Published Papers

Volume 32 - Issue 1 (Regular Issue)
Transactions Papers

Unleashing the power of AI and measure-while-drilling for enhanced overbreak prediction of a cavern project

Simon C M Leung, Matthew M K Chan and Felix C S Yu
Pages: 1-13Published: 18 Dec 2025
DOI: https://doi.org/10.33430/V32N1THIE-2024-0009
Cite thisHide

Leung CM, Chan MK and Yu CS, Unleashing the power of AI and measure-while-drilling for enhanced overbreak prediction of a cavern project, HKIE Transactions, Vol. 32, No. 1 (Regular Issue), Article THIE-2024-0009.R2, 2025, https://doi.org/10.33430/V32N1THIE-2024-0009

 Copy

Abstract:

Drill-and-blast excavation is crucial for constructing underground spaces, and artificial neural network control has farreaching implications for the success of these projects regarding safety, time, cost and environmental aspects. Although this method has been widely adopted in Hong Kong since the first Lion Rock Tunnel in the 1960s, the research on artificial neural network prediction from local projects is very limited. Adequate attention and qualitative enhancement of artificial neural network control are lacking in Hong Kong. In addition, the traditional perspective suggests that predicting artificial neural network is challenging due to its strong correlation with irregular and random geological features, as well as the complex interactions between blasting parameters. Consequently, the control and prediction of real-world outcomes of artificial neural network through a theoretical approach may not be deemed practical or reliable. Our project team therefore took help from the international experience to tackle the issue and went a step further by integrating the drilling data recorded from Measure-While-Drilling into Artificial Intelligence to predict the artificial neural network. A total of 114 sets of input data were analysed by using an artificial neural network to predict artificial neural network, and a model with a high level of accuracy (R2=0.8234) was developed for the current project and also other projects in the future.

Keywords:

Drill-and-blast excavation, overbreak prediction, cavern project, geological and blasting factors, measure-while-drilling, artificial neural network

Reference List:

1. Jang, H. and Topal, E. (2013). Optimising overbreak prediction based on geological parameters comparing multiple regression analysis and artificial neural network. Tunnelling and Underground Space Technology, 38, pp. 161-169. Available from
doi:10.1016/j.tust.2013.06.003.
2. Ibarra, J.A., Maerz, N.H. and Franklin, J.A. (1996). Overbreak and underbreak in underground openings part 2: Causes and implications. Geotechnical and Geological Engineering, 14(4), pp. 325-340. Available from: doi:10.1007/bf00421947.
3. Innaurato, N., Mancini, R. and Cardu, M. (1998). On the influence of rock mass quality on the quality of blasting work in tunnel driving. Tunnelling and Underground Space Technology, 13(1), pp. 81-89. Available from doi:10.1016/s0886-7798(98)00027-3.
4. Murthy, V.M.S.R., Dey, K. and Raitani, R. (2003). Prediction of Overbreak in Underground Tunnel Blasting - A Case Study. Journal of Canadian Tunneling. 2003, pp. 109-115. Available at: https://api.semanticscholar.org/CorpusID:54225980. [Accessed on 14 June 2024]
5. Mahtab, M.A. et al. (1997). Assessment of geological overbreak for tunnel design and contractual claims. International Journal of Rock Mechanics and Mining Sciences, 34(3-4). Available from doi:10.1016/s1365-1609(97)00086-5.
6. Schmitz, Robrecht Maria; Viroux, Sébastien; Charlier, Robert; Hick, Servais (2006) The role of rock mechanics in analyzing overbreak: application to the Soumagne tunnel. Taylor & Francis.: Application to the Soumagne Tunnel”, EUROCK 2006 - Multiphysics Coupling and Long Term Behaviour in Rock Mechanics, Van Cotthem, Charlier, Thimus and Tshibangu Ed., Taylor and Francis Group, London, ISBN 9780415410014, 0415410010, pp. 631-636.
7. Verma, H.K. et al. (2016). Causes, impact and control of overbreak in underground excavations. Proceedings of the conference on Recent Advances in Rock Engineering (RARE 2016). Available from doi:10.2991/rare-16.2016.4.
8. Simon, Leung, Elton, M.Y.K. (2022). Active Site Supervision to Enhance Drilling & Blasting, in: The HKIE Geotechnical Division 42nd Annual Seminar (GDAS2022) [online]. Hong Kong: The Hong Kong Institution of Engineers, Available: https://books.aijr.org/index.php/press/catalog/book/133/chapter/1721. [Accessed on 14 June 2024]
9. S. Paul Singh (1993), Investigation of Blast Damage and Underground Stability in: 12th Conference on Ground Control in Mining [online], Morgantown, West Virginia: International Conference on Ground Control in Mining, pp. 366-372.
10. Nick Ryland Barton and Eystein Grimstad (2014). Q-System Application in NMT and NATM and the Consequences of Overbreak in: 7th International Symposium on Sprayed Concrete - Modern Use of Wet Mix Sprayed Concrete for Underground Support
[online]. Sandefjord: Proc. 7th Int. Conf. on Sprayed Concrete, Available: https://www.researchgate.net/publication/321938006_The_Qsystem_followingthirty_years_of_development_and_application_in_
tunneling_projects.[Accessed on 14 June 2024].
11. Mottahedi, A., Sereshki, F. and Ataei, M. (2017). Development of overbreak prediction models in drill and blast tunneling using soft computing methods. Engineering with Computers, 34(1), pp. 45-58. Available from doi:10.1007/s00366-017-0520-3.
12. Shaorui, S., Jiaming, L. and Jihong, W. (2013). Predictions of overbreak blocks in tunnels based on the wavelet neural network method and the geological statistics theory. Mathematical Problems in Engineering, 2013, pp. 1-9. Available from doi:10.1155/2013/706491.
13. Mohammadi, M. et al. (2015). Use of fuzzy set theory for minimizing overbreak in underground blasting operations - a case study of Alborz Tunnel, Iran. International Journal of Mining Science and Technology, 25(3), pp. 439-445. doi:10.1016/j.ijmst.2015.03.018.
>> more<< less