Timely and effective identification of aircraft flight patterns is crucial in monitoring task. However, the existing flight pattern recognition methods have limitations in practical applications due to strong subjectivity and single pattern, which limits the flight monitoring capability in complex situations, and in turn leads to imprecise pattern boundary positioning and low recognition accuracy. For this reason, a flight pattern intelligent recognition method based on sensitive boundaries and long flight sequences is proposed for the intelligent recognition of flight states. In order to better explore the spatial relationships of multi-modal flight parameters, an adaptive graph embedding is designed. A denoising depth multi-scale autoencoder is proposed for the flight patterns at different durations, as well as the classification-weighted focal point loss and regression-joint spatio-temporal intersection loss for mitigating model loss. In order to verify the superiority of the proposed method, the real parameters of several civil flights covering 11 flight patterns are collected, and a flight state dataset is constructed by manual labelling. The results show that the proposed model is able to automatically distinguish different flight patterns in consecutive flight sorties and accurately extract the mode boundaries without any pre-processing or post-processing, with an identification accuracy of 99.07%. The intelligent recognition method can effectively improve the recognition accuracy and the flight state recognition of sensitive boundaries.
For the inaccurate track cost estimation in task allocation for multi-agent systems, a track cost calculation method based on extended rapidly-exploring random tree is proposed to rationally plan the motion trajectories of agents and improve the accuracy of track cost estimation. In order to solve the problem of premature contracting of dominant agents in improved contract net algorithm, an agent bidding transformation mechanism is proposed to make the dominant agents participate in the task bidding for multiple times and achieve the balance of task load between agents in a system. The simulated results show that the proposed track cost calculation method can be used to accurately calculate the trajectory between agent and target, and the trajectory between target and target. The agent bidding transformation mechanism solves the resource waste caused by the premature contracting of dominant agent, and the time of the agents to complete all tasks is reduced by 6.54%. However, when dealing with the dominant agent problem, the new mechanism will increase the bidding rounds of the entire task allocation.
The effective detection and tracking of water columns at marine impact points using visible light images is key to automatically check a target at sea. The existing detection and tracking algorithms still have a high false alarm rate and identity switch times (IDs) due to the movement of camera, the adjustment of focal length, and the changes of water columns. To solve the above problems, this paper proposes a detection and tracking algorithm based on dynamic features for water columns at marine impact points. The YOLOv8 target detector is used to detect the static water columns, and a small target detection head is added to the shallow feature map to enhance the model’s ability to detect small water columns. An improved ByteTrack tracker is used to track the water columns, and the tracking offsets caused by camera movement is compensated by combining camera movement and Kalman filtering. And then, a support vector machine is used for comprehensive decision-making to judge the water columns according to the spatiotemporal features of the water columns formation stage. Compared with traditional detection and tracking algorithms, the proposed algorithm is used to improve the three key performance indicators of multiple object tracking accuracy (MOTA), identification F1 (IDF1), and multiple object tracking precision (MOTP) by 7.8%, 5.1%, and 0.9%, respectively, the number of false positives (FP) is reduced by 112 times, and the numbers of IDs and false detections are both reduced to zero. Experimental results show that the proposed algorithm can not only accurately detect and track the water columns but also effectively exclude other interfering factors, thus achieving a significant enhancement in overall performance.
Remaining useful life (RUL) prediction is crucial for maintaining the reliability and safety of industrial equipment, but the existing RUL prediction methods still face many challenges in processing the high-dimensional sensor data and capturing the temporal degradation patterns. To address the above issues, this paper proposes a RUL prediction method based on bidirectional long short term memory network-variational auto encoder (BLSTMN-VAE) under the constraint of degradation trend smoothing. This method is used for data preprocessing, including data noise reduction, sliding window segmentation, and label correction. Then, a BLSTMN-based VAE type feature extractor is designed to effectively extract the nonlinear relationships and long-distance dependencies in time series data. Finally, a degradation trend smoothing constraint module based on manifold learning is proposed to enhance the robustness and generalization ability of the proposed model through the assumption of local invariance. The proposed RUL prediction method is verified using the aero-engine dataset. The results show that the proposed RUL prediction method outperforms various existing RUL prediction methods, and has lower prediction errors and higher stability.
In response to the problems of sonar operator having a heavy mental workload and the inability to ensure long-term effective working status in the process of underwater target recognition, a brain network feature-based underwater target recognition algorithm based on brain-computer interface (BCI) technology is proposed to assist sonar operators in achieving the rapid recognition of underwater targets. In order to enhance the extraction of brain neural activity information by the model and reduce the interference of brain irrelevant dependencies, the Granger causality (GC) and transfer entropy (TE) theories are used to reconstruct a brain network feature extraction algorithm, and a underwater acoustic target classification model is established by the proposed algorithm. A visual-auditory joint stimulation paradigm is designed for environmental simulation, and the experimental data is collected to complete the training and validation of the underwater acoustic target classification model. The analyzed results show that the proposed brain network feature algorithm can better capture the dependency information in neural activity. The validation of the underwater acoustic target classification model based on brain network features is verified by the visual-auditory joint stimulation paradigm, and the final recognition accuracy is over 90%.
