Accurate segmentation of retinal vessels is an essential prerequisite for the subsequent analysis of fundus images. Recently, a number of methods based on deep learning have been proposed and shown to demonstrate promising segmentation performance, especially U-Net and its variants. However, tiny vessels and low-contrast vessels are hard to detect due to the issues of a loss of spatial details caused by consecutive down-sample operations and inadequate fusion of multi-level features caused by vanilla skip connections. To address these issues and enhance the segmentation precision of retinal vessels, we propose a novel high-resolution network with strip attention. Instead of the U-Net-shaped architecture, the proposed network follows an HRNet-shaped architecture as the basic network, learning high-resolution representations throughout the training process. In addition, a strip attention module including a horizontal attention mechanism and a vertical attention mechanism is designed to obtain long-range dependencies in the horizontal and vertical directions by calculating the similarity between each pixel and all pixels in the same row and the same column, respectively. For effective multi-layer feature fusion, we incorporate the strip attention module into the basic network to dynamically guide adjacent hierarchical features. Experimental results on the DRIVE and STARE datasets show that the proposed method can extract more tiny vessels and low-contrast vessels compared with existing mainstream methods, achieving accuracies of 96.16% and 97.08% and sensitivities of 82.68% and 89.36%, respectively. The proposed method has the potential to aid in the analysis of fundus images.

Essential service water pumps are necessary safety devices responsible for discharging waste heat from containments through seawater; their condition monitoring is critical for the safe and stable operation of seaside nuclear power plants. However, it is difficult to directly apply existing intelligent methods to these pumps. Therefore, an intelligent condition monitoring framework is designed, including the parallel implementation of unsupervised anomaly detection and fault diagnosis. A model preselection algorithm based on the highest validation accuracy is proposed for anomaly detection and fault diagnosis model selection among existing models. A novel information integration algorithm is proposed to fuse the output of anomaly detection and fault diagnosis. According to the experimental results of modules, a kernel principal component analysis using mean fusion processing multi-channel data (AKPCA (fusion)) is selected, and a support vector machine using mean fusion processing multi-channel data (SVM (fusion)) is selected. The overall test accuracy and false negative rate of AKPCA (fusion) are 0.83 and 0.144, respectively, and the overall test accuracy and $f_1-score$ of SVM (fusion) are 0.966 and 1, respectively. The test results of AKPCA (fusion), SVM (fusion), and the proposed information integration algorithm show that the information integration algorithm successfully avoids a lack of abnormal status information and misdiagnosis. The proposed framework is a meaningful attempt to achieve the intelligent condition monitoring of complex equipment.

Centrifugal pumps are essential components in various industrial applications, where their stable and efficient operation is critical. The impeller, a key part of these pumps, plays a pivotal role in energy conversion; thus, any fracture in its blades can significantly impact the pump's performance. This study investigates the effects of a single-blade trailing edge fracture on the flow characteristics of a centrifugal pump, aiming to provide insights into fault diagnosis and performance optimization. By employing a combination of experimental analysis and numerical simulation, the study analyzes changes in pump performance, pressure distribution, vortex structures, entropy production, blade loading, transient radial force, and pressure pulsation. The results indicate that minor blade fractures have minimal impact on the pump's head and efficiency, while severe fractures cause a noticeable decrease in head across all flow rates, with efficiency remaining relatively stable at low-flow rates. Transient analyses reveal that blade fractures alter the distribution and magnitude of radial forces, leading to changes in pressure pulsation characteristics, with the shaft passing frequency amplitude increasing and gradually surpassing the blade passing frequency amplitude. These findings provide important references for diagnosing fluid-induced centrifugal pump failures, effectively enabling the extraction of hydraulic features to optimize the fault diagnosis process.

Centrifugal pumps are essential in various industrial applications, and their stable and efficient operation has a direct impact on the overall performance of the system. This study simulates different lengths of fractures at the LE (leading edge) of a single blade to conduct an in-depth analysis of their effects on internal flow and transient characteristics. The study reveals that the most significant effects of blade LE fractures on pump performance occur near a flow rate of 0.8Qd, where the head and efficiency can decrease by up to 6.19% and 3.77%, respectively, compared to the original blades. Blade fractures lead to deterioration of flow on the pressure and suction sides, creating vortices and inducing leakage flow, while entropy production significantly increases in this area. A 230.1% increase in the distribution angle and a 26.6% increase in the maximum radial force reflect changes in the radial force distribution. Also, LE fractures make the wall pressure pulsations stronger at the SPF (shaft passing frequency), and they make the amplitude of the pulsations on the blade surface much bigger at both SPF and 3SPF frequencies. Finally, LE fractures change the way vibrations behave at radial measurement points in both the x and y directions in a big way. The acceleration amplitudes at SPF and 3SPF frequencies go up by 125.8%, 193.1%, and 62.5%, 184.6%, respectively. These findings provide an important theoretical basis for the early warning and diagnosis of blade fracture failures.