水下无人系统学报

Deconvolution MIMO Sonar High Resolution Imaging Method Based on Acoustic Homing Platform

Cui Zhi-yuan, Yang Yun-chuan, Shi Lei, Yao Yuan, Liu Gang

, Available online , doi: 10.11993/j.issn.2096-3920.2025-0119

[Abstract](9) [FullText HTML] (7) [PDF 4046KB](8)

Abstract:
In response to the demand for imaging of the expected guidance part of the target by underwater vehicle, this paper attempts for the first time to apply MIMO sonar imaging to underwater vehicle acoustic homing, aiming to improve the resolution of underwater vehicle acoustic homing active imaging under limited aperture, obtain clear images, and guide underwater vehicle to judge the expected part of the target. This paper discusses the MIMO sonar transceiver array using the acoustic self-guided platform, and demonstrates through simulations that the MIMO sonar can be equivalent to a virtual SIMO sonar with a larger aperture, offering higher angular resolution than conventional SIMO sonar as well as a compact size. By using deconvolution processing, the angular and range resolution of the MIMO sonar can be effectively improved, while effectively suppressing the sidelobes in both angular and range dimensions. The innovation of this paper lies in designing the transmitting and receiving arrays based on an acoustic self-guided platform, developing Costas-coded signals, processing target scattering echoes, and validating the feasibility of the deconvolution MIMO sonar high-resolution imaging method on the acoustic self-guided platform, providing a new reference and method for high resolution imaging of MIMO sonar.

CFD Simulation for the Propulsion Performance in Cross-Medium Robot

SUN Yufeng, ZHOU Jing, ZHAO Liming, LIU Meiqin

, Available online , doi: 10.11993/j.issn.2096-3920.2025-0118

[Abstract](48) [FullText HTML] (24) [PDF 6966KB](15)

Abstract:
To meet the operational demands of cross-medium missions in complex ocean environments, this study conducts a computational fluid dynamics(CFD) analysis on the propulsion system of a cross-medium robot capable of both aerial and underwater motion. Owing to the significant differences in physical properties such as density and viscosity between air and water, traditional single-environment propellers cannot achieve high propulsion efficiency in both media. A three-dimensional transient CFD model covering typical aerial and underwater conditions was established. The Sliding Mesh and Volume of Fluid (VOF) methods were applied to perform comparative simulations of single-propeller and multi-propeller coupled systems. The study reveals the differences and patterns of thrust coefficient, propulsion efficiency, and wake interference under cross-medium conditions. Results show that at a speed of 3 knots, the underwater propulsion system achieves an efficiency of up to 48.48%, significantly higher than the aerial propulsion system (7.43%). Although multi-propeller operation induces wake coupling effects, an optimized layout can improve overall efficiency. This work establishes a unified CFD analysis framework for air-water propulsion and proposes a quantitative evaluation method for cross-medium propulsion performance, providing theoretical support for propulsion layout optimization and multimodal coordination design in cross-medium robots.

Research on USV path planning for assisted multi-AUVs navigation

MI Yanlong, YANG Huizhen, GUO Tianyang

, Available online , doi: 10.11993/j.issn.2096-3920.2025-0113

[Abstract](38) [FullText HTML] (17) [PDF 1625KB](15)

Abstract:
In the context of USV-assisted multi-AUVs operations, this paper proposes a multi-objective collaborative path planning method for USV-AUVs systems based on the Ultra-Short Baseline Locating System (USBL). The working principle of the USBL is analysed, and combined with the acoustic signal propagation characteristics in marine environments, the stable communication range for collaborative operations is defined by the effective zone of the USBL signal, the acoustic ray propagation boundary defined by ray acoustics theory, and the maximum effective range calculated using the sonar equation. While ensuring that the USV and AUV remain within the effective range of acoustic communication, the method further optimises path length, path smoothness, and communication performance between the USV and AUV. A multi-objective optimisation model for USV-AUVs collaborative path planning is established, and an improved genetic algorithm is used to solve it. Simulation experiments are conducted to investigate the influence of parameters such as communication distance and AUV operational depth on the USV planning path. The results indicate that the proposed method can effectively enhance the stability of USV-AUVs collaborative operations while satisfying USBL communication constraints, providing a reliable foundation for multiple AUVs to execute complex marine missions.

