Aircraft identification has been a research hotspot in remote-sensing fields. However, due to the presence of clouds in satellite-borne optical imagery, it is difficult to identify aircraft using a single optical image. In this paper, a Multi-path Interactive Network (MIN) is proposed to fuse Optical and Synthetic Aperture Radar (SAR) images for aircraft identification on cloudy days. First, features are extracted from optical and SAR images separately by convolution backbones of ResNet-34. Second, a piecewise residual fusion strategy is proposed to reduce the effect of clouds. A plug-and-play Interactive Attention Sum-Max fusion module (IASM), is thus constructed to interact with features from multi-modal images. Moreover, multi-path IASM is designed to mix multi-modal features from backbones. Finally, the fused features are sent to the neck and head of MIN for regression and classification. Extensive experiments are carried out on the Fused Cloudy Aircraft Detection (FCAD) dataset that is constructed, and the results show the efficiency of MIN in identifying aircraft under clouds with different thicknesses.Compared with the single-source model, the multi-source fusion model MIN is improved by more than 20%, and the proposed method outperforms the state-of-the-art approaches.
The application of general Joule-Thomson (J-T) coolers in the integrated electronic equipment is limited by its compactness in the heat exchanger and cooling power (a few milliwatts to hundreds of milliwatts). However, the microchannel with pillars has many advantages, such as compact structure, tiny axial thermal conductivity, and large heat transfer area. Besides, when the pressure variation of the fluid is large in the microchannel, the distributed Joule-Thomson effect is generated significantly. Therefore, this study proposed a throttling and heat exchange structure, where heat transfer and throttling coexisted, and fabricated a laminated microchannel distributed J-T cooler with pillars utilizing the processing technology of printed circuit heat exchanger.The refrigeration performance concerning the cold-end temperature, cooling power, and temperature distribution was then investigated through experiments with two refrigerants (argon and nitrogen). The study implies that the temperature difference and cooling power of the cooler both increase with the rise of the inlet pressure with argon, the no-load cold-end temperature is 166.1 K, and the gross cooling power is 3.83 W at 5.20 MPa. The temperature of the cooler increases with the rise of heat load, while the parasitic heat load decreases. The cold-end temperature is 186.0 K, then the parasitic heat load and the gross cooling power are respectively 3.17 W and 7.17 W at 5.20 MPa under the heat load's condition of 4 W. Comparing the refrigeration performance of nitrogen and argon, the cold-end temperature of nitrogen at 5.20 MPa is 235.7 K, which is close to that of argon at 2.98 MPa. Whereas the cooling time of nitrogen is slightly shorter than that of argon, and the cooling power is 3.10 W, higher than that of argon. In addition, this study provides new insight into increasing the cooling power and reducing the application cost of miniature coolers.
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.