Structural cracks have serious repercussions on the safety, adaptability, and longevity of structures. Therefore, assessing cracks is an important parameter when evaluating the quality of concrete construction. As numerous cutting-edge automated inspection systems that exploit cracks have been developed, the necessity for individual/personal onsite inspection has reduced exponentially. However, these methods need to be improved in terms of cost efficiency and accuracy. The deep-learning-based assessment approaches for structural systems have seen a significant development noticed by the structural health monitoring (SHM) community. Convolutional neural networks (CNNs) are vital in these deep learning methods. Technologies such as convolutional neural networks hold promise for precise and accurate condition evaluation. Moreover, transfer learning enables users to use CNNs without needing a comprehensive grasp of algorithms or the capability to modify pre-trained networks for particular purposes. Within the context of this study, a thorough analysis of well-known pre-trained networks for classifying the cracks in buildings made of concrete is conducted. The classification performance of convolutional neural network designs such as VGG16, VGG19, ResNet 50, MobileNet, and Xception is compared to one another with the concrete crack image dataset. It is identified that the ResNet50-based classifier provided accuracy scores of 99.91% for training and 99.88% for testing. Xception architecture delivered the least performance, with training and test accuracy of 99.64% and 98.82%, respectively.

Fire represents one of the significant hazards encountered by civil infrastructures, and thus providing appropriate fire safety measures is a major requirement in a building design for ensuring the safety of the occupants. Minimizing fire-induced damage and collapse of structural systems are the primary objectives in the design of concrete structures. An experimental investigation has been carried out to examine the mechanical properties such as compressive, tensile and flexural strengths of concrete exposed to elevated temperature following standard fire curve as per ISO 834. Capacity-based standards have been formulated to predict the residual strength of various grades of concrete exposed to various duration of heating. Stress strain behaviour, elastic modulus, weight loss, spalling and thermal crack pattern of specimens were also investigated. Water–cement ratio and porosity of concrete were found to be the critical factors for strength loss of concrete. A relationship is established between weight loss and strength loss of concrete. Higher grades of concrete were found to have more weight and strength loss than those of lower grades.

Health monitoring of concrete including, detecting defects such as cracking, spalling on fire affected concrete structures plays a vital role in the maintenance of reinforced cement concrete structures. However, this process mostly uses human inspection and relies on subjective knowledge of the inspectors. To overcome this limitation, a deep learning based automatic crack detection method is proposed. Deep learning is a vibrant strategy under computer vision field. The proposed method consists of U-Net architecture with an encoder and decoder framework. It performs pixel wise classification to detect the thermal cracks accurately. Binary Cross Entropy (BCA) based loss function is selected as the evaluation function. Trained U-Net is capable of detecting major thermal cracks and minor thermal cracks under various heating durations. The proposed, U-Net crack detection is a novel method which can be used to detect the thermal cracks developed on fire exposed concrete structures. The proposed method is compared with the other state-of-the-art methods and found to be accurate with 78.12% Intersection over Union (IoU).

The increase in the population creates an increased demand for construction activities with eco-friendly, sustainable, and high-performance materials. Insulated concrete form (ICF) is an emerging technology that satisfies the sustainability demands of the construction sector. ICF is a composite material (a combination of expanded polystyrene (EPS) and geopolymer concrete (GPC)) that enhances the performance of concrete (such as thermal insulation and mechanical properties). To investigate the axial strength performance, five different types of prototypes were created and tested. Type I (without reinforcement): (a) hollow EPS without concrete, (b) alternative cells of EPS filled with concrete, (c) and all the cells of EPS filled with concrete; and Type II (with reinforcement): (d) alternative cells of EPS filled with concrete; (e) and all the cells of EPS filled with concrete. Amongst all the five prototypes, two grades of GPC were employed. M15 and M20 grades are used to examine the effectiveness in terms of cost. For comparing the test results, a reference masonry unit was constructed with conventional clay bricks. The main aim of the investigation is to examine the physical and mechanical performance of sandwich-type ICFs. The presence of polystyrene in ICF changes the failure pattern from brittle to ductile. The result from the study reveals that the Type II prototype, i.e., the specimen with all the cells of EPS filled with concrete and reinforcement, possesses a maximum load-carrying capacity greater than the reference masonry unit. Therefore, the proposed ICF is recommended to replace the conventional load-bearing system and non-load-bearing walls.