The surface absorptivity of optical elements is the main factor causing the abnormal temperature rise under continuous laser irradiation. Research has found that the surface absorptivity of optical elements is influenced by multiple factors and exhibits nonlinear variations. Therefore, a concept of equivalent surface absorptivity is proposed to characterize the comprehensive absorption performance of optical elements for laser. Firstly, a finite element model of the optical element irradiated by Gaussian continuous laser is established to simulate the temperature rise process of optical elements under laser irradiation, and a laser irradiation effect experimental system is established. The surface absorptivity, surface morphology and temperature rise process of surface center point of optical elements are measured, tested and analyzed, and the correctness of the prtoposed model is verified by the experimental results. Based on the experimental results, the model parameters are adjusted to obtain the equivalent surface absorptivity of the optical element for laser. The research show that the simulated error of equivalent surface absorptivity is smaller and its simulated precision is higher compared with the measured surface absorptivity, The research results provide reference for the state monitoring of optical element and the pollution prevention and control.
In response to the significant reduction in target positioning accuracy caused by severe nonlinear factors affecting UAV electro-optical platforms, an algorithm based on improved mutant firefly algorithm-particle filter (IMFA-PF) is proposed for UAVs to accurately locate ground targets. Firstly, the state equations and measurement equations for target observation from UAV electro-optical platform are established. And then the IMFA-PF algorithm is utilized to estimate the geographic locatio of a target, and the interaction patterns among particles are altered by introducing multiple mutation strategies and an elasticity mechanism, thereby addressing the particle degradation issues caused by severe nonlinear factors and excessive optimization. Finally, the effectiveness of the algorithm is verified through a one-dimensional nonlinear unstable simulation system and actual flight experiments. Experimental results indicate that the proposed algorithm can improve the particle distribution’s resilience to observational nonlinearity and effectively tackle particle degradation issues, showing better robustness and positioning accuracy compared to the existing positioning methods.
The traditional detection methods have the disadvantages of inaccurate feature extraction and low detection efficiency when processing the complex and dynamic flight trajectory data with real-time change in data length. An proposed flight trajectory anomaly detection method using the gradient-based optimization of long short-term memory network and support vector data description model based on gradient training algorithm optimization (LSTM-GBSVDD)is proposed. The LSTM network is used to extract the key features of variable-length flight trajectories and convert them into a fixed-length sequence representation. A multidimensional hypersphere classifier is constructed using the SVDD algorithm, which is used to model the normal flight trajectories and identify the potentially abnormal flight trajectories. To further improve model performance, a gradient-based training algorithm (GB) is introduced to jointly train the parameters of LSTM and SVDD, which greatly improves the detection accuracy and computational efficiency. The simulated results show that the proposed flight trajectory anomaly detection method using the gradient-based optimization of long short-term memory network and support vector data description model based on gradient training algorithm optimization (LSTM-GBSVDD) has good effectiveness and superiority in dealing with complex and changeable flight trajectory anomaly detection tasks, and has good application prospects.
The influence of the free surface on the shape of supercavitation and the hydrodynamic characteristics of underwater vehicle is investigated. The motion process of a supercavitating vehicle near the free surface is numerically simulated using an adaptive mesh method and the volume of fluid method, and the effects of the free surface on the shape of supercavitation, and the lift, resistance and torque of the vehicle are analyzed. The research findings show that the presence of the free surface causes the tail of supercavitation to shift away from the free surface, resulting in the length of supercavitation being significantly shorter than that in an infinite water domain. The velocity of vehicle has a significant impact on its lift near the free surface. When the velocity of vehicle is less than 50m/s, its lift is negative; when the velocity of vehicle exceeds 60m/s, its lift becomes positive. When the vehicle is fully enveloped by the cavitation, only the cavitator head is wetted. A zero-torque point always appears near the front (x=1D, where D is the diameter of the cavitator) of the vehicle. When the interface of supercavitation tail intersects with the vehicle, it causes a change in the position of the zero-torque point. When the attack angle of the vehicle is positive, the torque is less affected by the water depth. However, when the attack angle is negative, the torque is significantly influenced by the water depth.
