157 results about "Ship dynamics" patented technology

The invention relates to the technical field of detection and identification, and discloses a mobile ship dynamic tracking and locking method and system based on target detection and identification, and the method comprises the steps: constructing a manifold embedded network, and mapping the multi-modal features of a ship to a Riemannian manifold space; constructing a continuous evolution modeler of the Shenchang differential equation model, and predicting a continuous evolution trajectory of the features under time, view angle and scale changes; a multi-scale bridging network is constructed, and bidirectional conversion between long and short distance feature representations is realized; constructing a differential geometric attitude encoder, and representing a ship attitude in an SO (3) Lie group space; a feature memory and reconstruction mechanism is realized, and the problem of short-time disappearance target recovery is solved; the components are integrated to construct a unified tracking and locking system. According to the method, the problems of discretization processing limitation, feature representation fragmentation, cross-condition consistency deficiency and the like in the prior art are solved, remarkable technical effects are achieved in the aspects of cross-condition recognition capability, continuous feature evolution capability, short-time disappearance target recovery capability and the like, and the method is suitable for the scenes of Yangtze River shipping monitoring, maritime affair safety supervision and the like.

The invention discloses a hierarchical cooperative motion control method for a ship dynamic positioning and wave compensation embarkation system. The method comprises the following steps: acquiring historical motion data of a ship; the historical motion data of the ship are fused, and the current ship posture and speed are obtained; the prediction model generates a predicted value of the disturbance of the ship in the future preset time; extracting to obtain a low-frequency slow drift motion component; the total output force of the thruster is calculated, and the ship dynamic positioning system controls the thruster to work based on the total output force of the thruster so as to compensate the low-frequency slow drift motion component; a Stewart platform in the wave compensation embarkation system controls supporting legs to work based on the target lengths of the supporting legs so as to compensate low-frequency motion left after compensation of the ship dynamic positioning system and high-frequency motion which is not compensated; and residual disturbance after the Stewart platform is compensated is compensated through the gangway ladder. According to the invention, an energy distribution mode that low-frequency disturbance is compensated by a ship dynamic positioning system and high-frequency disturbance is compensated by a wave compensation embarkation system can be realized.

The invention discloses a ship dynamic collision avoidance decision-making method based on an improved DWA algorithm. The ship dynamic collision avoidance decision-making method comprises the steps of constructing sea chart environment data containing obstacle density through a grid method; establishing a dynamic elliptical ship domain based on a quaternion ship domain (QSD) model, and calculating a distance collision risk degree (NCRI) between ships based on the dynamic elliptical ship domain; improving a DWA algorithm evaluation function, and adding a path yaw evaluation function and a collision avoidance rule evaluation function on the basis of optimizing a speed and azimuth angle evaluation function; fusing the multiple evaluation functions by adopting a weight distribution method; and finally, generating a local collision avoidance optimization route based on environment data, NCRI and an improved DWA algorithm. According to the method, safety boundary dynamic adjustment, rule compliance constraint and ship control characteristic cooperation are realized, and the robustness and practicability of collision avoidance decision making under complex sea conditions are remarkably improved.

The invention relates to the technical field of anti-collision systems, in particular to an offshore wind power construction safety pre-warning system based on AIS (automatic identification system) data, which comprises a ship dynamic uncertainty modeling module for acquiring AIS signal updating frequency and positioning precision marks of a target ship and generating a ship future position probability ellipse. According to the invention, the position coordinate, the speed value and the course angle of the ship are obtained in real time based on the AIS data, the reliability and the motion trend of ship position prediction are determined by combining the AIS signal updating frequency and the positioning precision mark, and the future position probability ellipse of the ship is accurately generated; a protection area is dynamically constructed, comprehensive calculation is carried out in combination with the spatial relation between a ship future position probability ellipse and the positions of surrounding fan pile foundations, and a hourly dynamic collision risk index sequence is obtained; and further according to the statistical deviation between the current motion state of the ship and the standard parameter of the function partition, combining with path difference analysis to obtain a navigation abnormity comprehensive index.

