Geomechanics and Engineering

  • 제39권1호
  • /
  • Pages.27-41
  • /
  • 2024
  • /
  • 2005-307X(pISSN)
  • /
  • 2092-6219(eISSN)
테크노프레스 (Techno-Press)
권호 표지
DOI QR코드

DOI QR Code

Estimation of tunnel boring machine penetration rate: Application of long-short-term memory and meta-heuristic optimization algorithms

  • Mengran Xu (College of Civil Engineering and Architecture, Xinjiang University) ;
  • Arsalan Mahmoodzadeh (IRO, Civil Engineering Department, University of Halabja) ;
  • Abdelkader Mabrouk (Department of Civil Engineering, College of Engineering, Northern Border University) ;
  • Hawkar Hashim Ibrahim (Department of Civil Engineering, College of Engineering, Salahaddin University-Erbil) ;
  • Yasser Alashker (Department of Civil Engineering, College of Engineering, King Khalid University) ;
  • Adil Hussein Mohammed (Department of Communication and Computer Engineering, Faculty of Engineering, Cihan University)
  • 투고 : 2023.02.14
  • 심사 : 2024.08.27
  • 발행 : 2024.10.10
⟨ 이전 논문 다음 논문 ⟩

초록

Accurately estimating the performance of tunnel boring machines (TBMs) is crucial for mitigating the substantial financial risks and complexities associated with tunnel construction. Machine learning (ML) techniques have emerged as powerful tools for predicting non-linear time series data. In this research, six advanced meta-heuristic optimization algorithms based on long short-term memory (LSTM) networks were developed to predict TBM penetration rate (TBM-PR). The study utilized 1125 datasets, partitioned into 20% for testing, 70% for training, and 10% for validation, incorporating six key input parameters influencing TBM-PR. The performances of these LSTM-based models were rigorously compared using a suite of statistical evaluation metrics. The results underscored the profound impact of optimization algorithms on prediction accuracy. Among the models tested, the LSTM optimized by the particle swarm optimization (PSO) algorithm emerged as the most robust predictor of TBM-PR. Sensitivity analysis further revealed that the orientation of discontinuities, specifically the alpha angle (α), exerted the greatest influence on the model's predictions. This research is significant in that it addresses critical concerns of TBM manufacturers and operators, offering a reliable predictive tool adaptable to varying geological conditions.

키워드

과제정보

The authors extend their appreciation to the Deanship of Research and Graduate Studies at King Khalid University for funding this work through Large Research Project under grant number RGP.2/163/45. The authors extend their appreciation to the Deanship of Scientific Research at Northern Border University, Arar, KSA for funding this research work through the project number "NBU-FFR2024-2507-03".

