Answers are grounded in this paper and cite their sources.
The increasing demand for underground infrastructure has expanded the use of Tunnel Boring Machines (TBMs), particularly in hard and abrasive rock formations where disc cutter wear significantly affects penetration rate, operational efficiency, and project cost. This review aims to synthesize current knowledge on the influence of rock mass properties on TBM disc cutter wear and to evaluate the development of wear prediction methodologies, with particular emphasis on Artificial Neural Network (ANN)-based approaches. A systematic literature review was conducted covering classical empirical, analytical, mechanistic, probabilistic, and data-driven models of cutter wear prediction. Studies related to rock mass properties, cutter design, operational parameters, wear mechanisms, and ANN-based prediction techniques were critically analyzed and compared. Key frameworks, including the CSM, NTNU, Gehring, QTBM, and RME models, were evaluated alongside recent machine-learning and deep-learning approaches. The review confirms that rock mass properties such as uniaxial compressive strength (UCS), Cerchar Abrasivity Index (CAI), equivalent quartz content, joint spacing, and rock mass structure are the primary factors governing disc cutter wear. High-strength and highly abrasive rocks are associated with increased wear rates, while appropriate cutter spacing and favorable joint orientations can enhance cutting efficiency. ANN and hybrid machine-learning models generally provide more accurate wear and penetration rate predictions than traditional empirical approaches. However, their effectiveness remains constrained by limited data availability, inconsistent wear metrics, and insufficient integration of real-time monitoring systems. Disc cutter wear is governed by complex interactions among geological, operational, and machine-related factors that cannot be fully captured using conventional empirical models alone. ANN-based approaches show significant potential for improving wear prediction and predictive maintenance capabilities. Future research should focus on standardized wear databases, sensor-based monitoring systems, and physics-informed AI frameworks to enable reliable real-time cutter wear forecasting and optimize TBM performance.
No takes yet. Share an insight, caveat, or question.
Paul et al. (2026) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: