PL EN


Preferencje help
Widoczny [Schowaj] Abstrakt
Liczba wyników
Tytuł artykułu

A machine learning method for soil conditioning automated decision-making of EPBM : hybrid GBDT and Random Forest Algorithm

Treść / Zawartość
Identyfikatory
Warianty tytułu
Języki publikacji
EN
Abstrakty
EN
There lacks an automated decision-making method for soil conditioning of EPBM with high accuracy and efficiency that is applicable to changeable geological conditions and takes drive parameters into consideration. A hybrid method of Gradient Boosting Decision Tree (GBDT) and random forest algorithm to make decisions on soil conditioning using foam is proposed in this paper to realize automated decision-making. Relevant parameters include decision parameters (geological parameters and drive parameters) and target parameters (dosage of foam). GBDT, an efficient algorithm based on decision tree, is used to determine the weights of geological parameters, forming 3 parameters sets. Then 3 decision-making models are established using random forest, an algorithm with high accuracy based on decision tree. The optimal model is obtained by Bayesian optimization. It proves that the model has obvious advantages in accuracy compared with other methods. The model can realize real-time decision-making with high accuracy under changeable geological conditions and reduce the experiment cost.
Rocznik
Strony
237--247
Opis fizyczny
Bibliogr. 34 poz., rys., tab.
Twórcy
autor
  • Harbin Institute of Technology, School of Mechatronics Engineering, Harbin, 150001, China
autor
  • Harbin Institute of Technology, School of Mechatronics Engineering, Harbin, 150001, China
autor
  • Harbin Institute of Technology, School of Mechatronics Engineering, Harbin, 150001, China
autor
  • Harbin Institute of Technology, School of Mechatronics Engineering, Harbin, 150001, China
  • Harbin Institute of Technology, School of Mechatronics Engineering, Harbin, 150001, China
autor
  • China Railway Construction Corporation Limited, Changsha, 410100, China
Bibliografia
  • 1. A CB, B MT. Application ranges of EPB shields in coarse ground based on laboratory research. Tunneling and Underground Space Technology 2015; 50: 296-304, https://doi.org/10.1016/j.tust.2015.08.006.
  • 2. Ahmadi S, Moosazadeh S, Hajihassani M, Moomivand H, Rajaei MM. Reliability, availability and maintainability analysis of the conveyor system in mechanized tunneling. Measurement 2019; 145: 756-764, https://doi.org/10.1016/j.measurement.2019.06.009.
  • 3. Bergstra J, Bengio Y. Random Search for Hyper-Parameter Optimization. Journal of Machine Learning Research 2012; 13: 281-305.
  • 4. Biau G. Analysis of a Random Forests Model. Journal of Machine Learning Research 2012; 13: 1063-1095.
  • 5. Chan J, Paelinckx D. Evaluation of Random Forest and Adaboost tree-based ensemble classification and spectral band selection for ecotope mapping using airborne hyperspectral imagery. Remote Sensing of Environment 2008; 112: 2999-3011, https://doi.org/10.1016/j.rse.2008.02.011.
  • 6. Kozłowski E, Antosz K, Mazurkiewicz D, Sęp J, Żabiński T. Integrating advanced measurement and signal processing for reliability decisionmaking. Eksploatacja i Niezawodnosc - Maintenance and Reliability 2021; 23: 777-787, https://doi.org/10.17531/ein.2021.4.20.
  • 7. Feurer M, Springenberg J, Hutter F. Initializing Bayesian Hyperparameter Optimization via Meta-Learning. Proceedings of the AAAI Conference on Artificial Intelligence 2015; 29(1), https://ojs.aaai.org/index.php/AAAI/article/view/9354.
  • 8. Friedman J. Greedy function approximation: A gradient boosting machine. Annals of Statistics 2001; 29: 1189-1232, https://doi.org/10.1214/aos/1013203451.
  • 9. Galli DIM, Thewes DIM. Investigations for the application of EPB shields in difficult grounds. Geomechanik und Tunnelbau 2014; 7: 31-44, https://doi.org/10.1002/geot.201310030.
  • 10. Galli M, Thewes M. Rheological Characterization of Foam-Conditioned Sands in EPB Tunneling. International Journal of Civil Engineering 2018, https://doi.org/10.1007/s40999-018-0316-x.
  • 11. Hollmann F, Thewes M. Assessment method for clay clogging and disintegration of fines in mechanised tunnelling. Tunneling and Underground Space Technology 2013; 37: 96-106, https://doi.org/10.1016/j.tust.2013.03.010.
  • 12. Hu Q, Wang S, Qu T, et al. Effect of hydraulic gradient on the permeability characteristics of foam-conditioned sand for mechanized tunnelling. Tunneling and Underground Space Technology 2020; 99, https://doi.org/10.1016/j.tust.2020.103377.
  • 13. Jerbi W, Ben Brahim A, Essoussi N. A Hybrid Embedded-Filter Method for Improving Feature Selection Stability of Random Forests. In. Cham 2017: 370-379, https://doi.org/10.1007/978-3-319-52941-7_37.