참고문헌

  1. Aufa, B.Z., Suyanto, S. and Arifianto, A. (2020), "Hyperparameter Setting of LSTM-based Language Model using Grey Wolf Optimizer", Proceedings of the 2020 International Conference on Data Science and Its Applications (ICoDSA), 1-5. https://doi.org/10.1109/ICoDSA50139.2020.9213031.
  2. Atashpaz-Gargari, E. and Lucas, C. (2007), "Imperialist competitive algorithm: An algorithm for optimization inspired by imperialistic competition", Proceedings of the 2007 IEEE Congress on Evolutionary Computation, 2007. https://doi.org/10.1109/CEC.2007.4425083.
  3. Azhdari Tehrani, H., Ramezaninejad, S., Mardani, M., Shokouhi, S., Darnahal, M. and Hakamifard, A. (2022), "Hematologic malignancies and COVID-19 infection: a monocenter retrospective study", Health Sci. Rep., 5, e638. https://doi.org/10.1002/hsr2.638
  4. Carter, T.G. and Marinos, V. (2020), "Putting geological focus back into rock engineering design", Rock Mech. Rock Eng., 53, 4487-4508. https://doi.org/10.1007/s00603-020-02177-1.
  5. Eusuff, M., Lansey, K. and Pasha, F. (2006), "Shuffled frog-leaping algorithm: a memetic meta-heuristic for discrete optimization", Eng. Optim., 38, 129-154. https://doi.org/10.1080/03052150500384759.
  6. Frough, O., Torabi, S.R. and Yagiz, S. (2015), "Application of RMR for estimating rock-mass-related TBM utilization and performance parameters: A case study", Rock Mech. Rock Eng., 48, 1305-1312. https://doi.org/10.1007/s00603-014-0619-4.
  7. Fattahi, H. (2016), "Adaptive neuro fuzzy inference system based on fuzzy c-means clustering algorithm, a technique for estimation of TBM penetration rate", Int. J. Optim. Civil Eng., 6, 159-171. http://ijoce.iust.ac.ir/article-1-243-en.html.
  8. Flor, A., Sassi, F., La Morgia, M., Cernera, F., Amadini, F., Mei, A. and Danzi, A. (2023), "Artificial intelligence for tunnel boring machine penetration rate prediction", Tunn. Undergr. Sp. Tech., 140, 105249. https://doi.org/10.1016/j.tust.2023.105249.
  9. Ghorbani, E. and Yagiz, S. (2024), "Estimating the penetration rate of tunnel boring machines via gradient boosting algorithms", Eng. Appl. Artif. Intell., 136, 108985. https://doi.org/10.1016/j.engappai.2024.108985.
  10. Gokceoglu, C. (2022), "Assessment of rate of penetration of a tunnel boring machine in the longest railway tunnel of Turkey", SN Appl. Sci., 4(1), 19. https://doi.org/10.1007/s42452-021-04903-y.
  11. Gong, Q.M. and Zhao, J. (2009), "Development of a rock mass characteristics model for TBM penetration rate prediction", Int. J. Rock Mech. Min. Sci., 46, 8-18. https://doi.org/10.1016/j.ijrmms.2008.03.003.
  12. Gers, F.A., Schmidhuber, J. and Cummins, F. (2000), "Learning to Forget: Continual Prediction with LSTM", Neural Comput., 12, 2451-2471. https://doi.org/10.1162/089976600300015015.
  13. Hochreiter, S. and Schmidhuber, J. (1997), "Long short-term memory", Neural Comput., 9(8), 1735-1780. https://doi.org/10.1162/neco.1997.9.8.1735.
  14. Han, W., Jiang, Y., Zhang, X., Koga, D. and Gao, Y. (2021), "Quantitative assessment on the reinforcing behavior of the CFRP-PCM method on tunnel linings", Geomech. Eng., 25(2), 123-134. https://doi.org/10.12989/gae.2021.25.2.123.
  15. Hamidi, K.J., Shahriar, K., Rezai, B. and Bejari, H. (2010), "Application of fuzzy set theory to rock engineering classification systems: An illustration of the rock mass excavability index", Rock Mech. Rock Eng., 43, 335-350. https://doi.org/10.1007/s00603-009-0029-1.
  16. Hassanpour, J., Rostami, J. and Zhao, J. (2011), "A new hard rock TBM performance prediction model for project planning", Tunn. Undergr. Sp. Tech., 26, 595-603. https://doi.org/10.1016/j.tust.2011.04.004.
  17. Jing, L., Li, J., Zhang, N., Chen, S., Yang, C. and Cao, H. (2021), "A TBM advance rate prediction method considering the effects of operating factors", Tunn. Undergr. Sp. Tech., 107, 103620. https://doi.org/10.1016/j.tust.2020.103620.
  18. Kennedy, J. and Eberhart, R. (1995), "Particle swarm optimization," Proceedings of ICNN'95", Proceedings of the International Conference on Neural Networks, 4, 1942-1948. https://doi.org/10.1109/ICNN.1995.488968.
  19. Koopialipoor, M., Fahimifar, A., Ghaleini, E.N., Momenzadeh, M. and Jahed Armaghani, D. (2020), "Development of a new hybrid ANN for solving a geotechnical problem related to tunnel boring machine performance", Eng. with Comput., 36, 345-357. https://doi.org/10.1007/s00366-019-00701-8.
  20. Li, L., Liu, Z., Fang, X. and Qi, W. (2024), "Multi-step real-time prediction of hard-rock TBM penetration rate combining temporal convolutional network and squeeze-and-excitation block", Scientific Reports, 14(1), 14326. https://doi.org/10.1038/s41598-024-65351-3.
  21. Liu, Z., Wang, Y., Li, L., Fang, X. and Wang, J. (2022), "Realtime prediction of hard rock TBM advance rate using temporal convolutional network (TCN) with tunnel construction big data", Front. Struct. Civil Eng., 16(4), 401-413. https://doi.org/10.1007/s11709-022-0823-3.
