Search Results (3)

Semantic segmentation of remote sensing (RS) images is a pivotal branch in the realm of RS image processing, which plays a significant role in urban planning, building extraction, vegetation extraction, etc. With the continuous advancement of remote sensing technology, the spatial resolution of remote sensing images is progressively improving. This escalation in resolution gives rise to challenges like imbalanced class distributions among ground objects in RS images, the significant variations of ground object scales, as well as the presence of redundant information and noise interference. In this paper, we propose a multi-scale context extraction network, ASPP⁺-LANet, based on the LANet for semantic segmentation of high-resolution RS images. Firstly, we design an ASPP⁺ module, expanding upon the ASPP module by incorporating an additional feature extraction channel, redesigning the dilation rates, and introducing the Coordinate Attention (CA) mechanism so that it can effectively improve the segmentation performance of ground object targets at different scales. Secondly, we introduce the Funnel ReLU (FReLU) activation function for enhancing the segmentation effect of slender ground object targets and refining the segmentation edges. The experimental results show that our network model demonstrates superior segmentation performance on both Potsdam and Vaihingen datasets, outperforming other state-of-the-art (SOTA) methods. Full article

Hydraulic water plunger pumps have come to be widely used in coal mining, seawater desalination, and oil exploitation due to their high output pressure and large flow characteristics. In a high-pressure large-flow plunger pump, the leakage of the annular channel of the plunger pair is an essential factor affecting volume efficiency. The axial pressure gradient exists in the fluid inside the annular channel, resulting in the plunger and plunger sleeve forming similar funnel-like shapes. Moreover, the characteristics of large diameter, high working pressure, and low fluid viscosity of the plunger pump will lead to the complicated flow of the annular channel. The influence of eccentricity and structural deformation on leakage is difficult to evaluate. Therefore, considering the deformation gradient and eccentricity of the plunger pair and the compressibility of the water, the deformation equations and leakage equations of the annular channel under the laminar and turbulent flow state are derived in this study. The eccentricity and leakage of the annular channel under different pressure conditions are measured using a built sealing test bench. It is proved that the discrepancy between the calculated model and the experimental results is less than 6% under different pressures, which effectively predicts the sealing performance of plunger pumps. The results show that under the laminar flow condition, the effects of eccentricity, structural deformation, and medium compressibility on leakage are 148%, 4.92%, and 0.92%, respectively. In turbulent conditions, they were 31%, 2.84%, and 1.19%, respectively. Besides, the reasonable material pairing of the plunger friction pair can reduce the variation of leakage due to structural deformation. Full article

With combining multi-particle collision dynamics (MPCD) for the solvent and molecular dynamics (MD) for the polymer chains, we have studied the conformation and untying behaviors of a trefoil knot polymer chain translocated through a confined funnel-like channel. For the trefoil knot chain, we found that the untying knot behavior mostly happens during the translocation process, and the translocation behavior of linear chains is also simulated as a comparison. Some characteristics of the trefoil knot chain during translocation process, such as average gyration radius <Rg> and the average end-to-end distances <S> are discussed, and we statistic the scale relations of the translocation time versus the chain length, and that of the chain rigidity. This study may help to understand translocation behaviors of the knotted linear polymer chain in the capillary flow field. Full article