(1. School of Civil Engineering，Wuhan University，Wuhan，Hubei 430072，China；2. Key Laboratory of Geotechnical and Structural Engineering Safety of Hubei Province，Wuhan University，Wuhan，Hubei 430072，China；3. State Key Laboratory of Geomechanics and Geotechnical Engineering，Institute of Rock and Soil Mechanics，Chinese Academy of Sciences，Wuhan，Hubei 430071，China)
Abstract：TBM method is a mechanized excavation process applied to roadway and tunnel construction. In order to realize the optimization of operating parameters by automatic execution of TBM in the process of stable tunneling，an autonomous decision-making model of TBM control parameters based on the transfer learning method is established. First，the core optimization strategy is proposed，which aims to improve the tunneling efficiency and reduce the energy consumption on the basis of fully reference to manual experience. Taking the penetration rate per revolution(PRev) and the cutterhead revolutions per minutes(RPM) as output parameters，the mathematical modeling is completed. Secondly，an optimization model is constructed. Deep artificial neural networks is used as the basic architecture，including two auxiliary networks in the source domain and one main network in the target domain，which respectively performs the regression of control parameters，the prediction of rock breaking specific energy，and the optimization of control parameters. The methods of transfer learning and frozen-layers are adopted to achieve the unification of the source and target domain. Third，key hyperparameters are identified. The optimal hyperparameters of auxiliary networks are determined by a combination of orthogonal experiments and Bayesian optimization. The key weights of the objective function of the main network in the target domain are determined based on analytic hierarchy process. Finally，relying on the TBM construction data set(4 459 effective data) collected from the transferring water project from Songhua River in Jilin，the established model is trained and tested. The results show that in stable phase，the heading efficiency is increased by 15.55% on average，the energy consumption is decreased by 7.13% on average，and the variance is reduced，which improves the overall stability. The research results can provide technical support for the establishment of TBM intelligent control system.
高 峰1，2，黄 兴3，刘泉声1，2，殷 欣1，2，伯 音1，2，王心语1，2. 基于人工神经网络多模型迁移学习的隧(巷)道机械化掘进装备控制参数自主决策方法[J]. 岩石力学与工程学报, 2023, 42(6): 1405-1420.
GAO Feng1，2，HUANG Xing3，LIU Quansheng1，2，YIN Xin1，2，BO Yin1，2，WANG Xinyu1，2. An autonomous decision-making method for mechanized tunneling equipment control parameters based on transfer learning of multiple ANN models#br#. , 2023, 42(6): 1405-1420.
[1] 刘泉声，刘 鹤，张鹏林，等. TBM卡机实时监测预警方法及其应用[J]. 岩石力学与工程学报，2019，38(增2)：3 354–3 361.(LIU Quansheng，LIU He，ZHANG Penglin，et al. Real-time monitoring and early warning approach of TBM jamming and its application[J]. Chinese Journal of Rock Mechanics and Engineering，2019，38(Supp.2)：3 354–3 361.(in Chinese))
[2] LIU Q S，WANG X Y，HUANG X，et al. Prediction model of rock mass class using classification and regression tree integrated AdaBoost algorithm based on TBM driving data[J]. Tunnelling and Underground Space Technology，2020，106：103595.
[3] HUANG X，ZHANG Q T，LIU Q S，et al. A real-time prediction method for TBM cutter-head torque using bidirectional long short-term memory networks optimized by multi-optimization algorithms[J]. Journal of Rock Mechanics and Geotechnical Engineering，2022，14(3)：798–812.
[4] ZHANG W，WU C，ZHONG H，et al. Prediction of undrained shear strength using extreme gradient boosting and random forest based on Bayesian optimization[J]. Geoscience Frontiers，2021，12(1)：469–477.
[5] 黄 兴，刘泉声，彭星新，等. 引大济湟工程TBM挤压大变形卡机计算分析与综合防控[J]. 岩土力学，2017，38(10)：2 962–2 972. (HUANG Xin，LIU Quansheng，PENG Xingxin，et al. Analysis and comprehensive prevention-control for TBM jamming induced bysqueezing deformation of surrounding rock around water diversion tunnel from Datong river into Huangshui river[J]. Rock and Soil Mechanics，2017，38(10)：2 962–2 972.(in Chinese))
[6] GONG Q M，ZHOU X X，LIU Y Q，et al. Development of a real-time muck analysis system for assistant intelligence TBM tunnelling[J]. Tunnelling and Underground Space Technology，2021，107：103655.1–103655.14.
[7] LIU B，WANG R，ZHAO G，et al. Prediction of rock mass parameters in the TBM tunnel based on BP neural network integrated simulated annealing algorithm[J]. Tunnelling and Underground Space Technology，2020，95：103103.1–103103.12.
[8] KOOPIALIPOOR M，NIKOUEI S S，MARTO A，et al. Predicting tunnel boring machine performance through a new model based on the group method of data handling[J]. Bulletin of Engineering Geology and the Environment，2019，78(5)：3 799–3 813.
[9] SYLVANUS S N，PROSPER E A A，JESSICA W A A，et al. Towards TBM automation：on-the-fly characterization and classification of ground conditions ahead of a TBM using data-driven approach[J]. Applied Sciences，2021，11(3)：10.3390.
[10] 温 森，赵延喜，杨圣奇. 基于Monte Carlo-BP神经网络TBM掘进速度预测[J]. 岩土力学，2009，30(10)：3 127–3 132.(WEN Sen，ZHAO Yanxi，YANG Shengqi. Prediction on penetration rate of TBM based on Monte Carlo-BP neural network[J]. Rock and Soil Mechanics，2009，30(10)：3 127–3 132.(in Chinese))
[11] 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.
[12] LI J H，LI P X，GUO D，et al. Advanced prediction of tunnel boring machine performance based on big data[J]. Geoscience Frontiers，2021，12(1)：331–338.
[13] ZHOU J，BEJARBANEH B Y，ARMAGHANI D J，et al. Forecasting of TBM advance rate in hard rock condition based on artificial neural network and genetic programming techniques[J]. Bulletin of Engineering Geology and the Environment，2019，79(2)：2 069–2 084.
[14] YIN X，LIU Q S，PAN Y C，et al. Strength of stacking technique of ensemble learning in rockburst prediction with imbalanced data： comparison of eight single and ensemble models[J]. Natural Resources Research，2021，30(2)：1 795–1 815.
[15] DARIO J，ANTHONY L，IVAN S，et al. Transfer learning：improving neural network based prediction of earthquake ground shaking for an area with insufficient training data[J]. Geophysical Journal International，2022，229(1)：704–718.
[16] MEI S. Multi-kernel transfer learning based on Chou's PseAAC formulation for protein submitochondria localization[J]. Journal of Theoretical Biology，2013，338(2)：112–112.
[17] 庄福振，罗 平，何 清，等. 迁移学习研究进展[J]. 软件学报，2015，26(1)：26–39.(ZHUANG Fushen，LUO Ping，HE Qing，et al. Survey on transfer learning research[J]. Journal of Software，2015，26(1)：26–39.(in Chinese))
[18] XUE Y D，JIA F，CAI X Y，et al. An optimization strategy to improve the deep learning-based recognition model of leakage in shield tunnels[J]. Computer-Aided Civil and Infrastructure Engineering，2022，37(3)：386–402.
[19] KALFARISI R，WU Z Y，SOH K. Crack detection and segmentation using deep learning with 3D reality mesh model for quantitative assessment and integrated visualization[J]. Journal of Computing in Civil Engineering，2020，34(3)：04020010.
[20] SCHMIDHUBER J. Deep learning in neural networks[J]. Neural Networks，2015，61：85–117.
[21] KINGMA D P，BA J. Adam：a method for stochastic optimization[J]. Computer Science，2014，1：CoRR abs/1412.6980.
