Predicting disc cutter wear using two optimized machine learning techniques

Ghorbani, Ebrahim; Yagiz, Saffet

doi:10.1007/s43452-024-00911-y

Artykuł - szczegóły

Tytuł artykułu

Predicting disc cutter wear using two optimized machine learning techniques

Autorzy

Ghorbani Ebrahim , Yagiz Saffet

Wybrane pełne teksty z tego czasopisma

http://www.springer.com/journal/43452

Identyfikatory

DOI

10.1007/s43452-024-00911-y

Warianty tytułu

Języki publikacji

Abstrakty

The estimation of disc cutter wear (CW) remains a complex problem in mechanized tunneling using tunnel boring machines (TBM), despite the development of numerous TBM performance models. This research aimed to estimate the cutter life index (CLI) as an index to predict the CW by developing predictive models based on two machine learning algorithms, namely gradient boosting (GB) and random forest (RF), optimized by three optimization techniques: particle swarm optimization (PSO), differential evolution (DE), and simulated annealing (SA). To gain the aim, a dataset consisting of four rock parameters-density (ρ), uniaxial compressive strength, Brazilian tensile strength (BTS), and brittleness index-with 80 mechanized tunnel cases for each parameter has been utilized by obtaining the sample and then relevant tests on them were conducted in the laboratory. First, various parameter selection methods, such as mutual information, have been employed to reduce the dimensionality of the problem, and it has been revealed that ρ and BTS have been the most influential parameters to estimate the CLI. Then, by developing six optimized models, including GB-PSO, GB-DE, GB-SA, RF-PSO, RF-DE, and RF-SA, using the two mentioned parameters, their performance has been assessed via three performance evaluation indices of coefficient of determination (r²), root mean square error (RMSE), and mean absolute percentage error (MAPE). The results showed that among six predictive models, the two models of GB-SA (with r², RMSE, and MAPE of 0.8274, 10.8329, and 0.3957, respectively) and RF-PSO (with r², RMSE, and MAPE of 0.8213, 11.0249, and 0.4113, respectively) outperformed the other models, with 82.74% accuracy of GB-SA and with 82.13% accuracy of the RF-PSO, and the two can be utilized to estimate disc cutter via CLI for different type of rock in the range of established dataset.

Słowa kluczowe

disc cutter wear cutter life index machine learning gradient boosting Random Forest

frez tarczowy uczenie maszynowe wzmocnienie gradientowe las losowy

Wydawca

Springer
Wrocław University of Science and Technology

Czasopismo

Archives of Civil and Mechanical Engineering

Rocznik

2024

Tom

Vol. 24, no. 2

Strony

art. no. e106, 2024

Opis fizyczny

Bibliogr. 60 poz., rys., tab., wykr.

Twórcy

autor

Ghorbani Ebrahim

ebrahim.ghorbani@nu.edu.kz

School of Mining and Geosciences, Department of Mining Engineering, Nazarbayev University, Astana 010000, Kazakhstan

https://orcid.org/0000-0003-0735-4824

autor

Yagiz Saffet

saffet.yagiz@nu.edu.kz

School of Mining and Geosciences, Department of Mining Engineering, Nazarbayev University, Astana 010000, Kazakhstan

