Prediction of rock mass parameters in the TBM tunnel based on BP neural network integrated simulated annealing algorithm

被引:142
作者
Liu, B. [1 ,2 ]
Wang, R. [1 ,2 ]
Zhao, G. [1 ,2 ]
Guo, X. [1 ]
Wang, Y. [1 ,2 ]
Li, J. [3 ]
Wang, S. [1 ]
机构
[1] Shandong Univ, Geotech & Struct Engn Res Ctr, Jinan, Shandong, Peoples R China
[2] Shandong Univ, Sch Qilu Transportat, Jinan, Shandong, Peoples R China
[3] China Railway Engn Equipment Grp, Zhengzhou, Henan, Peoples R China
基金
中国国家自然科学基金;
关键词
Simulated annealing; BP neural network; TBM; PENETRATION RATE; PERFORMANCE; OPTIMIZATION; MODEL; SYSTEM;
D O I
10.1016/j.tust.2019.103103
中图分类号
TU [建筑科学];
学科分类号
0813 ;
摘要
The prediction of rock mass parameters is of great significance in ensuring the safety and efficiency of tunnel boring machine (TBM) tunnel construction. Previous studies have confirmed the existence of a relationship between TBM driving parameters and rock mass parameters. In this work, we attempt to utilize the TBM driving parameters to predict rock mass parameters, including uniaxial compressive strength (UCS), brittleness index (Bi), distance between plane of weakness (DPW), and the orientation of discontinuities (alpha). We propose a hybrid algorithm (SA-BPNN) which integrates the back propagation neural network (BPNN) with simulated annealing (SA). A three-layer BPNN model was trained, using TBM driving and rock mass parameters from the Songhua River water conveyance project. We collected 320 samples, and randomly selected 280 of these to train the model, while the remaining 40 samples made up the first dataset to test the model. The predicted mean absolute percentage errors (MAPEs) of alpha, UCS, DPW, and Bi were 7.7%, 13.9%, 12.9%, and 11.0%, respectively, with the corresponding determination coefficient (R-2) of 0.845, 0.737, 0.731, and 0.657, respectively. Another 40 samples with different lithology were collected to verify the model. Although the prediction results were not as good as those from the first dataset, they were still acceptable. The results reveal that the SA-BPNN model has a relatively high accuracy. To verify the optimization effect of the SA method on the BPNN algorithm, a BPNN model was established and tested. The results of the SA-BPNN model were more accurate than those of the BPNN model.
引用
收藏
页数:12
相关论文
共 45 条
[1]  
[Anonymous], 1998, THESIS
[2]  
[Anonymous], P ANN TECHN M I SHAF
[3]   Prediction of pyrite oxidation in a coal washing waste pile using a hybrid method, coupling artificial neural networks and simulated annealing (ANN/SA) [J].
Bahrami, Saeed ;
Ardejani, Faramarz Doulati .
JOURNAL OF CLEANER PRODUCTION, 2016, 137 :1129-1137
[4]  
Barton N.R., 2000, TBM tunnelling in jointed and faulted rockM
[5]   Simultaneous Effects of Joint Spacing and Orientation on TBM Cutting Efficiency in Jointed Rock Masses [J].
Bejari, Hadi ;
Hamidi, Jafar Khademi .
ROCK MECHANICS AND ROCK ENGINEERING, 2013, 46 (04) :897-907
[6]   Modelling TBM performance with artificial neural networks [J].
Benardos, AG ;
Kaliampakos, DC .
TUNNELLING AND UNDERGROUND SPACE TECHNOLOGY, 2004, 19 (06) :597-605
[7]   Prediction of penetration per revolution in TBM tunneling as a function of intact rock and rock mass characteristics [J].
Benato, A. ;
Oreste, P. .
INTERNATIONAL JOURNAL OF ROCK MECHANICS AND MINING SCIENCES, 2015, 74 :119-127
[8]  
Bieniawski Z.T., 2006, TUNN UNDERGR SP TECH, V21, P237
[9]   Application of an optimized SA-ANN hybrid model for parametric modeling and optimization of LASOX cutting of mild steel [J].
Chaki S. ;
Ghosal S. .
Production Engineering, 2011, 5 (03) :251-262
[10]   Classification of overcurrent and inrush current for power system reliability using Slantlet transform and artificial neural network [J].
Chatterjee, Amitava ;
Maitra, Madhubanti ;
Goswami, Swapan Kumar .
EXPERT SYSTEMS WITH APPLICATIONS, 2009, 36 (02) :2391-2399