[22] 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)：1 648–1 657.(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)：1 648–1 657.(in Chinese))
[23] 朱梦琦，朱合华，王 昕，等. 基于集成CART算法的TBM掘进参数与围岩等级预测[J]. 岩石力学与工程学报，2020，39(9)：1 860–1 871.(ZHU Mengqi，ZHU Hehua，WANG Xin，et al. Study on CART-based ensemble learning algorithms for predicting TBM tunneling parameters and classing surrounding rockmasses[J]. Chinese Journal of Rock Mechanics and Engineering，2020，39(9)：1 860– 1 871.(in Chinese))
[24] 赵光祖，王亚旭，李 尧，等. 基于优化BP神经网络的TBM性能预测[J]. 河南理工大学学报：自然科学版，2020，39(5)：139–145.(ZHAO Guangzu，WANG Yaxu，LI Yao，et al. Prediction of TBM performance based on optimized BP neural network[J]. Journal of Henan Polytechnic University：Natural Science，2020，39(5)：139–145. (in Chinese))
[25] 李 港，李晓军，杨文翔，等. 基于深度学习的TBM掘进参数预测研究[J]. 现代隧道技术，2020，57(5)：154–159.(LI Gang，LI Xiaojun，YANG Wenxiang，et al. Research on prediction of TBM driving parameters based on deep learning[J]. Modern Tunnelling Technology，2020，57(5)：154–159.(in Chinese))
[26] 仉文岗，唐理斌，陈福勇，等. 基于4种超参数优化算法及随机森林模型预测TBM掘进速度[J]. 应用基础与工程科学学报，2021，29(5)：1 186–1 200.(ZHANG Wengang，TANG Libin，CHEN Fuyong，et al. Prediction for TBM penetration rate using four hyperparameter optimization methods and random forest model[J]. Journal of Basic Science and Engineering，2021，29(5)：1 186–1 200. (in Chinese))
[27] ZhOU J，QIU Y，ZHU S，et al. Estimating TBM advance rate in hard rock condition using XGBoost and Bayesian optimization[J]. Underground Space，2020，6(5)：506–515.
[28] 宋战平，郭德赛，徐 甜，等. 基于非线性模糊层次分析法的TBM施工风险评价模型研究[J]. 岩土力学，2021，42(5)：1 424–1 433. (SONG Zhanping，GUO Desai，XU Tian，et al. Risk assessment model in TBM construction based on nonlinear fuzzy analytic hierarchy process[J]. Rock and Soil Mechanics，2021，42(5)：1 424–1 433.(in Chinese))
[29] 司景钊，王唤龙，曹贵才，等. 高黎贡山隧道TBM掘进卡机段TSP法物性参数响应特征分析[J]. 隧道建设，2021，41(3)：396–401.(SI Jingzhao，WANG Huanlong，CAO Guicai，et al. Analysis of response characteristics of physical parameters of tunnel seismic prediction method in TBM-Jammed section of Gaoligongshan tunnel[J]. Tunnel Construction，2021，41(3)：396–401.(in Chinese))
[30] 詹金武，李 涛，李 超. 基于人工智能的TBM选型适应性评价决策支持系统[J]. 煤炭学报，2019，44(10)：3 258–3 271.(ZHAN Jinwu，LI Tao，LI Chao. Decision support system of adaptability evaluation for TBM selection based on artificial intelligence[J]. Journal of China Coal Society，2019，44(10)：3 258–3 271.(in Chinese))
[31] 齐 祥. 深部复合地层TBM选型与掘进适应性分析及评价软件开发[硕士学位论文][D]. 北京：北京交通大学，2017.(QI Xiang. Adaptability analysis and evaluation software development of TBM selection and tunneling in deep composite stratum[M. S. Thesis][D]. Beijing：Beijing Jiaotong University，2017.(in Chinese))
[32] 陈 川. 深埋复合地层TBM适应性评价指标体系及方法研究[硕士学位论文][D]. 北京：北京交通大学，2016.(CHEN Chuan. Study on evaluation index system and method for TBM adaptability in deep composite strata[M. S. Thesis][D]. Beijing：Beijing Jiaotong University，2016.(in Chinese))
[33] 陈 馈，孙振川，李 涛. TBM设计与施工[M]. 北京：人民交通出版社，2018：85–130.(CHEN Kui，SUN Zhenchuan，LI Tao. TBM design and construction[M]. Beijing：China Communications Press，2018：85–130.(in Chinese))
2023, Vol. 42 