Aiming at the strong nonlinear problem of the interaction between underwater-launched projectile and ice, the key dimensionless parameters affecting the ice-breaking of projectile are derived by similarity theory. The scaled model test is carried out for the high-speed penetration of projectile through the ice layer. Based on the Gaussian fitting function, an ice load prediction formula is proposed. A fluid-solid coupling model of ice-breaking is established. The ice-breaking phenomenon, the ice load and the motion characteristics of projectile are analyzed by changing the nose shape of projectile, the kinetic energy of projectile and the thickness of ice layer. The results show that the volume of projectile nose cavitation decreases during ice-breaking, the volume of shoulder cavitation gradually increases, and the asymmetry of shoulder cavitation increases with the increase in ice thickness. When the initial speed of projectile is 40m/s, the extreme values of the ice loads on projectiles with hemispherical, spherical conical and pointed conical noses are 35700kN, 33200kN and 18600kN, respectively. The speed loss rate of projectile with pointed conical nose is the lowest, and its ice breaking effect is the best. Under the condition that the ice thickness is 180mm and the ejection pressure is 3MPa and 5MPa, respectively, the speeds of projectile after icebreaking are reduced from 13.1m/s and 17.8m/s to 9.5m/s and 13.4m/s. The greater the ice-breaking speed of projectile is, the lower the speed loss rate is, and the greater the kinetic energy loss is.The extreme value of ice load and the speed loss rate of projectile increase with the increase in ice thickness, and the effect of the initial speed of projectile on the load characteristics and motion characteristics weakens with the decrease in ice thickness.
The deployment mode of distributed laser decoy jamming system directly determines its decoy effect. An evaluation method is proposed for evaluating the deployment effectiveness of distributed laser decoy jamming system. The proposed method combines analytic scoring method with analytic hierarchy process. Firstly, a hierarchical structure model of deployment effectiveness is established to clarify which functional units affect the deployment effectiveness and which deployment elements are included in the deployment of each functional unit. Then, an analytic scoring model of each deployment element is established. During the specific implementation, the deployment score of each element can be obtained as long as the deployment information of each functional unit and the protected target information are inputted into the scoring model. Next, the weight of each layout element is determined by the analytic hierarchy process. Finally, the deployment effectiveness can be evaluated by multiplying and summing the scores and weights of each deployment element. The analytical scoring method overcomes the influences of subjective factors and knowledge structure level in the common expert scoring method. The proposed evaluation method can be used for the automatic evaluation of the protection effectiveness of distributed laser decoy jamming system.
At present, the determination of segmentation scale in the object-oriented seafloor acoustic image classification is empirical and significantly influenced by human factors. A spatially adaptive segmentation scale determination method using the confusion index as an objective index is proposed. The mean value and standard deviation of echo intensity corresponding to the segmentation objects are calculated by giving a set of segmentation scales. The unsupervised K-means clustering algorithm is then adopted to calculate the confusion indexes pf classification results at different segmentation scales, and the segmentation scale corresponding to the minimum confusion index is selected as the optimal scale to extract the seafloor image features. Based on the seafloor image features extracted at the optimal scale, a supervised classification model is established by combining the sampled data to predict the distribution of sediments in the whole surveying area. Experimental results prove that the spatially adaptive segmentation scales can be used to improve the classification accuracy significantly. The effectiveness of the proposed method is verified by cross-check in the experiment. Moreover, for thesegments that are with the relatively consistent the echo intensity characteristics, the classification accuracy can be further improved by introducing the terrain features.
To verify the feasibility of equipping electric field sensors on fast motion platforms to detect ship targets, this manuscript analyzes the mechanism of background electric field generation on fast motion platforms, builds a high-speed motion platform electric field detection system based on surface speedboats, and conducts real boat sea measurement experiments. The background electric field of speedboats at different positions, engine operating conditions, and sailing speeds is measured, and the measurement results are analyzed. By analyzing the experimental data at sea, it is found that the background electric field comes from: 1) the motion induced electric field of the speedboat platform, 2) the corrosion and electromagnetic radiation of the speedboat itself. The background electric field has high energy in the frequency band below 1Hz (static electric field), so the ship’s electrostatic field is not suitable as a detection signal source. When the speed is below 20 knots, the background electric field spectral density of the speedboat detection platform in the 1-30Hz frequency band is about 0.4μV/$\sqrt{\mathrm{Hz}}$, so the ship’s shaft frequency electric field can be used as the target signal source. To verify the feasibility of electric field detection on the speedboat platform, electric field targets of 100A·m were detected at different speeds of 5~15kn, with a detection distance of 1500m. Therefore, it is practical to use a fast motion platform equipped with electric field sensors to detect the ship’s electric field.
The path planning and dynamic collision avoidance techniques for aircraft are effective means and key capabilities to prevent collisions caused by flight path conflicts. The three-dimensional collision detection is used for flight conflict judgment, and an aircraft flight corridor conflict detection method based on multi-view geometry is proposed. The flight route information is obtained through the automatic dependent surveillance-broadcast (ADS-B) system, and an aircraft flight corridor model is designed to construct a local situation of potential conflict area. Then, the conflict situation in the aircraft flight corridor is detected based on the geometric relationships in the three views of the local situation. Simulated results show that the proposed method can intuitively and accurately judge the conflict situation in aircraft flight corridor. Compared to the traditional spatial grid analysis method, the efficiency of solving the conflict situation is improved by 66.35%, the efficiency of solving nin-conflict situation is improved by 98.17%, and the overall solving efficiency is increased by 84.38%.