The invention discloses a fault detection method for a ship power condenser system based on multi-scale feature fusion, relates to the fault detection method for the ship power condenser system based on the multi-scale feature fusion, and belongs to the field of fault diagnosis and safety monitoring of ship power systems. The objective of the invention is to solve the problems of insufficient detection precision and high false alarm rate of a traditional fault diagnosis method. The method comprises the following steps: step 1, acquiring input and output information of a condenser system; 2, constructing a multi-scale feature extraction model; 3, obtaining a trained multi-scale feature extraction model and parameters; 4, inputting online data of the condenser system into the trained multi-scale feature extraction model, and outputting predicted values of the liquid level and the vacuum degree of the condenser by the trained multi-scale feature extraction model; the residual generator obtains an online prediction error signal based on the prediction value; and step 5, performing fault diagnosis based on the online prediction error.

The invention relates to the technical field of maritime navigation and intelligent shipping, in particular to an electronic chart shipping relation network construction and dynamic updating method and system based on a chart database, and the method comprises the steps: obtaining electronic chart static data and shipping dynamic information, and carrying out standardized preprocessing to unify a space reference and an attribute format; defining node types and edge relation types of channel space elements based on the graph database, and constructing a shipping relation network; shipping dynamic information is accessed in real time, and the weight and the attribute of the side relation are dynamically updated to reflect the real-time state of the navigation channel; and receiving a user path planning query request, executing a path planning algorithm fused with the navigation constraint condition based on the updated network, and generating and outputting an optimal route, thereby effectively solving the problems of weak data association, difficult cross-scale fusion and poor dynamic adaptability of a traditional electronic chart, realizing intelligent management and accurate path planning of a channel relationship, and improving the user experience. And the shipping efficiency and safety are improved.

The invention relates to an unmanned ship dynamic channel modeling method in an offshore water surface environment, and the method comprises the steps: constructing a three-dimensional offshore water surface simulation scene which comprises a sea surface, a wharf facility, an unmanned ship cluster and a communication node; establishing a wireless channel propagation model based on a ray tracing method, and simulating a propagation mechanism of direct, reflection and diffraction paths; establishing a motion characteristic model of the unmanned ship under the action of waves, and obtaining six-degree-of-freedom pose data of the unmanned ship; generating multiple frames of scene copies in batches by adopting an intelligent batch processing dynamic reconstruction method; dynamically correcting an antenna pattern in each frame of scene copy according to the pose data so as to couple the influence of hull motion on antenna radiation characteristics; importing the corrected antenna pattern into the wireless channel propagation model to generate a dynamic channel response; simulation is executed, and channel data obtained through simulation are collected and analyzed. According to the method, the motion characteristics of the unmanned ship in waves and the wireless channel propagation mechanism can be accurately coupled, and the accuracy of dynamic channel prediction is improved.

The invention belongs to the technical field of ship power equipment health management, and provides a ship main engine fault early warning method and system based on an LSTM dynamic threshold model. The method comprises the following steps: preprocessing collected three-axis vibration original data to remove noise or interference signals in the collected data; by constructing the space-time matrix, the time for capturing the vibration of the marine main engine is associated with the space difference, and the fault recognition precision of the marine main engine is further improved; through the double-layer LSTM model, the state of the marine main engine at multiple times in the future is predicted; and through a dynamic threshold updating mechanism, the problem that the false alarm rate is high or a fault cannot be found in time is solved. The fault probability is calculated through the dynamic threshold value and the residual error, and a high-precision fault probability basis is provided for subsequent multi-level early warning. By setting multi-level early warning, the early warning signal of the corresponding level can be accurately triggered according to the fault probability, and the misinformation risk caused by single-level setting is effectively avoided.

