PURPOSES : To enhance the accuracy of predicting the compressive strength of practical concrete mixtures, this study aimed to develop a machine learning model by utilizing the most commonly employed curing age, specifically, the 28-day curing period. The training dataset consisted of concrete mixture sample data at this curing age, along with samples subjected to a total load not exceeding 2,350 kg. The objective was to train a machine learning model to create a more practical predictive model suitable for real-world applications. METHODS : Three machine learning models—random forest, gradient boosting, and AdaBoost—were selected. Subsequently, the prepared dataset was used to train the selected models. Model 1 was trained using concrete sample data from the 28th curing day, followed by a comprehensive analysis of the results. For Model 2, training was conducted using data from the 28th day of curing, focusing specifically on instances where the total load was 2,350 kg or less. The results were systematically analyzed to determine the most suitable machine learning model for predicting the compressive strength of concrete. RESULTS : The machine learning model trained on concrete sample data from the 28th day of curing with a total weight of 2,350 kg or less exhibited higher accuracy than the model trained on weight-unrestricted data from the 28th day of curing. The models were evaluated in terms of accuracy, with the gradient boosting, AdaBoost, and random forest models demonstrating high accuracy, in that order. CONCLUSIONS : Machine learning models trained using concrete mix data based on practical and real-world scenarios demonstrated a higher accuracy than models trained on impractical concrete mix data. This case illustrates the significance of not only the quantity but also the quality of the data during the machine learning training process. Excluding outliers from the data appears to result in better accuracy for machine learning models. This underscores the importance of using high-quality and practical mixed concrete data for reliable and accurate model training.

고성능 콘크리트(HPC) 압축강도는 추가적인 시멘트질 재료의 사용으로 인해 예측하기 어렵고, 개선된 예측 모델의 개발이 필수적 이다. 따라서, 본 연구의 목적은 배깅과 스태킹을 결합한 앙상블 기법을 사용하여 HPC 압축강도 예측 모델을 개발하는 것이다. 이 논 문의 핵심적 기여는 기존 앙상블 기법인 배깅과 스태킹을 통합하여 새로운 앙상블 기법을 제시하고, 단일 기계학습 모델의 문제점을 해결하여 모델 예측 성능을 높이고자 한다. 단일 기계학습법으로 비선형 회귀분석, 서포트 벡터 머신, 인공신경망, 가우시안 프로세스 회귀를 사용하고, 앙상블 기법으로 배깅, 스태킹을 이용하였다. 결과적으로 본 연구에서 제안된 모델이 단일 기계학습 모델, 배깅 및 스태킹 모델보다 높은 정확도를 보였다. 이는 대표적인 4가지 성능 지표 비교를 통해 확인하였고, 제안된 방법의 유효성을 검증하였다.

The contemporary high-tech structures have become enlarged and their functions more diversified. Steel concrete structure and composite material structures are not exceptions. Therefore, there have been on-going studies on fiber reinforcement materials to improve the characteristics of brittleness, bending and tension stress and others, the short-comings of existing concrete. In this study, the purpose is to develop the estimated model with dynamic characteristics following the steel fiber mixture rate and formation ration by using the nerve network in mixed steel fiber reinforced concrete (SFRC). This study took a look at the tendency of studies by collecting and analyzing the data of the advanced studies on SFRC, and facilitated it on the learning data required in the model development. In addition, by applying the diverse nerve network model and various algorithms to develop the optimal nerve network model appropriate to the dynamic characteristics. The accuracy of the developed nerve network model was compared with the experiment data value of other researchers not utilized as the learning data, the experiment data value undertaken in this study, and comparison made with the formulas proposed by the researchers. And, by analyzing the influence of learning data of nerve network model on the estimation result, the sensitivity of the forecasting system on the learning data of the nerve network is analyzed.

Non-sintering cement was manufactured with briquette ash. Alkali activator for compression bodies used a NaOH solution. In order to apply alkali-activated briquette ash and the non-sintering cement to concrete, several experimental studies were performed. It was necessary to study the binder obtained by means of a substitute for the cement. This study concentrated on strength development according to the concentration of NaOH solution, the curing temperature, and the curing time. The highest compressive strength of compression bodies appeared as 353kgf/cm2 cured at 80˚C for 28 days. This result indicates that a higher curing temperature is needed to get a higher strength body. Also, geopolymerization was examined by SEM and XRD analysis after the curing of compression bodies. According to SEM and XRD, the main reaction product in the alkali activated briquette ash is aluminosilicate crystal.