As a common structure in engineering, axisymmetric structures have attracted widespread attention in the engineering community for their acoustic simulation calculations. A method to comprehensively utilize the equivalent surface sound source and point sound source for predicting the acoustic radiation from axisymmetric structure is proposed. In response to the non-uniqueness of solutions for the traditional equivalent point sound sources at the corresponding Dirichlet characteristic frequency inside the structure and the high sensitivity to acoustic parameters, a surface sound source is arranged inside the structure for the matching operations of external sound field, while the point sound source is located inside the surface sound source to ensure the uniqueness of the solution. Based on the symmetry of the structure, the surface sound pressure and vibration velocity are expanded into Fourier series form according to the rotation angle, and the orthogonality between the series is utilized to establish the expression of various undetermined coefficients. An equation for the relationship between the equivalent source strength and the undetermined coefficients of Fourier series is established based on the principle of wave superposition, and the virtual area integral equation is transformed into a product form of the outer boundary integral and rotation angle integral of axisymmetric structure. The shape function is utilized to interpolate the outer boundary of the structure in order to obtain the transfer function between the surface sound pressure and vibration velocity of axisymmetric structure. The accuracy of the proposed method is demonstrated by comparing the results of the proposed method with those of traditional equivalent point sound source method, surface sound source method, and analytical method.
Pressure field caused by ship sailing is an important information in the ocean battlefield. When a ship sails against waves, the pressure fluctuation caused by ship-wave interaction becomes the background interference of ship’s own hydrodynamic pressure field, which affects the accurate prediction and identification of ship target. Therefore, a fast algorithm for the target characterization of pressure field caused by ship sailing against regular waves in the shallow water is studied. The theoretical and numerical methods of pressure field suitable for regular waves environment and full speed of ship are established by using the wave source term method and moving pressure term method on the basis of shallow-water wave theory. Meanwhile, a fast and efficient numerical algorithm is developed, and an algorithmic program is compiled, which can simulate the regular waves in shallow water, the ship hydrodynamic pressure field in static water, and the temporal and spatial variation characteristics of pressure caused by ship sailing against waves. Based on the validation study, the characteristics of pressure field caused before and after a ship encounters with waves as well as the distribution characteristics of pressure at subcritical or supercritical speed are compared and analyzed, and the influence of waves interference on the temporal and spatial variation characteristics of pressure is revealed, which provides the theoretical basis and technical support for the prediction and identification of ship target under the disturbance of waves environment.
Study on the reliability importance of multi-state complex system can help analyze and identify the potential technical weaknesses in system design, and is of great significance for achieving the refined management of system state performance. By introducing an improved generating function model and constructing a system-level generating function for specific state reachable threshold, a generalized closed solution system and a high-precision analysis algorithm for reliability importance that can adapt to complex task functional systems with multiple states are proposed. Engineering case verification shows that the proposed algorithm has a high accuracy in distinguishing reliability importance, and is more conducive to achieving the refined management of reliable states in complex system. Meanwhile, the proposed algorithm has low requirements for programmatic computing resources and can avoid the technical bottleneck of state differential calculation in high-dimensional complex system. Its engineering application value is more prominent. The research results can be used for the importance analysis and refined management of other general quality characteristics in multi-state complex system, and have important technical guidance for scientifically allocating support resources and reasonably planning preventive maintenance work.
To analyze the induced electric fields generated by moving magnetic objects and address the limitations of existing models, this paper proposes a novel model that is more suitable for calculating the induced electric fields by the objects moving in any direction. The applicabilities and limitations of current models for induced electric fields from moving magnetic objects are evaluated. On the basis of evaluation, a mathematical model for the induced electric fields from moving magnetic objects is derived by using a vector potential model of magnetic dipole as the theoretical foundation. The proposed model is verified through theoretical analysis and simulating calculations. And it is further demonstrated through the case studies involving the magnetic field characteristics of actual ships. The results show that the proposed model is suitable for calculating the electric fields induced by the magnetic objects moving in any direction and is more concise in derivation and calculation compared to the traditional models based on Coulomb’s law and the Biot-Savart law. Case study results indicate that the induced electric fields generated by the motion of magnetic ships have distinct regional characteristics, with the electric field strength reaching mV/m level, which constitutes a significant component of the ship’s static electric field. The induced electric field model proposed in this study provides a more accurate theoretical basis for the detection of electric fields from moving magnetic objects and can be effectively applied to the detection and analysis of ship electric fields.
