• Geomechanics and Engineering
• /
• 제38권6호
• /
• pp.633-645
• /
• 2024

Disc cutters, used as excavation tools for rocks in a Tunnel Boring Machine (TBM), naturally undergo wear during the tunneling process, involving crushing and cutting through the ground, leading to various wear types. When disc cutters reach their wear limits, they must be replaced at the appropriate time to ensure efficient excavation. General disc cutter life prediction models are typically used during the design phase to predict the total required quantity and replacement locations for construction. However, disc cutters are replaced more frequently during tunneling than initially planned. Unpredictable disc cutter replacements can easily diminish tunneling efficiency, and abnormal wear is a common cause during tunneling in complex ground conditions. This study aims to overcome the limitations of existing disc cutter life prediction models by utilizing machine data generated during tunneling to predict disc cutter wear patterns and determine the need for replacements in real-time. Artificial intelligence classification algorithms, including K-nearest Neighbors (KNN), Support Vector Machine (SVM), Decision Tree (DT), and Stacking, are employed to assess the need for disc cutter replacement. Binary classification models are developed to predict which disc cutters require replacement, while multi-class classification models are fine-tuned to identify three categories: no replacement required, replacement due to normal wear, and replacement due to abnormal wear during tunneling. The performance of these models is thoroughly assessed, demonstrating that the proposed approach effectively manages disc cutter wear and replacements in shield TBM tunnel projects.

• 한국터널지하공간학회 논문집
• /
• 제26권3호
• /
• pp.281-301
• /
• 2024

송전선로 지중화 사업의 일환인 전력구 터널은 쉴드TBM 공법에 의해 건설된다. 쉴드TBM 구성요소 중 디스크커터는 암반을 파쇄하는 중요한 역할을 수행한다. 마모한계에 도달하거나 편마모와 같은 파손이 발생함에 따라 적절한 교체가 이루어져야 효율적인 터널 공사가 가능하다. 본 연구에서는 실시간으로 측정된 디스크커터의 마모량과 회전수를 기반으로 디스크커터의 마모상태를 판별하기 위한 딥러닝 알고리즘 개발을 수행하였다. 실대형 굴진시험 결과를 통해 디스크 커터의 마모상태에 따라 측정데이터가 상이하게 획득되는 것을 확인하였다. 합성곱신경망 모델을 기반으로 실시간 측정데이터를 활용하여 디스크커터의 마모특성을 판별할 수 있는 알고리즘을 개발하였다. 합성곱신경망의 필터를 통해 데이터의 분포 특성을 학습할 수 있고, 이러한 패턴 특징을 통해 균등마모와 편마모를 분류할 수 있는 모델의 성능을 확인하였다.