The invention relates to the technical field of ship information monitoring, and discloses a ship information acquisition and monitoring system based on AIS signals. The system comprises a ship dynamic information acquisition module which receives AIS base station ship real-time position data, extracts latitude and longitude coordinates, a navigational speed and a course angle, and generates a ship dynamic trajectory sequence in combination with a timestamp; a sailing state feature extraction module identifies acceleration, deceleration and steering behaviors of the ship according to a speed change rate and a course angle change rate in the track sequence, and marks state switching points to generate a sailing state feature set; the regional sailing density calculation module divides sea area grids, counts the number of ships in each grid and staying duration, and generates a regional ship density distribution diagram; the abnormal behavior detection module compares the navigation behavior with a preset normal mode, and screens abnormal behavior points to form a set; and the risk area labeling module integrates the high-density area and the abnormal behavior points, calculates the aggregation degree, generates a ship navigation risk thermodynamic diagram, and realizes ship navigation monitoring and risk early warning.

According to the SARIMA prediction-based inland river navigation draught optimization management and control method for the ship with the overrun draught, a multi-source time sequence data set is obtained and preprocessed to obtain an input time sequence set, and the input time sequence set is processed through a constructed SARIMA model to obtain a water level prediction sequence; a ship dynamic draught prediction sequence is obtained through the constructed ship dynamic draught model based on water level prediction sequence processing, a draught safety margin judgment operator is constructed to carry out draught safety margin evaluation and risk grading, and finally a draught optimization management strategy is solved through the draught optimization management model and issued. A ship draught control closed-loop chain of prediction-calculation-evaluation-optimization-feedback is formed, through deep coupling of SARIMA time sequence prediction, ship dynamic draught calculation and draught optimization management, prospective recognition and dynamic regulation and control of draught safety margin of a draught overrun ship are achieved, and under the premise of guaranteeing navigation safety, the ship draught safety margin is effectively controlled. And the water depth utilization efficiency of the inland waterway and the ship loading efficiency are greatly improved.

The invention discloses an intelligent control method and system applied to a marine floating target, and the method comprises the steps: collecting target ship information and marine environment data in real time through a multi-mode sensor array, and carrying out the time-space alignment and fusion processing, and obtaining an environment state vector; based on the ship kinematics principle, wind and flow disturbance force is decomposed into resultant force and moment vectors under a ship body coordinate system; evaluating the danger degree of the current navigation environment through the dynamic risk index, carrying out navigation risk intelligent grading, and triggering a grading control strategy; a self-adaptive controller is designed based on the Lyapunov stability theory, anti-interference dynamic adjustment is carried out on the target ship, and track deviation caused by environmental interference is eliminated; when an obstacle or a high-risk sea condition is detected, intelligent obstacle avoidance and path re-planning are carried out, and an optimized path for avoiding the obstacle or a surge area is generated in real time; and calculating the minimum safety distance based on the ship dynamics model, and implementing a graded braking strategy to perform dynamic safety braking on the target ship.

The invention discloses a navigation aid information real-time transmission and analysis system based on a navigation mark, and relates to the field of navigation mark telemetering, the system is composed of a plurality of functional modules, and the system comprises a data acquisition module for acquiring dynamic data, meteorological data and hydrological data of ships near the navigation mark; the edge calculation module is used for generating a ship real-time track according to the ship dynamic data, obtaining a ship prediction track based on the ship real-time track and the hydrological data, and calculating a deviation degree based on a preset ship channel and the ship prediction track; the risk prediction module carries out risk analysis on the deviation degree according to meteorological data and carries out route adjustment according to a risk analysis result, and the route adjustment module generates an optimized route by applying an A * algorithm and considering ship dynamic constraint and channel limitation and then sends an instruction in time through the VHF radio module, so that risks of ship deviation from a channel, collision and the like are effectively avoided; the safety of sailors, ships and goods is greatly guaranteed.

