This review provides an in-depth examination of machine learning applications in assessing concrete durability from 2013 to 2024, with a particular focus on critical degradation mechanisms, including carbonation, chloride-induced deterioration, sulfate attack, frost damage, shrinkage, and corrosion. It underscores the field’s heavy reliance on laboratory-based data and notes the limited use of field data and the scarcity of newly generated datasets. The review reveals that most studies utilize existing literature-based datasets, with few contributing novel data and limited open access to these databases, which hampers broader validation and application. The review classifies the features analyzed in studies into categories such as mixture proportions, engineering properties, exposure conditions, test parameters, and chemical compositions, highlighting a growing emphasis on chemical compositions. Modeling approaches are predominantly standalone, though ensemble and hybrid models are increasingly prevalent, with ensemble models showing particularly strong performance in recent years. High accuracy is observed across studies, with ensemble models, neural networks, and hybrid models leading in performance. Furthermore, the review stresses the growing importance of model explainability, noting that model-agnostic methods like SHAP are frequently used and that the focus on explainability has increased. To propel the field forward, the review advocates for the development of diverse new datasets that include both the chemical and physical properties of various mix ingredients and improved data-sharing practices. It recommends adopting a multi-task learning approach to simultaneously address multiple deterioration mechanisms, which can yield deeper insights and support the creation of more durable concrete structures.

In recent times, digital transformations and Industry 4.0 have revolutionized real-time bridge monitoring and its inspection. The use of smart Structural Health Monitoring (SHM) techniques is becoming powerful with the competencies of Building Information Modeling (BIM) tools, Artificial Intelligence (AI), Internet of Things (IoT), and Virtual/Augmented (VR/AR) technologies. However, the lack of interconnectivity between these tools limits their functionality. This research has addressed this problem by developing an integrated framework to assess serviceability and implement a smart SHM for a newly constructed extradosed bridge. Using Finite Element Analysis (FEA), the study proposes an integrated SHM system that utilizes various IoT sensors, including Wired Strain Gauges (WSG), Liquid Levelling Sensors (LLS), MEMS accelerometers, and a Weather Monitoring Station (WMS) to monitor concrete deformations, vertical displacements, structural vibrations, and weather conditions. BIM tool is used to develop the virtual replica of the proposed SHM system which is then used in the 3D Game Engine (GE) to develop an AR application. This application is then successfully deployed and tested in the AR headset (HoloLens) where its capabilities for onsite bridge health monitoring are discovered. This approach overcomes the limitations of HoloLens devices by providing real-time access to SHM data through a web platform, enabling on-site or remote AR-based bridge health monitoring. Conclusively, this paper emphasizes the numerical modeling of bridges for the design of a health monitoring system, that highlights the importance of robust SHM techniques in assessing bridge conditions. Moreover, it introduces a novel approach for smart bridge inspection and onsite visualization of structural defects in an AR environment.

The huge amount of solid waste from the brick manufacturing industry can be used as a cement replacement. However, replacement exceeding 10% causes a reduction in strength due to the slowing of the pozzolanic reaction. Therefore, in this study, the pozzolanic potential of brick waste is enhanced using ultrafine brick powder with hydrated lime (HL). A total of six self-compacting paste mixes were studied. HL 2.5% by weight of binder was added in two formulations: 10% and 20% of waste burnt brick powder (WBBP), to activate the pozzolanic reaction. An increase in the water demand and setting time was observed by increasing the replacement percentage of WBBP. It was found that the mechanical properties of mixes containing 5% and 10% WBBP performed better than the control mix, while the mechanical properties of the mixes containing 20% WBBP were found to be almost equal to the control mix at 90 days. The addition of HL enhanced the early-age strength. Furthermore, WBBP formulations endorsed improvements in both durability and rheological properties, complemented by reduced early-age shrinkage. Overall, it was found that brick waste in ultrafine size has a very high degree of pozzolanic potential and can be effectively utilized as a supplementary cementitious material.