Search

To enable quick and accurate detection of formaldehyde emissions from wood-based panels and to address the complexities of the full-scale chamber method and the inaccuracy of sensor-based methods, a modified formaldehyde emission model based on AdaBoost-MSBKA-SVMD-HKELM (AMSHKELM) is proposed. This model utilizes sensor data, which provides ease of use and rapid detection, as input and formaldehyde emission data measured by the full-scale chamber method as output. Initially, multiple strategies are employed to address the inherent limitations of the black-winged kite algorithm, which struggles to effectively find optimal solutions and is susceptible to getting trapped in local optima. The multi-strategy improved black-winged kite algorithm then optimizes key parameters of the successive variational mode decomposition (SVMD) and hybrid kernel extreme learning machine (HKELM). In addition, adaptive boosting is introduced to further improve the accuracy and robustness of the model. Then, the AMSHKELM formaldehyde emission modified deviation model is constructed to fit the decomposed subsequence. Moreover, an adaptive bandwidth kernel density estimation combined with the AMSHKELM is developed to construct an interval prediction model. Experimental results indicate that the AMSHKELM model achieves the coefficient of determination of up to 0.9767 and the root mean square error of 2.7141e-03, demonstrating higher fitting accuracy and stronger robustness compared to various other models. Additionally, the interval prediction model performs superiorly. This model can combine interval prediction information to effectively and comprehensively assess the pass rate of test samples, providing a fast and reliable solution for formaldehyde emission testing of wood-based panels.

Foundation models (FMs) have rapidly evolved and have achieved significant accomplishments in computer vision tasks. Specifically, the prompt mechanism conveniently allows users to integrate image prior information into the model, making it possible to apply models without any training. Therefore, we proposed a workflow based on foundation models and zero training to solve the tasks of photoacoustic (PA) image processing. We employed the Segment Anything Model (SAM) by setting simple prompts and integrating the model’s outputs with prior knowledge of the imaged objects to accomplish various tasks, including: (1) removing the skin signal in three-dimensional PA image rendering; (2) dual speed-of-sound reconstruction, and (3) segmentation of finger blood vessels. Through these demonstrations, we have concluded that FMs can be directly applied in PA imaging without the requirement for network design and training. This potentially allows for a hands-on, convenient approach to achieving efficient and accurate segmentation of PA images. This paper serves as a comprehensive tutorial, facilitating the mastery of the technique through the provision of code and sample datasets.

The application potential of unmanned aerial vehicles (UAVs) in marine search and rescue is especially of concern for the ongoing advancement of visual recognition technology and image processing technology. Limited computing resources, insufficient pixel representation for small objects in high-altitude images, and challenging visibility conditions hinder UAVs’ target recognition performance in maritime search and rescue operations, highlighting the need for further optimization and enhancement. This study introduces an innovative detection framework, CFSD-UAVNet, designed to boost the accuracy of detecting minor objects within imagery captured from elevated altitudes. To improve the performance of the feature pyramid network (FPN) and path aggregation network (PAN), a newly designed PHead structure was proposed, focusing on better leveraging shallow features. Then, structural pruning was applied to refine the model and enhance its capability in detecting small objects. Moreover, to conserve computational resources, a lightweight CED module was introduced to reduce parameters and conserve the computing resources of the UAV. At the same time, in each detection layer, a lightweight CRE module was integrated, leveraging attention mechanisms and detection heads to enhance precision for small object detection. Finally, to enhance the model’s robustness, WIoUv2 loss function was employed, ensuring a balanced treatment of positive and negative samples. The CFSD-UAVNet model was evaluated on the publicly available SeaDronesSee maritime dataset and compared with other cutting-edge algorithms. The experimental results showed that the CFSD-UAVNet model achieved an mAP@50 of 80.1% with only 1.7 M parameters and a computational cost of 10.2 G, marking a 12.1% improvement over YOLOv8 and a 4.6% increase compared to DETR. The novel CFSD-UAVNet model effectively balances the limitations of scenarios and detection accuracy, demonstrating application potential and value in the field of UAV-assisted maritime search and rescue.

This study delves into rotor–stator interaction within a bidirectional bulb tubular pump under cavitation conditions. Using pressure pulsation tests on a model pump and numerical simulations performed with ANSYS CFX software, we analyzed pressure pulsation and flow field data across three distinct flow rates and multiple cavitation numbers. Both time-domain and frequency-domain analyses were conducted to examine the patterns of pressure pulsation influenced by flow rates and cavitation numbers at various monitoring locations. A numerical flow field analysis further validated the findings. The results reveal that rotor–stator interaction manifests in the vaneless spaces of the pump during cavitation. The onset of cavitation alters the amplitudes of dominant frequencies at different flow rates. Near the guide vane and impeller, the dominant frequencies shift toward the impeller frequency and guide vane frequency, respectively. Under low-flow conditions, the rotor–stator interaction effect is more conspicuous due to the deteriorated flow pattern. Pressure pulsations are more strongly influenced in the front vaneless space (FVP) than in the rear vaneless space (RVP). This difference arises because the front guide vane destabilizes rather than stabilizes the flow pattern, worsening the rotor–stator interaction. Additionally, the FVP is less affected by the impeller than the RVP, further amplifying the influence of rotor–stator interaction on pressure pulsation. These findings provide a theoretical foundation for mitigating the effects of rotor–stator interaction on the operational stability and efficiency of bidirectional bulb tubular pumps.