Based on the first-order shear deformation theory (FSDT) and Kelvin–Voigt viscoelastic model, one derives a wave equation of longitudinal guide waves in viscoelastic orthotropic cylindrical shells, which analytically solves the wave equation and explains the intrinsic meaning of the wave propagation. In the numerical examples, the velocity curves of the first few modes for the elastic cylindrical shell are first calculated, and the results of the available literature are compared to verify the derivation and programming. Furthermore, the phase velocity curves and attenuation coefficient curves of the guide waves for a functionally graded (FG) shell are calculated, and the effects of viscoelastic parameters, material gradient patterns, material volume fractions, and size ratios on the phase velocity curves and attenuation curves are studied. This study can be widely used to analytically model the wave propagating in inhomogeneous viscoelastic composite structures and present a theoretical basis for the excellent service performance of composite structures and ultrasonic devices.

This review systematically integrates recent advancements in path optimization algorithms for the automated layout of mechanical, electrical, and plumbing (MEP) systems within complex building environments. A hybrid optimization framework is introduced, combining the global search capability of Ant Colony Optimization (ACO) with the local refinement efficiency of the A* algorithm, enhanced by dynamic weight adjustment and context-aware mechanisms. Simulation experiments based on a hospital BIM model demonstrate that the proposed approach improves design efficiency by approximately 25–35% and reduces conflict incidence by around 40%. The framework further incorporates Building Information Modeling (BIM) and real-time clash detection enabled by IoT devices to enable scalable, multi-objective optimization in high-density spatial configurations. The potential of generative artificial intelligence—such as Generative Adversarial Networks (GANs) and diffusion models—is also explored for generating initial pipeline layouts and enhancing spatial adaptability. To support low-carbon building initiatives, the framework is adaptable to LEED-compliant sustainable MEP design practices. Despite notable progress, challenges remain in algorithmic scalability, dynamic constraint modeling, and multi-objective trade-offs. This review identifies research gaps in diameter-aware layout optimization and BIM-driven multi-scale generative modeling, and outlines future directions toward intelligent, high-performance MEP system design in future sustainable buildings.

As the global economy expands, waterway transportation has become increasingly crucial to the logistics sector. This growth presents both significant challenges and opportunities for enhancing the accuracy of ship detection and tracking through the application of artificial intelligence. This article introduces a multi-object tracking system designed for unmanned aerial vehicles (UAVs), utilizing the YOLOv7 and Deep SORT algorithms for detection and tracking, respectively. To mitigate the impact of limited ship data on model training, transfer learning techniques are employed to enhance the YOLOv7 model’s performance. Additionally, the integration of the SimAM attention mechanism within the YOLOv7 detection model improves feature representation by emphasizing salient features and suppressing irrelevant information, thereby boosting detection capabilities. The inclusion of the partial convolution (PConv) module further enhances the detection of irregularly shaped or partially occluded targets. This module minimizes the influence of invalid regions during feature extraction, resulting in more accurate and stable features. The implementation of PConv not only improves detection accuracy and speed but also reduces the model’s parameters and computational demands, making it more suitable for deployment on computationally constrained UAV platforms. Furthermore, to address issues of false negatives during clustering in the Deep SORT algorithm, the IOU metric is replaced with the DIOU metric at the matching stage. This adjustment enhances the matching of unlinked tracks with detected objects, reducing missed detections and improving the accuracy of target tracking. Compared to the original YOLOv7+Deep SORT model, which achieved an MOTA of 58.4% and an MOTP of 78.9%, the enhanced system achieves a MOTA of 65.3% and a MOTP of 81.9%. This represents an increase of 6.9% in MOTA and 3.0% in MOTP. After extensive evaluation and analysis, the system has demonstrated robust performance in ship monitoring scenarios, offering valuable insights and serving as a critical reference for ship surveillance tasks.