Predicting carbonation depth of concrete using a hybrid ensemble model

Huo, Zehui; Huang, Yimiao

doi:10.1016/j.jobe.2023.107320

Cited by 10 publications

(6 citation statements)

References 57 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The proposed thesis will be correct in the narrow range of w/c ratios used in current research. As is known, the progress of carbonation depends on the microstructure and correlates more strongly with w/c, which in narrow ranges is linearly responsible for the properties of binders (28)(29)(30). Generally, the results obtained by applying the KAO method have higher values of the coeffi cient r 2 .…”

Section: -Dimension Of the Base Of The Rectangle MMmentioning

confidence: 99%

“…When analysing the entire area that has not been carbonated, the measurement removes the uncertainty associated with the selection of measurement points, as well as the error associated with the heterogeneity of the area covered by carbonation. silnie uzależnionej od stosunku w/c, który w wąskich zakresach odpowiada liniowo za właściwości spoiw (28)(29)(30). Generalnie uzyskiwane, poprzez zastosowanie metody KAO, wyniki mają większe wartości współczynnika r 2 .…”

Section: -Dimension Of the Base Of The Rectangle MMunclassified

See 1 more Smart Citation

Application of digital image analysis as a method of assessing the of carbonation process of cement binders – impact of distortion on the results of real and model samples

Szydłowski

2023

Cement Wapno Beton

View full text Add to dashboard Cite

Nowadays, because of the use of active additives in cement, studies on carbonation progress are crucial to ensure the safety of structures. Carbonation depth measurement involves the use of a calliper to determine the front of the carbonation. The values determined in this way are averaged, and the corrosion progress is estimated based on these values. Due to the fact that the standard approach assumes the use of a discrete method for determining the carbonation depth, the measurement may be subject to error, and its execution, especially for many samples, is time-consuming. An alternative method for determining the depth of carbonation may be continuous measurement, which determines the actual depth of carbonation since the entire sample area is analysed. Therefore, digital image analysis is the more precise and convenient approach. Unfortunately, it is not an approach, covered by the standards, but may help to assess the correctness of the determination, the carbonation depth. The problem with the use of digital analysis in proposed method may be the quality of the image obtained. The main problem may be the sphericity of the image, related to the nature of the camera, but also the lack of perpendicularity of the optical system of the camera to the sample when fixing its image, related to incorrect positioning by the camera operator. The results show that the digital image analysis is more accurate than the traditional approach, and that the distortion caused by the tilt of the image does not affect the obtained values to a greater degree than the measurement accuracy of the traditional approach.

show abstract

Section: -Dimension Of the Base Of The Rectangle MMmentioning

confidence: 99%

Section: -Dimension Of the Base Of The Rectangle MMunclassified

Application of digital image analysis as a method of assessing the of carbonation process of cement binders – impact of distortion on the results of real and model samples

Szydłowski

2023

Cement Wapno Beton

View full text Add to dashboard Cite

show abstract

“…Using Hong Kong as example, based on >20 years of data (1998-2019), we develop and evaluate several statistical, machine learning and deep learning approach. We further explore several ensemble forecast approaches that previously show superior performance in other diseases [4, 9, 17, 19] or geographics [20, 21]. We propose the idea of allowing model weights to be updated dynamically over time to better capture the rapid change of influenza activity in Hong Kong.…”

Section: Introductionmentioning

confidence: 99%

“…; https://doi.org/10.1101/2024.03. 27.24304945 doi: medRxiv preprint 5 17,19] or geographics [20,21]. We propose the idea of allowing model weights to be updated dynamically over time to better capture the rapid change of influenza activity in Hong Kong.…”

Section: Introductionmentioning

confidence: 99%

An adaptive weight ensemble approach to forecast influenza activity in the context of irregular seasonality

Tsang,

Du,

Cowling

et al. 2024

Preprint

View full text Add to dashboard Cite

Forecasting of influenza activity in tropical and subtropical regions such as Hong Kong is challenging due to irregular seasonality with high variability in the onset of influenza epidemics, and potential summer activity. To overcome this challenge, we develop a diverse set of statistical, machine learning and deep learning approaches to forecast influenza activity in Hong Kong 0-to 8- week ahead, leveraging a unique multi-year surveillance record spanning 34 winter and summer epidemics from 1998-2019. We develop a simple average ensemble (SAE), which is the average of individual forecasts from the top three individual models. We also consider an adaptive weight blending ensemble (AWBE) that allows for dynamic updates of each model contribution based on LASSO regression and uses decaying weights in historical data to capture rapid change in influenza activity. Overall, across all 9 weeks of horizon, all models outperform the baseline constant incidence model, reducing the root mean square error (RMSE) by 23%-29% and weighted interval score (WIS) by 25%-31%. The SAE ensemble only slightly better than individual models, reducing RMSE and WIS by 29%. The AWBE ensemble reduce RMSE by 45% and WIS by 46%, and outperform individual models for forecasts of epidemic trends (growing, flat, descending), and during both winter and summer seasons. Using the post-COVID surveillance data in 2023-2024 as another test period, the AWBE ensemble still reduces RMSE by 32% and WIS by 36%. Our framework contributes to the ensemble forecasting of infectious diseases with irregular seasonality.

show abstract

“…Specific areas of structures and materials have been used ANN to evaluate the applicability of machine learning in civil engineering, with the majority of the studies in this field aiming to predict physical, chemical, or mechanical properties, especially in concrete. Examples include the prediction of compressive strength [26,28,29,[34][35][36][37], the elastic modulus [38][39][40][41][42][43], the determination of the workability of concrete and its consistency in the fresh state [44][45][46][47], the mapping of composite degradation mechanisms [48][49][50][51][52][53][54], and the development of a concrete-mix design model [55][56][57][58].…”

Section: Introductionmentioning

confidence: 99%

Influence of the ANN Hyperparameters on the Forecast Accuracy of RAC’s Compressive Strength

Almeida,

Felix,

de Sousa

et al. 2023

Materials

View full text Add to dashboard Cite

The artificial neural networks (ANNs)-based model has been used to predict the compressive strength of concrete, assisting in creating recycled aggregate concrete mixtures and reducing the environmental impact of the construction industry. Thus, the present study examines the effects of the training algorithm, topology, and activation function on the predictive accuracy of ANN when determining the compressive strength of recycled aggregate concrete. An experimental database of compressive strength with 721 samples was defined considering the literature. The database was used to train, validate, and test the ANN-based models. Altogether, 240 ANNs were trained, defined by combining three training algorithms, two activation functions, and topologies with a hidden layer containing 1–40 neurons. The ANN with a single hidden layer including 28 neurons, trained with the Levenberg–Marquardt algorithm and the hyperbolic tangent function, achieved the best level of accuracy, with a coefficient of determination equal to 0.909 and a mean absolute percentage error equal to 6.81%. Furthermore, the results show that it is crucial to avoid the use of overly complex models. Excessive neurons can lead to exceptional performance during training but poor predictive ability during testing.

show abstract

Predicting carbonation depth of concrete using a hybrid ensemble model

Cited by 10 publications

References 57 publications

Application of digital image analysis as a method of assessing the of carbonation process of cement binders – impact of distortion on the results of real and model samples

Application of digital image analysis as a method of assessing the of carbonation process of cement binders – impact of distortion on the results of real and model samples

An adaptive weight ensemble approach to forecast influenza activity in the context of irregular seasonality

Influence of the ANN Hyperparameters on the Forecast Accuracy of RAC’s Compressive Strength

Contact Info

Product

Resources

About