TY - GEN
T1 - Breaking the tunnel vision
T2 - ITA-AITES World Tunnel Congress, WTC 2024
AU - Huang, Shengfeng
AU - Sousa, Rita
AU - Korfiatis, George
N1 - Publisher Copyright:
© 2024 The Author(s).
PY - 2024
Y1 - 2024
N2 - Accurately predicting the Penetration Rate (PR) in tunneling is crucial for evaluating the performance of Tunnel Boring Machines. However, a significant shortcoming of many existing studies is that the predictive models are developed using data from a single project, which limits their applicability to future tunnelling projects. This research addresses this issue by examining whether the model can generalize to other tunnelling projects and investigates the impact of an incremental learning strategy on its performance. In this study, the Extreme Gradient Boosting (XG Boost) model was initially trained and tested using data from one tunnel project and then generalized to a different tunneling project with similar geological conditions. To improve the model’s generalization performance, an incremental learning strategy was used, which involved iterativelyincor porating new data from the second tunneling project into the existing data from the first tunneling projectto update the model. Additionally, the study analyzed how the generalization ability of XG Boost varies with the incremental size of new data. The findings indicate that there is a promising potential for enhancing the model’sgeneralization ability using incremental learning techniques. However, additional research is needed to address the challenges related with skewed data and mitigating the effects of catastrophic forgetting.
AB - Accurately predicting the Penetration Rate (PR) in tunneling is crucial for evaluating the performance of Tunnel Boring Machines. However, a significant shortcoming of many existing studies is that the predictive models are developed using data from a single project, which limits their applicability to future tunnelling projects. This research addresses this issue by examining whether the model can generalize to other tunnelling projects and investigates the impact of an incremental learning strategy on its performance. In this study, the Extreme Gradient Boosting (XG Boost) model was initially trained and tested using data from one tunnel project and then generalized to a different tunneling project with similar geological conditions. To improve the model’s generalization performance, an incremental learning strategy was used, which involved iterativelyincor porating new data from the second tunneling project into the existing data from the first tunneling projectto update the model. Additionally, the study analyzed how the generalization ability of XG Boost varies with the incremental size of new data. The findings indicate that there is a promising potential for enhancing the model’sgeneralization ability using incremental learning techniques. However, additional research is needed to address the challenges related with skewed data and mitigating the effects of catastrophic forgetting.
KW - EPBM performance
KW - Generalization
KW - Incremental Learning
KW - Penetration Rate
KW - XGBoost
UR - http://www.scopus.com/inward/record.url?scp=85195475655&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85195475655&partnerID=8YFLogxK
U2 - 10.1201/9781003495505-247
DO - 10.1201/9781003495505-247
M3 - Conference contribution
AN - SCOPUS:85195475655
SN - 9781032800424
T3 - Tunnelling for a Better Life - Proceedings of the ITA-AITES World Tunnel Congress, WTC 2024
SP - 1843
EP - 1849
BT - Tunnelling for a Better Life - Proceedings of the ITA-AITES World Tunnel Congress, WTC 2024
A2 - Yan, Jinxiu
A2 - Celestino, Tarcisio
A2 - Thewes, Markus
A2 - Eberhardt, Erik
Y2 - 19 April 2024 through 25 April 2024
ER -