Advance Rate Prediction by Recurrent Neural Networks Analysis on In-situ Data of Tunnel Boring Machines
-
摘要: 本文基于工程实测数据, 在分析其序列性质的基础上, 提出了基于时序神经网络方法的盾构掘进速率预测方法, 并在天津地铁9号线这一实际工程算例中对所提出的方法的有效性进行验证, 讨论比较了Simple RNN、LSTM与GRU这3种不同时序神经网络算法的掘进速率预测表现。结果表明, 本文提出的基于时序神经网络的盾构掘进速率预测方法能够较好地分析掘进中积累的工程实测数据中的序列性质, 从而对前方掘进速率进行预测, 且比具有"门"性质的LSTM与GRU方法表现出了更好的预测效果。Abstract: Based on the in-situ data and the analysis of its time series properties, this paper proposes a prediction method of advance rate based on the Recurrent Neural Network(RNN) method, and verifies the effectiveness of the proposed method in the practical engineering example of Tianjin Metro Line 9. The prediction performances of other methods, such as Simple RNN, Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) are discussed and compared. The results show that the prediction method of TBM's advance rate based on RNN proposed in this paper can better analyze the sequence properties of the accumulated engineering measured data in tunneling, so as to predict the tunneling rate ahead, and show better prediction performance than the LSTM and GRU methods with ″gate″ properties.
-
Key words:
- tunnel boring machine /
- advance rate prediction /
- time series /
- neural networks /
- in-situ data
-
表 1 天津地铁9号线所用标段参量部分统计性质
参数名及单位 最大值 最小值 均值 标准差 掘进速率/(mm·min-1) 55.68 16.84 35.23 10.04 总推力/kN 24 701.68 10 436.07 15 840.43 2 905.33 刀盘扭矩/(kN·m) 1 706.28 803.08 1 264.49 148.71 刀盘转速/(r·min-1) 1.10 0.40 0.94 0.14 泊松比/kPa 7.89 4.70 6.57 0.01 容重/(g·cm-3) 0.31 0.23 0.29 0.52 粘聚力/kPa 2.23 1.60 2.10 0.06 静止土压力系数 32.93 19.84 28.03 2.10 内摩擦角/(°) 0.45 0.31 0.40 0.03 
下载: 导出CSV
-
[1] BARLA G, PELIZZA S. TBM tunnelling in difficult ground conditions[C]//Paper Presented at the ISRM International Symposium. Melbourne, Australia: ISRM, 2000 [2] ARMAGHANI D J, KOOPIALIPOOR M, MARTO A, et al. Application of several optimization techniques for estimating TBM advance rate in granitic rocks[J]. Journal of Rock Mechanics and Geotechnical Engineering, 2019, 11(4): 779-789 doi: 10.1016/j.jrmge.2019.01.002 [3] ENTACHER M, WINTER G, GALLER R. Cutter force measurement on tunnel boring machines-Implementation at Koralm tunnel[J]. Tunnelling and Underground Space Technology, 2013, 38: 487-496 doi: 10.1016/j.tust.2013.08.010 [4] LIU B, GUO Q, LIU Z Y, et al. Comprehensive ahead prospecting for hard rock TBM tunneling in complex limestone geology: a case study in Jilin, China[J]. Tunnelling and Underground Space Technology, 2019, 93: 103045 doi: 10.1016/j.tust.2019.103045 [5] LAN H, XIA Y M, ZHU Z M, et al. Development of on-line rotational speed monitor system of TBM disc cutter[J]. Tunnelling and Underground Space Technology, 2016, 57: 66-75 doi: 10.1016/j.tust.2016.02.023 [6] TANG B, CHENG H, TANG Y Z, et al. Experiences of gripper TBM application in shaft coal mine: a case study in Zhangji coal mine, China[J]. Tunnelling and Underground Space Technology, 2018, 81: 660-668 doi: 10.1016/j.tust.2018.08.055 [7] FROUGH O, TORABI S R, TAJIK M. Evaluation of TBM utilization using rock mass rating system: a case study of Karaj-Tehran water conveyance tunnel (Lots 1 and 2)[J]. Journal of Mining and Environment, 2012, 3(2): 89-98 http://jme.shahroodut.ac.ir/article_86_11.html [8] AVUNDUK E, COPUR H. Empirical modeling for predicting excavation performance of EPB TBM based on soil properties[J]. Tunnelling and Underground Space Technology, 2018, 71: 340-353 doi: 10.1016/j.tust.2017.09.016 [9] MACIAS F J, JAKOBSEN P D, SEO Y, et al. Influence of rock mass fracturing on the net penetration rates of hard rock TBMs[J]. Tunnelling and Underground Space Technology, 2014, 44: 108-120 doi: 10.1016/j.tust.2014.07.009 [10] BOUAYAD D, EMERIAULT F. 