• 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.

• 산업기술연구
• /
• 제25권B호
• /
• pp.55-62
• /
• 2005

This paper is the results of experimental and numerical works on analyzing the geotechnical engineering behavior and characteristics of excavated clay slope formed by the method of excavated replacement which is one of treatments in soft soil ground. For the centrifuge model tests, models of excavated clay slope were prepared by remolding the marine clayey soil sampled from the field. Tests were performed with changing the slope to investigate the behavior of them. On the other hand, numerical analyses were carried out to analyze the change of safety factor against instability of slope with time. Changes of pore water pressure, shear strength and displacement were also investigated. As results of centrifuge model tests with slopes of 1:1.5 and 1:3 using the confining body of simulating the effect of excavation, for the case of 1:1.5, slope failure occurred right after remove the confining body whereas relatively small displacements within the range of 3.2mm, implying to maintain the stability of slope, were observed for the case of 1:3 slope. From the results of numerical analyses using the software of PLAXIS to investigate the stability of slope after excavation, the minimum safety factor against slope failure was 1.28 for the case of 1:3 slope. The further researches in the future are required with considerations of build up of static pore water pressures during acceleration of centrifuge, depth of excavation influencing the behavior of the slope and permeability of the slope since excavation of the slope was not simulated well resulted from the limitations of apparatus at the stage of excavation during the centrifuge tests.

• 한국터널지하공간학회 논문집
• /
• 제22권5호
• /
• pp.575-589
• /
• 2020

최근 국내 터널에서 지속적으로 증가하고 있는 쉴드 TBM 공법의 주된 굴착도구는 디스크 커터로 굴진과정에서 자연스럽게 마모가 발생하고 이는 TBM의 굴진효능을 현저히 저하시키기 때문에 적절한 시기에 교체하는 것이 중요하다. 따라서 본 연구에서는 디스크 커터 교체 여부를 판단할 수 있는 예측 모델을 머신러닝 기법을 사용한 방법으로 제안하였다. 이를 위해 국내 기 시공된 쉴드 TBM 현장의 데이터 중 디스크 커터 소모에 상관성이 높은 굴진데이터(TBM 기계데이터, 지반정보 등)와 교체이력을 입력데이터로 사용하여 다양한 머신러닝 분류기법 중 서포트 벡터 머신, 최근접이웃 알고리즘, 의사결정트리 알고리즘을 사용하여 최적의 예측 모델을 구축하고 모델의 성능을 평가하기 위하여 분류성능평가 지표로 비교 분석하였다.

• Geomechanics and Engineering
• /
• 제29권3호
• /
• pp.249-258
• /
• 2022

A disc cutter is an excavation tool on a tunnel boring machine (TBM) cutterhead; it crushes and cuts rock mass while the machine excavates using the cutterhead's rotational movement. Disc cutter wear occurs naturally. Thus, along with the management of downtime and excavation efficiency, abrasioned disc cutters need to be replaced at the proper time; otherwise, the construction period could be delayed and the cost could increase. The most common prediction models for TBM performance and for the disc cutter lifetime have been proposed by the Colorado School of Mines and Norwegian University of Science and Technology. However, design parameters of existing models do not well correspond to the field values when a TBM encounters complex and difficult ground conditions in the field. Thus, this study proposes a series of machine learning models to predict the disc cutter lifetime of a shield TBM using the excavation (machine) data during operation which is response to the rock mass. This study utilizes five different machine learning techniques: four types of classification models (i.e., K-Nearest Neighbors (KNN), Support Vector Machine, Decision Tree, and Staking Ensemble Model) and one artificial neural network (ANN) model. The KNN model was found to be the best model among the four classification models, affording the highest recall of 81%. The ANN model also predicted the wear rate of disc cutters reasonably well.