The influence of launch depth on the ejection and ignition process of underwater vehicles

LIU Shang, HUANG Xi, WANG Lihang, LIU Pingan, CHU Yue

, Available online , doi: 10.11993/j.issn.2096-3920.2025-0129

[Abstract](31) [FullText HTML] (17) [PDF 2593KB](16)

Abstract:
Underwater-launched vehicle technology represents an important development direction in the field of underwater vehicles, in which the out-of-tube ignition process is a coupled process involving vehicle ejection from the launch tube and near-muzzle ignition. During this process, high-temperature and high-pressure combustion gases interact with the surrounding water environment, forming a complex multiphase flow field, while severe impacts occur between the vehicle and the launch tube wall, leading to dynamic load variations. Investigating the flow evolution characteristics of this process is of great significance for improving the theoretical framework of underwater launch systems. To investigate the out-of-tube ignition characteristics of a vehicle under deep-water conditions, this study employs Fluent software in conjunction with overset grid technology and user-defined functions (UDFs) to systematically examine the influence of launch depth on the process. The results indicate that launch depth has a significant effect on the evolution of the gas jet and thrust characteristics during the out-of-tube ignition process: with increasing depth, the radial expansion of gas bubbles at the tube exit is suppressed, the entrainment effect at the tube mouth after vehicle separation is markedly enhanced, gas jet breakup becomes more likely, and nozzle vortices lead to engine thrust losses.

Research on Overall Matching Optimization Design of Supporting Parameters of the Power Propulsion System for Underwater Vehicles

ZHOU Jingkun, WANG Zhong, ZHOU Jingjun, WANG Qian, ZHANG Zhimin, GENG Xiaoming

, Available online , doi: 10.11993/j.issn.2096-3920.2025-0137

[Abstract](28) [FullText HTML] (11) [PDF 910KB](12)

Abstract:
To verify the effect of the overall matching optimization design, this study takes the simulation model of a typical underwater vehicle Power Propulsion System (PPS) as an example. By establishing its finite element simplified model and based on the Multi Objective Genetic Algorithm (MOGA), the length ratio of the coupling to the tail shaft, the support position of the tail shaft, and the support stiffness are selected as parameter variables. The vibration levels at four key positions on the shell are used as the objective functions to carry out separate optimization of parameter variables and overall matching optimization respectively. The results show that the vibration response of the system can be optimized by adjusting the length ratio of the coupling to the tail shaft, changing the support position and support stiffness of the tail shaft, etc. Among them, the vibration reduction effect after optimizing the length ratio of the coupling to the tail shaft can reach 5.2 dB, while the overall matching optimization is more significant than the separate optimization of each parameter, with the vibration level drop reaching 9.2 dB. Finally, the conclusion is drawn that in the process of optimizing the support parameters of the power propulsion system, each parameter can be matched and optimized through a multi-objective genetic algorithm to minimize the overall vibration response level of the system. The overall matching optimization method can provide a new optimization idea for the vibration reduction optimization design of the power propulsion system of underwater vehicles.

Multi-ship cooperative search method based on dynamic Voronoi partitioning

JIANG Haijun, ZHANG Yichao, SUN Yaping, CHEN Hongkun

, Available online , doi: 10.11993/j.issn.2096-3920.2025-0123

[Abstract](27) [FullText HTML] (13) [PDF 1696KB](13)

Abstract:
Traditional multi-ship cooperative search often uses fixed partitioning and ignores target evasion, leading to low detection probability and poor realism. This paper proposes a dynamic Voronoi-based method with multi-source information fusion. Built on a Bayesian framework incorporating sonar detection and target diffusion models, it dynamically updates the probability distribution of the target’s location. Adaptive Voronoi partitioning enables distributed task allocation, reducing redundant coverage and eliminating blind spots. A multi-source scoring model integrating presence probability, unexplored area, and local entropy, with time-varying weights, balances exploration and exploitation throughout the search. Compared with fixed-area sweep and particle-swarm-based methods in 1 000 Monte Carlo simulations under evasion scenarios, the proposed method significantly reduces target acquisition time and improves detection probability, demonstrating superior realism and scalability in adversarial environments.

