Modular deep learning segmentation algorithm for concrete microscopic images

Hilloulin, Benoît; Bekrine, Imane; Schmitt, Emmanuel; Loukili, Ahmed

doi:10.1016/j.conbuildmat.2022.128736

Cited by 9 publications

(4 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The surface of mortar samples was observed after degradation using a 3D microscope. Three-dimensional maps of three lines were obtained along the height of each specimen using a Hirox RH2000 3D microscope (Tokyo, Japan) by merging hundreds of images evenly spaced along the section [38]. A magnification of ×50 was chosen according to the standard suggestion, leading to a final horizontal resolution of 3.13 µm/m.…”

Section: Microscopic Test and Imagingmentioning

confidence: 99%

Experimental Investigation on the Effects of Mineral Water Composition on the Leaching of Cement-Based Materials

Pouyanne,

Boudache,

Hilloulin

et al. 2024

Materials

Self Cite

View full text Add to dashboard Cite

The common phenomenon observed for concrete in aggressive water is leaching, which involves the dissolution of cement hydration products. Many studies have focused on leaching in demineralised water or acid attacks, but mineral water still deserves further investigation. In most standards, the aggressiveness of a given water body is determined by its pH and not its composition. The effect of the calcium content of the water on degradation is yet to be determined. In this paper, the leaching of Portland cement-based mortar was induced by two types of drinking water with different calcium contents and buffer capacity in controlled conditions. The Langelier saturation index (LSI) was used to describe water aggressiveness based on the calco-carbonic equilibrium. The studied waters had the same pH but LSIs of +0.5 and −1.0 corresponding to scaling with respect to aggressive water; demineralised water was used as a reference. Microstructural damage was checked by TGA and X-ray microtomography. Macroscopic measurements were used to monitor global degradation. The soft water caused a 53% deeper deterioration of the mortar sample than the hard water. Soft water-induced leaching was found to be similar yet slower to leaching via demineralised water (with a mass loss of −2.01% and −2.16% after 200 days, respectively). In contrast, hard water induced strongly time-dependent leaching, and the damage was located close to the surface. The roughness of leached specimens was 18% higher in hard water than in soft water. The formation of calcite on the sample surface not only affects the leaching rate by creating a protective surface layer, but it could also act as a calcium ion pump.

show abstract

Section: Microscopic Test and Imagingmentioning

confidence: 99%

Experimental Investigation on the Effects of Mineral Water Composition on the Leaching of Cement-Based Materials

Pouyanne,

Boudache,

Hilloulin

et al. 2024

Materials

Self Cite

View full text Add to dashboard Cite

show abstract

“…Since the publication of Procedure C, multiple research teams have applied machine learning and computer vision techniques for air void analysis 4–8 . However, standards governing current construction quality assurance practices have yet to catch up with these advances.…”

Section: Introductionmentioning

confidence: 99%

“…Since the publication of Procedure C, multiple research teams have applied machine learning and computer vision techniques for air void analysis. [4][5][6][7][8] However, standards governing current construction quality assurance practices have yet to catch up with these advances. As such, ASTM C457 Procedure C was specified by the owners for the project examined here: the ongoing construction of the Gordie Howe International Bridge.…”

mentioning

confidence: 99%

Paste, aggregate, or air? That is the question

Ossetchkina,

Chernoloz,

Bromerchenkel

et al. 2024

Journal of Microscopy

View full text Add to dashboard Cite

The Ambassador Bridge between Detroit, Michigan, and Windsor, Ontario, has served for almost 100 years as North America's busiest international border crossing. But in 2025, the Ambassador will be replaced by the new Gordie Howe International Bridge. The Gordie Howe is a cable‐stayed bridge, with two massive 220 m tall concrete piers on opposite banks of the St. Claire River, a single clear span of 853 m, and 42 m of clearance over this busy waterway. To ensure durability in this harsh freeze‐thaw environment, air‐entrained concrete is specified throughout. And, to ensure the quality of air entrainment, the ASTM C 457 Procedure C, Contrast Enhanced Method is employed. While a similar automated microscopic approach has been in use for well over a decade according to EN 480‐11 Determination of air void characteristics in hardened concrete, this is the first large‐scale application of automated air void assessment in North American infrastructure. According to the ASTM Procedure C, the air void characteristics are determined through digital image processing, while the paste content may be determined by either mix design parameters, manual point count, or ‘other means’. Of these three options, point counting is used for Gordie Howe; but in parallel, during each point count, the digital image coordinates and phase identifications for each evaluated stop are recorded. This allows for training of a neural network, for automated determination of paste content, as demonstrated here.

show abstract

“…In recent years, Machine Learning has been increasingly employed for predicting and analyzing cementitious materials' properties. Deep Learning techniques and Convolutional Neural networks help assess concrete properties at various scales: from crack and defect detection [18][19][20] to concrete microscopic image analysis [21][22][23] or mechanical properties [24]. Gaussian processes, Bayesian techniques, and exploration-exploitation techniques close to reinforcement learning have been successfully employed to infer mechanical characteristics from microindentation and nanoindentation [25] or quantitatively estimate uncertainties concerning concrete properties such as susceptibility to sulfate degradation [26].…”

Section: Introductionmentioning

confidence: 99%

Interpretable ensemble machine learning for the prediction of the expansion of cementitious materials under external sulfate attack

Hilloulin,

Hafidi,

Boudache

et al. 2023

Journal of Building Engineering

Self Cite

View full text Add to dashboard Cite

Modular deep learning segmentation algorithm for concrete microscopic images

Cited by 9 publications

References 41 publications

Experimental Investigation on the Effects of Mineral Water Composition on the Leaching of Cement-Based Materials

Experimental Investigation on the Effects of Mineral Water Composition on the Leaching of Cement-Based Materials

Paste, aggregate, or air? That is the question

Interpretable ensemble machine learning for the prediction of the expansion of cementitious materials under external sulfate attack

Contact Info

Product

Resources

About