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 [11] MAHDEVARI S, TORABI S R, MONJEZI M. Application of artificial intelligence algorithms in predicting tunnel convergence to avoid TBM jamming phenomenon[J]. International Journal of Rock Mechanics and Mining Sciences, 2012, 55: 33-44 doi: 10.1016/j.ijrmms.2012.06.005 [12] HYUN K C, MIN S, CHOI H, et al. Risk analysis using fault-tree analysis (FTA) and analytic hierarchy process (AHP) applicable to shield TBM tunnels[J]. Tunnelling and Underground Space Technology, 2015, 49: 121-129 doi: 10.1016/j.tust.2015.04.007 [13] SALIMI A, ROSTAMI J, MOORMANN C, et al. Application of non-linear regression analysis and artificial intelligence algorithms for performance prediction of hard rock TBMs[J]. Tunnelling and Underground Space Technology, 2016, 58: 236-246 doi: 10.1016/j.tust.2016.05.009 [14] SUN W, SHI M L, ZHANG C, et al. Dynamic load prediction of tunnel boring machine (TBM) based on heterogeneous in-situ data[J]. Automation in Construction, 2018, 92: 23-34 doi: 10.1016/j.autcon.2018.03.030 [15] SALIMI A, FARADONBEH R S, MONJEZI M, et al. TBM performance estimation using a classification and regression tree (CART) technique[J]. Bulletin of Engineering Geology and the Environment, 2018, 77(1): 429-440 doi: 10.1007/s10064-016-0969-0 [16] MAHDEVARI S, SHAHRIAR K, YAGIZ S, et al. A support vector regression model for predicting tunnel boring machine penetration rates[J]. International Journal of Rock Mechanics and Mining Sciences, 2014, 72: 214-229 doi: 10.1016/j.ijrmms.2014.09.012 [17] JAVAD G, NARGES T. Application of artificial neural networks to the prediction of tunnel boring machine penetration rate[J]. Mining Science and Technology (China), 2010, 20(5): 727-733 doi: 10.1016/S1674-5264(09)60271-4 [18] ADOKO A C, GOKCEOGLU C, YAGIZ S. Bayesian prediction of TBM penetration rate in rock mass[J]. Engineering Geology, 2017, 226: 245-256 doi: 10.1016/j.enggeo.2017.06.014 [19] SEKER S E, OCAK I. Performance prediction of roadheaders using ensemble machine learning techniques[J]. Neural Computing and Applications, 2019, 31(4): 1103-1116 doi: 10.1007/s00521-017-3141-2 [20] GAO X J, SHI M L, SONG X G, et al. Recurrent neural networks for real-time prediction of TBM operating parameters[J]. Automation in Construction, 2019, 98: 225-235 doi: 10.1016/j.autcon.2018.11.013 [21] FREITAG S, CAO B T, NINIĆ J, et al. Recurrent neural networks and proper orthogonal decomposition with interval data for real-time predictions of mechanised tunnelling processes[J]. Computers & Structures, 2018, 207: 258-273 http://www.sciencedirect.com/science/article/pii/S0045794917302195 [22] MISRA M, YUE H H, QIN S J, et al. Multivariate process monitoring and fault diagnosis by multi-scale PCA[J]. Computers & Chemical Engineering, 2002, 26(9): 1281-1293 http://www.sciencedirect.com/science/article/pii/S0098135402000935 [23] HOT A, KERSCHEN G, FOLTÊTE E, et al. Detection and quantification of non-linear structural behavior using principal component analysis[J]. Mechanical Systems and Signal Processing, 2012, 26: 104-116 doi: 10.1016/j.ymssp.2011.06.006 [24] SCHMIDHUBER J. Deep learning in neural networks: An overview[J]. Neural Networks, 2015, 61: 85-117 [25] DENG L, YU D. Deep learning: methods and applications[J]. Foundations and Trends in Signal Processing, 2014, 7(3-4): 197-387 doi: 10.1561/2000000039 [26] BENGIO Y, SIMARD P, FRASCONI P. Learning long-term dependencies with gradient descent is difficult[J]. IEEE Transactions on Neural Networks, 1994, 5(2): 157-166 doi: 10.1109/72.279181 [27] HOCHREITER S, SCHMIDHUBER J. Long short-term memory[J]. Neural Computation, 1997, 9(8): 1735-1780 doi: 10.1162/neco.1997.9.8.1735 [28] CHO K, VAN MERRIЁNBOER B, GULCEHRE C, et al. Learning phrase representations using RNN encoder-decoder for statistical machine translation[J]. arXiv preprint arXiv: 1406.1078, 2014 [29] TOKGÖZ N, SERKAN BINEN I, AVUNDUK E. An evaluation of fine grained sedimentary materials in terms of geotechnical parameters which define and control excavation performance of EPB TBM′s[J]. Tunnelling and Underground Space Technology, 2015, 47: 211-221 doi: 10.1016/j.tust.2014.12.007 [30] BERTHOZ N, BRANQUE D, WONG H, et al. TBM soft ground interaction: experimental study on a 1 g reduced-scale EPBS model[J]. Tunnelling and Underground Space Technology, 2018, 72: 189-209 http://www.sciencedirect.com/science/article/pii/S0886779816302309 -
点击查看大图
图(7) / 表(1)
计量
- 文章访问数: 97
- HTML全文浏览量: 49
- PDF下载量: 25
- 被引次数: 0
