Infrastructure is a significant factor in economic growth for systems of government. In order to increase economic productivity, maintaining infrastructure quality is essential. One of the elements of infrastructure is roads. Roads are means which help local and national economies be more productive. Furthermore, road damage such as potholes, debris, or cracks is the cause of many on-road accidents that have cost the lives of many drivers. In this paper, we propose a system that uses Convolutional Neural Networks to detect road degradations without data pre-processing. We utilize the state-of-the-art object detection algorithm, YOLO detector for the system. First, we developed a basic system working on data collecting, pre-processing, and classification. Secondly, we improved the classification performance achieving 97.98% in the overall model testing, and then we utilized pixel-level classification and detection with a method called semantic segmentation. We were able to achieve decent results using this method to detect and classify four different classes (Manhole, Pothole, Blurred Crosswalk, Blurred Street Line). We trained a segmentation model that recognizes the four classes mentioned above and achieved great results with this model allowing the machine to effectively and correctly identify and classify our four classes in an image. Although we obtained excellent accuracy from the detectors, these do not perform particularly well on embedded systems due to their network size. Therefore, we opted for a smaller, less accurate detector that will run in real time on a cheap embedded system, like the Google Coral Dev Board, without needing a powerful and expensive GPU.
Results of a laboratory modeling study are presented for excluding bed load sediment from a diversion/intake structure on the Rio Grande in Albuquerque, New Mexico. To achieve model similitude, crushed coal was used to model the prototype sediment in a 1:24 scaled model with an exaggerated slope such that shear force is adequately modeled. The Shields parameters and critical Shields parameters were matched between the prototype and the model, resulting in similar grain Reynolds numbers. Twenty-four tests, where guiding walls, submerged vanes, and/or the angle of the intake bay were altered, were conducted for a single river and diversion flow rate to develop the best performing sediment exclusion system at the intake structure. Independent vanes with 45°rotated intake bays were recommended for the most effective sediment exclusion at the intake structure.
River diversions are often equipped with some device to exclude fish, such as fish screens. Flow pattern changes due to fish screen systems were investigated using a three-dimensional numerical model solving the Reynolds-averaged Navier-Stokes (RANS) equations. A porous media obstacle, which is commonly used for ground water flow modelling, was employed to model a fish screen. Fish screens require a velocity component perpendicular to the screen (approach velocity), allowing for water diversion. Meanwhile, it is imperative that this velocity not result in pinning fish to the screen but allowing for fish to be guided to a different location. Thus the ratio of sweeping velocity to approach velocity (V R ) is an important criterion in fish screen design. 20:1 V R and 10:1 V R models were tested under high and low flow rates in this study. Screen head loss coefficients for various wire Reynolds numbers were compared with laboratory model measurements to verify the mathematical results. Two different screen types were simulated: perforated plate and wedged wire. Altering global porosity and local permeability of a porous obstacle results in flow direction changes that effectively simulate different screen materials in the numerical model. Model simulations of head loss coefficients and velocity ratios showed good agreement with the laboratory model measurements. The wedged wire allows for more control of the velocity ratio along the screen system than the perforated plate. Baffles installed behind each fish screen bay promote uniform flow distribution along the screen. The porous media obstacle assumption is shown to effectively simulate the hydraulics of various configurations of fish screens at river diversion channels.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.