Stress Analysis of Segmental Tunnel Lining Using Artificial Neural Network

  • Armin Rastbood School of Mining Engineering, College of Engineering, University of Tehran, Tehran, Iran
  • Yaghoob Gholipour School of Civil Engineering, College of Engineering, University of Tehran, Tehran, Iran
  • Abbas Majdi School of Mining Engineering, College of Engineering, University of Tehran, Tehran, Iran

Abstract

The paper describes an artificial neural network method(ANNM) to predict the stresses executed on segmental tunnellining. An ANN using multi-layer perceptron (MLP) is developed.At first, database resulted from numerical analyses wasprepared. This includes; depth of cover (H), horizontal to verticalstress ratio (K), thickness of segment (t), Young modulus ofsegment (E) and key segment position in each ring (θ) on thetunnel perimeter as input variables. Different types of stressesand extreme values of displacement have been considered asoutput parameters. Sensitivity analysis showed that the coverof the tunnel and key position are the most and less effectiveinput variables on output parameters, respectively. Resultsfor coefficient of determination (R2), variance accounted for(VAF), coefficient of efficiency (CE) and root mean squarederror (RMSE) illustrates a high accuracy of the presented ANNmodel to predict the stress types and displacements of segmentaltunnel lining.

Keywords

artificial neural network, tunnel, segment, lining, yield criterion
Published in Onlinefirst
27-02-2017
How to Cite
RASTBOOD, Armin; GHOLIPOUR, Yaghoob; MAJDI, Abbas. Stress Analysis of Segmental Tunnel Lining Using Artificial Neural Network. Periodica Polytechnica Civil Engineering, [S.l.], v. 61, n. 4, p. 664-676, 2017. ISSN 1587-3773. Available at: <https://pp.bme.hu/ci/article/view/9700>. Date accessed: 23 nov. 2017. doi: https://doi.org/10.3311/PPci.9700.
Section
Research Article