• Journal of the Institute of Convergence Signal Processing
• /
• v.23 no.4
• /
• pp.249-255
• /
• 2022

Potholes are an important clue to the structural defects of asphalt pavement and cause many casualties and property damage. Therefore, accurate pothole detection is an important task in road surface maintenance. Many machine learning technologies are being introduced for pothole detection, and data preprocessing is required to increase the efficiency of deep learning models. In this paper, we propose a preprocessing method that emphasizes important textures and shapes in pothole datasets. The proposed preprocessing method uses intensity transformation to reduce unnecessary elements of the road and emphasize the texture and shape of the pothole. In addition, the feature of the porthole is detected using Superpixel and Sobel edge detection. Through performance comparison between the proposed preprocessing method and the existing preprocessing method, it is shown that the proposed preprocessing method is a more effective method than the existing method in detecting potholes.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.364-364
• /
• 2021

최근 지구온난화에 따른 홍수 및 가뭄 재해의 피해는 심각해졌다. 그러므로 미래 재해로 인한 피해를 완화시키기 위한 수자원 계획 수립 및 관리의 중요성이 높아지고 있다. 전지구모형(General Circulation Model, GCM)은 기후 변화 연구에서 기후 요인의 변동을 조사하는데 널리 사용되어지고 있다. 본 연구에서는 기후 변화 시나리오를 고려하여 도시유역의 소유역 별 투수성포장 시설의 우선순위를 산정했다. 기후 변화 시나리오에는Representative Concentration Pathway(RCP)와 Shared Socioeconomic Pathway(SSP) 시나리오가 사용되었으며 CMIP5와 CMIP6의 GCM을 고려하였다. GCM을 이용하여 산정된 미래 월 강수량은 분위사상(Quantile Mapping)법의 비모수변환(Non-Parametirc Transformation)법 중 하나인 스플라인 평활(Smoothing Spline) 방법을 사용하여 편이보정 되었다. 연구대상지는 목감천 유역이 선정되었으며, 27개의 소유역에 대해 투수성포장 시설의 우선순위를 산정되었다. 우선순위 산정을 위한 평가 기준들은 Driving force-Pressure-State-Impact-Response(DPSIR) 모형을 기반으로 산정 되었다. 평가기준에 따른 27개의 소유역에 대한 값들은 통계청 및 국가수자원관리종합정보시스템(WAMIS), 편이보정 된 미래 강수량과 Storm Water Management Model(SWMM)을 이용한 유출분석 결과를 통해 도출했다. 평가기준들의 객관적 가중치 산정을 위해 엔트로피 방법을 이용했다. 최종적으로 목감천 소유역 별 투수성포장 시설의 우선순위 산정에는 다기준의사결정기법 중 하나인 TOPSIS방법을 사용했다. 산정 결과 DPSIR 모형을 기반으로 수문학적 요소에 큰 가중치를 부여한 경우 하류보다는 상류 유역에서 높은 우선순위를 확인했으며, 각 요소별 동일한 가중치를 주었을 때 하류 유역에 높은 우선순위가 집중되었다.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.26 no.3D
• /
• pp.435-444
• /
• 2006

This paper investigates the effect of 3-dimensional FE models to evaluation results of jointed concrete pavements which is back-calculated by AREA method. Sensitivity of 3-dimensional FE models developed to simulate the behavior of real jointed concrete pavement are analyzed after compared with 2-dimensional FE models using ILLISLAB. In comparison with 2-dimensional models, influence of concrete contraction under loading plate and base layer on surface deflections is more than that of loading configuration. Deflections at 3-dimensional model between linear and nonlinear temperature distribution under same temperature difference are similar, but noticeable differences are investigated in low elastic modulus of foundations. Dynamic deflections under loading plate are larger than static deflections in high elastic modulus of foundation, but smaller in low elastic modulus. Lower dynamic modulus of subgrade reactions are backcalculated by dynamic deflections than by static deflections. But reverse trend is investigated in the backcalculated elastic modulus of concrete which describes trends of the field backcalculation values calculated from AREA method.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.30 no.4D
• /
• pp.387-393
• /
• 2010

This paper studies static crack growth of asphalt pavement using the extended finite element method (XFEM). To consider nonlinear characteristics of asphalt concrete, a viscoelastic constitutive equation using the Maxwell chain is used. And a linear cohesive crack model is used to regularize the crack. Instead of constructing the viscoelastic constitutive law from the Prony approximation of compliance and retardation time measured experimentally, we use a smooth log-power function which optimally fits experimental data and is infinitely differentiable. The partial moduli of the Maxwell chain from the log-power function make analysis easy because they change more smoothly in a more stable way than the ordinary method such as the least square method. Using the developed method, we can simulates the static crack growth test results satisfactorily.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.26 no.1D
• /
• pp.73-79
• /
• 2006

A major purpose of this study is to develop high modulus asphalt mixtures for perpetual asphalt pavements which can save maintenance cost by increasing the design and performance periods of the pavements. Various physical and mechanical laboratory tests are performed for the high modulus asphalt binder developed in this study. The test results show that the properties of the high modulus binder are similar to those of the French high modulus binders. In addition to the binder tests, various performance tests are conducted for the high modulus and conventional mixtures. The dynamic modulus test results indicate that the dynamic modulus values of the high modulus mixtures are higher than those of the conventional mixtures by 10~15% at $5^{\circ}C$, 20~25% at $15^{\circ}C$ and 100% at $30^{\circ}C$. It is observed from the performance tests that the high modulus mixtures yield better fatigue, rutting and moisture damage performance than the conventional mixtures.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.29 no.2D
• /
• pp.217-225
• /
• 2009

