In the inspection and diagnosis of concrete construction, crack detection is highly recommended in the earliest phases to prevent any potential risks later. However, the flaws in concrete surfaces cannot be reliably and effectively identified using traditional crack detection techniques. The suggested algorithm is a supportive tool for agents or authorities to use in crack detection mechanisms to monitor and assess the current condition of buildings or bridges. The researchers aim to establish an intelligent model for automatic crack detection on different concrete surfaces based on image processing technology. Three different concrete surfaces—bridge decks, walls, and concrete cubes—are used to test the model. A subset of the public dataset of bridge decks and walls from SDNET (2018) and 150*150*150 mm of concrete cubes taken from the material laboratory of the faculty of engineering at Ain Shams University are applied to the model. The model F1-score measures are 98.87%, 97.43%, and 74.11% for detecting cracks in bridges, walls, and concrete cubes, respectively. The validation of the applicability of the suggested novel approach is based on a comparison with recent methods for crack recognition. The contribution of this study is that it could be applied to detect cracks efficiently on three different types of concrete surfaces, including uneven concrete surfaces, random noise, voids, dents, colour changes, and stain marks. The proposed method is transparent in its workflow and has a lower computational cost compared with deep learning frameworks. Thus, the outcomes of this model demonstrate its effectiveness in concrete defect field investigation.

Despite the benefits of change orders in allowing owners the exceptional flexibility to mitigate construction problems and respond quickly to capitalize upon opportunities, they have recently become the rule and a major dispute in many construction projects in the Middle East. This study focuses on the State of Kuwait as a case study for this phenomenon, where investigations indicate that around 70% of projects in Kuwait suffer from cost variations. Specifically, the main objectives of this study are to: (1) identify the causes of change orders in public projects; (2) characterize the impact of such change orders on project cost and duration; and (3) recommend practical solutions to minimize the negative impacts of change orders. Data is collected from 38 projects maintained by government agencies and analyzed to highlight common problems and patterns that lead to change orders. The most impacting factors are identified in order to facilitate further investigation of their effects and propose strategies to address these effects. The study also provides recommendations for government agencies to eliminate the causes of change orders or at least minimize their negative impact on projects. This should prove useful to other countries experiencing similar change order trends as it presents a systematic replicable approach to identify the cause and effect of change orders.

Bridge inspection become essential for ensuring structural safety and longevity. Recently, Artificial Intelligence (AI) has become significant in improving bridge assessment by supporting different approaches that enhance maintenance planning and minimize associated costs. Objective of this study is to investigate the more accurate and applicable AI-driven technique for assessing reinforced concrete bridges. Therefore, the presented study proposed two different techniques to estimate the current Bridge Condition Rating (BCR) of reinforced concrete (R.C.) bridges: 1) fuzzy decision-making and 2) Markov chain modelling. This paper focused on a corrosion attack as the main defect utilized to assess the bridge condition. The dual methods depend on visual inspection, applying field and laboratory tests, and reviewing the historical data of the inspected bridge to estimate its condition rating. The fuzzy decision model is used to find a correlation between corrosion degree and concrete surface condition to estimate the Bridge Condition Rating (BCR). The Markov chain model is applied to predict the current and the future Bridge Condition Rating (BCR) and when the bridge will reach the critical condition. The service life for each bridge element is evaluated due to the total time required for corrosion based on carbonation and chloride attack. The proposed models are validated through a real case study of R.C. bridge, and the results demonstrate that the fuzzy model is less accurate compared to the Markov chain. The introduced models provide valuable insights to provide proper Maintenance, Repair, and Replacement (MRR) decisions for the bridges.

Artificial Intelligence (AI) has recently played a crucial role in improving bridge assessment through diverse methodologies to optimize maintenance strategies and reduce costs. Therefore, the current study proposed two different methods to estimate the current condition rating of R.C. bridges by 1) Fuzzy Decision-Making; and 2) Markov Chain Modelling. The purpose of this study is to investigate the more applicable and accurate technique due to AI for reinforced concrete bridge assessment. The current study focused on corrosion as the main defect used to estimate the bridge condition rating. The dual methods depend on visual inspection, applying field and laboratory tests, and reviewing the historical data of the inspected bridge to estimate its condition rating. The fuzzy decision model is applied to find a correlation between corrosion degree and concrete surface condition to estimate the condition rating. The Markov chain model is used to predict the future condition rating for the whole bridge and when it will reach the critical condition. The service life for each bridge element is calculated due to carbonation and chloride attack. The Life 365 model is applied to estimate the service life due to chloride ingress. The proposed system is validated through a real case study, and the results show that the fuzzy is less accurate compared to the Markov Chain. The introduced models are expected to provide proper Maintenance, Repair, and Replacement (MRR) decisions for the bridges.

Measuring the crack width is one of the important defect properties to estimate the bridge’s health. Cracks may develop into catastrophic failures with expensive consequences for both human life and the economy if they are ignored and are allowed to get worse. Nevertheless, the traditional tools to measure crack width are suffering from time-consuming and some limitations related to subjectivity and uncertainty. In view of this, this paper presented a model based on image processing techniques to measure crack width. The proposed technique relies on developing a model that is used for crack detection to be able to measure their maximum width. Two types of datasets are used in the presented models, and these images were taken from two different types of cameras. The precision and recall for the crack detection achieved 98.32% and 99.43% respectively. Accordingly, 87 concrete crack widths are measured by traditional tools and compared with model results. The comparison shows that the minimum crack width measured by the model is 0.5 mm and the mean absolute error is 0.046 mm. The model is compared with previous studies and demonstrated its effectiveness in measuring crack width. The results show the adequacy of the crack measurement method for safety bridge assessments and to avoid working in hazardous conditions for a long time.