• Advances in concrete construction
• /
• 제13권6호
• /
• pp.461-470
• /
• 2022

Solid waste management is of great concern in today's world. An enormous amount of waste is generated from various industrial activities. Concrete production utilizing some of the potential waste materials will add to the benefit of society. These benefits will include reduction of landfill burden, improved air quality, riverbed protection due to excessive sand excavation, economical concrete production and much more. This study aims to utilize waste granite powder (GP) originating from granite industries as a sand replacement in concrete. Fine GP was collected in the form of slurry from different granite cutting industries. In this study, GP was added in an interval of ten percent as 10%, 20%, 30%, 40% and 50% by weight of sand in concrete. Mechanical assets; compressive strength, flexural strength and splitting tensile strength were prominent for control and blended mixes. Modulus of elasticity (MoE) and abrasion tests were also performed on control and blended specimens of concrete. To provide a comprehensive clarification for enhanced performance of GP prepared concrete samples, scanning electron microscopy (SEM) and X-ray diffraction (XRD) were performed. Results indicate that 30% replacement of sand by weight with GP enhances the mechanical assets of concrete and even the results obtained for 50% replacement are also acceptable. Comprehensive analysis through SEM and XRD for 30% replacement was better than control one. The performance of GP added to concrete in terms of abrasion and modulus of elasticity was far better than the control mix. A significant outcome shows the appropriateness of granite fines to produce sustainable and environmentally friendly concrete.

• 상하수도학회지
• /
• 제16권6호
• /
• pp.686-699
• /
• 2002

The purpose of this study is to estimate deterioration factors and weighting factors in pipe network which each local self-governments takes rehabilitation and replacement work present time. Deterioration factors in pipe network are able to effected of specific province or location related with water supply. Most of water supply pipes are laid under the ground, it is hard to quantify deterioration degree of water system. Moreover, the timing and economic limitation and insufficient information on the spot survey gives a difficulty to look over how old water supply system is. Accordingly, this study collects and analyses five data as the laying environment, visual analysis, analysis of soil contents, analysis of pipe material, and questionary survey data in water pipe of A city. The deterioration factor estimates 14 factors with excavation and experimental analysis and 9 factors without excavation and experimental analysis. Also, the weighting factors are estimated by using the multiple linear regressions and the linear programming. The estimated deterioration factor and weighting results are compared the analysis result of visual, pipe material, and soil contents with the Probabilistic Neural Network Model. Consequently, the model results of estimated 9 factors in this study and 14 factors show the 1-2% difference. The result show that the proposed model could be used to decide the deterioration condition of pipe line with real excavation and experimental analysis.

• 한국터널지하공간학회 논문집
• /
• 제24권1호
• /
• pp.57-78
• /
• 2022

TBM의 굴착효율을 높이는 가장 중요한 인자인 디스크커터와 커터비트는 커터헤드 설계 및 시공 시 핵심요소로 지반조건에 맞는 디스크커터의 배치, 간격, 개수, 크기, 재질 등은 TBM 공사의 성패를 좌우한다. 또한, 디스크커터는 대표적인 소모성 부품으로 교체횟수에 대한 정확한 예측이 수반되지 않으면, 공사비는 물론 공사에 막대한 지장을 초래 할 수 있다. 이에 본 연구에서는 대구경 이수식 쉴드TBM 현장에 대하여 설계 시 산정된 디스크커터의 교체횟수와 실제 시공 시 발생한 디스크커터의 마모깊이 및 교체위치에 대하여 현장데이터를 분석하여 비교·연구하였다. 정량적인 비교를 위하여 일정한 굴진데이터를 나타내는 구간에서 지반에 따라 풍화토/풍화암, 연암, 경암으로 나누어 구분하였으며, 디스크커터의 위치에 따라 동심원의 궤적이 다르므로 위치에 따라 비교분석 하였다.

