Cracking in concrete structures affects performance and is a major durability problem. Cracks must be detected and repaired in time in order to maintain the reliability and performance of the structure. This study focuses on vision-based crack detection algorithms, based on deep convolutional neural networks that detect and classify cracks with higher classification rates by using transfer learning. The image dataset, consisting of two subsequent image classes (no-cracks and cracks), was trained by the AlexNet model. Transfer learning was applied to the AlexNet, including fine-tuning the weights of the architecture, replacing the classification layer for two output classes (no-cracks and cracks), and augmenting image datasets with random rotation angles. The fine-tuned AlexNet model was trained by stochastic gradient descent with momentum optimizer. The precision, recall, accuracy, and F₁ metrics were used to evaluate the performance of the trained AlexNet model. The accuracy and loss obtained through the training process were 99.9% and 0.1% at the learning rate of 0.0001 and 6 epochs. The trained AlexNet model accurately predicted 1998/2000 and 3998/4000 validation and test images, which demonstrated the prediction accuracy of 99.9%. The trained model also achieved precision, recall, accuracy, and F₁ scores of 0.99, respectively.

Supplementary cementitious materials (SCMs) are commonly used to partially replace cements. Although it is necessary to investigate the rheological properties of the individual supplementary cementitious materials (SCMs) for understanding complex rheological behaviors of the blended mixes, the study on the investigation of rheological properties of various SCMs such as fly ash, blast-furnace slag, and silica fume, according to various solid volume fractions and prediction models is fairly limited. This study investigated the rheological properties of non-blended cementitious suspensions with Portland cement (PC), fly ash (FA), blast-furnace slag (BS), and silica fume (SF) materials in the experiments and predicted using YODEL (Yield stress mODEL) and Krieger–Dougherty’s (K–D’s) equation. Experiments were designed with various solid volume fractions ($\varphi$) from 0.28 to 0.44, and the rheological properties of all cementitious suspensions were noted to increase with increasing $\varphi$, showing an improved flowability at low $\varphi$. YODEL, derived from the first principles considering particle-size distributions, interparticle forces and microstructural parameters predicted the yield stress. The YODEL predictions were consistent with the experiments with a positive correlation coefficient of above 0.96. K–D’s equation with the maximum particle fractions and intrinsic viscosity as key parameters predicted the plastic viscosity. The K–D’s equation predictions match up with the experiments with a positive correlation coefficient of above 0.94. Both models showed more quantitative predictions without any fitting parameters and could be applied to any multimodal powder suspensions.

In recent years, advanced materials have attracted considerable interest in the field of temperature detection and sensing. This study examined the thermochromic properties of inorganic manganese violet (MV) with increasing temperature. According to the thermochromic test, the material was found to have reversible and irreversible color change properties. The MV pigment was then applied to cementitious material at ratios of 1%, 3%, and 5%. The mixed cement samples with MV pigment were heated in a furnace, and digital images were captured at each temperature interval to evaluate the changes in the color information on the surface of the specimen. The mixed samples exhibited an irreversible thermochromic change from dark violet to grayish green above 400 °C. At the critical temperature of 440 °C, the RGB values increased by approximately 22%–55%, 28%–68%, and 7%–25%, depending on the content of MV pigment. In Lab space, the L value increased by approximately 23%–60% at 440 °C. The a value completely changed from positive to negative, and the b value changed from negative to positive. All the values differed according to the content of MV pigment at room temperature but approached similar ranges at the critical temperature, irrespective of the amount of MV pigment. To assess the changes in their microstructure and composition, scanning electron microscopy and energy dispersive X-ray spectroscopy were performed on the samples exposed to temperatures ranging from room temperature to 450 °C.

Supplementary cementitious materials (SCMs), such as fly ash (FA), blast furnace slag (BS), and silica fume (SF), have been mostly used as a replacement for Portland cement (PC). Replacing the SCMs with cement can provide improved strength characteristics; however, their applicability depends on the flow characteristics of the fresh mixtures. In this study, the rheological performance of cementitious suspensions in paste scale with different water-to-solid (W/S) volume ratios, varied from 1.25, 1.50, 1.75, 2.00, 2.25, to 2.50, was evaluated. As a result of the rheological tests, the yield stress and plastic viscosity of PC, FA, BS, and SF suspensions decreased as the W/S ratio increased. This study also estimated the inter-particle distances of the cementitious suspensions, and their relationship to the rheological properties was established. The inter-particle distances of the PC, FA, BS, and SF suspensions were in the ranges of 5.74~14.67 µm, 5.18~11.66 µm, 3.82~9.34 µm, and 0.107~0.27 µm, respectively. For very fine particles with a large surface area, the sensitivity to the rheological properties was high and the sensitivity was low when the particle sizes increased, indicating that the rheological properties were more sensitive to fine particles.

This study examines the implementation of an MnNH₄P₂O₇ (ammonium manganese III pyrophosphate)-based coating on structural elements to obtain temperature information with color changes. Based on the MnNH₄P₂O₇ material, a coating was prepared and deposited on cement mortar surfaces. Heat experiments were then conducted to evaluate the thermochromism on the fabricated samples. The coated samples exhibited a superior irreversible thermochromic property at 400 °C with a color change from dark violet to light grayish blue at the heated surface. The color changes were retrieved at each temperature using a digital camera, and the change in color properties was evaluated in the RGB and L*a*b* color spaces using image processing techniques. With increasing temperature from room temperature, the RGB values were almost constant until 200 °C. At higher temperatures, the color changes started to accelerate until 400 °C. The values showed a 167%, 567%, and 49% increase in R, G, and B values, respectively, at 400 °C. In the L*a*b* color space, when the temperature was increased from room temperature to 400 °C, the L*a*b* values showed an increase of 211%, a decrease of 94%, and an increase of 78%, respectively.