Abstract
In order to deal with modeling problem of a pressure balance system with time-delay, nonlinear, time-varying and uncertain characteristics, an intelligent modeling procedure is proposed, which is based on artificial neural network (ANN) and input-output data of the system during shield tunneling and can overcome the precision problem in mechanistic modeling (MM) approach. The computational results show that the training algorithm with Gauss-Newton optimization has fast convergent speed. The experimental investigation indicates that, compared with mechanistic modeling approach, intelligent modeling procedure can obviously increase the precision in both soil pressure fitting and forecasting period. The effectiveness and accuracy of proposed intelligent modeling procedure are verified in laboratory tests.
Similar content being viewed by others
References
VINAI R, OGGERI C, PEILA D. Soil conditioning of sand for EPB applications: A laboratory research [J]. Tunnelling and Underground Space Technology, 2008, 23(3): 308–317.
DEVAU N, CADRE E L, HINSINGER P, GERARD F. A mechanistic model for understanding root-induced chemical changes controlling phosphorus availability [J]. Annals of Botany, 2010, 105(7): 1183–1197.
HONG Y S, ROSEN M R, REEVES R R, WANG L T. Dynamic fuzzy modeling of storm water infiltration in urban fractured aquifers [J]. Journal of Hydrologic Engineering, 2002, 7(5): 380–391.
SHI H, YANG H Y, GONG G F. Determination of the cutterhead torque for EPB shield tunneling machine [J]. Automation in Construction, 2011, 20(8): 1087–1095.
XU Q W, ZHU H H, DING W Q, GE X R. Laboratory model tests and field investigations of EPB shield machine tunneling in soft ground in Shanghai [J]. Tunnelling and Underground Space Technology, 2011, 26(1): 1–14.
YANG H Y, SHI H, GONG G F, HU G L. Electro-hydraulic proportional control of thrust system for shield tunneling machine [J]. Automation in Construction, 2009, 18(7): 950–956.
YEH I C. Application of neural networks to automatic soil pressure balance control for shield tunneling [J]. Automation in Construction, 1997, 5(5): 421–426.
PSICHOGIOS D C, UNGAR L H. A hybrid neural network-first principles approach to process modeling [J]. AIChE Journal, 1992, 38(10): 1499–1512.
KLEMENC J, WAGNER A, FAJDIGA M. Modeling the S-N curves of polyamide PA66 using a serial hybrid neural network [J]. Journal of Engineering Materials and Technology, 2011, 133(3): 1–14.
GUPTA S, LIU P H, SVORONOS S A, SHARMA R, ABDEL-KHALEK N A, CHENG Y, EL-SHALL H. Hybrid first-principles/ neural networks model for column flotation [J]. AIChE Journal, 1999, 45(3): 557–572.
SAFAVI A A, NOORAII A, ROMAGNOLI J A, HAN M. A hybrid model formulation for a distillation column and the online optimization study [J]. Journal of Process Control, 1999, 9(2): 125–134.
JEONG H, HWANG W, KIM E. Hybrid modeling approach to improve the forecasting capability for the gaseous radionuclide in a nuclear site [J]. Annals of Nuclear Energy, 2012, 42: 30–34.
FREIRE J R C S, NETO A D D, de AQUINO E M F. Comparative study between ANN models and equations in the conventional analysis of fatigue failure of GFRP [J]. Int J Fatigue, 2009, 31(5): 831–839.
VANEK M, HRNCIRIK P, VOVSK J, NAHLIK J. On-line estimation of biomass concentration using a neural network and information about metabolic state [J]. Bioprocess and Biosystems Engineering, 2004, 27(1): 9–15.
LEE D S, JEON C O, PARK J M, CHANG K S. Hybrid neural network modeling of a full-scale industrial wastewater treatment process [J]. Biotechnology and Bioengineering, 2002, 78(6): 670–682.
LEE D S, PARK J M. Neural network modeling for on-line estimation of nutrient dynamics in a sequentially-operated batch reactor [J]. Journal of Biotechnology, 1999, 75(2–3): 229–239.
