Utilizing convolutional neural network (CNN) models, computer vision technology has become a reliable and powerful tool for detecting potential damage in concrete structures at the pixel level. In this study, an advanced SWIN U-Net architecture was introduced to detect concrete cracks. The model integrates attention-based convolutional neural networks to enhance the speed and accuracy of crack detection significantly. The distinctive features of the SWIN Transformer make the application of the model to images of varying sizes possible while the computational resources are used efficiently. To train the model, a dataset consisting of crack images, each accompanied by a corresponding mask that highlighted the relevant regions within the image, was used. The training data were augmented using Flip, Rotate, Random Contrast, Random Gamma, Random Brightness, Elastic Transformation, Grid Distortion, and Optical Distortion to counter potential overfitting. Additionally, L2 and spatial dropout regularization techniques were applied to the proposed model. The model was fine-tuned using stochastic gradient descent with the Adam optimizer, employing the binary cross-entropy loss function, and a learning rate of 0.001. The model was trained over 100 epochs with an adjustment scheduler. The performance of the model was evaluated using various metrics. Then, it was compared with three benchmarks and impressive results were achieved. Notably, the Dice loss and IOU values were 93% and 79%, respectively. The trained model had the exceptional performance score of 0.99 in accuracy, precision, recall, F1, and sensitivity.
28 September 2017 in Advances in Materials Science and Engineering
Steady increase in overexploitation of stone quarries, generation of construction and demolition waste, and costs of preparing extra landfill space have become environmental and waste management challenges in metropolises. In this paper, aggregate production is studied in two scenarios: scenario 1 representing the production of natural aggregates (NA) and scenario 2 representing the production of recycled aggregates (RA). This study consists of two parts. In the first part, the objective is the environmental assessment (energy consumption and CO2 emission) and economic (cost) evaluation of these two scenarios, which is pursued by life-cycle assessment (LCA) method. In the second part, the results of the first part are used to estimate the optimal combination of production of NA and RA and thereby find an optimal solution (scenario) for a more eco-friendly aggregate production. The defined formulas and relationship are used to develop a model. The results of model validation show that the optimal ratio, in optimal scenario, is 50%. The results show that, compared to scenario 1, optimal scenario improves the energy consumption, CO2 emissions, and production cost by, respectively, 30%, 36%, and 31%, which demonstrate the effectiveness of this optimization.
Computer vision which uses Convolutional Neural Network (CNN) models is a robust and accurate tool for precise monitoring and pixel-level detection of potential damage in concrete structures. Using a state-of-the-art Dense ResU-Net model integrated with T-Max-Avg pooling layers, the present study introduces a novel and effective method for crack detection in concrete structures. The major innovation of this research is the introduction of the T-Max-Avg pooling layer within the Dense ResU-Net architecture which synergistically combines the strengths of both max and average pooling to improve feature retention and minimize information loss during crack detection. In addition, the incorporation of Residual and Dense blocks within the U-Net framework significantly enhances feature extraction and network depth, resulting in a more robust anomaly detection. The implementation of extensive data augmentation techniques improves the robustness of the model while the application of spatial dropout and L2 regularization techniques prevents overfitting. The proposed model showed a superior performance, outperforming traditional and state-of-the-art models. It had a Dice Coefficient score of 97.41%, an Intersection-over-Union (IoU) score of 98.63%, and an accuracy of 99.2% using a batch size of 32. These results confirmed the reliability and efficacy of the Dense ResU-Net with T-Max-Avg pooling layer for accurate crack detection, demonstrating its potential for real-world applications in structural health monitoring. By taking advantage of advanced deep learning techniques, the proposed method addressed the limitations of traditional crack detection techniques and offered significant improvements in robustness and accuracy.
1 September 2023 in Journal of Engineering Management and Systems Engineering
Project delays pose a substantial challenge in the construction sector. The primary objective of this research is to discern the root causes of project delays in the construction industry and proffer potential solutions, inclusive of the application of building information modeling (BIM) and integrated project delivery (IPD). The integration of IPD and BIM, predicated upon established blueprints, was explored to streamline cost management processes and investigate the potential incorporation of design information within the framework of building price lists. A comprehensive review of extant literature identified 20 possible causes of delays in Iranian construction projects. This study employed a descriptive research design, analyzing data collected from 90 questionnaires completed by construction experts using the statistical package for the social sciences (SPSS) statistical software. A case study of the Dehloran Azad University building project was undertaken, utilizing Revit software for simulation exercises. Field investigations, coupled with a questionnaire disseminated among construction consultants and contractors, elucidated four primary factors contributing to project delays in Iran: 1) the employer's failure to fulfill financial obligations; 2) disregard for the socio-political-economic conditions; 3) absence of a feasibility study prior to tender participation; and 4) inadequate interdepartmental communication. Successful project execution hinges on active team participation and the value that such teamwork brings. The implementation of the IPD model was found to encourage increased enthusiasm and participation. Given that the most significant source of delays in Iran's construction projects was identified as financial issues, the adoption of BIM/IPD may mitigate delays and risks associated with inaccurate estimates. This approach was also found to be effective in projects that are in mid-stage completion.