The invention discloses a ship dynamic high-precision positioning and abnormal behavior recognition method, and particularly relates to the technical field of navigation positioning. The method comprises the following steps: performing time sequence synchronization and noise elimination on satellite signal propagation time ranging data, carrier phase data and ship attitude data received by a ship; outputting a reflection path coupling relation parameter by analyzing a time-varying coupling relation between the rolling and pitching states of the ship body and a sea surface specular reflection path; by establishing a multi-path deviation correction model, error correction values of satellite signal propagation time ranging data and carrier phase data are calculated; ship track motion state data are output by extracting ship space attitude change features and track geometric morphology features; and updating the ship trajectory motion state data by using the corrected satellite signal propagation time ranging data and carrier phase data to obtain ship positioning trajectory data, and outputting a ship abnormal behavior identification result. And the detection accuracy and reliability of the abnormal behaviors of the ship are improved.

The invention discloses an intelligent ship navigation system based on a space-time prediction risk field and deep reinforcement learning, relates to the technical field of ship navigation, and aims to solve the problem that a conventional navigation system is insufficient in dynamic risk assessment and prospective planning in the prior art. The technical key points are that the system comprises a multi-source data acquisition module, a dynamic risk mapping module, an intelligent path planning module, a visual interaction module, a risk early warning module and a self-checking module. According to the system, multi-source data such as weather, ocean current and ship dynamics are collected in real time, a predictive risk field is generated by using a long-short-term memory network, a route is optimized in combination with an adaptive deep reinforcement learning algorithm, and risk distribution and a recommended route are visually presented in a multi-scale three-dimensional form; the system can early warn a high-risk area in real time, and the reliability is ensured through a self-checking function. According to the invention, the sailing safety and the intelligent level of the ship in a complex environment are obviously improved.

The invention discloses a ship dynamic path planning method and system based on an improved DRRT algorithm, and relates to the technical field of ship automatic sailing, and the method comprises the steps: obtaining the two-dimensional plane environment parameters of a ship sailing sea area, determining the boundary range of the sea area, collecting the position and contour data of a static obstacle, and collecting the state information of a dynamic obstacle in real time, determining a starting point and a target point of ship path planning; an improved DRRT algorithm is adopted, sampling points are determined through target and path point bias sampling, the extended step length is determined through step length adaptive adjustment, a path node set is determined through path node trimming and reconnection, and an initial path is generated through cubic B-spline smoothing; obstacles are monitored, whether part of path results are invalid or not is judged, if the failure phenomenon exists, an improved DRRT algorithm is adopted for re-planning, and a dynamic path is obtained. According to the invention, the comprehensive requirements of the real-time performance, the safety and the path quality of the path planning in the intelligent navigation process of the ship can be met.

The invention relates to the technical field of marine environment governance, in particular to a DQN enteromorpha salvage optimal path optimization method based on adjacent target guidance, which comprises the following steps: S1, integrating enteromorpha drift trajectory prediction and ship dynamics response, constructing a time-space coupled salvage weight correction matrix, and dynamically reflecting the matching degree of drift displacement and steering capability; s2, screening a current optimal unaccessed unit as an adjacent target based on the correction matrix, predicting an enteromorpha position when a ship arrives, and generating a guide action set limited by a minimum steering radius; and S3, constructing a dual-channel DQN network, extracting task accessibility by a main channel, describing a drift change trend by an auxiliary channel, and generating an optimal salvage path adaptive to a complex drift environment through a dynamic attenuation fusion mechanism. According to the method, by constructing the enteromorpha-ship coupling model and the acceleration sensing guiding mechanism, collaborative improvement of feasibility, stability and environmental adaptability of path planning is achieved.

The invention discloses a marine traffic flow probability prediction method based on multi-source AIS-meteorological data fusion, and belongs to the field of marine traffic safety management, and the method comprises the following steps: S1, obtaining a standardized multi-source data set; s2, fusing the dynamic statistical characteristics of the AIS ship and the meteorological environment characteristics through a ship motion transfer function, and constructing a space-time patch considering a short-term ship motion trend and a long-term sea condition trend; s3, based on the space-time patch, fusing patch Transform time sequence modeling and adaptive dynamic graph space correlation learning to obtain a space-time fusion feature; and S4, outputting the traffic flow state prediction value and the probability distribution of the traffic flow key indexes. The marine traffic flow probability prediction method based on multi-source AIS-meteorological data fusion breaks through the limitation that a traditional method is single in data dimension, insufficient in space-time correlation capture and lack of probability confidence, and high-precision probability prediction of the marine traffic flow under the complex sea condition is achieved.

