Data-Driven Estimation of Cerchar Abrasivity Index Using Rock Geomechanical and Mineralogical Characteristics
Source abstract
Abstract
The Cerchar Abrasivity Index (CAI) is essential for predicting tool wear in mechanized tunneling and mining, but direct measurement requires time-consuming laboratory procedures. We developed a data-driven framework to estimate CAI from standard geomechanical and mineralogical properties using 193 rock samples covering igneous, metamorphic, and sedimentary lithologies. After evaluating 278 feature combinations with multicollinearity constraints (VIF < 10.0), we identified an optimal four-variable subset: brittleness index B1, density, Equivalent Quartz Content (EQC), and Uniaxial Compressive Strength (UCS), with rock type indicators. CatBoost achieved the best performance (Test R2 = 0.907, RMSE = 0.420), and SHAP analysis confirmed that density and EQC are primary drivers of abrasivity. Additionally, symbolic regression derived an explicit formula using only three variables (density, EQC, B1) without rock type classification (Test R2 = 0.720). The proposed framework offers a practical approach for assessing rock abrasivity at early project stages.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Tunneling and Rock Mechanics · Mineral Processing and Grinding · Rock Mechanics and Modeling
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, Republic of Korea
Department of Energy and Resources Engineering, Kangwon National University, Chuncheon-si 24341, Republic of Korea
Funding
Korea Agency for Infrastructure Technology Advancement
References (45)
Show source-provided references
1. Cerchar abrasivity test and its applications in rock engineering: A review10.1007/s40789-024-00731-8 ↗
2. Effect of geomechanical properties on Cerchar Abrasivity Index (CAI) and its application to TBM tunnelling10.1016/j.tust.2016.02.006 ↗
3. Hard rock TBM cutterhead modeling for design and performance prediction10.1002/geot.200800002 ↗
4. ISRM Suggested Method for Determining the Abrasivity of Rock by the CERCHAR Abrasivity Test10.1007/s00603-013-0518-0 ↗
5. Käsling, H., and Thuro, K. (2010, January 15–18). Determining rock abrasivity in the laboratory. Proceedings of the ISRM EUROCK 2010, Lausanne, Switzerland.
6. Abrasivity Database of Different Genetic Rocks Based on CERCHAR Abrasivity Test10.1038/s41597-024-03470-2 ↗
7. Correlation of equivalent quartz content, Slake durability index and Is50 with Cerchar abrasiveness index for different types of rock10.1016/j.ijrmms.2016.04.003 ↗
8. Heydarian, P., Asef, M.R., Hamidi, J.K., and Talkhablo, M. (2024). The relationship between mechanical properties and mineralogical composition of some sedimentary rocks. Q. J. Eng. Geol. Hydrogeol., 57.10.1144/qjegh2024-069 ↗
9. A study to correlate LCPC rock abrasivity test results with petrographic and geomechanical rock properties10.1144/qjegh2017-112 ↗
10. Correlation of physico-mechanical properties of granitic rocks with Cerchar Abrasivity Index in Turkey10.1016/j.measurement.2016.05.034 ↗
11. Correlation between Cerchar abrasivity index and geotechnical properties of igneous rocks: A comprehensive analysis using machine learning algorithms and interpretative analysis10.1016/j.measurement.2025.118989 ↗
12. Investigation on the relationship among the Cerchar abrasivity index, drilling parameters and physical and mechanical properties of the rock10.1016/j.tust.2021.103907 ↗
13. Abrasivity evaluation for wear prediction of button drill bits using geotechnical rock properties10.1007/s10064-019-01587-y ↗
14. Evaluating the Relationships Between NTNU/SINTEF Drillability Indices with Index Properties and Petrographic Data of Hard Igneous Rocks10.1007/s00603-017-1289-9 ↗
15. Stress dependency of the Cerchar abrasivity index (CAI) and its effects on wear of selected rock cutting tools10.1016/j.tust.2007.05.008 ↗
16. Effects of rock water content on CERCHAR Abrasivity Index
17. Effects of variation in the particle size of the rock abrasion powder and standard rotational speed on the NTNU/SINTEF abrasion value steel test10.1007/s10064-017-1211-4 ↗
18. Investigating the effects of micro-texture and geo-mechanical properties on the abrasiveness of volcanic rocks10.1016/j.enggeo.2017.09.022 ↗
19. Rock brittleness indices and their applications to different fields of rock engineering: A review10.1016/j.jrmge.2020.06.008 ↗
20. Schubert, W. (2004, January 7–9). Wear prediction in hard rock excavation using the CERCHAR Abrasiveness Index (CAI). Proceedings of the EUROCK 2004 and 53rd Geomechanics Colloquium, Salzburg, Austria.
