이승원 교수

Advances in tunnel boring machines (TBM) have leveraged applied artificial intelligence to promote sustainable and automatic tunneling construction. This paper highlights the significance of AI-based management subsystems for automatic TBM operations and presents recent key contributions in the field by identifying three key parallel subsystems: modeling, monitoring, and control. Moreover, each subsystem is evaluated from the standpoint of practical implications. In this context, specific challe

Reliable estimates of peak particle velocity (PPV) from blasting-induced vibrations at a construction site play a crucial role in minimizing damage to nearby structures and maximizing blasting efficiency. However, reliably estimating PPV can be challenging due to complex connections between PPV and influential factors such as ground conditions. While many efforts have been made to estimate PPV reliably, discrepancies remain between measured and predicted PPVs. Here, we analyzed various methods f

The prediction of settlement during tunneling presents multiple challenges, as such settlement is governed by not only the local geology but also construction methods and practices, such as tunnel boring machine (TBM). To avoid undesirable settlement, engineers must predict the settlement under given conditions. The widely used methods are analytical solutions, empirical solutions, and numerical solutions. Analytical or empirical solutions, however, have limitations, which cannot incorporate the

The abrasiveness of rocks significantly influences the wear endured by excavation tools in tunnel boring machines (TBMs). In slurry shield TBMs, wear occurs not only in excavation tools but also in discharge pipes and pumps of slurry transport systems. To explore this phenomenon, this study investigated the effect of rock abrasiveness on the wear of both disc cutters and slurry discharge pipes in slurry shield TBMs. The radial wear of disc cutters and the thickness of slurry discharge pipes were

Subsidence at abandoned mines sometimes causes destruction of local areas and casualties. This paper proposes a mine subsidence risk index and establishes a subsidence risk grade based on two separate analyses of A and B to predict the occurrence of subsidence at an abandoned mine. For the analyses, 227 locations were ultimately selected at 15 abandoned coal mines and 22 abandoned mines of other types (i.e., gold, silver, and metal mines). Analysis A predicts whether subsidence is likely using a

Experiments with gypsum as a model rock material were conducted to investigate the characteristics of crack growth under monotonic and cyclic loading. The specimens had two pre-existing flaws that were placed at different inclination angle, spacing and continuity. Tensile or wing cracks and secondary or shear cracks were observed in both the monotonic and cyclic tests. Wing cracks or tensile cracks initiated at (or near) the tips of flaws and grew parallel to the loading direction. Secondary or

Drill and blast is the most cost-effective excavation method for underground construction, however, vibration and noise, induced by blasting, have been consistently reported as problems. Cut blasting has been widely employed to reduce the blast-induced problems during underground excavation. We propose that the large hole boring method using the state-of-the-art MSP (Multi-setting smart-investigation of the ground and pre-large hole boring) machine (“MSP method”) can efficiently improve vibratio

Cut blasting is one of the most essential processes to reduce blast-induced vibration in tunnel blasting. The long and large-diameter uncharged hole boring (LLB) method is an example of one of the cut blasting methods, which utilizes large-diameter uncharged holes drilled in the tunnel face. In this study, blasting simulations were performed to analyze its blasting mechanism, and the LLB method and the traditional burn-cut method were simulated to compare their blasting efficiency. A 3D numerica

Nano-enabled sensing is an expanding interdisciplinary field of emerging science with dynamic multifunctional detecting capabilities, equipped with a wide range of multi-faceted nanomaterial having diverse dimensions and composition. They have proven to be highly robust, sensitive, and useful diagnostic tools ranging from advanced industrial processes to ordinary consumer products. As no single nanomaterial has proved to be unparalleled, recent years has witnessed a large number of nanomaterial-

Pre-investigation of geological conditions beyond the excavation face is crucial for assessment of safety and design in underground construction. This study developed a boring data monitoring system equipped for a multi-setting smart-investigation of the ground and pre-large hole boring (MSP) machine that typically drills a horizontal distance of 50 m to reduce blast-induced vibration. The monitoring system was applied to the tunnel construction site, which drills 40 m with the MSP method to inv

This study introduces a real-time unsupervised monitoring framework for monitoring sinkhole formation events during earth pressure balance (EPB) shield tunneling operations. A feature extractor (FE) is constructed by coupling variational Autoencoders structure with convolutional neural network layers (VAE-CNN) to manage the complexity of EPB operational data, including non-linearity and temporal dependencies. The monitoring framework consists of two main phases: offline modeling and online monit

During tunnel construction, the ground properties, initially evaluated, are continuously assessed and verified through back analysis. This procedure generally requires many numerical analyses, so a metamodel based on artificial neural networks has been used to reduce the number of analyses. More datasets can be used to create more reliable metamodels. However, there are no established rules regarding the optimum number of datasets for a reliable metamodel. Metamodels predicting the vertical disp