Abstract
Existing indicators of excavation efficiency often rely on sieve analysis of rock debris generated during
excavation, which may make it challenging to respond promptly to efficiency changes during mechanical
excavation. This study proposed the chip size index (CSI) as a simplified and immediate indicator of excavation
efficiency for drag picks. Rock cutting tests were conducted on two limestone samples using conical picks at various
cutting depths and line spacings. The generated rock debris was subjected to sieve analysis to obtain traditional
excavation efficiency indicators. Results showed that these indicators increased as specific energy (SE) decreased and
formed strong power-law relationships with the coarseness index (CI). Increasing the cutting depth and line spacing
also led to higher values of the indicators, which reached their maximum at the optimal ratio of line spacing to cutting
depth (s/d = 3–4.5), where SE was minimized (32.48–127.59 MJ/m3 Similarly, CSI increased as SE decreased and
exhibited a strong power-law relationship with CI. Furthermore, as cutting depth and spacing increased, CSI rose,
ranging from 11.87 to 62.33 and reaching its peak at the same optimal s/d ratio. Further validation was performed
using published linear cutting test datasets for drag tools obtained under comparable cutting configurations. These
independent datasets confirmed the power law relationship between SE and CSI, with average coefficients of
determination of 0.786 for conical picks and 0.619 for chisel picks. The proposed CSI may be a practical tool for
monitoring and optimizing mechanical excavation operations without the need for sieve analysis of rock debris.
Key Words
chip size index ; conical pick; excavation efficiency; mechanical excavation; rock cutting
Address
Ji-seok Yun: Department of Geotechnical Engineering Research, Korea Institute of Civil Engineering and Building
Technology, 283 Goyangdae-ro, Ilsanseo-gu, Goyang-si, 10223, South Korea
Han-eol Kim: Department of Geotechnical Engineering Research, Korea Institute of Civil Engineering and Building
Technology, 283 Goyangdae-ro, Ilsanseo-gu, Goyang-si, 10223, South Korea;
Underground Safety Evaluation Center, Korea Expressway Corporation Research Institute,
24, Dongtansunhwan-daero 17-gil, Hwaseong-si, 18489, South Korea
Abstract
This study investigates the mineralogical and microstructural changes of bentonite treated with dune sand
(DS) and recycled tire rubber (RTR), with particular emphasis on reducing the free swell strain of expansive soils. A
comprehensive experimental program was conducted, including one dimensional free-swell tests, X-ray diffraction
(XRD), and scanning electron microscopy (SEM). The results indicate that partial replacement of bentonite with DS
and RTR significantly reduces both the magnitude and rate of free swell strain. The optimum mixture, consisting of
5% RTR and 10% DS, exhibited the lowest swell strain (8.9%) along with a dense and well-integrated
microstructure characterized by reduced pore connectivity. XRD analysis revealed increased quartz crystallinity and
decreased montmorillonite activity, while SEM observations confirmed enhanced particle interlocking and matrix
densification. These findings demonstrate a combined stabilization mechanism, where DS improves granular rigidity
and RTR provides elastic confinement, leading to enhanced dimensional stability. The proposed DS–RTR
stabilization approach offers a sustainable and effective solution for mitigating swelling in expansive soils used in
subgrade and embankment applications.
Address
Belgacem Choungache and Rebih Zaitri: Department of Civil Engineering, Faculty of Technology, University of Djelfa, 17000, Algeria
Abdelhalim Bensaada: Laboratory of Civil Engineering and Protection of the Environment (LCEPE), Department of Civil Engineering,
Faculty of Technology, University of Medea, Algeria
Naas Allout: Laboratory of Civil Engineering and Sustainable Development, Department of Civil Engineering,
Faculty of Technology, University of Djelfa, 17000, Algeria
Abstract
Surface morphology significantly influences the shear properties of natural rock fractures under the
constant normal stiffness (CNS) boundary conditions, typically quantified using various roughness indexes.
Currently, it has not been verified whether rock fractures with the identical roughness index necessarily have the
same shear characteristics, introducing uncertainty in rock mass engineering practice. To address this issue, this study
first introduces several fracture profiles having identical roughness index o*
max/(C+1) but differing geometries.
Subsequently, numerical fracture specimens with identical roughness index were established by Discrete Element
Method (DEM), and CNS shear tests were carried out considering varying roughness grades and normal stiffness
(Kn). The test results were analyzed to explore the differences in shear mechanical characteristics of rock fractures
having the identical roughness index, such as stress, deformation and failure. Additionally, the stress features of local
asperities on fractures were examined to elucidate the role of roughness in resisting external loads. It was found that
local asperity distribution is an important factor contributing to the discrete shear behavior of rough rock fractures,
recommending its inclusion in roughness evaluation methods.
