All Issue

2025 Vol.27, Issue 6 Preview Page

Research Paper

Machine learning model for predicting the roadheader performance

로드헤더의 굴진속도 예측을 위한 머신러닝 모델

Jin-Won Seo1
,
Ki-Il Song2*
,
Pok-Hwan Bae3
서 진원1
,
송 기일2*
,
배 복환3
1Graduate Student, Dept. of Smart City Engineering, Inha University
2Professor, Dept. of Civil Engineering, Inha University
3Graduate Student, Dept. of Civil Engineering, Inha University
1비회원, 인하대학교 스마트시티공학과 석사과정
2정회원, 인하대학교 사회인프라공학과 정교수
3정회원, 인하대학교 토목공학과 박사과정
*Corresponding Author
30 November 2025. pp. 539-553
PDF XML Citation
Abstract

The development of underground space has been actively promoted worldwide to address urban overcrowding and mechanized tunneling methods are increasingly encouraged in urban areas to mitigate noise and blasting-related complaints. Among these methods, the roadheader tunneling technique has attracted attention due to its adaptability to varying tunnel cross-sectional shapes and high mobility. However, to ensure process efficiency under diverse rock conditions, it is essential to establish a reliable approach for accurately predicting the cutting performance of roadheaders. In this study, ground condition and excavation data from a large-scale roadheader tunneling project in Korea were collected and analyzed to develop predictive models using five machine learning techniques: Random Forest (RF), eXtreme Gradient Boosting (XGBoost), K-Nearest Neighbor (KNN), Deep Neural Network (DNN), and Tabular Prior-Data Fitted Network (TabPFN). Rock strength, pick consumption per face, and advance length were selected as input features, and suitable hyperparameters were tuned for model construction. A total of 135 datasets were divided into training and test sets at an 8:2 ratio. Comparative analysis of model performance showed that the DNN and TabPFN models achieved relatively superior results, with coefficients of determination (R2) of 0.68 and 0.72, and root mean square error (RMSE) of 1.43 and 1.34, mean absolute error (MAE) of 1.04 and 1.07, respectively.

Keywords
Roadheader
Roadheader performance
Roadheader performance prediction
Data analysis
Machine learning

전 세계적으로 도심지 과밀화 문제를 해결하기 위해 지하공간 개발이 활발히 추진되고 있으며, 도심지에서의 소음과 발파 민원을 해결하기 위해 기계식 터널 굴착 공법을 장려하고 있다. 그 중 터널 단면 형상 변화에 대한 대응력과 이동성이 우수한 로드헤더 공법이 주목받고 있으며, 다양한 암반 조건에 대응하고, 공정의 효율성을 확보하기 위해서는 로드헤더의 굴진 성능을 정확하게 예측할 수 있는 방안이 필요하다. 본 연구에서는 국내 대형 로드헤더 터널 시공 현장의 지반 조건 및 굴진 데이터를 수집하여 분석하고, Random Forest (RF), eXtreme Gradient Boosting (XGBoost), K-Nearest Neighbor (KNN), Deep Neural Network (DNN), Tabular Prior-Data Fitted Network (TabPFN)의 5가지 머신러닝 기법을 이용하여 굴진속도 예측 모델을 개발하였다. 예측 모델의 입력 특성으로 암반 강도, 막장당 피크 소모량, 굴진장을 선정하였으며, 수집된 데이터셋에 적합한 하이퍼파라미터를 탐색하여 모델을 구축하였다. 총 135개의 데이터셋을 학습 데이터와 테스트 데이터를 각각 8:2 비율로 나누어 학습하고, 학습 성능을 비교·분석한 결과 DNN과 TabPFN 모델이 각각 0.68, 0.72의 결정계수(R2)와 1.43, 1.34의 평균 제곱근 오차(root mean square error, RMSE), 1.04, 1.07의 평균 절대 오차(mean absolute error, MAE)로 비교적 우수한 결과를 나타냈다.

키워드
로드헤더
로드헤더 성능
굴진속도 예측
데이터 분석
머신러닝
References
1

Balci, C., Demircin, M.A., Copur, H., Tuncdemir, H. (2004), “Estimation of optimum specific energy based on rock properties for assessment of roadheader performance (567BK)”, Journal of the Southern African Institute of Mining and Metallurgy, Vol. 104, No. 11, pp. 633-641.

2

Bilgin, N., Seyrek, T., Shahriar, K. (1988), “Roadheader performance in Istanbul. Golden Horn clean-up contributes valuable data”, Tunnels and Tunnelling, Vol. 20, No. 6, pp. 41-44.