The invention discloses a ship intelligent navigation digital simulation method and system, and relates to the technical field of intelligent navigation and digital simulation, and the method comprises the following steps: 1, receiving a test task submitted by a user, the test task comprising task basic information, tested object information and scene configuration information; 2, calling a digital simulation model based on the scene configuration information, wherein the digital simulation model comprises a ship dynamics model, an environment model and a navigation algorithm model; 3, executing a test task, and collecting ship motion data, environment data and decision control data in real time in a simulation process; 4, processing and analyzing the collected data, and generating a test evaluation report; and 5, displaying the simulation process and result in real time through a visualization module.

This invention discloses a ship dynamic positioning anti-interference control method considering vertical dynamic optimization, comprising: establishing a four-degree-of-freedom nonlinear dynamic model of the ship and obtaining the error vector by combining the desired pose; defining a virtual control law by backstepping and processing the velocity error using a first-order filter; approximating the uncertainties in the model based on an improved Actor-Critic reinforcement learning framework and designing an interference observer to estimate external disturbances; calculating the compensated desired acceleration by combining the approximation output of the uncertainties, the estimated value of the external disturbances, and the velocity error; obtaining the thruster pitch ratio based on the desired acceleration and generating the final control command through a thrust distribution model. This invention can effectively handle model uncertainties and external environmental disturbances in ship dynamic positioning, especially optimizing vertical dynamic performance and improving control accuracy, response speed, and system robustness.

The invention relates to the technical field of ship power control, in particular to an intelligent linkage control system and method for multiple outboard engines based on dynamic load distribution. According to the intelligent linkage control system for the multiple outboard engines based on dynamic load distribution, the intelligent linkage control system comprises a protocol adaptation module, a sensor set and a central controller, the protocol adaptation module is connected with the central controller and used for receiving operation data from multiple outboard engines of different brands or protocols, and the sensor set is connected with the central controller. The unified control instruction of the central controller is converted into a specific protocol instruction identified by each outboard engine; and the sensor group is connected with the central controller and is used for acquiring attitude information, position information and motion state information of the ship in real time. According to the method, a universal protocol adaptation layer is constructed, and a dynamic load distribution algorithm based on ship kinematics and a multi-modal control strategy are introduced, so that intelligent collaborative operation of multiple outboard engines under high synchronization precision and high adaptability is realized.

The invention provides a ship cabin washing water discharge monitoring method and system based on Beidou short message communication, and the method comprises the steps: obtaining and analyzing the instantaneous flow rate of ship cabin washing water and a ship dynamic information data flow, and obtaining structured input data; judging whether a discharge event of the ship cabin washing water occurs, and if yes, converting structured data when the event occurs into a monitoring data packet; transmitting the monitoring data packet to a shore-end monitoring platform through a Beidou short message link to obtain a structured emission event record; judging whether emission is performed in the forbidden zone or not, if yes, continuing to judge whether the navigational speed is smaller than the preset minimum navigational speed or not, and obtaining a compliance judgment result; and according to a compliance determination result, alarm pushing is carried out, an alarm evidence chain is generated, and an emission event file is obtained. According to the invention, active discovery, real-time alarm and evidence solidification of the discharge behavior of the cabin washing water of the ship are realized, and the intelligent and precise level of maritime affair supervision is obviously improved.