Key Words
CNS condition; DEM; rock fracture; roughness grade; shear properties
Address
Jiuyang Huan: College of Architectural Engineering, Yangzhou Polytechnic Institute, Yangzhou 225100, China;
State Key Laboratory of Eco-hydraulics in Northwest Arid Region, Xi
Abstract
Liquefaction-induced ground damage remains a critical challenge in seismically active regions,
particularly following large-magnitude earthquakes. While conventional liquefaction assessments are typically
limited to susceptibility evaluation or single-index analysis, integrated and scenario-based prediction of depthdependent
liquefaction hazards remains insufficiently explored. This study presents a unified machine learning–based
framework for the simultaneous prediction of the Liquefaction Potential Index (LPI) and Liquefaction Severity Index
(LSI), addressing an important gap in existing liquefaction modeling studies. A comprehensive dataset comprising
320 borehole locations (160 liquefaction-observed and 160 non-observed sites) was analyzed under five earthquake
scenarios with moment magnitudes (Mw) ranging from 6.0 to 8.0 and corresponding peak ground acceleration (PGA)
values between 0.2 g and 0.6 g. Geotechnical and seismic input parameters—including groundwater level (GWL),
average shear wave velocity (Vs30), Standard Penetration Test (SPT) values, cyclic resistance ratio (CRR), cyclic
stress ratio (CSR), effective stress (o), Mw, and PGA—were used to compute LPI and LSI based on established
methodologies. Predictive modeling was performed using an Artificial Neural Network (ANN) based on the
Multilayer Perceptron (MLP) architecture and four ensemble learning techniques: Additive Regression, Bagging,
Stacking, and Voting. Model performance was evaluated using 10-fold cross-validation and multiple statistical
metrics, including the coefficient of determination (R2), RMSE, MAE, RAE, P/R ratio, and ANOVA. Among all
models, Additive Regression exhibited superior predictive performance, achieving R2 values of 0.97 for LPI and 0.98
for LSI, and consistently outperforming the other approaches. Taylor diagram and error distribution analyses further
confirmed the robustness and reliability of the proposed framework. The results demonstrate that the proposed
approach provides a computationally efficient and engineering-relevant tool for scenario-based regional liquefaction
hazard assessment, supporting rapid post-earthquake screening and informed decision-making in earthquake-prone
areas
Key Words
artificial neural network (ANN); liquefaction potential index (LPI); liquefaction severity index
(LSI); meta ensemble learning
Address
Mitat Öztürk: Osmaniye Korkut Ata University, Faculty of Engineering and Natural Sciences,
Department of Civil Engineering, Osmaniye, Türkiye;
Present Adress: Kahramanmaraş Sütçü İmam University, Faculty of Engineering and Architecture,
Department of Civil Engineering, Kahramanmaraş, Türkiye
Yakup Önal: Osmaniye Korkut Ata University, Faculty of Engineering and Natural Sciences,
Department of Civil Engineering, Osmaniye, Türkiye;
Present Adress: Kilis 7 Aralik University, Faculty of Engineering and Architecture,
Department of Civil Engineering, Kilis, Türkiye;
FAYRISE Engineering Technology Industry Trade Ltd., Technology Development Zones, Sakarya University,
Sakarya, 54050, Türkiye
Abstract
Soil liquefaction-induced settlement poses a major risk to infrastructure in earthquake-prone regions. This
study introduces a hybrid deep learning model, CNN-BiLSTM-AM, that combines convolutional and bidirectional
long short-term memory networks with an attention mechanism to improve the prediction of liquefaction-induced
settlement using Standard Penetration Test (SPT) data. The model uses key input features such as depth (m), unit
weight (kN/m3), corrected SPT-N (N1(60)) values, and cyclic stress ratio (CSR). These parameters reflect critical soil
properties and seismic loading conditions. Actual vs. predicted graphs, and performance metrics including R2, MAE,
RMSE, and MSE were utilized to evaluate the proposed model. Comparative analysis confirms the robustness of the
CNN-BiLSTM-AM model showed the highest accuracy of 94.69%. Sensitivity analysis confirmed that N1(60) as
the most crucial input feature, aligning with geotechnical understanding of soil resistance to seismic deformation. The
model not only demonstrates high predictive accuracy but also reflects practical engineering relationships, offering a
valuable tool for seismic design and risk mitigation. This work lays the groundwork for further investigation by
emphasizing the potential and difficulties of utilizing SPT dataset to forecast soil liquefaction-induced settlement.
Key Words
attention mechanism; bidirectional long short-term memory; convolutional neural network;
soil liquefaction; standard penetration test
Address
Pravallika Chithuloori, Jin-Man Kim: Soil Mechanics and Dynamics Engineering Laboratory, Department of Civil and Environmental Engineering,
Pusan National University, Busandaehak-ro 63beon-gil, Geumjeong-gu, Busan, 46241, South Korea
Abstract
A plane elastic-plastic problem of stress distribution in a rock mass weakened by a circular working is
considered. It is assumed that V.V. Sokolovsky's plasticity condition is satisfied. The stress level in the rock mass is
such that the working is entirely covered by the plastic zone. It is assumed that crack initiation occurs in the elastic
zone of the rock mass during loading. Perturbation methods and theories of analytical functions are used. The
obtained system of equations makes it possible to determine the critical value of external load, the location and size of
the pre-fracture zone for the state of limit equilibrium.
Key Words
circular working; crack formation; elastic-plastic boundary; rock mass; Sokolovsky's plasticity
condition
Address
Vagif M. Mirsalimov, Fuad F. Hasanov: Department of Mechanics, Azerbaijan Technical University, Baku, H. Javid av, 25, AZ1073, Azerbaijan
Nailya M. Kalantarly: Department of Sports management and communication, Azerbaijan Sports Academy,
Baku, 98, AZ1072, Azerbaijan