Review of Research Progress on AI Driven Decision and Control of Maritime Unmanned Systems

DENG Yingjie, XU Yifei, YAN Jing, ZHAO Dingxuan, LI Mengxia

, Available online , doi: 10.11993/j.issn.2096-3920.2025-0095

[Abstract](46) [FullText HTML] (14) [PDF 1392KB](23)

Abstract:
Maritime unmanned systems refer to intelligent unmanned platforms on the water surface, underwater, and in the air with autonomous operation capabilities. It is an inevitable development trend in the future to adopt artificial intelligence(AI) technology to improve the decision-making and control level of maritime unmanned systems. Although AI technology has made considerable progress, its application in maritime unmanned systems is still restricted by many factors such as environmental interference and system characteristics. The basic decision-making and control framework of maritime unmanned systems are illustrated at first, and the shortcomings of traditional techniques are summarized. Then, the development status of AI-driven maritime unmanned systems in various countries is expounded, and the research progress and existing problems of AI in key technologies including environmental perception and positioning, path planning and guidance, motion control, and multi-system collaboration are summarized. Finally, the challenges and development opportunities of AI supporting the decision-making and control of maritime unmanned systems are discussed.

Ocean sound separation algorithm based on time-frequency interleaved attention

WANG Yudi, YANG Mingzhong, LIU Lixin

, Available online , doi: 10.11993/j.issn.2096-3920.2025-0127

[Abstract](35) [FullText HTML] (15) [PDF 2460KB](13)

Abstract:
Ocean sound contains rich information, but the complex ocean acoustic environment and the variable characteristics of underwater target signals pose a serious challenge to the ability of fine perception and discrimination of underwater sound features. In order to truly restore the underwater target sound of interest, the paper proposes a marine sound source separation algorithm based on integrated filtration module(IFM). The model adopts a frequency band segmentation strategy, uses an encoder to convert the mixed audio to the time-frequency spectrum, cross extracts the time-frequency gain using a multi-scale attention mechanism, and improves the separation capability of the underwater sound by the IFM proposed in the paper. Among them, the IFM employs an adaptive weighting mechanism to efficiently fuse the features extracted from the multiscale convolutional spatial filtering pathway and the self-attention feature-dependent pathway with the original features, and inputs the fused features into a decoder to reconstruct high-quality pure target audio, which enhances the details of the target signals while efficiently filtering out the background noises and interferences. Experimental results on marine typical sound datasets show that the proposed algorithm can significantly improve the audio separation performance of the target of interest, and the SDRi reaches 8.56dB and 10.74dB in the audio separation experiments between humpback whales and passenger ships, and killer whales and passenger ships, respectively, and also outperforms the existing baseline model in a variety of other metrics.

Overall Design and Control of a Pixhawk-Based Underwater Vehicle

LI Hanghang, ZHU Faxin, LI Jingjing, WANG Shenger

, Available online , doi: 10.11993/j.issn.2096-3920.2025-0136

[Abstract](33) [FullText HTML] (14) [PDF 2800KB](12)