https://orcid.org/0000-0002-7271-3136

Bibliografia

1. Maidl B, et al. Mechanised shield tunnelling. Wilhelm Ernst & Sohn; 2012.
2. Bruland A. Hard rock tunnel boring advance rate and cutter wear. Trondheim: Norwegian Institute of Technology. 1999.
3. Wijk G. A model of tunnel boring machine performance. Geotech Geol Eng. 1992;10:19-40.
4. Rostami J, Ozdemir L. A new model for performance prediction of hard rock TBMs. In: Proceedings of the rapid excavation and tunneling conference. 1993.
5. Yagiz S. Assessment of brittleness using rock strength and density with punch penetration test. Tunn Undergr Space Technol. 2009;24(1):66-74.
6. Blindheim O. Boreability predictions for tunneling. Trondheim, Norway: The Norwegian Institute of Technology. 1979.
7. Hassanpour J, et al. Introduction of an empirical TBM cutter wear prediction model for pyroclastic and mafic igneous rocks; a case history of Karaj water conveyance tunnel Iran. Tunn Undergr Space Technol. 2014;43:222-31.
8. Oparin V, Tanaino A. A new method to test rock abrasiveness based on physico-mechanical and structural properties of rocks. J Rock Mech Geotech Eng. 2015;7(3):250-5.
9. Farrokh E, Kim DY. A discussion on hard rock TBM cutter wear and cutterhead intervention interval length evaluation. Tunn Undergr Space Technol. 2018;81:336-57.
10. Bakar MA, Majeed Y, Rostami J. Influence of moisture content on the LCPC test results and its implications on tool wear in mechanized tunneling. Tunn Undergr Space Technol. 2018;81:165-75.
11. Karami M, Zare S, Rostami J. Tracking of disc cutter wear in TBM tunneling: a case study of Kerman water conveyance tunnel. Bull Eng Geol Env. 2021;80:201-19.
12. She L, et al. Prediction of TBM disc cutter wear based on field parameters regression analysis. Geomechanics and Engineering. 2023;35(6):647.
13. Tripathy A, Singh T, Kundu J. Prediction of abrasiveness index of some Indian rocks using soft computing methods. Measurement. 2015;68:302-9.
14. Kadkhodaei M, Ghasemi E. Development of a GEP model to assess CERCHAR abrasivity index of rocks based on geomechanical properties. Journal of Mining and Environment. 2019;10(4):917-28.
15. Massalov T, Yagiz S, Adoko AC. Application of soft computing techniques to estimate cutter life index using mechanical properties of rocks. Appl Sci. 2022;12(3):1446.
16. Ding X, Xie A, Xue H. Quantitative estimation of TBM disc cutter wear from in-situ parameters by optimization algorithm improved back-propagation neural network: a case study of a metro tunnel in Guangzhou, China. In: Expanding underground-knowledge and passion to make a positive impact on the world. CRC Press; 2023. p. 2627-34.
17. Kilic K, et al. One-Dimensional convolutional neural network for pipe jacking EPB TBM cutter wear prediction. Appl Sci.2022;12(5):2410.
18. Gong Q, et al. Study on the cutter wear based on the cutter-head working status monitoring system in TBM tunneling. In: Expanding underground-knowledge and passion to make a positive impact on the world. CRC Press; 2023. p. 1267-75.
19. Liu Y, et al. Prediction model of tunnel boring machine disc cutter replacement using kernel support vector machine. Appl Sci. 2022;12(5):2267.
20. Hamzaban M-T, et al. Wear of cutting tools in hard rock excavation process: a critical review of rock abrasiveness testing methods. Rock Mech Rock Eng. 2023;56(3):1843-82.
21. Rajati M-H, et al. A study on predicting the wear of TBM disc cutters using Cerchar testing. Tunn Undergr Space Technol. 2023;140: 105290.
22. Ko TY, et al. Effect of geomechanical properties on Cerchar Abrasivity Index (CAI) and its application to TBM tunnelling. Tunn Undergr Space Technol. 2016;57:99-111.
23. Aligholi S, et al. Evaluating the relationships between NTNU/SINTEF drillability indices with index properties and petrographic data of hard igneous rocks. Rock Mech Rock Eng. 2017;50:2929-53.
24. Ge Y, et al. Effects of rock properties on the wear of TBM disc cutter: a case study of the Yellow River Diversion Project, China. Int J Geomech. 2022;22(4):04022011.
25. Sun J, et al. A new prediction model for disc cutter wear based on Cerchar Abrasivity Index. Wear. 2023;526: 204927.
26. Ewendt, D., Erfassung der Gesteinsabrasivität und Prognose des Werkzeugverschleißes beim maschinellen Tunnelvortrieb mit Diskenmeißeln. Kurzberichte aus der Bauforschung, 1992. 33(9).
27. Gehring K. Leistungs-und Verschleißprognosen im maschinellen Tunnelbau. Felsbau. 1995;13(6):439-48.
28. Rostami J, et al. Development of soil abrasivity testing for soft ground tunneling using shield machines. Tunn Undergr Space Technol. 2012;28:245-56.
29. Dahl F, Grøv E, Breivik T. Development of a new direct test method for estimating cutter life, based on the Sievers’ J miniature drill test. Tunn Undergr Space Technol. 2007;22(1):106-16.