The study on the left turning trajectory has not done many times in Korea. Because of this, there are a lot of intersections built without considering on turning trajectory of vehicles, in Korea, and we can see many conflicts, reduced capacity of turn, especially at small intersections. Even if left turn trajectory is designed well, it is not easy to mark exactly on the pavement according to the turn trajectory. This study suggests "drop Islands" which can be seen in Europe, and is introduced in Korea recently, to solve the problems of conflicts and reduced capacity of turning. It suggests a table of location of the stop line so that the engineers who design the intersection design appropriate left turn trajectory and marking of the stop line and turn trajectory is done more exactly. To evaluate the effect of "drop island", two intersections with and without drop island were compared on the turnning radii and location of stop line. Construction of "drop island" can increase the capacity of intersection and safety without additional land and construction expenses.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.30 no.5D
• /
• pp.505-512
• /
• 2010

Generally, the repeated traffic loading condition should be considered to predict the long-term deformation on road foundations or foundation systems. However, it is not easy to estimate long-term deformation on multi-layered system like roads and railways. For more quantitative analysis, mechanistic-empirical approach requires proper analytical tool, material's model, and material properties of foundation geomaterials under both traffic and environmental loadings. In this study, therefore, laboratory data from the long-term repeated load triaxial tests were used to predict accumulated deformation on pavement foundations and the results were analyzed based on the nonlinear models and stress state considered. All these results are presented and verified on laboratory based scale using the finite element analysis with the deformation characteristics of foundation geomaterials at various stress states.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.30 no.2A
• /
• pp.185-191
• /
• 2010

Because the concrete crack that is the reason of the serviceability and durability degradation of concrete structure can be arisen from either the stress magnitude and gradient or other structural and material defects, the crack strength of concrete is hard to accurately evaluate. Especially, stress-state in concrete plate components such as rigid pavement and long span slab is biaxial flexure stress, and the flexural strength of those component may be different than the traditional rupture modulus of concrete subjected to uniaxial stress. In this study, an experimental investigation to assess of mechanical behavior under uniaxial and biaxial flexure stress is conducted and the proposed optimum specimen configuration is adopted. From the test, the modulus of rupture under uniaxial and biaxial stress are decreased as the size of aggregate or specimen is larger. And biaxial flexure strength of concrete specimens is varied from 39.5 to 99.2% as compared with that of uniaxial strength, and the biaxial strength of specimen with 20mm aggregate size is only 76% of uniaxial strength.

• Geomechanics and Engineering
• /
• v.36 no.1
• /
• pp.39-50
• /
• 2024

Bitumen and high-quality subangular aggregates, the two principal materials used for asphalt concrete construction, are finite and expensive materials. The general availability of crumb rubber and naturally occurring aggregates of different shapes, especially flat and elongated shapes, indicates that they are feasible alternative materials for expanding the volume of bitumen and utilizing a wider range of aggregate shapes for the development of asphalt concrete, with an associated environmental benefit. The study investigated the effect of adding up to 15% crumb rubber and aggregates sorted into different groups, i.e., rounded, elongated, flat, and their combinations, on the rheological and mechanical properties and durability of 50/70 of hot-mix asphalt pavement. The addition of crumb rubber decreased ductility and penetration but increased the softening point. For a 5.5% bitumen content, asphalt concrete briquettes consisting of 7% crumb rubber and three types of aggregate shapes, i.e., 100% rounded, a mix of 75% rounded and 25% elongated, and a mix of 75% rounded, 15% elongated and 10% flat, were associated with high Marshall stability and indirect tensile strength as well as low lateral deformation due to their high solidity and moderate angularity ratio. Also, the addition of 7% crumb rubber resulted in a significant improvement in the tensile strength ratio and rebound strain of briquettes consisting of 75% rounded and 25% elongated aggregates and those with 75% rounded, 15% elongated and 10% flat aggregates. In relation to the parameters investigated, the three groups of briquettes met some of the local (South Africa) requirements for the surface course and base course of low traffic volume roads.

• Advances in materials Research
• /
• v.13 no.1
• /
• pp.63-86
• /
• 2024

Asphalt concrete (AC), is a mixture of bitumen and aggregates, which is very sensitive in the design of flexible pavement. In this study, the Marshall stability of the glass and carbon fiber bituminous concrete was predicted by using Artificial Neural Network (ANN), Support Vector Machine (SVM), Random Forest (RF), and M5P Tree machine learning algorithms. To predict the Marshall stability, nine inputs parameters i.e., Bitumen, Glass and Carbon fibers mixed in 100:0, 75:25, 50:50, 25:75, 0:100 percentage (designated as 100GF:0CF, 75GF:25CF, 50GF:50 CF, 25GF:75CF, 0GF:100CF), Bitumen grade (VG), Fiber length (FL), and Fiber diameter (FD) were utilized from the experimental and literary data. Seven statistical indices i.e., coefficient of correlation (CC), mean absolute error (MAE), root mean squared error (RMSE), relative absolute error (RAE), root relative squared error (RRSE), Scattering index (SI), and BIAS were applied to assess the effectiveness of the developed models. According to the performance evaluation results, Artificial neural network (ANN) was outperforming among other models with CC values as 0.9147 and 0.8648, MAE values as 1.3757 and 1.978, RMSE values as 1.843 and 2.6951, RAE values as 39.88 and 49.31, RRSE values as 40.62 and 50.50, SI values as 0.1379 and 0.2027 and BIAS value as -0.1 290 and -0.2357 in training and testing stage respectively. The Taylor diagram (testing stage) also confirmed that the ANN-based model outperforms the other models. Results of sensitivity analysis showed that the fiber length is the most influential in all nine input parameters whereas the fiber combination of 25GF:75CF was the most effective among all the fiber mixes in Marshall stability.