Advertisement

Rock Mechanics and Rock Engineering

, Volume 51, Issue 10, pp 3029–3043 | Cite as

A Real-Time Back-Analysis Technique to Infer Rheological Parameters from Field Monitoring

  • Chongchong QiEmail author
  • Andy Fourie
Original Paper

Abstract

The long-term stress analysis of engineering projects can be significantly expedited if we can determine an appropriate rheological model and its corresponding parameters. In the present contribution, we show that an accurate and real-time estimation of rheological parameters is possible by employing deep learning and metaheuristic algorithms. A real-time back-analysis technique was proposed using a deep long short-term memory neural network (DeepLSTM) as a substitute for numerical modelling and firefly algorithm (FA) to search for the optimum parameter. The performance of the proposed technique, the DeepLSTM-FA, was verified using a tunnel response with the FLAC 2D finite difference program. Furthermore, the application of the DeepLSTM-FA to an engineering instance, namely, the Adriatic Motorway near Draga Valley, was discussed in detail, revealing that the DeepLSTM-FA can provide practitioners with an accurate and real-time estimation of rheological parameters, thereby allowing for timely stress and stability analyses. We found that an accurate estimation of rheological parameters can be made using the first few points of displacement data instead of the whole displacement profile. This technique extends recent efforts to determine rheological parameters in real time and significantly accelerates the application of stress and stability analyses in the future.

Keywords

Back-analysis Rheological parameters Deep long short-term memory Firefly algorithm 

List of symbols

DeepLSTM

Deep long short-term memory neural network

FA

Firefly algorithm

AI

Artificial intelligence

CVISC

Burger-creep visco-plastic model

FNN

Feed-forward neural network

RNN

Recurrent neural network

MSE

Mean squared error

APE

Absolute percentage error

l

Neural layer

a

Activation value for the neurons

W

Weight matrix

b

Bias

\(\sigma\)

Activation function

h

Hidden sequence values

t

Time

i, f, and o

Input, forget, and output gates

c

Cell activation

\({x_i}\) and \({x_j}\)

Fireflies i and j

\({r_{ij}}\)

Mutual distance between \({x_i}\) and \({x_j}\)

\(\beta\)

Attractiveness at \({r_{ij}}=0\)

\(\gamma\)

Light absorption coefficient

\({\alpha _t}\)

Step size parameter

\({\epsilon _t}\)

Random number

\({\overline {Y} _i}\) and \({Y_i}\)

Predicted and field responses

\({\sigma _x}\) and \({\sigma _x}\)

In situ horizontal and vertical stresses

\({\gamma _r}\)

Unit weight

\({c_{\text{r}}}\)

Cohesion

\(\phi\)

Internal friction angle

\({\sigma _t}\)

Tensile strength

\(\Phi\)

Dilation angle

\(K\)

Bulk modulus

\({G^{\text{M}}}\)

Maxwell shear modulus

\({G^{\text{K}}}\)

Kelvin shear modulus

\({\eta ^{\text{M}}}\)

Maxwell viscosity

\({\eta ^{\text{K}}}\)

Kelvin viscosity

Notes

Acknowledgements

The first author was supported by the China Scholarship Council under Grant number: 201606420046.

Compliance with ethical standards

Conflict of interest

The authors declare that they have no conflict of interest.

