“…Machine learning techniques have been successfully used in several applications in the field of construction engineering, such as automatic crack detection [20,21], concrete failure surface modelling [22], compressive strength prediction [23][24][25], durability assessment [26], concrete dam reliability analysis [27], and carbonation prediction [28].…”
We propose a deep learning approach to better utilize the spatial and temporal information obtained from image sequences of the self-compacting concrete- (SCC-) mixing process to recover SCC characteristics in terms of the predicted slump flow value (SF) and V-funnel flow time (VF). The proposed model integrates features of the convolutional neural network and long short-term memory and is trained to extract features and compute an estimate. The performance of the method is evaluated using the testing set. The results indicate that the proposed method could potentially be used to automatically estimate SCC workability.
“…Machine learning techniques have been successfully used in several applications in the field of construction engineering, such as automatic crack detection [20,21], concrete failure surface modelling [22], compressive strength prediction [23][24][25], durability assessment [26], concrete dam reliability analysis [27], and carbonation prediction [28].…”
We propose a deep learning approach to better utilize the spatial and temporal information obtained from image sequences of the self-compacting concrete- (SCC-) mixing process to recover SCC characteristics in terms of the predicted slump flow value (SF) and V-funnel flow time (VF). The proposed model integrates features of the convolutional neural network and long short-term memory and is trained to extract features and compute an estimate. The performance of the method is evaluated using the testing set. The results indicate that the proposed method could potentially be used to automatically estimate SCC workability.
“…Han et al [4] evaluated carbonation depth and probability of corrosion initiation in harbor concrete structures. Taffese et al [5] evaluated the carbonation depth by using machine learning methods that consisted of neural networks, decision trees, and ensemble methods. Marques et al [6,7] proposed a carbonation service-life model considering the initial period and propagation period after carbonation.…”
Section: Introductionmentioning
confidence: 99%
“…www.mdpi.com/journal/sustainability Sustainability 2017, 9, 157 2 of 15 aforementioned studies [4][5][6][7] is the effect of factors attributed to climate change, such as increases in the CO 2 budget or changes in temperature.…”
Section: Introductionmentioning
confidence: 99%
“…To address the drawbacks in the current models [3][4][5][6][7][8][9][10][11][12][13][14][15], this study presents a probabilistic approach that predicts the service life of concrete structures subjected to carbonation-induced corrosion. The effects of concrete material properties, curing conditions, and climate change on service life are considered.…”
Abstract:The increase in CO 2 concentrations and global warming will increase the carbonation depth of concrete. Furthermore, temperature rise will increase the rate of corrosion of steel rebar after carbonation. On the other hand, compared with normal concrete, high volume fly ash (HVFA) concrete is more vulnerable to carbonation-induced corrosion. Carbonation durability design with climate change is crucial to the rational use of HVFA concrete. This study presents a probabilistic approach that predicts the service life of HVFA concrete structures subjected to carbonation-induced corrosion resulting from increasing CO 2 concentrations and temperatures. First, in the corrosion initiation stage, a hydration-carbonation integration model is used to evaluate the contents of the carbonatable material, porosity, and carbonation depth of HVFA concrete. The Monte Carlo method is adopted to determine the probability of corrosion initiation. Second, in the corrosion propagation stage, an updated model is proposed to evaluate the rate of corrosion, degree of corrosion for cover cracking of concrete, and probability of corrosion cracking. Third, the whole service life is determined considering both corrosion initiation stage and corrosion propagation stage. The analysis results show that climate change creates a significant impact on the service life of durable concrete.
“…No entanto, Possan (2010) cita que estes modelos possuem grande complexidade quanto à resolução das equações que regem a difusão do CO2 no concreto, além de possuírem parâmetros de difícil obtenção, por exemplo, o coeficiente de difusão do dióxido de carbono. A utilização de ferramentas computacionais, a exemplo das Redes Neurais Artificiais (RNAs), apresenta-se como uma alternativa para contornar as dificuldades impostas à modelagem da carbonatação do concreto, devido à capacidade de mapear e modelar problemas complexos e não lineares sem a necessidade de se conhecer todos os fenômenos envolvidos (Braga et al, 2000, Lu et al, 2009Kwon et al, 2010;Güneyisi et al, 2014;Taffese et al, 2015;Félix, 2016). Tendo em vista que diversas variáveis influenciam no avanço da carbonatação do concreto (Pauletti et al, 2007), analisa-se neste estudo a influência da umidade relativa do ar, concentração de CO2, composição do concreto, tipo de cimento, teor de adições, condições de exposição à chuva e da resistência à compressão do concreto sobre o fenômeno da carbonatação.…”
RESUMOO presente trabalho tem como objetivo analisar parametricamente a influência dos principais fatores que afetam o avanço da carbonatação em estruturas de concreto. Para tal, desenvolveu-se um modelo numérico empregando Redes Neurais Artificiais (RNAs) do tipo Multi-Layer Perceptron, sendo concebido em linguagem orientada a objetos C++, o qual foi testado com dados reais de degradação disponíveis na literatura. Os resultados obtidos na análise paramétrica reforçam conceitos já conhecidos na literatura, demonstrando a eficiência de RNAs no estudo da carbonatação do concreto, além de agregar conhecimento à área de patologia das construções. Palavras chave: carbonatação do concreto; tempo de iniciação da corrosão; Redes Neurais Artificiais; modelagem matemática.
_______________________________________________________________
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.