  • 14. Jianjun Z, Diming C, Dongyuan W, Lu-Lu Z, Li-Min Z. Failure Probability of Transverse Surface Settlement Induced by EPB Shield Tunneling in Clayey Soils. Asce Asme Journal of Risk & Uncertainty in Engineering Systems Part a Civil Engineering 2018; 4: 4018030, https://doi.org/10.1061/AJRUA6.0000981.
  • 15. Kim TH, Kim BK, Lee KH, Lee IM. Soil Conditioning of Weathered Granite Soil used for EPB Shield TBM: A Laboratory Scale Study. KSCE Journal of Civil Engineering 2019; 23: 1829-1838, https://doi.org/10.1007/s12205-019-1484-1.
  • 16. Opricovic S, Tzeng G. Compromise solution by MCDM methods: A comparative analysis of VIKOR and TOPSIS. European Journal of Operational Research 2004; 156: 445-455, https://doi.org/10.1016/S0377-2217(03)00020-1.
  • 17. Peila D. Soil conditioning for EPB shield tunnelling. KSCE Journal of Civil Engineering 2014; 18: 831-836, https://doi.org/10.1007/s12205-014-0023-3.
  • 18. Pourmand S, Chakeri H, Sharghi M, Bonab M, Ozcelik Y. Laboratory Studies on Soil Conditioning of Sand in the Mechanized Tunneling. Journal of Testing and Evaluation 2020; 48: 3658-3672, https://doi.org/10.1520/JTE20170395.
  • 19. Putatunda S, Rama K. A Comparative Analysis of Hyperopt as Against Other Approaches for Hyper-Parameter Optimization of XGBoost. In. NEW YORK; 2018: 6-10, https://doi.org/10.1145/3297067.3297080.
  • 20. Qu T, Wang S, Hu Q. Coupled Discrete Element-Finite Difference Method for Analysing Effects of Cohesionless Soil Conditioning on Tunneling Behaviour of EPB Shield. KSCE Journal of Civil Engineering 2019; 23: 4538-4552, https://doi.org/10.1007/s12205-019-0473-8.
  • 21. Sakata R, Ohama I, Taniguchi T. An Extension of Gradient Boosted Decision Tree incorporating Statistical Tests. 2018 IEEE International Conference on Data Mining Workshops (ICDMW) 2018: https://doi.org/10.1109/ICDMW.2018.00139.
  • 22. Selmi M, Kacem M, Jamei M, Dubujet P. Physical Foam Stability of Loose Sandy-Clay: a Porosity Role in the Conditioned Soil. Water and Soil Pollution 2020; 231, https://doi.org/10.1007/s11270-020-04598-8.
  • 23. Scornet E. Random Forests and Kernel Methods. IEEE Transactions on Information Theory 2016; 62: 1485-1500, https://doi.org/10.1109/TIT.2016.2514489.
  • 24. T GA, M HA. Reliability assessment of EPB tunnel-related settlement. Geomechanics and Engineering 2010; 2: 57-69, https://doi.org/10.12989/gae.2010.2.1.057.
  • 25. Thewes M, Hollmann F. Assessment of clay soils and clay-rich rock for clogging of TBMs. Tunneling and Underground Space Technology 2016; 57: 122-128, https://doi.org/10.1016/j.tust.2016.01.010.
  • 26. Vinai R, Oggeri C, Peila D. Soil conditioning of sand for EPB applications: A laboratory research. Tunneling and Underground Space Technology 2008; 23: 308-317, https://doi.org/10.1016/j.tust.2007.04.010.
  • 27. Wang S, Hu Q, Wang H, Thewes M, Liu P. Permeability Characteristics of Poorly Graded Sand Conditioned with Foam in Different Conditioning States. Journal of Testing and Evaluation 2020, https://doi.org/10.1520/JTE20190539.
  • 28. Wei Y, Yang Y, Tao M, Wang D, Jie Y. Earth pressure balance shield tunneling in sandy gravel deposits: a case study of application of soil conditioning. Bulletin of Engineering Geology and the Environment 2020; 79: 5013-5030, https://doi.org/10.1007/s10064-020-01856-1.
  • 29. Xia Y, Liu C, Li Y, Liu N. A boosted decision tree approach using Bayesian hyper-parameter optimization for credit scoring. Expert Systems with Applications 2017; 78: 225-241, https://doi.org/10.1016/j.eswa.2017.02.017.
  • 30. Xiao C, Tan L, Xia Y, et al. Excavation parameters characteristics of earth pressure balanced shield based on soil modification. Journal of Railway Science and Engineering 2017.
  • 31. You M, Liu J, Li G, Chen Y. Embedded Feature Selection for Multi-Label Classification of Music Emotions. International Journal of Computational Intelligence Systems 2012; 5: 668-678, https://doi.org/10.1080/18756891.2012.718113.
  • 32. Zhao M, Li J. Tuning the Hyper-parameters of CMA-ES with Tree-structured Parzen Estimators. 2018 Tenth International Conference on Advanced Computational Intelligence (ICACI) 2018: 613-618, https://doi.org/10.1109/ICACI.2018.8377530.
  • 33. Zheng G, Sun W, Zhang H, Zhou Y, Gao C. Tool wear condition monitoring in milling process based on data fusion enhanced long short-term memory network under different cutting conditions. Eksploatacja i Niezawodnosc - Maintenance and Reliability 2021; 23: 612-618, https://doi.org/10.17531/ein.2021.4.3.
  • 34. Zou T, Dang W, Zhang G, Liu K, Li P. Prior distribution selection criterion in accelerated degradation. 2017 International Conference on Sensing, Diagnostics, Prognostics, and Control (SDPC) 2018: 694-698,
Uwagi
Opracowanie rekordu ze środków MEiN, umowa nr SONP/SP/546092/2022 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2022-2023).
Typ dokumentu
Bibliografia
Identyfikator YADDA
bwmeta1.element.baztech-2e8bcc28-4c4a-4a67-87b1-486aba75aef9
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.