30. Dahl F, et al. Classifications of properties influencing the drillability of rocks, based on the NTNU/SINTEF test method. Tunn Undergr Space Technol. 2012;28:150-8.
31. Maidl B, et al. Hardrock tunnel boring machines. New York: John Wiley & Sons; 2008.
32. Bieniawski Z, et al. Prediction of cutter wear using RME. In: ITA-AITES World Tunnel Congress, Budapest. 2009.
33. Frenzel C. Disc cutter wear phenomenology and their implications on disc cutter consumption for TBM. In: 45th US Rock Mechanics/Geomechanics Symposium. OnePetro. 2011.
34. Wang L, et al. The energy method to predict disc cutter wear extent for hard rock TBMs. Tunn Undergr Space Technol. 2012;28:183-91.
35. Hassanpour J, Rostami J, Zhao J. A new hard rock TBM performance prediction model for project planning. Tunn Undergr Space Technol. 2011;26(5):595-603.
36. Liu Q, et al. A wear rule and cutter life prediction model of a 20-in. TBM cutter for granite: a case study of a water conveyance tunnel in China. Rock Mech Rock Eng. 2017;50:1303-20.
37. Zhao Y, et al. Effects of jointed rock mass and mixed ground conditions on the cutting efficiency and cutter wear of tunnel boring machine. Rock Mech Rock Eng. 2019;52:1303-13.
38. Wang R, et al. A TBM cutter life prediction method based on rock mass classification. KSCE J Civ Eng. 2020;24:2794-807.
39. Farrokh E. Cutter change time and cutter consumption for rock TBMs. Tunn Undergr Space Technol. 2021;114: 104000.
40. Zhang Z, Zhang K, Dong W. Experimental investigation on the influence factors on TBM cutter wear based on composite abrasion test. Rock Mech Rock Eng. 2021;54:6533-47.
41. Barzegari G, Khodayari J, Rostami J. Evaluation of TBM cutter wear in Naghadeh water conveyance tunnel and developing a new prediction model. Rock Mech Rock Eng. 2021;54:6281-97.
42. Li X, et al. Disc cutter wear prediction method of hard rock TBM Based on Bayesian networks. In: ARMA US Rock Mechanics/Geomechanics Symposium. ARMA. 2018.
43. Mahmoodzadeh A, et al. Machine learning forecasting models of disc cutters life of tunnel boring machine. Autom Constr. 2021;128: 103779.
44. Elbaz K, et al. Prediction of disc cutter life during shield tunneling with AI via the incorporation of a genetic algorithm into a GMDH-type neural network. Engineering. 2021;7(2):238-51.
45. Yu H, et al. A field parameters-based method for real-time wear estimation of disc cutter on TBM cutterhead. Autom Constr. 2021;124: 103603.
46. Ding X, et al. A new approach for developing EPB-TBM disc cutter wear prediction equations in granite stratum using backpropagation neural network. Tunn Undergr Space Technol. 2022;128: 104654.
47. Li A, et al. Hybrid Model for Predicting Average Cutter Wear in TBM Excavation. In: Proceedings of The 17th East Asian-Pacific Conference on Structural Engineering and Construction. EASEC-17. 2023. Springer, Singapore.
48. Yagiz S. Unpublished database obtained from different mechanical tunnel projects. Earth Mechanics Institute of Colorado School of Mines, personnel experience and data. 1995-2022. Co, USA
49. Yagiz S, et al. Application of two non-linear prediction tools to the estimation of tunnel boring machine performance. Eng Appl Artif Intell. 2009;22(4-5):808-14.
50. Friedman JH. Greedy function approximation: a gradient boosting machine. Annals of statistics. 2001. p. 1189-1232.
51. Liaw A, Wiener M. Classification and regression by randomForest. R news. 2002;2(3):18-22.
52. Abido MA. Optimal power flow using particle swarm optimization. Int J Electr Power Energy Syst. 2002;24(7):563-71.
53. Lu Z-S, Hou Z-R, Du J. Particle swarm optimization with adaptive mutation. Front Electr Electron Eng China. 2006;1:99-104.
54. Zhang, L.-B., et al. Solving multi objective optimization problems using particle swarm optimization. In: The 2003 Congress on Evolutionary Computation. CEC’03. 2003. IEEE. 2003.
55. Storn R, Price K. Differential evolution-a simple and efficient heuristic for global optimization over continuous spaces. J Global Optim. 1997;11:341-59.
56. Das S, Suganthan PN. Differential evolution: a survey of the state-of-the-art. IEEE Trans Evol Comput. 2010;15(1):4-31.
57. Kirkpatrick S, Gelatt CD Jr, Vecchi MP. Optimization by simulated annealing. Science. 1983;220(4598):671-80.
58. Delahaye D, Chaimatanan S, Mongeau M. Simulated annealing: from basics to applications. Handbook of Metaheuristics. 2019: pp. 1-35.
59. Xiang Y, et al. Generalized simulated annealing for global optimization: the GenSA package. R J. 2013;5(1):13.
60. Varma S, Simon R. Bias in error estimation when using cross-validation for model selection. BMC Bioinf. 2006;7(1):1-8.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa nr POPUL/SP/0154/2024/02 w ramach programu "Społeczna odpowiedzialność nauki II" - moduł: Popularyzacja nauki (2025).

Typ dokumentu

Bibliografia

Identyfikator YADDA

bwmeta1.element.baztech-2376009d-5e3e-4705-9db2-284a2e18e650