Abstract:
To further optimize the development cycle and project cost of underwater vehicles, this paper designs and implements a Remotely Operated Vehicle (ROV) system based on an open-source hardware and software platform. Firstly, Fusion360 software is used for the three-dimensional modeling of the underwater vehicle, and 3D printing technology is adopted to achieve rapid prototyping. Secondly, a combined hierarchical control architecture of Pixhawk and Raspberry Pi is designed: the upper layer uses Raspberry Pi as the decision-making unit, which is responsible for running Robot Operating System (ROS) nodes, processing visual data, task planning, and high-speed communication with the ground; the lower layer uses Pixhawk as the real-time motion control unit, which calculates the navigation attitude and drives the thrusters. The MAVLink communication protocol is used to realize data interaction between the upper and lower layers, as well as between the system and the remote ground control station. Tests conducted in a static water environment show that the vehicle platform can stably receive and respond to control commands sent by the ground station, with a depth-keeping control accuracy within ±0.3 meters and a heading control deviation of less than ±3 degrees. The research indicates that the approach proposed in this paper, which is based on the open-source Pixhawk flight control platform and low-cost manufacturing technology, is feasible. This scheme shortens the development cycle and reduces the cost of the underwater robot system, and its hardware and software architecture has good scalability, providing reusable technical references and practical experience for the rapid development of small and medium-sized underwater detection equipment.

Rapid prediction and numerical verification of high-speed water-entry impact response of spherical-nosed cone

LIU Ping, HUANG Jiahao, WANG Xinggang, ZHAO Junqi, ZENG Mengcheng, YAN Zhi, XIONG Yongliang

, Available online , doi: 10.11993/j.issn.2096-3920.2025-0116

[Abstract](21) [FullText HTML] (15) [PDF 3178KB](13)

Abstract:
Aiming at the complex physical phenomena of spherical-nosed cone across media water entry, this study develops a rapid prediction model for water-entry impact overload of spherical-nosed cone based on water-entry dynamics and exact geometric characterization method. Based on water-entry dynamics of the projectile, for typical water entry stages, the rapid predicting model incorporates the influence of added mass to, obtain ideal fluid forces, while viscous fluid forces are obtained through force analysis of cross-sectional slice analysis of the submerged projectile. By integrating the ideal fluid forces and viscous fluid forces of each slice along the axial direction of the structural body, multi-stage dynamic equations governing the water entry process of spherical-nosed cone obtained finally. To verify the validity of the proposed model, numerical experiments employ multiphase flow model, k-ε turbulence model and overlapping mesh method. Based on the CFD, high-speed water entry process of conical-nose projectiles with 5°–15° angles and 50–90°(vertical) impact angles into quiescent water from air is investigate, then high-speed water entry law of the projectile is obtained. By comparing with the results from numerical simulations, it is demonstrated that the rapid prediction model could accurately predict the impact loads-as well as the occurrence of projectiles entering water, while achieving a 2-order-of-magnitude improvement in computational efficiency over conventional CFD methods, making it suitable for rapid assessment in the field of engineering.

Numerical Analysis of the Effect of Stern Flap on the Hydrodynamic Performance of Amphibious Vehicles

ZHANG Guoqing, FENG Yikun, JIN Haobin, GE Qiqian, XU Xiaojun

, Available online , doi: 10.11993/j.issn.2096-3920.2025-0126

[Abstract](30) [FullText HTML] (15) [PDF 1846KB](13)

Abstract:
To explore the effect mechanism of stern flap on the hydrodynamic performance of amphibious vehicles, a combination of towing tests and numerical simulation methods was adopted to comparatively analyze the motion parameters, waveforms and pressure distribution of the vehicle at different speeds before and after the installation of stern flap base on STAR-CCM+. The results show that stern flap significantly alters the hydrodynamic characteristics of the vehicle. In terms of motion parameters, its introduction leads to a trend of first decreasing and then increasing in resistance, with a resistance reduction rate of 21.6% at Fr = 0.738. The regulation effect on sailing attitude is prominent, with a peak difference in pitch angle reaching 63.3% (Fr = 0.738), and it effectively suppresses the heave within the speed range. The stern flap significantly reconstructs the waveform of flow field around the amphibious vehicle and the pressure distribution characteristics of vehicle by changing the pitch angle and heave amplitude, and its effect is speed-dependent.

