Puhui Chen

Cloud detection serves as a critical preprocessing step in remote sensing image processing and quantitative applications. However, prevailing deep learning-based models often depend on computationally intensive backbone networks to achieve high accuracy, which hinders their deployment in resource-constrained scenarios such as on-board processing or edge computing. To bridge the trade-off between accuracy and efficiency, this paper introduces a lightweight network for cloud detection. The core innovations of our network are twofold: (1) a dual-path feature enhancer that operates at the front end to extract and fuse multi-scale features through a parallel architecture, significantly enriching feature diversity and representational capacity, thereby alleviating the need for a complex backbone, and (2) a bidirectional gated fusion module, which adaptively integrates multi-scale features from the dual-path feature enhancer with deep semantic features from the backbone decoder through a gated attention mechanism and dynamic convolution, thereby enhancing feature discriminability. Comprehensive experiments on the public HRC_WHU dataset demonstrate that the proposed model achieves a high overall accuracy of 96.31% and a mean intersection-over-union of 92.82%, with only 12.04 GFLOPs of computational cost, outperforming several state-of-the-art methods. These results validate that our approach effectively balances high detection performance with computational efficiency, offering a practical solution for real-time, lightweight cloud detection in high-resolution remote sensing imagery.

Aiming at the complexity of network architecture design and the low computational efficiency caused by variations in the number of modalities in multimodal cloud detection tasks, this paper proposes an efficient and unified multimodal cloud detection model, M2Cloud, which can process any number of modal data. The core innovation of M2Cloud lies in its novel multimodal data fusion method. This method avoids architectural changes for new modalities, thereby significantly reducing incremental computing costs and enhancing overall efficiency. Furthermore, the designed multimodal data fusion module possesses strong generalization capabilities and can be seamlessly integrated into other network architectures in a plug-and-play manner, greatly enhancing the module’s practicality and flexibility. To address the challenge of unified multimodal feature extraction, we adopt two key strategies: (1) constructing feature extraction modules with shared but independent weights for each modality to preserve the inherent features of each modality; (2) utilizing cosine similarity to adaptively learn complementary features between different modalities, thereby reducing redundant information. Experimental results demonstrate that M2Cloud achieves or even surpasses the state-of-the-art (SOTA) performance on the public multimodal datasets WHUS2-CD and WHUS2-CD+, verifying its effectiveness in the unified multimodal cloud detection task. The research presented in this paper offers new insights and technical support for the field of multimodal data fusion and cloud detection, and holds significant theoretical and practical value.

A proposed strategy for managing airspace and preventing illegal drones from compromising security involves the use of autonomous drones equipped with three key functionalities. Firstly, the implementation of YOLO-v5 technology allows for the identification of illegal drones and the establishment of a visual-servo system to determine their relative position to the autonomous drone. Secondly, an extended Kalman filter algorithm predicts the flight trajectory of illegal drones, enabling the autonomous drone to compensate in advance and significantly enhance the capture success rate. Lastly, to ensure system robustness and suppress interference from illegal drones, an adaptive fast nonsingular terminal sliding mode technique is employed. This technique achieves finite time convergence of the system state and utilizes delay estimation technology for the real-time compensation of unknown disturbances. The stability of the closed-loop system is confirmed through Lyapunov theory, and a model-based hardware-in-the-loop simulation strategy is adopted to streamline system development and improve efficiency. Experimental results demonstrate that the designed autonomous drone accurately predicts the trajectory of illegal drones, effectively captures them using a robotic arm, and maintains stable flight throughout the process.

This paper proposes a cascaded dual closed-loop control strategy that incorporates time delay estimation and sliding mode control (SMC) to address the issue of uncertain disturbances in logistic unmanned aerial vehicles (UAVs) caused by ground effects, crosswind disturbances, and payloads. The control strategy comprises a position loop and an attitude loop. The position loop, which functions as the outer loop, employs a proportional–integral–derivative (PID) sliding mode surface to eliminate steady-state error through an integral component. Conversely, the attitude loop, serving as the inner loop, utilizes a fast nonsingular terminal sliding mode approach to achieve finite-time convergence and ensure a quick system response. The time-delay estimation technique is employed for the online estimation and real-time compensation of unknown disturbances, while SMC is used to enhance the robustness of the control system. The combination of time-delay estimation and SMC offers complementary advantages. The stability of the system is proven using Lyapunov theory. Hardware-in-the-loop simulation and flight tests demonstrate that the control law can achieve a smooth and continuous output. The proposed control strategy can be effectively applied in complex scenarios, such as hovering, crash recovery, and high maneuverability flying, with significant practicality in engineering applications.

