Recently, the field of vehicle-mounted visual intelligence technology has witnessed a surge of interest in pedestrian detection. Existing algorithms for dense pedestrian detection at intersections face challenges such as high computational weight, complex models that are difficult to deploy, and suboptimal detection accuracy for small targets and highly occluded pedestrians. To address these issues, this paper proposes an improved lightweight multi-scale pedestrian detection algorithm, YOLOv8-CB. The algorithm introduces a lightweight cascade fusion network, CFNet (cascade fusion network), and a CBAM attention module to improve the characterization of multi-scale feature semantics and location information, and it superimposes a bidirectional weighted feature fusion path BIFPN structure to fuse more effective features and improve pedestrian detection performance. It is experimentally verified that compared with the YOLOv8n algorithm, the accuracy of the improved model is increased by 2.4%, the number of model parameters is reduced by 6.45%, and the computational load is reduced by 6.74%. The inference time for a single image is 10.8 ms. The cascade fusion algorithm YOLOv8-CB has higher detection accuracy and is a lighter model for multi-scale pedestrian detection in complex scenes such as streets or intersections. This proposed algorithm presents a valuable approach for device-side pedestrian detection with limited computational resources.

In light of recent advances in deep learning and Synthetic Aperture Radar (SAR) technology, there has been a growing adoption of ship detection models that are based on deep learning methodologies. However, the efficiency of SAR ship detection models is significantly impacted by complex backgrounds, noise, and multi-scale ships (the number of pixels occupied by ships in SAR images varies significantly). To address the aforementioned issues, this research proposes a Pyramid Pooling Attention Network (PPA-Net) for SAR multi-scale ship detection. Firstly, a Pyramid Pooled Attention Module (PPAM) is designed to alleviate the influence of background noise on ship detection while its parallel component favors the processing of multiple ship sizes. Different from the previous attention module, the PPAM module can better suppress the background noise in SAR images because it considers the saliency of ships in SAR images. Secondly, an Adaptive Feature Balancing Module (AFBM) is developed, which can automatically balance the conflict between ship semantic information and location information. Finally, the detection capabilities of the ship detection model for multi-scale ships are further improved by introducing the Atrous Spatial Pyramid Pooling (ASPP) module. This innovative module enhances the detection model’s ability to detect ships of varying scales by extracting features from multiple scales using atrous convolutions and spatial pyramid pooling. PPA-Net achieved detection accuracies of 95.19% and 89.27% on the High-Resolution SAR Images Dataset (HRSID) and the SAR Ship Detection Dataset (SSDD), respectively. The experimental results demonstrate that PPA-Net outperforms other ship detection models.

This study proposes a new condition diagnosis method for rotating machinery developed using least squares mapping (LSM) and a fuzzy neural network. The non-dimensional symptom parameters (NSPs) in the time domain are defined to reflect the features of the vibration signals measured in each state. A sensitive evaluation method for selecting good symptom parameters using detection index (DI) is also proposed for detecting and distinguishing faults in rotating machinery. In order to raise the diagnosis sensitivity of the symptom parameters the synthetic symptom parameters (SSPs) are obtained by LSM. Moreover, possibility theory and the Dempster & Shafer theory (DST) are used to process the ambiguous relationship between symptoms and fault types. Finally, a sequential diagnosis method, using sequential inference and a fuzzy neural network realized by the partially-linearized neural network (PLNN), is also proposed, by which the conditions of rotating machinery can be identified sequentially. Practical examples of fault diagnosis for a roller bearing are shown to verify that the method is effective.

The vertical axis hydrokinetic turbine is increasingly being used as a renewable energy device to harness tidal energy. In coastal regions with low tidal flow velocities, vertical-axis hydrokinetic turbines often exhibit low energy conversion efficiency, limiting their engineering applications. However, research in this field lacks systematic reviews and reliable solutions for improving efficiency. The paper, based on the traditional vertical axis hydrokinetic turbines, utilized numerical calculations and experimental methods to investigate the effects of blade helicity and airfoil curvature on the energy conversion efficiency of vertical axis hydrokinetic turbines in low flow velocity conditions. Additionally, an improved vertical-axis turbine model is proposed to enhance energy conversion efficiency in low-flow environments. The results indicate that increasing the blade helical angle and airfoil curvature can better optimize the flow conditions around the turbine, significantly improving the energy conversion efficiency of vertical axis turbines. The airfoil blade with a 20% curvature performs best at blade angle, with its power coefficient curve reaching higher peak values at several azimuth angles. At this point, the maximum efficiency reaches 24.42%. Compared to the conventional straight-blade design, the improved turbine model exhibits 6.13% increase in average energy capture efficiency, 3.70% increase in average dynamic torque, and 11.1% improvement in self-starting performance. Comparative analysis reveals that vertical-axis helical blade turbines exhibit superior hydrodynamic performance under low-flow conditions, effectively overcoming the limitations of conventional straight-blade turbines, including poor self-starting capability and low efficiency. This research provides valuable insights into improving the performance of vertical-axis turbines in low-flow environments and suggests innovative solutions for optimizing turbine design.

By combining computational fluid dynamics (CFD) and surrogate model method (SMM), the relationship between turbine performance and airfoil shape and flow characteristics at low flow rate is revealed. In this paper, the flow velocity tidal energy airfoil model is designed based on the Kriging model, and the original airfoil with a relative thickness of 12% and a relative curvature of 2.5% is obtained. The parameter optimization is carried out by setting the 4th CST equations through the surrogate model; the maximum lift-drag ratio is the optimization goal, the optimization design variable is 10, the maximum number of iterations is 100, and the maximum number of sub-optimization iterations is 200. The results show that the hydrodynamic performance of the airfoil with thinner thickness and more curvature is better, the maximum thickness part is shifted forward by 4.58%, and the lift-drag ratio is improved by 4.03%. The flow field and the efficiency are more stable, which provides an engineering reference for the optimal design of hydraulic turbine airfoils under low flow velocity. It supplements the research on the performance of turbine blades in low velocity.

The hulls of marine vehicles are generally very effective at attenuating airborne acoustic noise generated by their powertrains. However, conventional hull designs are generally not very effective at attenuating wide-band low-frequency noise. Meta-structure concepts offer an opportunity for the design of laminated hull structures tailored to address this concern. This research proposes a novel meta-structure laminar hull concept using periodic layered Phononic crystals to optimize the sound insolation performance on the air–solid side of the hull structure. The acoustic transmission performance is evaluated using the transfer matrix, the acoustic transmittance, and the tunneling frequencies. The theoretical and numerical models for a proposed thin solid-air sandwiched meta-structure hull indicate ultra-low transmission within a 50-to-800 Hz frequency band and with two predicted sharp tunneling peaks. The corresponding 3D-printed sample experimentally validates the tunneling peaks at 189 Hz and 538 Hz, with 0.38 and 0.56 transmission magnitudes, respectively, with the frequency band between those values showing wide-band mitigation. The simplicity of this meta-structure design provides a convenient way to achieve acoustic band filtering of low frequencies for marine engineering equipment and, accordingly, an effective technique for low-frequency acoustic mitigation.