3

Chang, S.H. (2015), “A consideration for mechanical rock excavation focusing on TBM and roadheader”, Journal of the Korean Society of Mineral and Energy Resources Engineers, Vol. 52, No. 5, pp. 531-548.

10.12972/ksmer.2015.52.5.531
4

Copur, H., Ozdemir, L., Rostami, J. (1998), “Roadheader applications in mining and tunneling industries”, Mining Engineering, Vol. 50, No. 3, pp. 38-42.

5

Ebrahimabadi, A., Azimipour, M., Bahreini, A. (2015), “Prediction of roadheaders’ performance using artificial neural network approaches (MLP and KOSFM)”, Journal of Rock Mechanics and Geotechnical Engineering, Vol. 7, No. 5, pp. 573-583.

10.1016/j.jrmge.2015.06.008
6

Ebrahimabadi, A., Goshtasbi, K., Shahriar, K., Cheraghi Seifabad, M. (2011), “A model to predict the performance of roadheaders based on the Rock Mass Brittleness Index”, Journal of the Southern African Institute of Mining and Metallurgy, Vol. 111, No. 5, pp. 355-364.

7

Gehring, K.H. (1989), “A cutting comparison”, Tunnels and Tunnelling (UK), Vol. 21, No. 11, pp. 27-30.

8

Hollmann, N., Müller, S., Purucker, L., Krishnakumar, A., Körfer, M., Hoo, S.B., Schirrmeister, R.T., Hutter, F. (2025), “Accurate predictions on small data with a tabular foundation model”, Nature, Vol. 637, pp. 319-326.

10.1038/s41586-024-08328-639780007PMC11711098
9

Jung, J.H., Yim, J.H., Lee, J.W., Kang, H.B., Kim, D.H., Shin, Y.J. (2023), “Development of roadheader performance prediction model and review of machine specification”, Journal of Korean Tunnelling and Underground Space Association, Vol. 25, No. 3, pp. 221-243.

10.9711/KTAJ.2023.25.3.221
10

Kim, Y.G. (2021), “An analysis of artificial intelligence algorithms applied to rock engineering”, Tunnel and Underground Space, Vol. 31, No. 1, pp. 25-40.

10.7474/TUS.2021.31.1.025
11

Kim, Y.G., Jeong, H.Y., Cho, J.W., Park, S.W., Lee, Y.J. (2021), “Roadheader excavation in urban tunnelling”, Magazine of Korean Tunnelling and Underground Space Association, Vol. 23, No. 1, pp. 61-80.

12

Park, Y.T., Choi, S.W., Park, J.H., Lee, C.H., Jang, S.H. (2013), “Excavation mechanism of roadheader and statistical analysis of its key design parameters based on database”, Tunnel and Underground Space, Vol. 23, No. 5, pp. 428-441.

10.7474/TUS.2013.23.5.428
13

Salsani, A., Daneshian, J., Shariati, S., Yazdani-Chamzini, A., Taheri, M. (2014), “Predicting roadheader performance by using artificial neural network”, Neural Computing and Applications, Vol. 24, No. 7, pp. 1823-1831.

10.1007/s00521-013-1434-7
14

Sandvik (2017), SANDVIK MT720 roadheader product leaflet.

15

Seker, S.E., Ocak, I. (2019), “Performance prediction of roadheaders using ensemble machine learning techniques”, Neural Computing and Applications, Vol. 31, No. 4, pp. 1103-1116.

10.1007/s00521-017-3141-2
16

Thuro, K., Plinninger, R.J. (1999), “Roadheader excavation performance-geological and geotechnical influences”, Proceedings of the 9th ISRM Congress, Theme 3: Rock Dynamics and Tectonophysics/Rock Cutting and Drilling, Paris, pp. 1241-1244.

Information
  • Publisher :Korean Tunneling and Underground Space Association
  • Publisher(Ko) :한국터널지하공간학회
  • Journal Title :Journal of Korean Tunnelling and Underground Space Association
  • Journal Title(Ko) :한국터널지하공간학회 논문집
  • Volume : 27
  • No :6
  • Pages :539-553
  • Received Date : 2025-10-02
  • Revised Date : 2025-11-07
  • Accepted Date : 2025-11-10
  • DOI :https://doi.org/10.9711/KTAJ.2025.27.6.539
Journal Informaiton Journal of Korean Tunnelling and Underground Space Association Journal of Korean Tunnelling and Underground Space Association
Online Submission & Review System
  • NRF
  • KOFST
  • KISTI Current Status
  • KISTI Cited-by
  • crosscheck
  • orcid
  • open access
  • ccl
Journal Informaiton Journal Informaiton - close