• Geomechanics and Engineering
• /
• 제32권4호
• /
• pp.411-426
• /
• 2023

Soft clay is widely distributed in the southeast coastal areas of China. Many large underground structures, such as subway stations and underground pipe corridors, are shallow buried in the soft clay foundation, so the dynamic characteristics of the soft clay must be considered to the seismic design of underground structures. In this paper, the dynamic characteristics of saturated soft clay in Shanghai under the bidirectional excitation for earthquake loading are studied by dynamic triaxial tests, comparing the backbone curve and hysteretic curve of the saturated soft clay under different confining pressures with those under different vibration frequencies. Considering the coupling effects of the confining pressure and the vibration frequency, a fitting model of the maximum dynamic shear modulus was proposed by the multiple linear regression method. The M-D model was used to fit the variations of the dynamic shear modulus ratio with the shear strain. Based on the Chen model and the Park model, the effects of the consolidation confining pressure and the vibration frequency on the damping ratio were studied. The results can provide a reference to the earthquake prevention and disaster reduction in soft clay area.

• Smart Structures and Systems
• /
• 제32권3호
• /
• pp.179-193
• /
• 2023

This study explores an alternative to the existing centralized process for data anomaly detection in modern Internet of Things (IoT)-based structural health monitoring (SHM) systems. An edge intelligence framework is proposed for the early detection and classification of various data anomalies facilitating quality enhancement of acquired data before transmitting to a central system. State-of-the-art deep neural network pruning techniques are investigated and compared aiming to significantly reduce the network size so that it can run efficiently on resource-constrained edge devices such as wireless smart sensors. Further, depthwise separable convolution (DSC) is invoked, the integration of which with advanced structural pruning methods exhibited superior compression capability. Last but not least, quantization-aware training (QAT) is adopted for faster processing and lower memory and power consumption. The proposed edge intelligence framework will eventually lead to reduced network overload and latency. This will enable intelligent self-adaptation strategies to be employed to timely deal with a faulty sensor, minimizing the wasteful use of power, memory, and other resources in wireless smart sensors, increasing efficiency, and reducing maintenance costs for modern smart SHM systems. This study presents a theoretical foundation for the proposed framework, the validation of which through actual field trials is a scope for future work.

• 한국지반공학회:학술대회논문집
• /
• 한국지반공학회 2009년도 춘계 학술발표회
• /
• pp.1210-1224
• /
• 2009

The present paper illustrates the outcome of the monitoring of the consolidation behavior of a soft foundation soil under a large submerged sand embankment. Measurements of settlements and excess pore water pressures showed a good agreement with predictions evaluated using the large strain consolidation theory. Soft soil improvement by means of deep mixing has been optimized. Moreover, the principles and developments of underwater geosynthetics applications are discussed.

• 한국지반공학회:학술대회논문집
• /
• 한국지반공학회 2010년도 추계 학술발표회 3차
• /
• pp.96-103
• /
• 2010

The GK immersed tunnel as a part of the Busan-Geoje Fixed Link Project, introduced the immersed tunnel method into Korea for the first time. This challeging project to be completed in 2010 will open a new era to link oceans of the world with optimized design and safety for future use. The immersed tunnel method would possibly suitable for use in construction of a sub sea tunnel from Korea to Japan and from Korea to China that could potentially be built in the distant future. We hope the techniques learned from the Busan-Geoje Fixed Link Project can be applied to further projects in the near future.

• 산업경영시스템학회지
• /
• 제44권3호
• /
• pp.98-105
• /
• 2021

The sensory stimulation of a cosmetic product has been deemed to be an ancillary aspect until a decade ago. That point of view has drastically changed on different levels in just a decade. Nowadays cosmetic formulators should unavoidably meet the needs of consumers who want sensory satisfaction, although they do not have much time for new product development. The selection of new products from candidate products largely depend on the panel of human sensory experts. As new product development cycle time decreases, the formulators wanted to find systematic tools that are required to filter candidate products into a short list. Traditional statistical analysis on most physical property tests for the products including tribology tests and rheology tests, do not give any sound foundation for filtering candidate products. In this paper, we suggest a deep learning-based analysis method to identify hand cream products by raw electric signals from tribological sliding test. We compare the result of the deep learning-based method using raw data as input with the results of several machine learning-based analysis methods using manually extracted features as input. Among them, ResNet that is a deep learning model proved to be the best method to identify hand cream used in the test. According to our search in the scientific reported papers, this is the first attempt for predicting test cosmetic product with only raw time-series friction data without any manual feature extraction. Automatic product identification capability without manually extracted features can be used to narrow down the list of the newly developed candidate products.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권6호
• /
• pp.1530-1544
• /
• 2023

Data monitoring is an important foundation of modern science. In most cases, the monitoring data is time-series data, which has high application value. The deep learning algorithm has a strong nonlinear fitting capability, which enables the recognition of time series by capturing anomalous information in time series. At present, the research of time series recognition based on deep learning is especially important for data monitoring. Deep learning algorithms require a large amount of data for training. However, abnormal sample is a small sample in time series, which means the number of abnormal time series can seriously affect the accuracy of recognition algorithm because of class imbalance. In order to increase the number of abnormal sample, a data augmentation method called GANBATS (GAN-based Bi-LSTM and Attention for Time Series) is proposed. In GANBATS, Bi-LSTM is introduced to extract the timing features and then transfer features to the generator network of GANBATS.GANBATS also modifies the discriminator network by adding an attention mechanism to achieve global attention for time series. At the end of discriminator, GANBATS is adding averagepooling layer, which merges temporal features to boost the operational efficiency. In this paper, four time series datasets and five data augmentation algorithms are used for comparison experiments. The generated data are measured by PRD(Percent Root Mean Square Difference) and DTW(Dynamic Time Warping). The experimental results show that GANBATS reduces up to 26.22 in PRD metric and 9.45 in DTW metric. In addition, this paper uses different algorithms to reconstruct the datasets and compare them by classification accuracy. The classification accuracy is improved by 6.44%-12.96% on four time series datasets.

