Naval University of Engineering

Parameter identification-based control strategies are considered the preferred solution for achieving constant current and constant voltage charging control in communication-free inductive power transfer systems. However, identification errors in mutual inductance, load resistance and other parameters can affect control accuracy. To improve control accuracy and response speed, a communication-free control strategy based on neural networks and deep transfer learning is proposed. This strategy eliminates the need to identify parameters like mutual inductance and load resistance. Only a few measured data are required to train the network model offline, a trained model can online estimate output voltage/current will be obtained. By combining with a controller, constant voltage/current charging control can be achieved under conditions of real-time variations in mutual inductance and load resistance. The experimental results show that the proposed control strategy achieves a static error of only 1.5% and a response time of no more than 24ms. Compared to the parameter identification-based control strategy, the proposed strategy demonstrates lower static error, shorter response time, and a wider dynamic range.

Nerve injury-induced protein 1 (NINJ1) is a multifunctional membrane protein historically studied for its roles in nerve regeneration and cell adhesion. A groundbreaking study fundamentally revised our understanding by demonstrating that NINJ1 acts as the active executor of plasma membrane rupture in lytic cell death pathways such as pyroptosis and ferroptosis, establishing this final step as a biologically regulated process. Recent structural insights now reveal that NINJ1 adopts distinct molecular forms-including the full-length monomer, a soluble fragment, and a membrane-rupturing oligomer-which dictate its functional roles in adhesion, chemotaxis, and cell lysis. This revised understanding calls for a systematic integration of previous observations, particularly given NINJ1's context-dependent and often contradictory roles in inflammation, cancer, and tissue injury. Here, we review the structural basis of NINJ1 function, its pathological implications, and propose a unified structure-function model to reconcile its diverse phenotypes and bridge its traditional roles with its newly identified function in membrane rupture.

To address the calibration challenge caused by the nonlinear variation in intrinsic parameters during continuous camera zooming in UAV electro-optical pods, this paper proposes an online calibration method based on IMU-visual fusion. Traditional offline calibration cannot adapt to dynamic scenarios, while existing self-calibration methods suffer from slow convergence and insufficient robustness. The proposed method aims to achieve real-time and accurate estimation of camera intrinsic parameters during zooming. Specifically, we first construct a unified state estimation framework that encodes the internal and external parameters of the camera and the 3D positions of scene feature points into a high-dimensional state vector, then establish a camera motion model based on IMU data, construct a visual observation model by combining the pinhole camera and second-order radial distortion model to establish a nonlinear mapping from 3D feature points to 2D pixel coordinates, and adopt an improved ORB algorithm for feature extraction and LK optical flow method to achieve high-precision cross-frame feature matching to enhance the stability of visual observation. Most importantly, we design a tight-coupling fusion strategy based on the Extended Kalman Filter (EKF) prediction-update iteration mechanism, which fuses IMU high-frequency motion constraints and visual geometric constraints in real time to suppress parameter drift induced by focal length changes. Finally, we recursively solve the state vector to complete the online dynamic estimation of intrinsic parameters. Monte Carlo simulation experiments and real UAV flight experiments confirm that the method has both high estimation accuracy and strong environmental adaptability, can meet the high-precision calibration needs of UAVs in dynamic scenarios, and provides reliable technical support for accurate target positioning.

Underwater micro-bubble detection entails multiple challenges, including diminutive target sizes, sparse pixel information, pronounced specular highlights and water scattering, indistinct bubble boundaries, and adhesion or overlap between instances. To address these issues, we propose HSMD-YOLO, an improved detector tailored for high-resolution micro-bubble detection and built upon YOLOv11. The model incorporates three novel components: the Scale Switch Block (SSB), a scale-transformation module that suppresses artifacts and background noise, thereby stabilizing edges in thin-walled bubble regions and enhancing sensitivity to geometric contours; the Global Local Refine Block (GLRB), which achieves efficient global relationship modeling with an asymptotic linear complexity (O(N)) in spatial dimensions while further refining local features, thereby strengthening boundary perception and improving bubble–background separability; and the Bidirectional Exponential Moving Attention Fusion (BEMAF), which accommodates the multi-scale nature of bubbles by employing a parallel multi-kernel architecture to extract spatial features across scales, coupled with a multi-stage EMA based attention mechanism to enhance detection robustness under weak boundaries and complex backgrounds. Experiments conducted on an Side-Illuminated Light Field Bubble Database (SILB-DB) and a public gas–liquid two-phase flow dataset (GTFD) demonstrate that HSMD-YOLO achieves mAP@50 scores of 0.911 and 0.854, respectively, surpassing mainstream detection methods. Ablation studies indicate that SSB, GLRB, and BEMAF contribute performance gains of 1.3%, 2.0%, and 0.4%, respectively, thereby corroborating the effectiveness of each module for micro-scale object detection.