Modern warfare highly relies on the carriers such as images to collect intelligence. The images obtained in foggy conditions can interfere with the clear presentation of a battlefield scene and also conceal the important features, thus affecting the acquisition of battlefield information. In view of the common issues, such as color distortion and image detail loss, of current image dehazing algorithms, this paper proposes a multi-scale feature interaction dehazing network (MFI-DehazeNet), which uses a hybrid architecture of convolutional neural network (CNN) and Transformers. The MFI-DehazeNet uses an encoder-decoder structure to achieve a single image dehazing in an end-to-end manner. First, a multi-scale feature interaction module that enables cross-scale fusion of CNN network features is introduced inMFI-DehazeNet. And then the Transformer structure is improved by using a global feature expression module to boost the network’s global expression capability, thus addressing the receptive field limitations of convolutional structures. The output from the encoder, which integrates the two heterogeneous architectures of CNN and Transformer networks, is processed through the feature reconstruction module (i.e., the decoder) to restore and reconstruct dehazed images. Experimental results indicate that MFI-DehazeNet outperforms other algorithms in dehazing both synthetic and real hazy images.
With the widespread application of composite cylindrical shells in engineering fields such as missile launch and submarines, the random vibration caused by random loads has gradually become an important consideration for their dynamic design optimization. The first-order shear shell theory and Hamilton’s principle are used to construct the motion control equations of the shell, and the boundary conditions are applied by artificial virtual springs. The pseudo-excitation method and the reverberation-ray matrix method are used to separate the non-homogeneous excitation equations in the generalized solution vector, and the unified matrix column formula under base acceleration and random load excitation is derived to complete the stochastic dynamic analytical modeling and solution of composite cylindrical shells. The calculated stationary/non-stationary random response results are compared with finite element simulations to prove the effectiveness of the proposed analytical model. On this basis, a series of engineering examples for power spectrum are developed to reveal the influences of shell thickness-to-diameter ratio, orthogonal anisotropy ratio and number of plies on the random vibration response of cylindrical shell.
In the context of large-scale unmanned aerial vehicle (UAV) swarm cooperative flight scenarios, the high computational time consumption in swarm path planning is caused by frequent path conflicts. Aiming at the problem above,a large-scale UAV swarm path planning method based on reinforcement learning conflict resolution is developed. A dual-layer planning architecture, comprising a high-level layer of conflict resolution and a low-level layer of path planning, is constructed to reduce the spatial and temporal dimensions of path conflicts. At the high-level layer of conflict resolution, a conflict resolution strategy network based on the Rainbow deep Q-networks (DQN) algorithm training framework is designed. This network transforms the resolution process of each path conflict into the action selection process of left and right tree nodes of a binary tree. This approach maps different conflict resolution sequences to their outcomes, thereby reducing the traversal of tree nodes and improving the efficiency of conflict resolution. At the low-level layer of path planning, the time dimension is incorporated into the spatial collision avoidance strategy. A re-planning jump point search (ReJPS) method based on a node re-expansion mechanism is proposed, which increases the feasible planning domain and enhances the ability to resolve the path conflicts. Simulated results indicate that, compared to the path planning methods based on the conflict-based search (CBS)+A* and CBS+ReJPS, the proposed method reduces the average planning time by 86.64% and 19.65%, respectively, while maintaining comparable optimality.
The cavitation and ballistic characteristics of an underwater electromagnetically launched projectile during ejection process under the cross-flow environment are studied. The ejection process of underwater electromagnetically launched projectile without gas at different cross-flow velocities is numerically simulated based on the overlapped grid technology, VOF multiphase flow model and Schnerr-Sauer cavitation model. This paper aims to investigate the coupling mechanism of the cross-flow, the ejection cavitation and the motion of the projectile. The results show that the supercavities on the windward side decrease and the supercavities on the leeward side increase under the effect of cross-flow, while the windward surface of the projectile near the launch tube is still wetted. As the pressure of projectile increases, the viscous drag of projectile out of the launch tube increases, and the differential pressure force acts in the direction of the cross-flow, and it becomes more significant with the increase in the cross-flow velocity. Meanwhile the windward supercavities disappear, the windward surface is completely wetted, and the pressure in the wake region of the leeward side decreases dramatically, which leads to the large expansion of the supercavities. The local pressure near the leeward stationary point in the wake region increases, causing the center of the supercavities to collapse inward. The lateral force and drag of projectile motion are dramatically increased, and the pitching moment is along the clockwise direction due to the greater force in the conical section of projectile as compared to the cylindrical section, which leads to the deflection of projectile in the direction of the cross-flow, resulting in a clockwise deflection. The deflection of projectile becomes more pronounced with the growth of displacement, and the trajectory destabilization occurs.
Aiming at the structural damage caused by the water-entry impact of trans-media vehicle, an auxetic hood load-shedding method is proposed to make use of the special tensile expansion effect of auxetic structure, so that the hood can absorb more impact energy. The arbitrary Lagrangian-Eulerian algorithm is used to analyze the influence law of the auxetic hood on the load-shedding characteristics of the vehicle, and the numerical method is verified by experimental data. The results show that, compared with the traditional load-shedding cowl, the auxetic hood effectively reduces the impact load of the structure entering into water on the basis of structural lightweight, and the peak acceleration can be reduced by 75%, 70% and 68% at the water-entry speeds of 20m/s, 35m/s and 50m/s, which is a good load-shedding cushioning effect. And the load-shedding characteristics of auxetic structure differ greatly under the different parameters of the cell angle, the wall thickness and the length of the sides. The load-shedding characteristics of auxetic hood reaches the optimal effect with cell angle of 20°, cell wall thickness of 0.5mm and cell side length of 1.6 times.