DE AZEVEDO S F, DAHM B, OLIVEIRA F R. Hybrid modelling of biochemical processes: A comparison with the conventional approach [J]. Computers Chem Engng, 1997, 21: S751–S756.
LITH P F, BETLEM B H L, ROFFEL B. A structured modeling approach for dynamic hybrid fuzzy-first principles models [J]. Journal of Process Control, 2002, 12(5): 605–615.
SCHENK M, GANI R, BOGLE D, PISTIKOPOULOS E N. Pistikopoulos, a hybrid modelling approach for separation systems involving distillation [J]. Trans Chem Eng Res Des, 1999, 77(6): 519–535.
PSICHOGIOS D C, UNGAR L H. A hybrid neural network-first principles approach to process modeling [J]. AIChE Journal, 1992, 38(10): 1499–1511.
VERIKAS A, BACAUSKIENE M. Using artificial neural networks for process and system modeling [J]. Chemometrics and Intelligent Laboratory Systems, 2003, 67(2): 187–191.
GRIMA M A, BRUINES P A, VERHOEF P N W. Modeling tunnel boring machine performance by neuro-fuzzy methods [J]. Tunnelling and Underground Space Technology, 2000, 15(3): 259–269.
GAJEWSKI J, JONAK J. Towards the identification of worn picks on cutterdrums based on torque and power signals using artificial neural networks [J]. Tunnelling and Underground Space Technology, 2011, 26(1): 22–28.
WARNES M R, GLASSEY J, MONTAGUE G A, KARAB B. On data-based modelling techniques for fermentation processes [J]. Process Biochemistry, 1996, 31(2): 147–155.
ANAGNOSTOU G, KOVAR K. Face stability conditions with earth-pressure-balanced shields [J]. Tunnelling and Underground Space Technology, 1996, 11(2): 165–173.
KIM S H, TONON F. Face stability and required support pressure for TBM driven tunnels with ideal face membrane-drained case [J]. Tunnelling and Underground Space Technology, 2010, 25(5): 526–542.
LI S J, CAO L J, SHANGGUAN Z C, LIU B. Parameter identification and pressure control of dynamic system in shield tunneling using least squares method [J]. Journal of Coal Science & Engineering, 2010, 16(3): 256–261.
LI S J, LIU Y X. Identification of vibration loads on hydro generator by using hybrid genetic algorithm [J]. Acta Mechanica Sinica, 2006, 22(6): 603–610.
PALIWAL M, KUMAR U A. Neural networks and statistical techniques: A review of applications [J]. Expert Systems with Applications, 2009, 36(1): 2–17.
WAN W S, MABU S, SHIMADA K, HIRASAWA K, HU J L. Enhancing the generalization ability of neural networks through controlling the hidden layers [J]. Applied Soft Computing, 2009, 9(1): 404–414.
WU S T, CHOW T W S. Self-organizing and self-evolving neurons: A new neural network for optimization [J]. IEEE Transactions on Neural Networks, 2007, 18(2): 385–396.
PEILA D, OGGERI C, VINAI R. Screw conveyor device for laboratory tests on conditioned soil for EPB tunneling operations [J]. Journal of Geotechnical and Environmental Engineering, 2007, 133(12): 1622–1625.
MERRITT A S, MAIR R J. Mechanics of tunnelling machine screw conveyors: Model tests [J]. Geotechnique, 2006, 56(9): 605–615.
QUEBAUD S, SIBAI M, HENRY J P. Use of chemical foam for improvements in drilling by earth pressure balanced shields in granular soils [J]. Tunnelling and Underground Space Technology, 1998, 13(2): 173–180.
Author information
Authors and Affiliations
Corresponding author
Additional information
Foundation item: Project(2013CB035402) supported by the National Basic Research Program of China; Projects(51105048, 51209028) supported by the National Natural Science Foundation of China
Rights and permissions
About this article
Cite this article
Li, Sj., Yu, S. & Qu, Fz. Modeling approaches to pressure balance dynamic system in shield tunneling. J. Cent. South Univ. 21, 1206–1216 (2014). https://doi.org/10.1007/s11771-014-2055-8
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11771-014-2055-8