Detecting small objects in complex outdoor conditions remains challenging. This paper proposes an improved version of YOLOv8n for the detection of blueberry in challenging outdoor scenarios. In this context, this article addresses feature extraction, small-target detection, and multi-scale feature fusion. Specifically, the C2F-RFAConv module is introduced to enhance spatial receptive field learning and a P2-level detection layer is introduced for small and distant targets and fused by a four-head adaptive spatial feature fusion detection head (Detect-FASFF). Additionally, the Focaler-CIoU loss is chosen to mitigate sample imbalance, accelerate convergence, and improve overall model performance. Experiments on our blueberry maturity dataset show that the proposed model outperforms YOLOv8n, achieving 2.8% higher precision, 4% higher recall, and a 4.5% increase in mAP@0.5, with an FPS of 80. It achieves 89.1%, 91.0%, and 85.5% AP for ripe, semi-ripe, and unripe blueberries, demonstrating robustness under varying lighting, occlusion, and distance conditions. Compared to other lightweight networks, the model offers superior accuracy and efficiency. Future work will focus on model compression for real-world deployment.
Under low-temperature conditions, the load-bearing capacity of piezoelectric stacks arises from coupled thermo-electro-mechanical interactions, with temperature fluctuations, compressive prestress, and excitation voltage critically modulating performance. This study introduces an integrated measurement platform to systematically quantify these interdependencies, employing a cantilever-based sensing mechanism where bending strain serves as a direct metric of load-bearing capacity. A particle swarm-optimized theoretical framework guides the spatial configuration of actuators and sensors, maximizing strain signal fidelity while suppressing noise interference. Experimental characterization reveals three key findings: 1. Voltage-dependent linear enhancement of load-bearing capacity across all operational regimes, unaffected by thermal or mechanical variations; 2. Prestress-induced amplification (79–90% increase from 0 to 6 MPa) and thermally driven attenuation (15–30% reduction from 20 to −70 °C) of static performance; 3. Frequency-dependent degradation (1–6 Hz) in dynamic load-bearing capacity. The methodology establishes a robust foundation for designing multiphysics-compatible instrumentation systems, enabling precise evaluation of smart material behavior under extreme coupled-field conditions.
Piping systems can be analogized to the “vascular systems” of vessels, but their transmission characteristics often result in loud noises and large vibrations. The integration of flexible inserts within these piping systems has been shown to isolate and/or mitigate such vibrations and noise. In this work, a novel sandwich flexible insert (NSFI) was presented specifically to reduce the vibrations and noise associated with piping systems on vessels. In contrast to conventional flexible inserts, the NSFI features a distinctive three-layer configuration, comprising elastic inner and outer layers, along with a honeycomb core exhibiting a zero Poisson’s ratio. The dynamic characteristics, specifically axial impedance, of the fluid-filled NSFI are examined utilizing a fluid–structure interaction (FSI) four-equation model. The validity of the theoretical predictions is corroborated through finite element analysis, experimental results, and comparisons with existing literature. Furthermore, the study provides a comprehensive evaluation of the effects of geometric and structural parameters on the dynamic characteristics of the NSFI. It is worth noting that axial impedance is significantly affected by these parameters, which suggests that the dynamic characteristics of the NSFI can be customized by parameter adjustments.