Ionospheric nighttime enhancements are manifested in an increase of the electron density at nighttime. This paper studies the latitudinal variation of the specific local time of postmidnight enhancement peaks using ionosondes distributed at low latitudes. To obtain the parameters of the ionosphere, we manually extracted ionograms recorded by ionosondes. Cases show that there are significant latitudinal variations in the observed local time of the postmidnight enhancement peaks. Results show that the lower the geomagnetic latitude, the earlier the enhancement peak occurred in the geomagnetic northern hemisphere. Additionally, the enhancement peaks occurred earlier in the geomagnetic southern hemisphere than that in the geomagnetic northern hemisphere for these present cases. We suggest that the combined effect of the geomagnetic inclination and transequatorial meridional wind might be the main driving force for latitudinal variation of the local time of the occurrence.

Roller bearings are some of the most critical and widely used components in rotating machinery. Appearance defect inspection plays a key role in bearing quality control. However, in real industries, bearing defects are usually extremely subtle and have a low probability of occurrence. This leads to distribution discrepancies between the number of positive and negative samples, which makes intelligent data-driven inspection methods difficult to develop and deploy. This paper presents a small data-driven convolution neural network (SDD-CNN) for roller subtle defect inspection via an ensemble method for small data preprocessing. First, label dilation (LD) is applied to solve the problem of an imbalance in class distribution. Second, a semi-supervised data augmentation (SSDA) method is proposed to extend the dataset in a more efficient and controlled way. In this method, a coarse CNN model is trained to generate ground truth class activation and guide the random cropping of images. Third, four variants of the CNN model, namely, SqueezeNet v1.1, Inception v3, VGG-16, and ResNet-18, are introduced and employed to inspect and classify the surface defects of rollers. Finally, a rich set of experiments and assessments is conducted, indicating that these SDD-CNN models, particularly the SDD-Inception v3 model, perform exceedingly well in the roller defect classification task with a top-1 accuracy reaching 99.56%. In addition, the convergence time and classification accuracy for an SDD-CNN model achieve significant improvement compared to that for the original CNN. Overall, using an SDD-CNN architecture, this paper provides a clear path toward a higher precision and efficiency for roller defect inspection in smart manufacturing.

No abstract

No abstract

No abstract