In order to effectively identify the visual and auditory channel workloads of operators during the operation of a special vehicle, a machine learning-based workload recognition model is constructed from the electroencephalogram (EEG) signals acquired in a simulated driving environment. A total of 30 participants were recruited for experiment, and the visual and auditory workload states were induced by increasing the scenario complexity and administering an auditory N-back task. The experimental results show that, the power spectral densities in δ, θ, and α bands in the frontal lobe, δ and θ bands in the temporal lobe, θ band in the occipital lobe, and all four frequency bands in the parietal lobe under the auditory workload condition are significantly higher than those under the visual workload condition. Moreover, the brain network has a stronger connectivity at θ and β bands under the auditory workload condition exhibites. Notably, the θ-band power spectral density (PSD) emerges as the most effective feature for the identification of visual and auditory workload channels, enabling the random forest algorithm to achieve a maximum classification accuracy of 95.68%. Shapley additive explanations (SHAP) analysis indicates that the frontal lobe contributes most significantly to the classification outcomes. These findings demonstrate the effectiveness of EEG-based indicators in identifying the visual and auditory channel workloads, providing a theoretical foundation for the development of adaptive interaction systems.
A motion parameter estimation method based on acoustic measurement is proposed for identifying the kinetic characteristics of high dynamic underwater vehicle. In the proposed method, the position and velocity data series are obtained by point-by-point solution, and then the data jitters caused by random errors are removed by functional reconstruction and coefficient identification, so a smooth and continuous parameter sequence is obtained. In simulation, the high dynamic underwater vehicle moves from the depth of several tens of meters to surface, and the motion parameter is measured by the seabed four-receiver array. The simulated results show that the estimated parameter sequence has higher accuracy in vertical direction than the point-by-point solved one, and the root mean square errors (RMSE) of position and velocity are reduced by 27.8% and 47.2%, respectively. Calculations based on large samples indicate that the estimated parameter sequence approaches the true value, and the deviations of position and velocity are 0.042m and 0.056m/s, respectively. The water-tank test results show that the estimated parameter sequence generated by the high dynamic physical model is well consistent with the inertial sensor data, and the RMSEs of position and velocity in vertical direction are 0.024m and 0.141m/s, respectively. The proposed method can provide an accurate, smooth and continuous parameter sequence for the high dynamic underwater vehicle in performance testing and has certain engineering application value in sea trials.
In view of the time limit and complexity of ammunition support operation of carrier-borne aircraft, a scheduling optimization method is proposed for the ammunition support operation of carrier-borne aircraft facing the elevator hatch through scene modeling and task allocation under the premise of the known support task. A transportation path model with obstacle avoidance principle, an ammunition distribution model with equilibrium principle, and a carrier-based aircraft ammunition transport scheduling model with both actual combat and high efficiency are constructed. Based on the actual operation situation, the guarantee object of each elevator hatch is determined by Safe A* algorithm and greedy algorithm, and an improved genetic algorithm based on chromosome segment coding is proposed to solve the scheduling model with the goal of minimizing the completion time of ammunition support operation. The results show that the proposed method is better than other allocation strategies and scheduling algorithms in terms of time consuming and resource utilization, which verifies its feasibility and efficiency in the actual ammunition support process.
The route planning issue for island and reef cruise based on the dynamic collaboration among ships and drones is investigated to enhance the efficiency of maritime cruise. The issue is characterized by the dynamic cooperation among ships and drones, the precise spatio-temporal coupling, and the simultaneous optimization of discrete and continuous variables. Accordingly, a mixed-integer second-order cone programming model to minimize the mission completion time is developed for a combined optimization of the ship navigation path, the drone flight trajectory, and the drone takeoff and landing positions. The adaptive large neighborhood search (ALNS) algorithm is applied to design three destruction operators, two repair operators, and their adaptive mechanisms. A case analysis is conducted based on data from several islands and reefs in a specific maritime area, demonstrating that the cruise time can be reduced by more than 45% under the ship-drone coordination mode. The computational results indicate that the ALNS algorithm can solve the instances with up to 80 islands and reefs within 90 seconds, significantly outperforming the CPLEX solver and the two-stage heuristic algorithm in terms of solution quality and efficiency. The proposed route planning method for island and reef cruise based on ship-drone collaboration provides a reference for efficiently conducting maritime rights protection and law enforcement missions.