• 지질공학
• /
• 제30권2호
• /
• pp.131-145
• /
• 2020

연약지반 상에 도로성토를 시공할 경우 연약지반에는 편재하중이 작용하게 되어 연약지반의 측방유동이나 활동파괴가 종종 발생하게 된다. 본 연구에서는 연약지반에 설치되는 교대말둑기초의 안정성과 말뚝의 거동특성을 파악하는 것이다. 지반의 측방유동으로 인하여 말뚝에 작용하는 수평하중에 대한 기존 연구자들의 연구내용을 파악하고 유한요소해석을 수행하여 교대말뚝기초의 거동특성과 보강효과를 확인하여 측방유동을 받는 교대말뚝기초의 거동을 연구하였다. 압밀도 분석 결과, 압밀 단계에 따라 연약지반 강도증가율에 의해 연약지반의 강도정수인 점착력은 약 1.1~1.8배 증가하였다. 측방유동 검토 결과, 허용수평변위 기준은 3.8 cm를 사용하는 것이 경제적으로나 시공적인 면에서 타당한 것으로 판단되나, 구조물의 중요도 및 지반의 불확실성 등을 고려하여 시공 시 계측을 실시하고 그에 따른 측방유동에 대한 철저한 안전관리가 이루어져야 할 것으로 판단된다.

• 한국지반환경공학회 논문집
• /
• 제23권4호
• /
• pp.29-39
• /
• 2022

도심지의 심각한 교통체증을 해결하기 위해 지하차도, 대심도 지하도로, 광역급행철도 등 대규모 지하공간 개발이 이루어지고 있다. 도심지 지하차도로 건설로 인해 인접한 도시철도 A호선 교각기초 영향 최소화 및 안정성 확보를 위해 흙막이 가시설 보강, 기초 보강 등을 실시하였다. 본 연구에서는 근접도 평가와 함께 지하차도 굴착공사로 인한 안정성을 검토하기 위해 3차원 유한요소해석을 수행하고 수치해석 결과를 통해 보강효과를 정량적으로 분석하였다. 분석결과 기존 보강을 수행한 결과에 비해 겹침 CIP와 지반보강 그라우팅을 실시할 경우 흙막이 가시설 벽체 변위는 50% 이상 저감되었고 기초말뚝의 응력에서도 45% 이상 감소 효과가 있었다. 수치해석결과 분석을 토대로 근접시공 시 보강그라우팅, 가시설 벽체의 강성 증대 등을 통해 가시설 벽체의 변위 발생을 적극적으로 억제해야 함을 확인할 수 있었다.

• 한국지반환경공학회 논문집
• /
• 제9권1호
• /
• pp.41-46
• /
• 2008

본 연구에서는 대심도 연약지반에서 PHC말뚝을 항타관입한 후 일정기간 이후 정재하시험을 통한 하중전이분석을 실시하였다. 하중전이분석에서 단위주면마찰력은 상부의 사질토에서 $7.4t/m^2$, 심도 14m에서 33m의 점성토구간에서는 $6.4t/m^2$, 말뚝선단부가 근입된 사질토에서는 $23.3t/m^2$이 발휘되었으며, 단위선단지지력은 $955t/m^2$으로 실측되었다. 전이된 단위주면마찰력과 국내외에서 알려져 있는 정역학적 지지력산정식과의 비교를 해본 결과 토층별로 가장 적합한 공식을 선정한다면, 사질토의 단위주면마찰력의 경우 한국지반공학회의 구조물기초설계기준 및 해설이, 점성토의 단위주면마찰력의 경우 철도청의 철도설계기준이 가장 실측치에 근접한 값을 나타내었다.

• Geomechanics and Engineering
• /
• 제24권4호
• /
• pp.389-397
• /
• 2021

Pile foundation is a typical form of bridge foundation and viaduct, and large-diameter rock-socketed piles are typically adopted in bridges with long span or high piers. To investigate the effect of a mountain slope with a deep overburden layer on the bearing characteristics of large-diameter rock-socketed piles, four centrifuge model tests of single piles on different slopes (0°, 15°, 30° and 45°) were carried out to investigate the effect of slope on the bearing characteristics of piles. In addition, three pile group tests with different slope (0°, 30° and 45°) were also performed to explore the effect of slope on the bearing characteristics of the pile group. The results of the single pile tests indicate that the slope with a deep overburden layer not only accelerates the drag force of the pile with the increasing slope, but also causes the bending moment to move down owing to the increase in the unsymmetrical pressure around the pile. As the slope increases from 0° to 45°, the drag force of the pile is significantly enlarged and the axial force of the pile reduces to beyond 12%. The position of the maximum bending moment of the pile shifts downward, while the magnitude becomes larger. Meanwhile, the slope results in the reduction in the shaft resistance of the pile, and the maximum value at the front side of the pile is 3.98% less than at its rear side at a 45° slope. The load-sharing ratio of the tip resistance of the pile is increased from 5.49% to 12.02%. The results of the pile group tests show that the increase in the slope enhances the uneven distribution of the pile top reaction and yields a larger bending moment and different settlements on the pile cap, which might cause safety issues to bridge structures.