Reliable prediction for TBM energy consumption during tunnel excavation: A novel technique balancing explainability and performance

Recently, AI-based models have been applied to accurately estimate tunnel boring machine (TBM) energy consumption. Although data-driven models exhibit strong predictive capabilities, their outputs derived from “black box” processes are challenging to interpret and generalize. Consequently, this stud...

Full description

Saved in:
Bibliographic Details
Main Authors: Wenli Liu, Yafei Qi, Fenghua Liu
Format: Article
Language:English
Published: KeAi Communications Co., Ltd. 2025-06-01
Series:Underground Space
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2467967424001338
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850235087839297536
author Wenli Liu
Yafei Qi
Fenghua Liu
author_facet Wenli Liu
Yafei Qi
Fenghua Liu
author_sort Wenli Liu
collection DOAJ
description Recently, AI-based models have been applied to accurately estimate tunnel boring machine (TBM) energy consumption. Although data-driven models exhibit strong predictive capabilities, their outputs derived from “black box” processes are challenging to interpret and generalize. Consequently, this study develops an XGB_MOFS model that cooperates extreme gradient boosting (XGBoost) and multi-objective feature selection (MOFS) to improve the accuracy and explainability of energy consumption prediction. The XGB_MOFS model includes: (1) a causal inference framework to identify the causal relationships among influential factors, and (2) a MOFS approach to balance predictive performance and explainability. Two case studies are carried out to verify the proposed method. Results show that XGB_MOFS achieves a high degree of accuracy and robustness in energy consumption prediction. The XGB_MOFS model, balancing accuracy with explainability, serves as an effective and feasible tool for regulating TBM energy consumption.
format Article
id doaj-art-38d45f3de9bb4078918c8f1feebb69f8
institution OA Journals
issn 2467-9674
language English
publishDate 2025-06-01
publisher KeAi Communications Co., Ltd.
record_format Article
series Underground Space
spelling doaj-art-38d45f3de9bb4078918c8f1feebb69f82025-08-20T02:02:25ZengKeAi Communications Co., Ltd.Underground Space2467-96742025-06-0122779510.1016/j.undsp.2024.09.004Reliable prediction for TBM energy consumption during tunnel excavation: A novel technique balancing explainability and performanceWenli Liu0Yafei Qi1Fenghua Liu2School of Civil and Hydraulic Engineering, Huazhong University of Science and Technology, Wuhan 430074, China; National Center of Technology Innovation for Digital Construction, Huazhong University of Science and Technology, Wuhan 430074, ChinaSchool of Civil and Hydraulic Engineering, Huazhong University of Science and Technology, Wuhan 430074, China; National Center of Technology Innovation for Digital Construction, Huazhong University of Science and Technology, Wuhan 430074, ChinaCorresponding author at: School of Civil and Hydraulic Engineering, Huazhong University of Science and Technology, Wuhan 430074, China.; School of Civil and Hydraulic Engineering, Huazhong University of Science and Technology, Wuhan 430074, China; National Center of Technology Innovation for Digital Construction, Huazhong University of Science and Technology, Wuhan 430074, ChinaRecently, AI-based models have been applied to accurately estimate tunnel boring machine (TBM) energy consumption. Although data-driven models exhibit strong predictive capabilities, their outputs derived from “black box” processes are challenging to interpret and generalize. Consequently, this study develops an XGB_MOFS model that cooperates extreme gradient boosting (XGBoost) and multi-objective feature selection (MOFS) to improve the accuracy and explainability of energy consumption prediction. The XGB_MOFS model includes: (1) a causal inference framework to identify the causal relationships among influential factors, and (2) a MOFS approach to balance predictive performance and explainability. Two case studies are carried out to verify the proposed method. Results show that XGB_MOFS achieves a high degree of accuracy and robustness in energy consumption prediction. The XGB_MOFS model, balancing accuracy with explainability, serves as an effective and feasible tool for regulating TBM energy consumption.http://www.sciencedirect.com/science/article/pii/S2467967424001338Machine learningMulti-objective feature selectionExplainabilityEnergy consumptionShield tunneling
spellingShingle Wenli Liu
Yafei Qi
Fenghua Liu
Reliable prediction for TBM energy consumption during tunnel excavation: A novel technique balancing explainability and performance
Underground Space
Machine learning
Multi-objective feature selection
Explainability
Energy consumption
Shield tunneling
title Reliable prediction for TBM energy consumption during tunnel excavation: A novel technique balancing explainability and performance
title_full Reliable prediction for TBM energy consumption during tunnel excavation: A novel technique balancing explainability and performance
title_fullStr Reliable prediction for TBM energy consumption during tunnel excavation: A novel technique balancing explainability and performance
title_full_unstemmed Reliable prediction for TBM energy consumption during tunnel excavation: A novel technique balancing explainability and performance
title_short Reliable prediction for TBM energy consumption during tunnel excavation: A novel technique balancing explainability and performance
title_sort reliable prediction for tbm energy consumption during tunnel excavation a novel technique balancing explainability and performance
topic Machine learning
Multi-objective feature selection
Explainability
Energy consumption
Shield tunneling
url http://www.sciencedirect.com/science/article/pii/S2467967424001338
work_keys_str_mv AT wenliliu reliablepredictionfortbmenergyconsumptionduringtunnelexcavationanoveltechniquebalancingexplainabilityandperformance
AT yafeiqi reliablepredictionfortbmenergyconsumptionduringtunnelexcavationanoveltechniquebalancingexplainabilityandperformance
AT fenghualiu reliablepredictionfortbmenergyconsumptionduringtunnelexcavationanoveltechniquebalancingexplainabilityandperformance