The sea surface corner reflector exhibits extremely strong radar echo characteristics. It creates the false targets that interferes continuously in the time domain and generates a deceptive situation to bring a significant challenge to the precision strike capability of a seeker. To address this issue, the immunity of infrared sensors to corner reflector interference is leveraged, and an intelligent recognition algorithm for corner reflectors in multi-target scenarios based on radar-infrared feature-level fusion is proposed. The target interference in infrared images is preliminarily discriminated by YOLOv8 network. The high-confidence target images can directly output the recognition results. The low-confidence target images are individually cropped for target correlation using radar-infrared angular information and radar feature extraction. The radar features and infrared images are input into a dual-channel fusion network, achieving the secondary recognition of low-confidence targets. The measured data validate that the recognition accuracy of the proposed method exceeds 96%. The research work has significant reference value for corner reflector interference recognition.
Effective range is one of the most important performance indexes of supercavitating projectiles, which is influenced by the coupling of shape and weight parameters. In order to increase the effective range of supercavitating projectile, a numerical model for calculating the effective range of supercavitating projectiles is established, and a combination of four factors and five levels is designed according to the principle of orthogonal test design. The effective range data set of supercavitating projectiles under the influence of shape and weight parameters is obtained by simulation calculation, and an optimization method of design parameters of supercavitating projectiles is established by using BP(back propagation) neural network method and genetic algorithm, and the maximum effective range of supercavitating projectile and its corresponding shape and weight parameters are obtained. The results show that the underwater trajectory of supercavitating projectile has a stable tail beat characteristic. The mass has the greatest impact on the effective range through range analysis In the absence of precise mathematical model, the accuracy of the effective range prediction model trained by BP neural network based on limited data points is high with the average error of 0.735%. The optimal range of the whole domain under the influence of four-factors coupling is obtained by genetic algorithm. The range is improved by 5.01% compared with the best result of data set, and by 1.95% compared with the result of orthogonal optimization. The research results can providereference for the overall design of supercavitating projectile.
With the escalating complexity of modern naval warfare, the role of carrier-based aircraft in intricate battlefield environments has become increasingly prominent. The collaborative optimization of task assignment and ammunition configuration for carrier-based aircraft is studied to enhance the combat effectiveness and resource utilization efficiency of carrier-based aircraft and alleviate the burden on commanders in formulating the combat plans. The key elements in the collaborative decision-making process are systematically analyzed. Then, an integrated optimization model of carrier-based aircraft task assignment and ammunition configuration is established by taking the maximized mission benefit, minimized destruction cost of carrier-based aircraft and minimized ammunition cost as the optimization objectives. Furthermore, a fitness-based adaptive global artificial bee colony algorithm is developed by combining the characteristics of the model for model solving. The simulated results demonstrate the effectivenesses of the proposed model and algorithm, and that they can significantly improve the mission benefits of carrier-based aircraft while reducing the operational costs. The research results can provide theoretical reference and decision-making basis for the development and improvement of carrier-based aircraft combat plan.
The water-exit process of supercaviting projectile often has an angle of attack due to launch perturbation, cross-current, wave, etc., which affects the trajectory of projectile and interferes with the successful water-exit of projectile. A numerical model for the water-exit process of supercaviting projectile with angle of attack is established based on the volume-of-fluid multiphase flow model and the moving computational domain method, and the water-exit processes of projectile at with different angles of attack and velocities are simulated. The calculated results show that a small angle of attack of the projectile has little effect on the cavity morphology in the water movement stage, and the shoulder and tail of projectile are wet with the increase in the angle of attack. A secondary cavity produced by the shoulder wetting may be rewrapped in the tail, and leads to the longer and obvious asymmetric radial distribution of cavity on the inflow side. The cavity has a tendency to expand after the projectile penetrates the water surface. The surface pressure of projectile is high at the beginning of the movement, and the high pressure region decreases rapidly as a cavity is generated, and the local high pressure occurs in the subsequent movement due to local wetting, cavity closure near the water surface, and splash collision with the water surface. The local high pressure occurs mostly on the inflow side, resulting in a higher pressure on that side than on the backflow side. The lateral forces and yaw moments appearing on the projectile cause the trajectory and attitude of the projectile to change and the angle of attack to decrease. The larger the initial angle of attack is, the more obvious its effect on the angle of attack, yaw angle change and trajectory of projectile is. When the projectile is at an angle of attack of 5° and the velocity continues to increase, the effect of velocity on the cavity morphology, the motion trajectory and yaw angle of projectile is weakened.
In order to ensure the safety of unmanned underwater vehicle (UUV) when performing the complex tasks such as coastline patrol, collision avoidance of large vessels, and traversing dense islands and reefs, an elliptical modeling obstacle avoidance method based on control barrier function (CBF) is proposed. A control barrier function containing the heading angle constraints is designed on the basis of elliptical modeling obstacles, a quadratic programming (QP) problem with constraints is constructed, and a closed-form obstacle avoidance guidance law is proposed by combining with the guidance law in obstacle-free environment. The simulated results verify the effectiveness of the proposed method, which globally satisfies the safety and stability requirements. The proposed method has practical application value for the safe navigation of unmanned underwater vehicle in complex marine environment.