• 한국터널지하공간학회 논문집
• /
• 제21권5호
• /
• pp.641-656
• /
• 2019

본 연구에서는 쉴드 TBM (Tunnel Boring Machine) 터널 디스크 커터의 적절한 교체 시기를 예측하기 위한 방법으로 머신러닝 기법을 사용한 방법을 제안하였으며, 이를 위해 국내 기 시공된 쉴드 TBM 현장의 데이터를 이용하여 다양한 머신러닝 알고리즘 중 SVM (Support Vector Machine)을 이용하여 예측 모델을 구축하고 그 성능을 평가하였다. 지반 조건별 디스크 커터의 마모와 높은 상관성을 갖는 TBM 기계 데이터와 디스크 커터 교체 이력을 분류하고, 이들을 SVM의 변수로 사용하여 3종류의 분류 함수를 적용하여 각각 학습을 한 후 예측을 수행한 결과, 각 지반 조건에 대해서 3종류의 SVM 분류 함수 중 전체적으로 RBF (Radial Basis Function) SVM의 예측성능이 가장 우수하며(평균적으로 80%의 정확도, 10% 오분류율), 지반 조건별로 구분 시 디스크 커터 교체 데이터의 수가 많을수록 예측 결과가 좋은 것으로 나타났다. 향후 많은 데이터를 축적하고 이를 모두 활용하여 학습모델을 지속적으로 발전시켜 나간다면 이와 같은 디스크 커터 교환주기를 예측하기 위한 머신러닝 기법의 실무 적용성이 매우 클 것으로 기대한다.

• 한국해양공학회지
• /
• 제20권5호
• /
• pp.49-56
• /
• 2006

In this thesis, centrifuge model experiments and numerical analyses were carried out to investigate the behavior of an excavated slope in soft clay ground. Centrifuge model tests were performed with various slopes for the excavated ground, such as 1:1.5 and 1:2. Pore pressuresthe model ground were measured to find their effects on the stability of the excavated slope. These experiments showed that the model with 1:2.5 maintained its stability within a short period of time and failed gradually. Therefore, anexcavated slope of soft soil with this slope might maintain stable conditions within a certain time. The mode1 with a 1:3 slope was observed to maintain a very stable condition, showing insignificant deformation in the ground after being excavated. Numerical analyses with PLAXIS, a commerciallyavailable software implemented with the finite element numerical technique, were performed to find the pore pressure distribution within the ground mass and the deformation of the soil. From the results of numerical analysis, a negative pore pressure was developed after the excavation and thus the stability of the slope was maintained. The safety factor for slope failure was found to decrease with time because of the dissipation of negative pore pressure with time.

• 대한토목학회논문집
• /
• 제31권6D호
• /
• pp.839-848
• /
• 2011

TBM(Tunnel Boring Machine) 터널은 굴진 도중 장비의 교체나 개조 등은 불가능하기 때문에 굴진 종료 시까지 투입된 장비로 굴진하여야만 한다. 특히 토압식 쉴드TBM은 막장관찰이 어려우므로 굴진 중에 수집된 자료를 분석하여 지반상태의 변화를 예측하고 이를 시공에 반영하여야한다. 지금까지의 TBM에 대한 연구는 굴착 대상이 되는 지반의 특성에 따른 장비선정 및 굴진속도 예측모델 개발이 주로 이루어져왔다. 그러나 굴착의 주체가 되는 TBM 장비의 굴진자료에 의한 지반상태의 추정 및 운전방법의 개선에 초점을 맞춘 연구는 그리 많이 수행되지 않았다. 본 연구는 토압식 쉴드TBM 시공 사례에서 얻은 굴진자료를 활용하여 투입된 장비의 운전조건에 따른 굴진속도의 변화와 최적 운전조건에 대해 알아보았다. 본 연구의 결과를 요약하면 다음과 같다. 첫째, 커터헤드의 회전속도와 총추력이 굴진속도에 가장 큰 영향을 주며 둘째, 적정한 굴진속도를 위해서는 최적 회전속도를 유지하면서 총추력을 조정하는 것이 좋으며 셋째, 총추력의 증가 추세에 따라 지반조건의 변화에 대한 예측이 가능하여 이에 따라 적절한 운전조건의 변경을 결정할 수 있다.