This paper was examined the compressive strength properties of HPFRCC according to spraying stage as a part of the basic research for development of sprayed HPFRCC for protection and blast resistant of existing structures.

In this paper, evaluation of compressive strength development of concrete cured by microwave heating system is introduced. For this evaluation, core strength tests were conducted. Test results show that the development was accelerated by microwave heating system. And two parameters in a equation for predicting initial strength development were presented when using this system.

To examine the in-place strength development of concrete of nuclear containment structures with the wall thickness of 1200 mm, mock-up wall specimens were prepared. For maturity evaluation, the temperature rise in the wall specimens owing to hydration heat of cementitious materials was also measured. The in-place strength of concrete was measured using core specimens collected at different locations of mock-up walls. Test results showed that in-place compressive strength development was 1.5 times higher than the strength measured from the standard cylinders. This indicates the maturity effect is needed to be considered in predicting the compressive strength development of concrete in mass structures.

In this study, It was found that replacing a large amount of mineral admixture, we satisfied the target, compressive strength of 30, 50MPa and manufactured lightweight concrete reducing CO2 emissions up to 42.1～52.8% comparing normal concrete

To the goal of improving the early compressive strength of the mortar including Ground granulated blast furnace slag under low-temperature environment, Industrial byproducts including SiO2 and Al2O3 was fired and than 7% of it was added into Ground granulated blast furnace slag. By checking compressive strength and activity index from different mixing rate, in spite of low strength development than OPC 100%, when using firing powder, the expectation of increasing strength by curing time was affirmative

선체는 기본적으로 얇은 판부재들의 조합으로 구성되어 있으며 이들 중 상당수는 유공을 가진 유공판(Perforated plate)으로 이루어져있다. 선체에 설치된 유공판으로서는 선체 상갑판 해치(하역시설로 사용), 선저부의 거더와 플로어(중량경감과 선박 건조 및 검사시 통로확보용), 다이어프램(중량경감 및 파이프 관통의 목적)등이 있다. 이들 유공판에 압축하중이 작용하면 좌굴과 최종강도 특성이 크게 변화할 뿐만 아니라 수반되는 면내응력도 재 분포하게 되어 심각한 문제를 발생한다. 본 연구에서는 실선에서 사용 중인 유공보강판의 모델을 조사하여 비선형 유한요소법(ANSYS)을 사용하여 종방향 압축하중이 작용하는 경우에 대해서 유공비, 웹 치수, 웹 두께 그리고 보강재 단면을 변화시켜가며, 최종강도 시리즈 해석을 수행하고, 최종강도 예측 설계식을 제안하였으며, 식의 정도성을 검증하기 위하여 유한요소해석 결과와 비교하여 정도를 확인하였다. 제안된 설계식은 초기구조설계 시 유공보강판의 최종강도 계산에 유용하게 사용되리라 판단된다.

선체구조 부재에는 이중저의 거더 및 늑판 등에서 유공을 가진 판이 많이 사용되고 있고, 이는 중량 경감, 사람 및 화물의 이동, 배관 등의 목적으로, 보통은 강도상 큰 문제가 없는 부위에 위치하지만, 때로는 불가피하게 높은 응력이 작용하는 부위에 설치해야 할 경우도 있다. 이러한 판에 유공의 존재는 면내 하중에 의한 탄성좌굴강도 및 최종강도에 큰 영향을 주게 된다. 따라서 유공판의 탄성좌굴강도 및 최종강도 평가는 선박의 초기 구조설계단계에서 구조부재 치수를 결정할 때 검토해야 할 중요한 설계기준 중의 한가지 이다. 그러므로, 유공판에 대한 합리적인 신뢰적인 탄성좌굴강도 및 최종강도 평가가 필요시 되고 있으며 본 연구에서는 다양한 종횡비와 유공비 그리고 세장비의 영향을 고려하여 탄소성 대변형 유한요소 시리즈해석 결과를 바탕으로 하여 간단한 설계식을 도출하였다.