This paper proposes a deep convolutional neural network (CNN) -based technique for the detection of micro defects on metal screw surfaces. The defects we consider include surface damage, surface dirt, and stripped screws. Images of metal screws with different types of defects are collected using industrial cameras, which are then employed to train the designed deep CNN. To enable efficient detection, we first locate screw surfaces in the pictures captured by the cameras, so that the images of screw surfaces can be extracted, which are then input to the CNN-based defect detector. Experiment results show that the proposed technique can achieve a detection accuracy of 98%; the average detection time per picture is 1.2 s. Comparisons with traditional machine vision techniques, e.g., template matching-based techniques, demonstrate the superiority of the proposed deep CNN-based one.
Excessive drinking of alcohol is becoming a worldwide problem, and people have recognized that there exists a close relationship between chronic kidney disease (CKD) and alcohol consumption. However, there are many inconsistencies between experimental and clinical studies on alcohol consumption and kidney damage. The possible reason for this contradictory conclusion is the complex drinking pattern of humans and some bioactivators in wine. In addition, the design itself of the clinical studies can also produce conflicting interpretations of the results. Considering the benefits of light-to-moderate alcohol consumption, we recommend that CKD patients continue light-to-moderate drinking, which is beneficial to them. Because alcohol consumption can lead to adverse events, we do not advise non-drinkers to start to drink. Although light-to-moderate alcohol consumption may not pose a risk to patients with CKD, the patients’ condition needs to be considered. Consumption of even small amounts of alcohol can be associated with increased death risk. Additional clinical and experimental studies are needed to clarify the effect of alcohol on the kidneys and alcohol consumption on CKD patients.
Fluid–structure interactions of non-circular prisms are of significance from a scientific and practical viewpoint. In this paper, we present a new experimental observation of flow-induced vibrations and associated spectral characteristics of a transversely oscillating D-section prism at an angle of attack α varying from 0° to 180°, where α = 0° and 180° represent the configuration with the upstream curved and flat part, respectively. The Reynolds number range is 530–9620, and the reduced velocity range is 1–32, based on the projected prism width in the crossflow direction. The mass ratio of the prism is 11.35, and the structural damping ratio in still water is 0.0036. Based on the response amplitudes and spectral traits, the D-prism exhibits the typical vortex-induced vibration (VIV) at α = 0°–30°, the first transition response at α = 45°–60°, the small-amplitude VIV response at α = 105°–135°, the second transition response at α = 150°–165°, the combined VIV-galloping response at α = 90°, and the pure galloping at α = 75° and 180°. The second transition response between low- and high-amplitude branches is found to be hysteretic and intermittent. Flow physics behind the D-prism responses are further elucidated by the wake patterns based on a high-speed camera and the flow velocity spectra downstream of the prism.
Metal component surfaces are random textured and non-smooth. There are many stains on the surface of metal component that are similar to the gray scale of the scratches. The scratches have non-uniform gray distribution, various shapes, and low contrast in their background, posing challenges in accurate scratch detection. This paper presents a method for detecting weak scratches on metal component surfaces based on deep convolutional neural networks (DCNNs). First, a DCNN is trained using labeled scratch images. Then, the scratches and some faults are detected by the trained DCNN, and most of the faults can be removed through properly thresholding based on the size of connected regions. Finally, the scratch length united in the number of pixels is obtained by the skeleton extraction. The experimental results show that the proposed method can effectively deal with background noise, thereby achieving accurate scratch detection. INDEX TERMS Deep convolutional neural network, scratch, machine vision.
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.