Phase Compensation Self-interference Cancellation Method for Full-duplex Single-carrier Underwater Acoustic Communication

WU Songwen, LU Yinheng, ZHOU Feng, QING Xin, LI Yanlong, ZHAO Zichen

, Available online , doi: 10.11993/j.issn.2096-3920.2025-0157

[Abstract](30) [FullText HTML] (13) [PDF 2896KB](12)

Abstract:
Aiming at the problem that the self-interference cancellation performance is degraded due to the phase mismatch between the transmitting and receiving samples in the in-band full-duplex underwater acoustic communication, this paper proposes a method to improve the self-interference cancellation through two-stage phase compensation in single-carrier communication. The traditional method assumes that the phase of the reference signal is consistent with the phase of the received signal, and directly cancels under this premise. In contrast, this paper introduces phase compensation into the construction process of the reference signal, and takes the minimum residual energy as the optimization goal. This method first estimates the initial phase based on the correlation between the reference signal and the received signal, and further searches in the field of this result to find the optimal compensation phase and compensate, and combines the adaptive filtering algorithm to improve the self-interference cancellation ability. The effectiveness of the proposed method is verified by the simulation of single frequency signal and QPSK signal, the pool experiments and sea experiments. The results show that after phase compensation, the self-interference cancellation performance of the system is improved, the self-interference cancellation performance in the pool experiment is improved by 5.289 dB, and the self-interference cancellation performance in the sea trial experiment is improved by 1.986 dB. After compensation, the main side lobe ratio of the correlation peak of the far-end signal demodulation is optimized. The phase compensation method proposed in this paper can effectively improve the self-interference cancellation performance and filter convergence speed, thereby improving the accuracy of system demodulation, and providing key technical support for the practical application of full-duplex underwater acoustic communication.

A Fault-Tolerant Navigation Algorithm for AUV Based on Collaborative Fault Detection and Robust Estimation

XIAO Ruibin, MA Tiefeng, HU Youfeng

, Available online , doi: 10.11993/j.issn.2096-3920.2025-0156

[Abstract](41) [FullText HTML] (16) [PDF 2309KB](14)

Abstract:
When facing progressive faults in the Doppler velocity log (DVL), traditional adaptive filters fail to provide effective fault tolerance in autonomous underwater vehicle(AUV) integrated navigation systems due to conflicts between noise estimation and fault detection. To address this issue, this paper proposes a collaborative fault-tolerant navigation method that integrates long short-term memory (LSTM) networks for fault detection with variational bayesian adaptive Kalman filter (VBAKF) and IGG-III robust filtering. The proposed approach utilizes LSTM networks to effectively identify early characteristics of progressive faults. Upon fault confirmation, the filter switches from VBAKF to IGG-III robust filtering mode, dynamically adjusting weights to mitigate fault impact. Normal operation resumes using VBAKF after fault resolution. Experimental results demonstrate that, in the event of DVL progressive faults, the proposed method achieves higher navigation accuracy than several mainstream filtering algorithms, effectively suppresses state estimation distortion, and enhances the precision and robustness of AUV integrated navigation systems in uncertain underwater environments.

Research on Optimization of Acoustic Deception Countermeasure Based on Adaptive Mutation Particle Swarm

XIA Zhijun, REN Yunchong, HAN Yunfeng, JIANG Lei

, Available online , doi: 10.11993/j.issn.2096-3920.2025-0081

[Abstract](32) [FullText HTML] (18) [PDF 1303KB](12)

Abstract:
In view of the lack of research on the cooperative combat system of multiple acoustic decoys in the decision-making system for surface ships to defend against underwater guidance device, as well as the problems of low efficiency and poor portability in the traditional exhaustive method, this paper introduces the particle swarm optimization algorithm to optimize the countermeasure model and improves the particle swarm algorithm by introducing adaptive inertia weight and multi-radius mutation mechanism. A multi-objective optimization function composed of defense success rate, minimum engagement distance and ship survival time is established. The optimization parameters include the ship's evasive course, the launch distance and angle of the first flying acoustic decoy, and the launch distance and angle of the second flying acoustic decoy. The simulation results show that the proposed improved particle swarm algorithm has higher efficiency, faster convergence speed and higher fitness value compared with the traditional algorithm. Through simulation, the differences in the optimal countermeasure strategies under different bearing angles and their tactical significance are revealed, which has important reference value for the formulation of defense strategies against underwater guidance device in real naval battles.

