A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Machine Learning Methods on Predicting TBM's Penetration Rate in Athens Metro
https://orcid.org/http://orcid.org/0009-0008-7243-6889
https://orcid.org/http://orcid.org/0000-0001-8200-0407
Tunnel Boring Machines (TBM) are primarily used for the excavation of metro tunnels in urban areas, as they can achieve almost zero disturbance to the surrounding rock mass and can attain high advance rates. Modeling the penetration rate (PR) of a TBM is an important aspect of any tunnel excavation, as its more accurate prediction impacts the overall construction cost, and the potential delay of the tunnel delivery to the society but also can provide insights of upcoming safety issues. This paper deals with the prediction of the PR with Machine Learning (ML) methods utilizing data coming from part of the construction of Athens metro Line 2. The data consists of the TBM data, provided by Attiko Metro. By using an Earth Pressure Balance-Tunnel Boring Machine (EPB-TBM), it is possible to balance the pressure conditions at the tunnel face, avoiding face collapse and controlling ground settlements. A solitary analysis of just the machine parameters without any additional information (geological, geometrical, etc.) can derive meaningful information regarding the quality and quantity effects the additional information e.g., geological medium has on a tunnel excavation when using an EPB-TBM. Two ML models (Extreme Gradient Boosting Regression—XGBR, Artificial Neural Networks—ANN) were developed and compared between them utilizing a set of input parameters derived from a feature importance analysis. The results show promising results having a consistent behavior across almost the entire range of the test dataset used, closely following the trend and behavior of the actual PR.
Machine Learning Methods on Predicting TBM's Penetration Rate in Athens Metro
https://orcid.org/http://orcid.org/0009-0008-7243-6889
https://orcid.org/http://orcid.org/0000-0001-8200-0407
Tunnel Boring Machines (TBM) are primarily used for the excavation of metro tunnels in urban areas, as they can achieve almost zero disturbance to the surrounding rock mass and can attain high advance rates. Modeling the penetration rate (PR) of a TBM is an important aspect of any tunnel excavation, as its more accurate prediction impacts the overall construction cost, and the potential delay of the tunnel delivery to the society but also can provide insights of upcoming safety issues. This paper deals with the prediction of the PR with Machine Learning (ML) methods utilizing data coming from part of the construction of Athens metro Line 2. The data consists of the TBM data, provided by Attiko Metro. By using an Earth Pressure Balance-Tunnel Boring Machine (EPB-TBM), it is possible to balance the pressure conditions at the tunnel face, avoiding face collapse and controlling ground settlements. A solitary analysis of just the machine parameters without any additional information (geological, geometrical, etc.) can derive meaningful information regarding the quality and quantity effects the additional information e.g., geological medium has on a tunnel excavation when using an EPB-TBM. Two ML models (Extreme Gradient Boosting Regression—XGBR, Artificial Neural Networks—ANN) were developed and compared between them utilizing a set of input parameters derived from a feature importance analysis. The results show promising results having a consistent behavior across almost the entire range of the test dataset used, closely following the trend and behavior of the actual PR.
Machine Learning Methods on Predicting TBM's Penetration Rate in Athens Metro
https://orcid.org/http://orcid.org/0009-0008-7243-6889
https://orcid.org/http://orcid.org/0000-0001-8200-0407
Tunnel Boring Machines (TBM) are primarily used for the excavation of metro tunnels in urban areas, as they can achieve almost zero disturbance to the surrounding rock mass and can attain high advance rates. Modeling the penetration rate (PR) of a TBM is an important aspect of any tunnel excavation, as its more accurate prediction impacts the overall construction cost, and the potential delay of the tunnel delivery to the society but also can provide insights of upcoming safety issues. This paper deals with the prediction of the PR with Machine Learning (ML) methods utilizing data coming from part of the construction of Athens metro Line 2. The data consists of the TBM data, provided by Attiko Metro. By using an Earth Pressure Balance-Tunnel Boring Machine (EPB-TBM), it is possible to balance the pressure conditions at the tunnel face, avoiding face collapse and controlling ground settlements. A solitary analysis of just the machine parameters without any additional information (geological, geometrical, etc.) can derive meaningful information regarding the quality and quantity effects the additional information e.g., geological medium has on a tunnel excavation when using an EPB-TBM. Two ML models (Extreme Gradient Boosting Regression—XGBR, Artificial Neural Networks—ANN) were developed and compared between them utilizing a set of input parameters derived from a feature importance analysis. The results show promising results having a consistent behavior across almost the entire range of the test dataset used, closely following the trend and behavior of the actual PR.
Machine Learning Methods on Predicting TBM's Penetration Rate in Athens Metro
Lecture Notes in Civil Engineering
Wu, Wei (editor) / Leung, Chun Fai (editor) / Zhou, Yingxin (editor) / Li, Xiaozhao (editor) / Sioutas, K. N. (author) / Benardos, A. (author)
Conference of the Associated research Centers for the Urban Underground Space ; 2023 ; Boulevard, Singapore
2024-07-10
6 pages
Article/Chapter (Book)
Electronic Resource
English
| British Library Conference Proceedings | 1994
Tunnelling problems delay Athens metro
| Online Contents | 1996
Design Criteria for TBM's with respect to real rock pressure
| British Library Conference Proceedings | 1996
| British Library Online Contents | 1996
| Online Contents | 1996