  22. Liu, B., Wang, R., Guan, Z., Li, J., Xu, Z., Guo, X. and Wang, Y. (2019). "Improved support vector regression models for predicting rock mass parameters using tunnel boring machine driving data", Tunn. Undergr. Sp. Tech., 91, 102958. https://doi.org/10.1016/j.tust.2019.04.014.
  23. Li, J., Li, P., Guo, D., Li, X. and Chen, Z. (2021), "Advanced prediction of tunnel boring machine performance based on big data", Geosci. Front., 12, 331-338. https://doi.org/10.1016/j.gsf.2020.02.011.
  24. Lislerud, A. (1988), "Hard rock tunnel boring: Prognosis and costs", Tunn. Undergr. Sp. Tech., 3, 9-17. https://doi.org/10.1016/0886-7798(88)90029-6.
  25. Mahmoodzadeh, A., Taghizadeh, M., Mohammad, A.H., Ibrahim, H.H., Samadi, H., Mohammadi, M. and Rashidi, S. (2022a), "Tunnel wall convergence prediction using optimized LSTM deep neural network", Geomech. Eng., 31(6), 545-556. https://doi.org/10.12989/gae.2022.31.6.545.
  26. Mahmoodzadeh, A., Nejati, H. R., Mohammadi, M., Ibrahim, H.H., Mohammed, A.H. and Shima, R. (2022b), "Assessment of wall convergence for tunnels using machine learning techniques", Geomech. Eng., 31(3), 265-279. https://doi.org/10.12989/gae.2022.31.3.265.
  27. Mahmoodzadeh, A., Nejati, H.R., Mohammadi, M., Ibrahim. and Hama Ali, H.F. (2022c), "Several models for tunnel boring machine performance prediction based on machine learning", Geomech. Eng., 30(1), 75-91. https://doi.org/10.12989/gae.2022.30.1.075.
  28. Mirjalili, S., Mirjalili, S.M. and Lewis, A. (2014), "Grey wolf optimizer", Adv. Eng. Software, 69, 46-61. https://doi.org/10.1016/j.advengsoft.2013.12.007.
  29. Mahmoodzadeh, A., Mohammadi, M., Hashim Ibrahim, H., Nariman Abdulhamid, S., Farid Hama Ali, H., Mohammed Hasan, A., Khishe, M. and Mahmud, H. (2021), "Machine learning forecasting models of disc cutters life of tunnel boring machine", Automat. Constr., 128, 103779. https://doi.org/10.1016/j.autcon.2021.103779.
  30. Ozdemir, L. (1977), "Development of Theoretical Equations for Predicting Tunnel Borability", Ph.D. Thesis. T-1969, Colorado School of Mines, Golden, CO, USA. http://hdl.handle.net/11124/78500.
  31. Pan, Q., Chen, Z., Wu, Y., Dias, D. and Oreste, P. (2021), "Probabilistic tunnel face stability analysis: A comparison between LEM and LAM", Geomech. Eng., 24(4), 399-406. https://doi.org/10.12989/gae.2021.24.4.399.
  32. Rayatdust, H., Shahriar, K., Ahangari, K. and Kamali-Bandpey, H. (2012), "A statistical model for prediction TBM performance using rock mass characteristics in the TBM driven Alborz tunnel project", Am. J. Appl. Sci., 4, 5048-5054. https://www.researchgate.net/publication/236011428.
  33. Shan, F., He, X., Jahed Armaghani, D., Zhang, P. and Sheng, D. (2022), "Success and challenges in predicting TBM penetration rate using recurrent neural networks", Tunn. Undergr. Sp. Tech., 130, 104728. https://doi.org/10.1016/j.tust.2022.104728.
  34. Salimi, A., Rostami, J., Moormann, C. and Delisio, A. (2016), "Application of non-linear regression analysis and artificial intelligence algorithms for performance prediction of hard rock TBMs", Tunn. Undergr. Sp. Tech., 58, 236-246. https://doi.org/10.1016/j.tust.2016.05.009.
  35. Torabi, S.R., Shirazi, H., Hajali, H. and Monjezi, M. (2013), "Study of the influence of geotechnical parameters on the TBM performance in Tehran-Shomal highway project using ANN and SPSS", Arabian J. Geosci., 6(4), 1215-1227. https://doi.org/10.1007/s12517-011-0415-3.
  36. Yalei, Y., Lijie, D., Rong, T., Fei, W. and Huilan, Z. (2024), "Prediction of TBM penetration rate for different surrounding rocks and cutter head diameters", Heliyon, 10(12), e33174. https://doi.org/10.1016/j.heliyon.2024.e33174.
  37. Yagiz, S. and Karahan, H. (2015), "Application of various optimization techniques and comparison of their performances for predicting TBM penetration rate in rock mass", Int. J. Rock Mech. Min. Sci., 80, 308-315. https://doi.org/10.1016/j.ijrmms.2015.09.019.
  38. Yagiz, S. (2008), "Utilizing rock mass properties for predicting TBM performance in hard rock conditions", Tunn. Undergr. Sp. Tech., 23, 326-339. https://doi.org/10.1016/j.tust.2007.04.011.
  39. Yagiz, S., Gokceoglu, C., Sezer, E. and Iplikci, S. (2009), "Application of two non-linear prediction tools to the estimation of tunnel boring machine performance", Eng. Appl. Artif. Intell., 22, 808-814. https://doi.org/10.1016/j.engappai.2009.03.007.
  40. Yagiz, S. and Karahan, H. (2011), "Prediction of hard rock TBM penetration rate using particle swarm optimization", Int. J. Rock Mech. Min. Sci., 48, 427-433. https://doi.org/10.1016/j.ijrmms.2011.02.013.
  41. Zhou, J., Qiu, Y., Jahed Armaghani, D., Zhang, W., Li, C., Zhu, S. and Tarinejad, R. (2021), "Predicting TBM penetration rate in hard rock condition: A comparative study among six XGB-based metaheuristic techniques", Geosci. Front., 12, 101091. https://doi.org/10.1016/j.gsf.2020.09.020.