21. Sun, J., Fan, X., Wang, H., Shang, Y., and Sun, C. (2025). New Prediction Model of Rock Cerchar Abrasivity Index Based on Gene Expression Programming. Appl. Sci., 15.10.3390/app152010901 ↗
22. Machine learning-based regression analysis for estimating Cerchar abrasivity index
23. Estimation of Cerchar abrasivity index based on rock strength and petrological characteristics using linear regression and machine learning
24. Prediction of abrasiveness index of some Indian rocks using soft computing methods10.1016/j.measurement.2015.03.009 ↗
25. Modeling of Micro Deval abrasion loss based on some rock properties10.1016/j.jafrearsci.2017.04.006 ↗
26. The correlations between the Cerchar abrasivity index and the geomechanical properties of building stones10.1007/s12517-018-3958-8 ↗
27. Development of a GEP model to assess CERCHAR abrasivity index of rocks based on geomechanical properties
28. The usability of Cerchar abrasivity index for the estimation of mechanical rock properties10.1016/j.ijrmms.2020.104258 ↗
29. Statistical evaluation of CERCHAR Abrasivity Index (CAI) measurement methods and dependence on petrographic and mechanical properties of selected rocks of Pakistan10.1007/s10064-015-0799-5 ↗
30. Determination of Rock Abrasiveness using Cerchar Abrasiveness Test10.7474/TUS.2012.22.4.284 ↗
31. Eide, L.N.R. (2014). TBM Tunnelling at the Stillwater Mine. [Master’s Thesis, Norwegian University of Science and Technology (NTNU)].
32. Macias, F.J. (2016). Hard Rock Tunnel Boring: Performance Predictions and Cutter Life Assessments. [Ph.D. Thesis, Norwegian University of Science and Technology (NTNU)].
33. New Rock Abrasivity Test Method for Tool Life Assessments on Hard Rock Tunnel Boring: The Rolling Indentation Abrasion Test (RIAT)10.1007/s00603-015-0854-3 ↗
34. Prokhorenkova, L., Gusev, G., Vorobev, A., Dorogush, A.V., and Gulin, A. (2018, January 3–8). CatBoost: Unbiased Boosting with Categorical Features. Proceedings of the 32nd International Conference on Neural Information Processing Systems (NeurIPS’18), Montréal, QC, Canada.
35. A Caution Regarding Rules of Thumb for Variance Inflation Factors10.1007/s11135-006-9018-6 ↗
36. (2025, November 10). Ver. 3.1.4. Symbolic Regression Software, Available online: https://turingbotsoftware.com/.
37. Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., Ye, Q., and Liu, T.-Y. (2017, January 4–9). LightGBM: A Highly Efficient Gradient Boosting Decision Tree. Proceedings of the 31st International Conference on Neural Information Processing Systems (NIPS’17), Long Beach, CA, USA.
38. Akiba, T., Sano, S., Yanase, T., Ohta, T., and Koyama, M. (2019, January 4–8). Optuna: A Next-Generation Hyperparameter Optimization Framework. Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (KDD’19), Anchorage, AK, USA.10.1145/3292500.3330701 ↗
39. Lundberg, S.M., and Lee, S.-I. (2017, January 4–9). A Unified Approach to Interpreting Model Predictions. Proceedings of the 31st International Conference on Neural Information Processing Systems (NIPS’17), Long Beach, CA, USA.
40. A Comprehensive Evaluation of Ensemble Machine Learning in Geotechnical Stability Analysis and Explainability10.1007/s10999-023-09679-0 ↗
41. Application of Artificial Intelligence in Geotechnical Engineering: A State-of-the-Art Review10.1016/j.earscirev.2022.103991 ↗
42. AI-Powered Geotechnics: Enhancing Rock Mass Classification for Safer Engineering Practices10.1007/s00603-024-04189-7 ↗
43. A statistical approach for the correlation between Cerchar Abrasivity Index and Uniaxial Compressive Strength of rocks
44. Prediction of TBM Disc Cutter Wear and Penetration Rate in Tunneling Through Hard and Abrasive Rock Using Multi-Layer Shallow Neural Network and Response Surface Methods10.1007/s00603-022-02834-7 ↗
45. Prediction of Abnormal TBM Disc Cutter Wear in Mixed Ground Condition Using Interpretable Machine Learning with Data Augmentation10.1016/j.jrmge.2024.05.027 ↗