The application discloses a ship power system optimization scheduling method and system based on a genetic algorithm, and relates to the technical field of ship power control. The method comprises the following steps: acquiring real-time operation parameters of a ship power system; constructing an initial population of the genetic algorithm based on the operation parameters; calculating a comprehensive fitness value of each individual based on energy consumption characteristic indexes and emission characteristic indexes; performing selection operation, crossover operation and mutation operation on the initial population to generate a new population; repeatedly performing population iteration optimization until a preset condition is met; outputting a combination of ship speed adjustment parameters, a generator set start-stop decision sequence and a power distribution scheme; and generating a ship power system control instruction set. The ship power system optimization scheduling method and system based on the genetic algorithm improve the operation efficiency of the ship power system, reduce energy consumption and reduce carbon emissions.

The application provides an unmanned ship dynamic collision avoidance decision method and system based on a diffusion model and an adversarial inverse reinforcement learning. The method comprises the following steps: 1, collecting expert collision avoidance data; 2, training a diffusion model; 3, performing data enhancement; 4, building a training environment; 5, constructing a generator and a discriminator; 6, updating the discriminator; 7, updating the generator; and 8, completing the training. The diffusion model is trained by using limited expert sample data, additional collision avoidance data is generated by using the trained diffusion model, and the additional data and the original expert data jointly participate in the training process of the adversarial inverse reinforcement learning, so that the problem of limited expert collision avoidance data can be effectively solved. Furthermore, an engineering application plan is provided for the proposed algorithm, the algorithm is verified, and a systematic solution is formed by combining theory with practice.

The invention relates to a multi-unmanned ship vector propeller game control method based on hierarchical multi-agent reinforcement learning, and belongs to the technical field of intelligent ship navigation and vector propulsion control. The method comprises the steps that an unmanned ship kinetic model is established, a utility function of a propeller is designed, and a Stackelberg game model is constructed to coordinate movement of a leading ship and a following ship; stackelberg-Nash balance (SNE) is solved through an H-MARL algorithm, and cooperative control of the whole system is achieved; upper and lower layers of neural networks are used for controlling the leader boat propeller and the following boat propeller; and the control strategy is adjusted through interaction of the intelligent agent, so that task targets such as trajectory tracking, formation adjustment and collision avoidance are ensured to be completed. Through the layered structure of the multi-agent system, the cooperative capability of the multi-unmanned-ship system in a dynamic environment is optimized, the task execution precision, stability and safety are remarkably improved, and the method is suitable for cooperative operation of the multi-unmanned-ship system in a complex environment.

The application discloses a kind of multi-source sensing and space-time matching inland waterway navigability test and evaluation method, belong to waterway engineering and ship test evaluation technical field.Pass through the layout shore base monitoring unit and integrated shipboard perception unit, unified space-time datum is constructed;Based on unified space-time datum, space-time matching fusion is carried out to ship dynamic response data and waterway environment data, forms ship response-environment excitation coupling data set, constructs three-layer navigability performance evaluation system, uses improved fuzzy analytic hierarchy process to determine index weight in combination with three scale method and optimal transfer matrix, uses cloud model to complete index quantization and comprehensive evaluation value calculation, finally determines waterway navigability effect grade according to comprehensive expectation value.The application realizes the quantitative evaluation of multi-source data accurate fusion and subjective and objective fusion, forms standardization test and evaluation process, truly reflects the coupling navigability characteristics of waterway and ship, provides technical support for inland waterway engineering acceptance, navigation safety management and waterway optimization design.

The application relates to the technical field of intelligent control of ships, and discloses a ship intelligent driving control system based on multi-source information fusion, which comprises an interaction and cloud service layer, a perception layer, a decision control layer and an execution layer. The interaction and cloud service layer extracts a route intention and initializes a theoretical load; the perception layer collects cabin visual images and multi-source environment data; a water surface automatic driving domain controller of the decision control layer adjusts a working mode of the perception layer based on a route intention parameter, a multi-source fusion algorithm unit of the decision control layer calculates a ship dynamic eccentricity moment, fuses environment data to calculate a space-time residual error to filter out false targets, and extracts a local water surface lateral disturbance force vector; an autonomous control algorithm unit updates a ship dynamics model online and adaptively based on the theoretical load, the ship dynamic eccentricity moment and the lateral disturbance force vector, generates autonomous berthing and unberthing control instructions, and the execution layer receives the instructions for closed-loop execution. The application improves berthing and unberthing control precision under complex water surface variable load conditions.