Operational command decision-making is the core content of joint combat activities and the key to the success of joint combat action. The paper aims to fundamentally solve the problem about “weak command and decision-making ability of combined formation” from the perspective of cognitive psychology. Based on the systematic analysis of formation operational command decision-making, the bounded rationality decision-making is scientifically mapped from the perspective of dual-process theory. A function model of bounded rationality decision-making is constructed, the types of bounded rationality decision-making are divided, and the cognitive deviation of bounded rationality decision-making is identified. An intelligent hybrid decision-making framework is proposed for warship formation operational command. The strategy of enhancing the bounded rationality decision-making ability of formation operational command is formed. The results show that the research framework is scientific, effective and intelligent, and can greatly improve the commander’s operational decision-making ability. It provides strong theoretical and technical support for the development of the next generation auxiliary decision support system.
The launching mechanism of submarine-launched missiles under polar underwater environments is studied. The Arbitrary Lagrangian-Eulerian (ALE) method and the smoothed particle hydrodynamics (SPH) method are used to establish the fluid and infinite whole ice models, respectively, based on finite element software, and a plastic compressive tension material model with equation of state is used to reproduce the sensitivity of mechanical properties of ice to stain rate. Consequently, a fluid-structure interaction model of underwater vehicle ice-breaking is built. Based on the validated key numerical methods, the load and collision force characteristics of underwater vehicle under different ice thicknesses and vehicle speed conditions are investigated by simulation. and the stress distributions of vehicle and ice in the process of ice-breaking are analyzed. The result shows that the load and interaction time imposed on the vehicle increase with the increase in ice thickness, and with the increase in vehicle speed, the loads imposed on the vehicle increase, and the interaction time decreases.
For the simulation requirements of acoustic scattering characteristics of cyclic symmetric structures such as cable, wire rope and metasurface, a substructure method based on finite elements principle is proposed to realize the fast calculation of acoustic scattering. Through expanding the Fourier series of surface acoustic loads and displacements of a single-period substructure, and applying the phase-mapping constraints related to orders on boundary loads and displacements, the scattering acoustic field for each order and the total scattering acoustic field are rapidly calculated. The enhancement mechanism of scattering acoustic field in non-mirror direction observed in the experiment is analyzed. The simulated and experimental results of spiral groove structure indicate that the computational results obtained by the proposed method exhibit high accuracy. The proposed method requires less memory and achieves faster computation speed compared to the traditional three-dimensional finite elements method under the condition of the same computational accuracy, with an acceleration ratio being equal to the number of circumferential periods.
Amphibious aircraft inevitably suffers from the hydrodynamic impact of waves and other complex sea conditions during taxiing on the water surface, and in serious cases, the fuselage structure may be deformed and destroyed, which threatens the safety of airframe and aircrew. The structured arbitrary Lagrange-Euler (S-ALE) method is used to investigate the hydrodynamic response of amphibious aircraft during taxiing on a wavy water surface by taking a domestic large-scale amphibious aircraft as the research object. A coupled fluid-structure simulation method based on S-ALE and penalty function contact algorithm is established, and a numerical wave pool is generated and simulated by using the physically imitated push-plate wave-making mode and the mass-damped wave dissipation method, and the hydrodynamic characteristics and wave resistance of the aircraft during taxiing on calm and wavy surfaces are investigated, respectively. The results show that the S-ALE method can effectively simulate the dynamic response of amphibious aircraft taxiing on water surface; the attitude angle of aircraft taxiing at a steady speed of 19.4m/s under a wave height of 1.2m is 7°, and the corresponding resonance wavelength is two or three times of the fuselage length. When the ratio of the airplane fuselage to the wavelength is 1, the vertical overload becomes bigger and bigger under the environment of 1.8m wave height, and will gradually converges under the wave height of 1.2 m. While the changes of the wave height have no obvious effect on the pitch and heave of the aircraft.
The cavity flow and ballistic characteristics of a supercavitating projectile with tail fin under the action of transverse flow when entering water are studied. The vertical water-entry process of the projectile under the transverse flow interference is numerically simulated by using the overlapping mesh technique and a 6DoF dynamic model, and the influence of transverse flow on the cavitation shape, hydrodynamic characteristics and trajectory characteristics of the projectile during water entry is analyzed. The results show that the effect of transverse flow restricts the radial development of cavitation bubble on the windward side, but promotes the expansion of cavitation bubble on the leeward side, shifting the overall cavitation shape along the flow direction. As a result, the wetted area of the windward shoulder and tail fin of projectile is increased, and the distribution of the pressure field near the wetted area is changed, making the amplitude frequency of the projectile’s tail fin beat much greater than that in the absence of transverse flow. The intensification of tail fin beat motion inside the cavitation bubble increases the lift/drag coefficient and accelerates the attenuation of the projectile velocity. Besides, the deflection of cavitation shape along the flow direction causes the swing amplitude of pitch angle on the leeward side to be greater than that on the windward side, thus resulting in a deviation of the ballistic trajectory. Therefore, the transverse flow significantly impacts the trajectory and attitude angle of projectile.