A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Hyperspectral imaging features for mortar classification and compressive strength assessment
https://orcid.org/0000-0001-5287-5608
https://orcid.org/0000-0002-0658-4356
https://orcid.org/0000-0003-3674-3845
Abstract In this study, hyperspectral imagery with two computational algorithms are proposed to classify the type of mortar and assess the in-situ strength of fresh mortar in near real time. Each scanning on a mortar surface includes 30 spatial pixels selected for analysis, each assigned with a light reflectance spectrum over 400–2500 nm. Three groups of mortar samples with a water-to-cement (W/C) ratio of 0.6, 0.5 and 0.4, respectively, were cast and scanned from Day 1 to 14 of curing. Reflectance data at a wavelength range of 1920 nm to 1980 nm, associated with the O–H chemical bond, were extracted and averaged to classify the different mortar types with K-Nearest Neighbors (KNN) and Support Vector Machine (SVM) algorithms and to predict their compressive strength from a regression equation. The results showed that the average reflectance increased with time due to water molecules reaction during curing process. The KNN classification model with K = 5 had a prediction accuracy of 70% to 75%, and the SVM classification model with C = 1000 and σ = 10 showed a prediction accuracy of approximately 90%. Therefore, the SVM classification algorithm is recommended for use in mortar classification. The compressive strength is well correlated with the average reflectance with a coefficient of over 0.98.
Hyperspectral imaging features for mortar classification and compressive strength assessment
https://orcid.org/0000-0001-5287-5608
https://orcid.org/0000-0002-0658-4356
https://orcid.org/0000-0003-3674-3845
Abstract In this study, hyperspectral imagery with two computational algorithms are proposed to classify the type of mortar and assess the in-situ strength of fresh mortar in near real time. Each scanning on a mortar surface includes 30 spatial pixels selected for analysis, each assigned with a light reflectance spectrum over 400–2500 nm. Three groups of mortar samples with a water-to-cement (W/C) ratio of 0.6, 0.5 and 0.4, respectively, were cast and scanned from Day 1 to 14 of curing. Reflectance data at a wavelength range of 1920 nm to 1980 nm, associated with the O–H chemical bond, were extracted and averaged to classify the different mortar types with K-Nearest Neighbors (KNN) and Support Vector Machine (SVM) algorithms and to predict their compressive strength from a regression equation. The results showed that the average reflectance increased with time due to water molecules reaction during curing process. The KNN classification model with K = 5 had a prediction accuracy of 70% to 75%, and the SVM classification model with C = 1000 and σ = 10 showed a prediction accuracy of approximately 90%. Therefore, the SVM classification algorithm is recommended for use in mortar classification. The compressive strength is well correlated with the average reflectance with a coefficient of over 0.98.
Hyperspectral imaging features for mortar classification and compressive strength assessment
https://orcid.org/0000-0001-5287-5608
https://orcid.org/0000-0002-0658-4356
https://orcid.org/0000-0003-3674-3845
Abstract In this study, hyperspectral imagery with two computational algorithms are proposed to classify the type of mortar and assess the in-situ strength of fresh mortar in near real time. Each scanning on a mortar surface includes 30 spatial pixels selected for analysis, each assigned with a light reflectance spectrum over 400–2500 nm. Three groups of mortar samples with a water-to-cement (W/C) ratio of 0.6, 0.5 and 0.4, respectively, were cast and scanned from Day 1 to 14 of curing. Reflectance data at a wavelength range of 1920 nm to 1980 nm, associated with the O–H chemical bond, were extracted and averaged to classify the different mortar types with K-Nearest Neighbors (KNN) and Support Vector Machine (SVM) algorithms and to predict their compressive strength from a regression equation. The results showed that the average reflectance increased with time due to water molecules reaction during curing process. The KNN classification model with K = 5 had a prediction accuracy of 70% to 75%, and the SVM classification model with C = 1000 and σ = 10 showed a prediction accuracy of approximately 90%. Therefore, the SVM classification algorithm is recommended for use in mortar classification. The compressive strength is well correlated with the average reflectance with a coefficient of over 0.98.
Hyperspectral imaging features for mortar classification and compressive strength assessment
Fan, Liang (author) / Fan, Ming (author) / Alhaj, Abdullah (author) / Chen, Genda (author) / Ma, Hongyan (author)
2020-03-27
Article (Journal)
Electronic Resource
English
Study on Compressive Strength of Geopolymer Mortar
| British Library Conference Proceedings | 2014
Brick-Mortar Bond and Masonry Compressive Strength
| Online Contents | 2005
Brick-Mortar Bond and Masonry Compressive Strength
| British Library Online Contents | 2005