Search

To solve the non-uniformity of stress in space membrane structure and the lack of shear compliant border configuration design method, shear compliant borders are designed, optimized, and verified in terms of configuration. Firstly, an orthotropic model of the borders is built by combining Hill and Christensen-Lo composite material models. Secondly, a finite element form-finding method is put forward by establishing rectangular and cylindrical coordinates in different areas. The configuration of borders is obtained and the influence of the borders on the edge of the membrane is 0.23%, which means that the borders are compatible with the existing tensegrity systems, especially the tensioning components and the cable sleeves. Thirdly, simulation verifies that borders can cut the spread of shear stress and improve the stress uniformity in membrane structure. The maximum stress in the membrane effective area is decreased by 35.6% and the stress uniformity is improved by 30.5%. Finally, a membrane extension experiment is committed to compare the flatness of membrane surface under shear stress with and without shear compliant borders. The borders decrease the increment speed of flatness by 58.1%, which verifies the amelioration of stress uniformity. The shear compliant border configuration design method provides a reference for space membrane structure stress-uniform design. [ABSTRACT FROM AUTHOR]

Cerebrovascular and airway structures are tubular structures used for transporting blood and gases, respectively, providing essential support for the normal activities of the human body. Accurately segmenting these tubular structures is the basis of morphology research and pathological detection. Nevertheless, accurately segmenting these structures from images presents great challenges due to their complex morphological and topological characteristics. To address this challenge, this paper proposes a framework UARAI based on the U-Net multi-scale reverse attention network and sparse convolution network. The framework utilizes a multi-scale structure to effectively extract the global and deep detail features of vessels and airways. Further, it enhances the extraction ability of fine-edged features by a joint reverse attention module. In addition, the sparse convolution structure is introduced to improve the features' expression ability without increasing the model's complexity. Finally, the proposed training sample cropping strategy reduces the influence of block boundaries on the accuracy of tubular structure segmentation. The experimental findings demonstrate that the UARAI-based metrics, namely Dice and IoU, achieve impressive scores of 90.31% and 82.33% for cerebrovascular segmentation and 93.34% and 87.51% for airway segmentation, respectively. Compared to commonly employed segmentation techniques, the proposed method exhibits remarkable accuracy and robustness in delineating tubular structures such as cerebrovascular and airway structures. These results hold significant promise in facilitating medical image analysis and clinical diagnosis, offering invaluable support to healthcare professionals. [ABSTRACT FROM AUTHOR]