Unmanned Aerial Vehicle Aeromagnetic Positioning Method for Nearshore Submarine Cables Based on Power Frequency Magnetic Characteristics

SUN Yunkun, LI You, CAO Xiangdong, CHEN Mei, ZHANG Lei, LI Minyue, ZHAO Jie, HAN Qi

, Available online , doi: 10.11993/j.issn.2096-3920.2025-0083

[Abstract](22) [FullText HTML] (9) [PDF 6578KB](13)

Abstract:
Aiming at the technical bottleneck of high-precision detection and positioning of the "last mile" of nearshore submarine cables, this study proposes a comprehensive unmanned aerial vehicle(UAV) aeromagnetic detection method integrating the analysis of power frequency magnetic field characteristics. Firstly, a forward model of the power frequency magnetic field of submarine cables is established, and the propagation and attenuation law of the power frequency magnetic characteristic signal of the cables is revealed through numerical simulation. Secondly, an innovative frequency-domain signal extraction algorithm based on power frequency magnetic characteristics is constructed, effectively improving the recognition accuracy of weak magnetic signals in the background of strong environmental noise. Then, a reverse analytical positioning method combined with the geomagnetic direction is proposed to achieve the meter-level spatial inversion of the direction of submarine cables. The experiment adopted the self-developed rotorcraft ultra-low-altitude (flight altitude of 1 meter) magnetic measurement unmanned aerial vehicle system to conduct actual measurement and verification in the coastal waters of Wenzhou. The results show that the system conducts aerial magnetic detection operations of power frequency magnetic characteristics under the complex terrain conditions of the intertidal zone. Through comparative analysis, it is found that the power frequency characteristic positioning method has significant advantages over the conventional magnetic anomaly positioning method in the nearshore shallow water area. Its positioning error does not exceed 4 meters, and it can accurately track the cable burial path. This research provides a new technical paradigm for the inspection and positioning of submarine cable projects.

A Double-Layer Autonomous Decision-Making Method Based on Expert Knowledge and Deep Reinforcement Learning

Xiao Wenwen, Cai Qianya, Mao Lifu, Lin Yuan, Zhao Yuan, WANG Mianjin

, Available online , doi: 10.11993/j.issn.2096-3920.2025-0098

[Abstract](41) [FullText HTML] (31) [PDF 1450KB](16)

Abstract:
Due to the complex and dynamic underwater environment, underwater unmanned systems face challenges of unpredictability and incomplete perception, which makes it difficult for them to accurately and efficiently accomplish autonomous decision - making tasks. Traditional methods highly rely on complete perception data and map information. However, limited by the dynamic characteristics of the underwater environment, it is difficult to construct effective map information in real - time, thus leading to limited efficiency of underwater unmanned systems in executing tasks such as underwater detection, resource exploration, and environmental monitoring. To address the above challenges, this paper proposes a double-layer decision-making method based on expert knowledge and deep reinforcement learning. This method can effectively enhance the adaptive ability of unmanned systems in underwater intelligent decision-making and significantly improve the efficiency of task execution. Specifically, an autonomous decision-making strategy generation method is first proposed to enhance the adaptive ability of underwater unmanned systems in unknown scenarios, further strengthening their autonomous decision-making level in complex environments. Secondly, a double-layer autonomous decision-making method is put forward. By enhancing the robustness of the system, it effectively ensures navigation safety. Finally, a multi - module design method is proposed to achieve the decoupling of each functional module, effectively improving the research and development efficiency of underwater unmanned systems. Taking the unmanned underwater vehicle (UUV) as the research object, experimental results show that the success rate and the convergence speed of the average reward value of the method in this paper outperform various benchmark methods in the simulation scenarios of UUV autonomous navigation and obstacle avoidance, providing a solid theoretical support for autonomous decision - making in real-world scenarios.

