingyu,GAO Chao,GAO Weixian,et al. Prediction of rock breaking force of disc cutters based on coulomb moore criterion[J]. Journal of Mechanical Engineering,2016,52(20):126-136.
[11] 石茂林,孙伟,宋学官. 隧道掘进机大数据研究进展:数据挖掘助推隧道挖掘[J]. 机械工程学报,2021,57(22):344-358. SHI Maolin,SUN Wei,SONG Xueguan. Research progress on big data of tunnel boring machine:How data mining can help tunnel boring[J]. Journal of Mechanical Engineering,2021,57(22):344-358.
[12] 侯少康,刘耀儒,张凯. 基于IPSO-BP混合模型的TBM掘进参数预测[J]. 岩石力学与工程学报,2020,39(8):1649-1657. HOU Shaokang,LIU Yaoru,ZHANG Kai. Prediction of TBM tunnelling parameters based on IPSO-BP hybrid model[J]. Chinese Journal of Rock Mechanics and Engineering,2020,39(8):1649-1657.
[13] 景毅,王世称,苑清扬. 马尔科夫过程在地质学中的应用[M]. 北京:地质出版社,1986. JING Yi,WANG Shicheng,YUAN Qingyan. Application of the Markov process in geology[M]. Beijing:Geology Press,1986.
[14] SALVINDER S,SHAHRUM A,ABDULLAH N M N,et al. Markov chain modelling of reliability analysis and prediction under mixed mode loading[J]. Chinese Journal of Mechanical Engineering,2015,28(2):307-314.
[15] SALIMI A,ROSTAMI J,MOORNANM C. Application of rock mass classification systems for performance estimation of rock TBMs using regression tree and artificial intelligence algorithms[J]. Tunnelling and Underground Space Technology,2019(92):103046.

基于双路神经网络的TBM实时性能预测研究

Research on Real-time Performance Prediction of TBM Based on Dual Neural Networks

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	张赛凡, 李博, 轩福贞. 激光选区熔化过程声发射信号的降噪与分类预测方法[J]. 机械工程学报, 2024, 60(6): 163-176.
[2]	王丹丹, 黄伟迪, 张军辉, 赵守军, 于斌, 刘施镐, 吕飞, 苏琦, 徐兵. 基于边缘计算的轴向柱塞泵磨损状态辨识方法研究[J]. 机械工程学报, 2024, 60(4): 189-199.
[3]	黄浩, 单忠德, 张丽娇, 孙正, 郭子桐, 刘检华, 金鹏. 异形截面复合材料构件成形及力学性能预测方法研究[J]. 机械工程学报, 2024, 60(2): 107-118.
[4]	褚端峰, 刘鸿祥, 高博麟, 王金湘, 殷国栋. 车辆队列预测巡航控制研究综述[J]. 机械工程学报, 2024, 60(18): 218-246.
[5]	童哲铭, 马鑫航. 基于孪生支持向量回归的多级离心泵外特性曲线预测及设计方法[J]. 机械工程学报, 2024, 60(14): 364-377.
[6]	张照煌, 程克凤, 刘书兵. 全断面岩石掘进机三维破岩理论研究[J]. 机械工程学报, 2024, 60(11): 332-341.
[7]	何洪文, 王浩宇, 王勇, 李双歧. 基于实车运行数据的锂离子电池健康状态估计[J]. 机械工程学报, 2023, 59(22): 46-58.
[8]	张墅野, 段晓康, 罗克宇, 许孙武, 张志昊, 陈捷狮, 何鹏. 基于机器学习电子封装互连材料研究现状[J]. 机械工程学报, 2023, 59(22): 222-233.
[9]	任靖渊, 胡钊政, 陶倩文, 李娜, 万金杰. 基于强制闭环与隐马尔可夫模型序列匹配的多机器人协同建图[J]. 机械工程学报, 2023, 59(17): 44-55.
[10]	王栓程, 杨冰, 廖贞, 肖守讷, 康国政, 阳光武, 朱涛. 金属材料疲劳短裂纹萌生与扩展研究综述[J]. 机械工程学报, 2023, 59(16): 32-53.
[11]	吴跃忠, 张婷, 费铭昊, 吴登昊, 任芸. 基于QP改进模型的离心泵性能预测方法[J]. 机械工程学报, 2023, 59(13): 280-289.
[12]	华丰, 王亚森, 金骏阳, 袁烨. 一种数据隐私保护下多方无损线性模型学习方法[J]. 机械工程学报, 2023, 59(12): 17-27.
[13]	周子洪, 尤伟涛, 陆胤瑜, 郗宇凡, 王可幸, 王冠云, 孙凌云. 支持形态自定义和自感知的可变形界面设计方法[J]. 机械工程学报, 2023, 59(11): 84-93.
[14]	管寅昕, 杨吉祥, 丁汉. 考虑控制电信号中间量的机床运动控制误差数据驱动建模方法[J]. 机械工程学报, 2022, 58(23): 178-187.
[15]	詹梅, 董赟达, 翟卓蕾, 樊晓光, 石志鹏, 安强. 塑性成形快速数值仿真方法的研究进展[J]. 机械工程学报, 2022, 58(16): 2-20.