References

  1. Amiri B, Hossain L, Crawford JW, Wigand RT (2013) Community detection in complex networks: multi-objective enhanced firefly algorithm. Knowl Based Syst 46:1–11CrossRefGoogle Scholar
  2. Apuani T, Masetti M, Rossi M (2007) Stress–strain–time numerical modelling of a deep-seated gravitational slope deformation: preliminary results. Quater Int 171–172:80–89.  https://doi.org/10.1016/j.quaint.2007.01.014 CrossRefGoogle Scholar
  3. Arbanas Ž, Benac Č, Andrić M, Jardas B (1994) Geotechnical properties of flysch on the Adriatic Motorway from Orehovica to St. Kuzam. In: Proceedings symposium geotechnical engineering in transportation projects, Croatian Geotechnical Society, Novigrad, October, pp 5–8Google Scholar
  4. Arbanas Ž, Grošić M, Dugonjić S (2008) Behaviour of the reinforced cuts in flysch rock mass. In: Proceedings of the 1st international conference on transportation geotechnics, Nottingham, UK, pp 283–291Google Scholar
  5. Asadollahpour E, Rahmannejad R, Asghari A, Abdollahipour A (2014) Back analysis of closure parameters of Panet equation and Burger׳s model of Babolak water tunnel conveyance. Int J Rock Mech Mining Sci 68:159–166CrossRefGoogle Scholar
  6. Barla G, Bonini M, Debernardi D (2008) Time dependent deformations in squeezing tunnels. In: Proceedings of the 12th IACMAG International conference on computer methods and advances in geomechanics, Goa, IndiaGoogle Scholar
  7. Boidy E, Bouvard A, Pellet F (2002) Back analysis of time-dependent behaviour of a test gallery in claystone. Tunnell Undergr Space Technol 17:415–424CrossRefGoogle Scholar
  8. Brady BH, Brown ET (2013) Rock mechanics: for underground mining. Springer Science & Business MediaGoogle Scholar
  9. Cai M, Morioka H, Kaiser PK, Tasaka Y, Kurose H, Minami M, Maejima T (2007) Back-analysis of rock mass strength parameters using AE monitoring data. Int J Rock Mech Mining Sci 44:538–549.  https://doi.org/10.1016/j.ijrmms.2006.09.012 CrossRefGoogle Scholar
  10. Chen B-R, Zhao X-J, Feng X-T, Zhao H-B, Wang S-Y (2014) Time-dependent damage constitutive model for the marble in the Jinping II hydropower station in China. Bull Eng Geol Environ 73:499–515CrossRefGoogle Scholar
  11. Espada M, Lamas L (2017) Back analysis procedure for identification of anisotropic elastic parameters of overcored rock specimens. Rock Mech Rock Eng 50:513–527CrossRefGoogle Scholar
  12. Feng XT, Zhao H, Li S (2004) A new displacement back analysis to identify mechanical geo-material parameters based on hybrid intelligent methodology. Int J Num Anal Meth Geomech 28:1141–1165CrossRefGoogle Scholar
  13. Fister I Jr, Yang IF, Brest XS J (2013) A comprehensive review of firefly algorithms. Swarm Evol Comput 13:34–46CrossRefGoogle Scholar
  14. Goodman RE (1989) Introduction to rock mechanics, vol 2. Wiley, New YorkGoogle Scholar
  15. Grošić M (2014) Time-dependent deformation of Flysch Rock Mass: Doctoral Thesis. M. GrošićGoogle Scholar
  16. Guan Z, Jiang Y, Tanabashi Y (2009) Rheological parameter estimation for the prediction of long-term deformations in conventional tunnelling. Tunnell Undergr Space Technol 24:250–259CrossRefGoogle Scholar
  17. Guan Z, Deng T, Huang H, Jiang Y (2013) Back analysis technique for mountain tunneling based on the complex variable solution. Int J Rock Mech Mining Sci 59:15–21CrossRefGoogle Scholar
  18. He J, Chen S-h, Shahrour I (2011) Back analysis of equivalent permeability tensor for fractured rock masses from packer tests. Rock Mech Rock Eng 44:491CrossRefGoogle Scholar
  19. Khaledi K, Mahmoudi E, Datcheva M, König D, Schanz T (2016) Sensitivity analysis and parameter identification of a time dependent constitutive model for rock salt. J Comput Appl Math 293:128–138.  https://doi.org/10.1016/j.cam.2015.03.049 CrossRefGoogle Scholar
  20. Lee H, Pham P, Largman Y, Ng AY (2009) Unsupervised feature learning for audio classification using convolutional deep belief networks. Adv Neural Inform Process Syst 1096–1104Google Scholar
  21. Manzanal D, Drempetic V, Haddad B, Pastor M, Stickle MM, Mira P (2016) Application of a new rheological model to rock avalanches: an SPH approach. Rock Mech Rock Eng 49:2353–2372CrossRefGoogle Scholar
  22. Miranda T, Dias D, Eclaircy-Caudron S, Correia AG, Costa L (2011) Back analysis of geomechanical parameters by optimisation of a 3D model of an underground structure. Tunnell Undergr Space Technol 26:659–673CrossRefGoogle Scholar