Analysis of the Impact of Shock Waves on the Safe Exit of the Rocket-assisted Vehicle Nose Cap during the Thermal Emission Process of a Concentric Canister Launcher

LIU Gangqi, YUAN Xin, GAO Shan, CUI Canli, YE Jianhong

, Available online , doi: 10.11993/j.issn.2096-3920.2024-0156

[Abstract](154) [FullText HTML] (76) [PDF 1529KB](22)

Abstract:
In response to the impact of shock waves on the safety of the vehicle nose cap during the concentric tube thermal launch process, computational fluid dynamics (CFD) software was used to numerically simulate the ignition and launch process. The propagation process of shock waves and gas generated by solid rocket motors in the concentric tube was analyzed in detail, and the force variation curve of the nose cap under the action of shock waves was obtained, revealing the force mechanism of the nose cap inside the tube under the action of shock waves. The test data illustrates the force variation process of the nose cap in the shock wave environment. The research results contribute to a clear understanding of the mechanism of force changes on the nose cap under the shock wave during the thermal emission process of concentric cylinders, and can be used to guide the safety design of the nose cap exiting the cylinder.

Research on Comprehensive Detection Methods for Weak Signals in Underwater Target Shaft Frequency Electric Fields

YU Pingyang, WANG Honglei, YANG Yixin

, Available online , doi: 10.11993/j.issn.2096-3920.2025-0079

[Abstract](94) [FullText HTML] (69) [PDF 1094KB](70)

Abstract:
To address the issue of weak target signals that are easily masked by noise in the detection of ship shaft frequency electric field signals, this paper proposes an electric field signal detection method based on the principle of ‘priority detection and selective enhancement.’ First, complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) is combined with narrowband power spectrum energy peak entropy ratio (EPER) features. Then, sliding window and dynamic threshold techniques are used to detect the target signal. After successful detection, the proposed method triggers a tri-stable stochastic resonance and variable step-size least mean P-norm (VSS-LMP) enhancement mechanism to further enhance the spectral characteristics of the target signal, thereby enabling the extraction of the target signal's characteristic frequency. Simulation results show that the proposed method achieves a detection accuracy rate exceeding 85% under a signal-to-noise ratio of -12 dB, with a false detection rate below 30%, and can accurately extract the target signal's characteristic frequency, providing a feasible technical approach for real-time monitoring of weak electromagnetic field signals from ships.

Ship Radiated Noise Recognition Based on Dual Low-Rank Adaptation Training

MA Zhixun, TANG Ning, LI Xuan, HAO Chengpeng

, Available online , doi: 10.11993/j.issn.2096-3920.2025-0114

[Abstract](108) [FullText HTML] (50) [PDF 1844KB](16)

Abstract:
To address the limited generalization capability of deep learning models in ship-radiated noise recognition, this paper proposes a dual low-rank transfer learning framework that simultaneously optimizes both model weights and feature representations. Specifically, in the weight space, the pretrained weights are frozen, and a lightweight low-rank weight adjustment(WLoRA) module is introduced to construct learnable low-rank increments. This strategy enables efficient fine-tuning with significantly fewer trainable parameters, thereby mitigating the risk of overfitting. In the feature space, considering the inherent low-rank properties of Mel spectrograms derived from ship-radiated noise, a low-rank feature adjustment(FLoRA) module is designed to compress and reconstruct the extracted features. This explicit low-rank constraint encourages the model to learn compact and discriminative representations that better capture the essential structures of ship-radiated noise. By jointly exploiting low-rank optimization in both the weight and feature dimensions, the framework maximizes the potential of pretrained models and improves transfer learning performance. The experimental results on two publicly available underwater acoustic datasets, ShipsEar and Deepship, demonstrate that the proposed method significantly enhances the performance of transfer learning in the classification model of ship-radiated noise compared to direct fine-tuning of pre-trained models. Furthermore, ablation studies validate the effectiveness of the two low-rank modules.

