Model Performance Improvement by Accumulated Application of Machine Data in Machine Learning Model for TBM Advance Rate Prediction
Source abstract
Abstract
This study quantitatively verified the impact of applying accumulated data on the model’s prediction accuracy, overfitting, and adaptive learning ability by using a method that accumulates and retrains machine data of a TBM generated whenever excavation progresses at regular intervals. To achieve this, the performance of five machine learning algorithms was evaluated on two field datasets. The best-performing gradient boosting model was selected as the preliminary model. The performance results of the preliminary model and the cumulative model were then compared using another field dataset. The field data for the performance comparison were divided into 14 steps based on ground information, and the performance of the two models was compared sequentially at each step. The results showed that the preliminary and cumulative models exhibited similar predictive performance in the initial intervals. However, the cumulative model more closely matched actual measurements as new data was added than the preliminary model. Consequently, the preliminary model, based on past data, has clear limitations in adapting to the diverse variables encountered in real-world situations. On the other hand, cumulative models are essential for improving real-time prediction performance of processes with constantly changing environments, such as TBM, by continuously increasing relevant field data.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Tunneling and Rock Mechanics · Drilling and Well Engineering · Hydraulic and Pneumatic Systems
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Geotechnical Engineering Research, Korea Institute of Civil Engineering and Building Technology, Goyang-si 10223, Gyeonggi-do, Republic of Korea
Funding
National R&D Project for Smart Construction Technology · the Korea Agency for Infrastructure Technology Advancement under the Ministry of Land, Infrastructure, and Transport, and managed by the Korea Expressway Corporation
References (22)
Show source-provided references
1. Rostami, J., and Ozdemir, L. (1993, January 13–17). A new model for performance prediction of hard rock TBMs. Proceedings of the Rapid Excavation Tunnel Conference, Boston, MA, USA.
2. Influence of rock brittleness on TBM penetration rate in Singapore granite10.1016/j.tust.2006.07.004 ↗
3. Optimization of SVM with metaheuristics for TBM rate prediction10.1016/j.engappai.2020.104015 ↗
4. Xu, H., Zhou, J., Asteris, P.G., Armaghani, D.J., and Tahir, M.M. (2019). SML techniques for TBM penetration rate. Appl. Sci., 9.10.3390/app9183715 ↗
5. Soft ground micro-TBM jack speed and torque prediction using ML10.1038/s41598-024-60681-8 ↗
6. Katuwal, T.B., and Panthi, K.K. (2025). TBM penetration rate prediction in Himalayan geology using machine learning. Rock Mech. Rock Eng., 1–33.10.1007/s00603-025-05044-z ↗
7. A support vector regression model for predicting TBM penetration rates10.1016/j.ijrmms.2014.09.012 ↗
8. Real-time prediction of TBM cutterhead torque using BiLSTM10.1016/j.jrmge.2021.11.008 ↗
9. Zhang, Y., Chen, J., Han, S., and Li, B. (2022). Big data-based performance analysis of tunnel boring machine tunneling using deep learning. Buildings, 12.10.3390/buildings12101567 ↗
10. Hybrid deep learning model for TBM advance rate prediction10.1016/j.jrmge.2023.06.010 ↗
11. Real-time prediction of hard-rock TBM advance rate using TCN10.1007/s11709-022-0823-3 ↗
12. AL-iGAN: Active learning framework for geology reconstruction
13. Physical feature shared online transfer learning framework for cross-engineering rock mass quality perception during TBM excavation10.1016/j.tust.2025.107111 ↗
14. Feature fusion method for rock mass classification prediction and interpretable analysis based on TBM operating and cutter wear data10.1016/j.tust.2024.106351 ↗
15. Latif, K., Sharafat, A., and Seo, J. (2023). Digital twin-driven framework for TBM performance prediction, visualization, and monitoring through machine learning. Appl. Sci., 13.10.3390/app132011435 ↗
16. Real-time unsupervised monitoring of earth pressure balance shield-induced sinkholes in mixed-face ground conditions via convolutional variational autoencoders10.1016/j.tust.2024.105908 ↗
17. Gao, X., Song, X., Shi, M., Zhang, C., and Zhang, H. (2021). Real-time forecast models for TBM load parameters based on machine learning methods. arXiv.
18. Prediction method of TBM tunnel surrounding rock classification based on LSTM-SVM10.1177/16878132241255209 ↗
19. Real-time prediction of TBM penetration rates using a transformer-based ensemble deep learning model10.1016/j.autcon.2024.105793 ↗
20. Online multi-objective optimization for real-time TBM attitude control with spatio-temporal deep learning model10.1016/j.autcon.2023.105220 ↗
21. Prediction and analysis of slurry shield TBM disc cutter wear and its application in cutter change time10.1016/j.wear.2022.204314 ↗
22. Prediction of shield tunneling-induced ground settlement using machine learning techniques10.1007/s11709-019-0561-3 ↗