  23. Mo Y-b, Ma Y-z, Zheng Q-y (2013) Optimal choice of parameters for firefly algorithm. In: Conference on digital manufacturing and automation (ICDMA), 2013 fourth international, IEEE, pp 887–892Google Scholar
  24. Ordonez FJ, Roggen D (2016) Deep convolutional and lstm recurrent neural networks for multimodal wearable activity recognition. Sensors (Basel) 16:115.  https://doi.org/10.3390/s16010115 CrossRefGoogle Scholar
  25. Qi C, Tang X (2018) Slope stability prediction using integrated metaheuristic and machine learning approaches: a comparative study. Comput Indust Eng 118:112–122.  https://doi.org/10.1016/j.cie.2018.02.028 CrossRefGoogle Scholar
  26. Qi C, Fourie A, Chen Q (2018a) Neural network and particle swarm optimization for predicting the unconfined compressive strength of cemented paste backfill. Constr Build Mater 159:473–478.  https://doi.org/10.1016/j.conbuildmat.2017.11.006 CrossRefGoogle Scholar
  27. Qi C, Fourie A, Chen Q, Zhang Q (2018b) A strength prediction model using artificial intelligence for recycling waste tailings as cemented paste backfill. J Cleaner Prod 183:566–578.  https://doi.org/10.1016/j.jclepro.2018.02.154 CrossRefGoogle Scholar
  28. Qi C, Fourie A, Du X, Tang X (2018c) Prediction of open stope hangingwall stability using random forests. Nat Hazards.  https://doi.org/10.1007/s11069-018-3246-7 CrossRefGoogle Scholar
  29. Qi C, Fourie A, Ma G, Tang X, Du X (2018d) Comparative study of hybrid artificial intelligence approaches for predicting hangingwall stability. J Comput Civil Eng 32:04017086.  https://doi.org/10.1061/(asce)cp.1943-5487.0000737 CrossRefGoogle Scholar
  30. Sharifzadeh M, Tarifard A, Moridi MA (2013) Time-dependent behavior of tunnel lining in weak rock mass based on displacement back analysis method. Tunnell Undergr Space Technol 38:348–356CrossRefGoogle Scholar
  31. Sulem J, Panet M, Guenot A (1987) Closure analysis in deep tunnels. Int J Rock Mech Mining Sci Geomech Abstr, Elsevier, pp 145–154Google Scholar
  32. Sundermeyer M, Ney H, Schlüter R (2015) From feedforward to recurrent LSTM neural networks for language modeling. IEEE/ACM Trans Audio Speech Lang Process (TASLP) 23:517–529CrossRefGoogle Scholar
  33. Tian HM, Chen WZ, Yang DS, Gong Z (2015) Experimental and numerical analysis of the time-dependent behaviour of argillaceous red sandstone under high in situ stress. Bull Eng Geol Environ 74:567–575CrossRefGoogle Scholar
  34. Tran-Manh H, Sulem J, Subrin D (2016) Progressive degradation of rock properties and time-dependent behavior of deep tunnels. Acta Geotech 11:693–711CrossRefGoogle Scholar
  35. Vardakos S, Gutierrez M, Xia C (2016) Back-analysis of tunnel response from field monitoring using simulated annealing. Rock Mech Rock Eng 49:4833–4852CrossRefGoogle Scholar
  36. Yang X-S (2010) Nature-inspired metaheuristic algorithms. Luniver press, FromeGoogle Scholar
  37. Yang Z, Wang Z, Zhang L, Zhou R, Xing N (2001) Back-analysis of viscoelastic displacements in a soft rock road tunnel. Int J Rock Mech Mining Sci 38:331–341CrossRefGoogle Scholar
  38. Yang F, Zhang C, Zhou H, Liu N, Zhang Y, Azhar MU, Dai F (2017) The long-term safety of a deeply buried soft rock tunnel lining under inside-to-outside seepage conditions. Tunnell Undergr Space Technol 67:132–146CrossRefGoogle Scholar
  39. Yu Y, Zhang B, Yuan H (2007) An intelligent displacement back-analysis method for earth-rockfill dams. Comput Geotech 34:423–434CrossRefGoogle Scholar
  40. Zeyer A, Doetsch P, Voigtlaender P, Schlüter R, Ney H (2017) A comprehensive study of deep bidirectional LSTM RNNs for acoustic modeling in speech recognition. In: Conference on acoustics, speech and signal processing (ICASSP), 2017 IEEE international, IEEE, pp 2462–2466Google Scholar
  41. Zhang Y, Mitri HS (2008) Elastoplastic stability analysis of mine haulage drift in the vicinity of mined stopes. Int J Rock Mech Mining Sci 45:574–593.  https://doi.org/10.1016/j.ijrmms.2007.07.020 CrossRefGoogle Scholar
  42. Zhang L, Yue Z, Yang Z, Qi J, Liu F (2006) A displacement-based back-analysis method for rock mass modulus and horizontal in situ stress in tunneling–Illustrated with a case study. Tunnell Undergr Space Technol 21:636–649CrossRefGoogle Scholar

Copyright information

© Springer-Verlag GmbH Austria, part of Springer Nature 2018

Authors and Affiliations

  1. 1.School of Civil, Environmental and Mining EngineeringUniversity of Western AustraliaPerthAustralia

Personalised recommendations