1,720,978 research outputs found
Lightweight pixel-wise segmentation for efficient concrete crack detection using hierarchical convolutional neural network
No full textThe aging of concrete structures is a threat to public safety; therefore, maintenance and repair of these structures have been highly emphasized. However, regular inspections to detect concrete cracks that rely on operators lack objectivity and consume a lot of time. To overcome this limitation, high-resolution image processing and deep learning have been adopted. Nevertheless, cracks on structure surfaces are still challenging to detect owing to the variety of shapes of cracks and the dependence of recognition performance on image conditions. Herein, we propose a new concrete crack detection method that applies the semantic segmentation technique using 1196 concrete crack images and labeled images produced in this study. A new segmentation algorithm is developed using a hierarchical convolutional neural network to improve speed, and a multi-loss update method is proposed to improve accuracy. The performance of the proposed network is evaluated in terms of accuracy and speed. The results show that the proposed network produces a 2.165% increase in the intersection over union of crack, 65.90% decrease in the average inference time, and 99.90% decrease in the number of parameters compared with the best accuracy results using existing segmentation networks. It is expected that the application of this improved crack detection method will result in faster and more accurate crack detection and, consequently, improved safety, thereby making it suitable for application in structure safety inspections.
Semi-empirical model for abrasive particle velocity prediction in abrasive waterjet based on momentum transfer efficiency
No full textAbrasive waterjet (AWJ) is a technology that removes a target material with an abrasive accelerated by ultra-high-pressure water. Recently, its application for rock excavations in civil and geotechnical engineering has increased. AWJ excavation performance is affected by the abrasive velocity formed by momentum transfer during mixing and acceleration. The abrasive velocity varies owing to changes in the abrasive flow rate, focusing tube diameter, and focusing tube length. In this study, the momentum transfer efficiency (MTE) according to the abrasive flow rate and focusing tube geometry was investigated by a numerical analysis to better understand the multiphase flow inside the AWJ system. The MTE was defined based on the theoretical relationship between the abrasive velocity ratio and focusing tube factor, and evaluated through the empirical relationship between the water stiffness and focusing tube length. The optimal abrasive flow rate for generating efficient MTE was approximately 15 g/s, which enabled economical and effective acceleration of abrasive particles. Accordingly, a prediction model based on the derived MTE was developed for the final abrasive velocity generated at the tip of the focusing tube. Using the prediction model, it is possible to evaluate the comprehensive relationship between various AWJ parameters. Based on the prediction model, the abrasive-water flow ratio to generate the optimal abrasive velocity was 0.83. The developed prediction model provides guidelines for selecting the optimal focusing tube geometry and applying an economical abrasive flow rate when designing an AWJ system.
Numerical study to prevent ground settlements induced by over-excavation with EPB shield TBM
No full text
Assessment of Abrasive Impact Frequency depending on the Traverse Rate in Waterjet Rock Cutting
No full textNumerical analysis of abrasive waterjet rock drilling according to the standoff distance
No full text
- …