The capacities of Z‐pinning in improving the bending performance of composite T‐joints were examined experimentally and numerically. It was found that Z‐pinning was not effective in enhancing the maximum bending load capacities of the T‐joints. Delamination at the interfaces of flange/filler, flange/flange, flange/skin, in the arc‐flange, as well as the fracture of the upper corner of the filler was observed. Among those failure patterns, the notorious delamination formed in the arc‐flange assumed the main responsibility of the disability of Z‐pinning in enhancing the maximum bending load capacity. Despite this, Z‐pinning was found to be highly effective in improving the residual plateau load‐carrying capacities of the T‐joints and the maximum bending displacement could also be dramatically increased, making the T‐joint maintain considerable bending load capacity under large deformation and preventing the T‐joint from catastrophe failure once the maximum bending load was attained.

The fastener pull-through resistance is a key performance index of composite laminates used for engineering application, and increasing research attention is being paid to developing methods for its calculation or estimation. The currently available research methods mainly focus on the standard test and the finite element analysis for determining the pull-through resistance of composite laminates suffering transverse load by the fasteners. Based on the results of the fastener pull-through resistance experiment performed on X850 composite laminates, a model for estimating the maximum affordable load of composite laminates for the fastener pull-through resistance is proposed, using generalized regression neural network technology. The inputs of this model are simplified to six parameters: the proportion of the ±45° layer of the laminates, the number of the layers, the thickness of the laminates, the bolt head shape, whether the bolt has a washer or not, and the nominal diameter of the bolt; the Gauss function is used as the hidden layer function. The model uses a large portion of the experimental data to train for finding the optimal smoothness factor, which is used to reconstruct the model, and simulation is performed with the remainder of the experimental data. The comparison between the estimated results using the model and the experimental results shows that the generalization ability of the proposed model can meet the estimation requirements. Moreover, the pull-through resistance of composite laminates under transverse load from a fastener can be estimated with high accuracy after some standard fastener pull-through resistance tests of the composite laminates.

A new periodic unit cell model was proposed to quantify the longitudinal tensile strength of laminates with different Z‐pin parameters. A modified three‐dimensional Hashin criterion was used to predict the failure of the laminate and Z‐pin, while maximum stress criterion was utilized to analyze the damage in the resin‐rich zone. Benchmark tests were carried out to verify the model, and finite element (FE) results agreed well with the experimental data. Hence, a parametric study was carried out to examine the influence of Z‐pin parameters on the longitudinal tensile strength and damage mode of unidirectional laminates. FE results show that the changing trend of the tensile strength against Z‐pin parameter is obviously more complicated than that of the modulus and is related to the change of damage mode or microstructure.

Experiments and simulations were carried out to study the tensile performance of unreinforced and Z‐pinned composite T‐joints with low Z‐pin density (Z‐pin spacing larger than 5 mm). It was found that the initial load drop of the Z‐pinned specimen was obviously smoother than that of the unpinned specimen, and the improvement to the ultimate strength of the T‐joint was over 45% by Z‐pinning. Besides, the tensile performance of the Z‐pinned T‐joint was significantly related to the distance of the Z‐pin to the symmetry plane of the T‐joint and Z‐pin diameter, while was independent of the column spacing. Regarding the numerical study, the proposed macro T‐joint model was found to be capable of successfully predicting the tensile performance of Z‐pinned and unreinforced T‐joints in terms of both load‐displacement response and damage mode.

This study investigated the effect of the fusion-bonded dots of veil interleaves on the crack propagation path of the interlaminar fracture of continuous carbon fiber reinforced epoxy resin. Two thin fiber layers (i.e., nylon veil (NV) with fusion-bonded dots and Kevlar veil (KV) physically stacked by fibers) were used to toughen composites as interleaves. Result shows that the existence of fusion-bonded dots strongly influenced the crack propagation and changed the interlaminar fracture mechanism. The Mode I fracture path of the nylon veil interleaved composite (NVIC) could propagate in the plane where the dots were located, whereas the path of the Kevlar veil interleaved composite (KVIC) randomly deflected inside the interlayer without the pre-cracking of the dots. The improvement of Mode I toughness was mainly based on fiber bridging and the resulting fiber breakage and pull-out. Fiber breakage was often observed for NVIC, whereas fiber pull-out was the main mechanism for KVIC. For the Mode II fracture path, the fusion-bonded NV dots guided the fracture path largely deflected inside the interlayer, causing the breakage of tough nylon fibers. The fracture path of the physically stacked KVIC occurred at one carbon ply/interlayer interface and only slightly deflected at fiber overlapped regions. Moreover, the fiber pull-out was often observed.