Search

The self-circulating casing treatment can effectively expand the stable working range of the compressor, with little impact on its efficiency. With a single-stage transonic axial flow compressor NASA (National Aeronautics and Space Administration) Stage 35 as the research object, a multi-channel unsteady numerical calculation method was used here to design three types of self-circulating casing treatment structures: 20% Ca (axial chord length of the rotor blade tip), 60% Ca, and 178% Ca (at this time, the bleed position is at the stator channel casing) from the leading edge of the blade tip. The effects of these three bleed positions on the self-circulating stability expansion effect and compressor performance were studied separately. The calculation results indicate that the further the bleed position is from the leading edge of the blade tip, the weaker the expansion ability of the self-circulating casing treatment, and the greater the negative impact on the peak efficiency and design point efficiency of the compressor. This is because the air inlet of the self-circulating casing with an air intake position of 20% Ca is located directly above the core area of the rotor blade top blockage, which can more effectively extract low-energy fluid from the blockage area. Compared to the other two bleed positions, it has the greatest inhibitory effect on the leakage vortex in the rotor blade tip gap and has the strongest ability to improve the blockage at the rotor blade tip. Therefore, 20% Ca from the leading edge of the blade tip has the strongest stability expansion ability, achieving a stall margin improvement of 11.28%. [ABSTRACT FROM AUTHOR]

Hyperspectral images (HSIs) are pivotal in various fields due to their rich spectral–spatial information. While convolutional neural networks (CNNs) have notably enhanced HSI classification, they often generate redundant spatial features. To address this, we introduce a novel HSI classification method, OMDSC, employing 3D Octave convolution combined with multiscale depthwise separable convolutional networks. This method initially utilizes 3D Octave convolution for efficient spectral–spatial feature extraction from HSIs, thereby reducing spatial redundancy. Subsequently, multiscale depthwise separable convolution is used to further improve the extraction of spatial features. Finally, the HSI classification results are output by softmax classifier. This work compares the method with other methods on three publicly available datasets in order to confirm its efficacy. The outcomes show that the method performs better in terms of classification. [ABSTRACT FROM AUTHOR]

In order to categorize feature classes by capturing subtle differences, hyperspectral images (HSIs) have been extensively used due to the rich spectral-spatial information. The 3D convolution-based neural networks (3DCNNs) have been widely used in HSI classification because of their powerful feature extraction capability. However, the 3DCNN-based HSI classification approach could only extract local features, and the feature maps it produces include a lot of spatial information redundancy, which lowers the classification accuracy. To solve the above problems, we proposed a spatial attention network (SATNet) by combining 3D OctConv and ViT. Firstly, 3D OctConv divided the feature maps into high-frequency maps and low-frequency maps to reduce spatial information redundancy. Secondly, the ViT model was used to obtain global features and effectively combine local-global features for classification. To verify the effectiveness of the method in the paper, a comparison with various mainstream methods on three publicly available datasets was performed, and the results showed the superiority of the proposed method in terms of classification evaluation performance. [ABSTRACT FROM AUTHOR]