In the present study, the amount of fragments generated and their travel distances due to vehicle collision with concrete median barrier (CMB) was analyzed and predicted. In this regard, machine learning was applied to the results of numerical analysis, which were developed by comparing with field test. The numerical model was developed using smoothed particle hydrodynamics (SPH). SPH is a mesh-free method that can be used to predict the amount of fragments and their travel distances from concrete structures under impact loading. In addition, deep neural network (DNN) and gradient boosting machine (GBM) were also employed as machine learning methods. In this study, the results of DNN, GBM, and numerical analysis were then compared with the conducted field test. Such comparisons revealed that numerical analysis generated lower error than both DNN and GBM. When prediction results of both the amount of fragments and their travel distances were considered, the result of DNN showed smaller errors than that of GBM. Therefore, in studies where machine learning is used to predict the amount of fragments and their travel distances, careful selection of an appropriate method from the various available machine learning methods such as DNN, GBM, and random forest is absolutely important.

The production of commercially used cement-based bricks has significant environmental implications, necessitating the development of robust, environmentally friendly alternatives. This study assesses the strength and durability of soil bricks by utilizing an eco-friendly stabilizer, which includes lime and natural-fiber-derived staple fibers. Soil bricks, each sized 50 mm × 100 mm and featuring varying proportions of stabilizer and wood chips, were subjected to unconfined compression and bending strength tests, permeability assessments, steel ball/golf ball (SB/GB) evaluations, and wetting–drying tests. The results demonstrated that higher stabilizer ratios and lower wood chip ratios led to enhanced unconfined compressive strength. Additionally, repeated wetting–drying cycles reduced the strength by up to 63%, while the relative dynamic modulus of elasticity decreased by as much as 45% with increasing wetting–drying cycles. Notably, the eco-friendly stabilizer significantly improved soil shear strength, ultimately enhancing the durability of the soil bricks.

The failure or debonding of CEIs (Concrete-Epoxy Interfaces) in Fiber-Reinforced Polymer concrete (FRP) systems occurs in one or a combination of three modes: CC (Cohesive failure in Concrete), CE (Cohesive failure in Epoxy), and IF (Interfacial Failure). These failure modes are usually identified, and their relationships are established by human intuition, which is prone to subjectivity. This study proposes a novel method based on image processing techniques to analyze CEI fracture surfaces and evaluate their failure modes. The failure modes of CEI fracture surfaces of specimens from a 3PB (Three-Point Bending) experiment were assessed using an HVS, CIE L*a*b*, YC_bC_r, or RGB color space image segmentation-based image processing technique on the preprocessed images of the CEI failure sides. A manual approach was adopted to validate the accuracy of the proposed method. Comparing the failure mode (CE) obtained using the manual and the proposed methodology, an RMSE (Root Means Square Error) of 0.19, 0.10, 0.23, and 0.26 was obtained for HVS, CIE L*a*b*, YC_bC_r, or RGB color space, respectively. The epoxy area selected with CIE L*a*b* color space produced the most accurate evaluation of the failure modes. This study provides an accurate method of quantifying the failure modes of CEI fracture surfaces. The methodology proposed in this study is recommended for forensic investigations to understand better the possible causes of failure in externally bounded fiber-reinforced polymers.

본 연구의 목적은 콘크리트-에폭시 계면(concrete-epoxy interface, CEI)의 파괴면 분석을 위한 이미지분석 방법 개발에 있다. 콘크리트-에폭시 계면은 FRP(fiber-reinforced polymer) 시트 외부 부착공법을 콘크리트 구조물에 적용 시 에폭시와 콘크리트 사이에 형성된다. 콘크리트-에폭시 계면 부착성능은 공용 중 발생 가능한 환경하중에 의해 크게 영향을 받는다. 콘크리트-에폭시계면의 파괴 유형은 크게 세 가지로 구분할 수 있다: 콘크리트면내파괴(cohesive failure in concrete, CC), 계면부착파괴(interfacial failure, IF), 그리고 에폭시면내파괴(cohesive failure in epoxy). 본 연구에서 제안한 정량적인 이미지 분석방법과 파괴모드 기준을 활용하여 콘크리트-에폭시 계면 실험체 2종(일면전단실험체와 휨 실험체)에 대한 부착성능 및 파괴모드를 분석하였다. 콘크리트-에폭시 계면 실험체의 부착성능평가는 일면전단실험체의 경우 최대부착파괴하중(부착강도) 그리고 휨 실험체의 경우 부착파괴 에너지를 활용하였다. 본 연구의 결과는 파괴모드와 콘크리트-에폭시 계면의 부착성능은 상당한 상관관계가 있으며 지속하중기간이 증가할수록 부착성능이 저하되며 파괴모드 역시 콘크리트면내파괴(CC)에서 계면부착파괴(IF)로 전이가 발생하였다.

Rainfall-induced erosion and deformation of soil slopes remain important concerns for long-term slope stability, highlighting the need for effective surface reinforcement methods. This study experimentally investigated the mechanical and rainfall-resistant performance of carbon fiber-reinforced stabilized soil for slope surface protection. Four soil types were initially evaluated using unconfined compression tests with different Eco Soil Binder (E.S.B.) contents, and well-graded sand (SW) with 20% E.S.B. was selected for further testing. Carbon fiber contents ranging from 0 to 1.2% were considered; however, stable specimens could not be formed at 1.2%, while 0.6% provided the highest compressive strength among the valid test conditions. The selected mixture of SW, 20% E.S.B., and 0.6% carbon fiber was further characterized through triaxial compression tests, yielding an apparent cohesion of 0.152 MPa and a friction angle of 37.23°. Artificial rainfall tests were then conducted using 1:50 geometrically scaled slope models with berm lengths of 0.05 and 0.15 m under a rainfall intensity of 20 mm/h for 48 h. Under the tested small-scale conditions, the stabilized slope models exhibited approximately 47–60% lower settlement than the unreinforced models, together with lower final moisture contents and less visible surface deterioration. Because the two model configurations differed in both material composition and initial unit weight, these results should be interpreted as descriptive comparative observations rather than as isolated effects of E.S.B. and carbon fiber.