Optimized Smith Predictor Combined with HCOPSO Algorithm for Unman Surface Vehicle Heading Control

LI Zhiqi, LIU Lanjun, CHEN Jialin

, Available online , doi: 10.11993/j.issn.2096-3920.2025-0104

[Abstract](108) [FullText HTML] (45) [PDF 1857KB](18)

Abstract:
In the heading control of high-speed unmanned surface vessel(USV), the presence of time delay elements in both the forward channel and feedback loop significantly degrades the system's overall performance. Moreover, a larger delay to dynamic time ratio further exacerbates the control difficulty. Conventional Smith predictors can only effectively compensate for time delays in the forward channel and are ineffective against time delays in the feedback loop. In this paper, the time delay in the feedback loop is incorporated into the design of the Smith predictor, constructing a predictive model that accounts for time delays in both directions. This approach allows for simultaneous compensation of time delays in both the forward and feedback paths, thereby significantly reducing the erosion of the system's phase margin caused by bidirectional time delays. Furthermore, a hybrid mean center opposition based learning particle swarm optimization (HCOPSO) algorithm is introduced for the parameter tuning of the PID controller. This algorithm employs a mean center opposition - based learning strategy in the early stages of iteration to expand the search range and utilizes an adaptive compression factor in the later stages for fine-tuning. Thus, it combines the advantages of both global exploration and local exploitation. Simulation results based on a USV heading model demonstrate that the improved Smith predictor PID controller shows significant improvements in system overshoot and settling time compared to conventional PID controllers and traditional Smith predictor PID controllers, with a steady-state error of less than 0.1°. When the compensation model of the optimized Smith predictor contains parameter deviations, the system can still maintain good dynamic stability and steady-state accuracy. Additionally, when comparing the HCOPSO algorithm with other algorithms such as PSO, GA, and WOA for parameter optimization of the improved Smith predictor PID controller, the HCOPSO algorithm achieves an ITAE index that is respectively 55.38%, 22.47%, and 24.63% lower than those obtained by PSO, GA, and WOA, and it exhibits stronger disturbance suppression capability and faster heading recovery performance under different disturbance scenarios, which further verifies the effectiveness of the proposed method.

Research on the Extraction and Recognition of Space-Time-Frequency Features for Underwater Moving Targets

LIU Xiaochun, YANG Yunchuan, HU Youfeng, WANG Chenyu, LI Yongsheng

, Available online , doi: 10.11993/j.issn.2096-3920.2025-0067

[Abstract](118) [FullText HTML] (66) [PDF 1231KB](16)

Abstract:
Aiming at the issue of inadequate bearing-angle adaptability in active sonar target recognition, this paper elaborates on the physical mechanism of active sonar target information perception from wave equation theory. Based on generalized multiple signal classification(MUSIC) spatial spectrum estimation, a novel method is proposed for acquiring the pseudo three-dimensional spatial feature of underwater targets by incorporating distance information, thereby effectively enhancing the adaptability of spatial features across different bearing angles. Additionally, research is conducted on methods to enhance Pseudo Wigner-Ville Distribution(PWVD) time-frequency features and extract Doppler frequency shift distribution features of moving targets. By leveraging the complementary advantages of these two algorithms, the bearing-angle adaptability is further improved. To address the challenge of scarce and imbalanced underwater target samples, the concept of meta-learning is integrated to construct a data-level fusion target recognition network that incorporates spatial, time-frequency, and Doppler domain features. The network is trained and tested using simulation and experimental data. The results demonstrate that the fusion features significantly improve the bearing-angle adaptability and anti-interference capability, providing a novel approach for the development of intelligent underwater target recognition technology.

Latest Articles

Journal News> >

Download> >