• Geomechanics and Engineering
• /
• v.37 no.1
• /
• pp.49-64
• /
• 2024

Rocks undergoing repeated loading and unloading over an extended period, such as due to earthquakes, human excavation, and blasting, may result in the gradual accumulation of stress and deformation within the rock mass, eventually reaching an unstable state. In this study, a CNN-CCM is proposed to address the mechanical behavior. The structure and hyperparameters of CNN-CCM include Conv2D layers × 5; Max pooling2D layers × 4; Dense layers × 4; learning rate=0.001; Epoch=50; Batch size=64; Dropout=0.5. Training and validation data for deep learning include 71 rock samples and 122,152 data points. The AI Rock Constitutive Model learned by CNN-CCM can predict strain values(ε₁) using Mass (M), Axial stress (σ₁), Density (ρ), Cyclic number (N), Confining pressure (σ₃), and Young's modulus (E). Five evaluation indicators R², MAPE, RMSE, MSE, and MAE yield respective values of 0.929, 16.44%, 0.954, 0.913, and 0.542, illustrating good predictive performance and generalization ability of model. Finally, interpreting the AI Rock Constitutive Model using the SHAP explaining method reveals that feature importance follows the order N > M > σ₁ > E > ρ > σ₃.Positive SHAP values indicate positive effects on predicting strain ε₁ for N, M, σ₁, and σ₃, while negative SHAP values have negative effects. For E, a positive value has a negative effect on predicting strain ε₁, consistent with the influence patterns of conventional physical rock constitutive equations. The present study offers a novel approach to the investigation of the mechanical constitutive model of rocks under cyclic loading and unloading conditions.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.10 no.2
• /
• pp.105-118
• /
• 2008

Shotcrete is one of the main support materials in tunnelling. Its bonding state on excavated rock surfaces controls the safety of the tunnel: De-bonding of shotcrete from an excavated surface decreases the safety of the tunnel. Meanwhile, the bonding state of shotcrete is affected by blasting during excavation at tunnel face as well as bench cut. Generally, the bonding state of shotcrete can be classified as void, de-bonded, or fully bonded. In this study, the state of the back-surface of shotcrete is investigated using impact-echo (IE) techniques. Numerical simulation of IE technique is performed with ABAQUS. Signals obtained from the IE simulations were analyzed at time, frequency, and time-frequency domains, respectively. Using an integrated active signal processing technique coupled with a Short-Time Fourier Transform (STFT) analysis, the bonding state of the shotcrete can be evaluated accurately. As the bonding state worsens, the amplitude of the first peak past the maximum amplitude in the time domain waveform and the maximum energy of the autospectral density are increasing. The resonance frequency becomes detectable and calculable and the contour in time-frequency domain has a long tail parallel to the time axis. Signal characteristics with respect to ground condition were obtained in case of fully bonded condition. As the ground condition worsens, the length of a long tail parallel to the time axis is lengthened and the contour is located in low frequency range under 10 kHz.

• The Journal of Engineering Geology
• /
• v.5 no.1
• /
• pp.1-20
• /
• 1995

A train overturn accident occurred on March 1993 in the Gupo area, northern part of Pusan, unfortunately had taken a heavy toll of lives and caused a great loss of property as well. The reasons for the subsidence of the basement under the railroads, which presumed to be the main cause of the accident, have been investigated from many different angles, including conventional geotechnical investigation methods. The deduced nuin reasons of the subsidence were: 1. blasting for tunnel excavation (NATM) at about 39 meter under the railroads, and 2. unexpected change of bedrock conditions along the direction of tunnel. But this accident was derived nrranlv from the lack of geological and geotechnical information under railroad area because it was impossible to drill beneath the railroads. This paper introduces a new geophysical survey techniqueseisrnic geotomography, and shows some results of the method applying to investigate the underground structure of the accident area. This method not only overcomes the unfavourable environment which many conventional investigation methods cannot face, but produces an image of underground structure with high resolution. Furthermore, the outputs from geotomogaphic analysis could provide very valuable in-situ basic parameters (like seismic velocities, elastic moduli, etc.) which is essential to the design and construction.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.24 no.5
• /
• pp.431-449
• /
• 2022

As many tunnels generally have been constructed, various experiences and techniques have been accumulated for tunnel design as well as tunnel construction. Hence, there are not a few cases that, for some usual tunnel design works, it is sufficient to perform the design by only modifying or supplementing previous similar design cases unless a tunnel has a unique structure or in geological conditions. In particular, for a tunnel blast design, it is reasonable to refer to previous similar design cases because the blast design in the stage of design is a preliminary design, considering that it is general to perform additional blast design through test blasts prior to the start of tunnel excavation. Meanwhile, entering the industry 4.0 era, artificial intelligence (AI) of which availability is surging across whole industry sector is broadly utilized to tunnel and blasting. For a drill and blast tunnel, AI is mainly applied for the estimation of blast vibration and rock mass classification, etc. however, there are few cases where it is applied to blast pattern design. Thus, this study attempts to automate tunnel blast design by means of machine learning, a branch of artificial intelligence. For this, the data related to a blast design was collected from 25 tunnel design reports for learning as well as 2 additional reports for the test, and from which 4 design parameters, i.e., rock mass class, road type and cross sectional area of upper section as well as bench section as input data as well as16 design elements, i.e., blast cut type, specific charge, the number of drill holes, and spacing and burden for each blast hole group, etc. as output. Based on this design data, three machine learning models, i.e., XGBoost, ANN, SVM, were tested and XGBoost was chosen as the best model and the results show a generally similar trend to an actual design when assumed design parameters were input. It is not enough yet to perform the whole blast design using the results from this study, however, it is planned that additional studies will be carried out to make it possible to put it to practical use after collecting more sufficient blast design data and supplementing detailed machine learning processes.

• Journal of the Korean Society for Railway
• /
• v.20 no.5
• /
• pp.668-682
• /
• 2017

Alignments of railways recently constructed in Korea have been straightened due to the advent of high-speed rail, which means increasing the numbers of tunnels and bridges. Overbreak during tunnel construction may be unavoidable, and is very influential on overall stability. Over-excavation in tunneling is also one of the most important factors in construction costs. Overbreak problems around crown areas have decreased with improvements of excavation methods, but overbreak problems around bottom areas have not decreased because those areas are not very influential on tunnel stability compared with crown areas. The filling costs of 10 cm thickness of overbreak at the bottom of a tunnel are covered under construction costs by Korea Railway Authority regulations, but filling costs for more than the covered thickness are considered losses of construction cost. The filling material for overbreak bottoms of tunnels should be concrete, but concrete and mixed granular materials with fractured rock are also used for some sites. Tunnels in which granular materials with fractured rock are used may have a discontinuous section under the concrete slab track. The discontinuous section influences the propagation of waves generated from train operation. When the bottom of a tunnel is filled with only concrete material, the bottom of the tunnel can be considered as a continuous section, in which the waves generated from a train may propagate without reflection waves. However, a discontinuous section filled with mixed granular materials may reflect waves, which can cause resonance of vibration. The filled materials and vibration propagation characteristics are studied in this research. Tunnel bottom filling materials that have ratios of granular material to concrete of 5.0 %, 11.5 %, and 18.0 % are investigated. Samples were made and tested to determine their material properties. Static numerical analyses were performed using the FEM program under train operation load; test results were found to satisfy the stability requirements. However, dynamic analysis results show that some mixed ratios may generate resonance vibration from train operation at certain speeds.