The invention relates to the technical field of ship power superchargers, in particular to an air-entraining self-circulation groove optimization design method for an air compressor, which comprises the following steps: firstly, establishing a parameterized model containing a plurality of key dimensions such as the axial position of a backflow groove and the axial position of a suction groove, and generating a corresponding air compressor flow field simulation model; performing aerodynamic performance simulation based on the model to obtain pressure ratio and efficiency data; then, an objective function used for evaluating the deviation between a simulation result and a target value is constructed according to the design requirement of the gas compressor; and finally, carrying out iterative optimization on the target function by adopting a simulated annealing particle swarm algorithm, and automatically adjusting the structural parameters of the air-entraining self-circulation tank until a parameter combination meeting a global optimal condition is obtained. The method effectively solves the technical problem that the global optimization of the comprehensive performance of the gas compressor is difficult to realize due to the fact that the mutual coupling influence among size parameters cannot be considered in a traditional control variable method, and realizes the collaborative optimization of the stable working range, the pressure ratio and the efficiency of the gas compressor.

The invention relates to the technical field of state monitoring and fault diagnosis of ship power devices, and provides a noise data processing method based on cavitation flow characteristics of a propeller. According to the method, observable dynamic frequencies such as leaf frequency and cavitation bubble falling main frequency and statistical non-stationary quantities such as a frequency spectrum broadening factor, self-correlation time, broadband energy and kurtosis are unified in the same analysis framework, a mapping model of a cavitation state and signal processing parameters is constructed, analysis parameters such as FFT, STFT and CWT are adaptively configured, and the analysis parameters of the cavitation state and the signal processing parameters are analyzed. And multi-scale feature extraction of non-stationary pressure pulsation signals under different cavitation types and cavitation intensities is realized. According to the method, the cavitation state and type are identified and evaluated on the basis of the extracted multi-domain features, the threshold and mapping parameters are reversely updated according to the identification result, a closed loop of state judgment, parameter mapping, multi-domain analysis, feature output, cavitation identification and parameter updating is formed, and the precision and engineering applicability of propeller cavitation monitoring and diagnosis are improved.

The invention provides an abnormal data sensing and repairing method for ship key equipment, which comprises the following steps: acquiring a mild fault data set and a severe fault data set based on a ship power device hydraulic system; a data mask mechanism is introduced, missing data positions are identified, standardization processing is carried out on non-missing data, and a standard data set is obtained; a bidirectional gating unit is introduced into the generative adversarial network for joint modeling, and a BiGRU-GAN model used for data generation and restoration is obtained; and iteratively training the model, carrying out primary optimization, carrying out data prediction completion by utilizing an optimized generator to obtain a repaired data set, and carrying out effect evaluation on the repaired data set to carry out secondary optimization adjustment on the model. The method can highly fit the actual complex working condition of the ship, adapts to the distribution of various data such as missing, abnormal and multi-label data, and greatly improves the consistency between the repair result distribution and the real data.

The application provides a kind of unmanned warship dynamic perception method based on double branch detection and multi-target tracking, image quality detection is carried out on original image to obtain the image to be detected;The image to be detected is input into the double branch detection model to obtain the target detection frame and its attribute label output by the double branch detection model, the double branch detection model includes a main branch for detecting regular scale targets and a saliency branch for compensating detection of small scale targets;According to the attribute label, the corresponding target detection frame is hierarchically matched to obtain the trajectory update result of the current frame;The trajectory prediction state in the trajectory update result of the current frame is fused with the detection side state obtained based on the target detection frame to obtain the joint state estimation result of the target in the current frame.The application organically connects the four links of image selective enhancement, double branch detection, hierarchical matching and state fusion, and forms a closed-loop perception mechanism for complex sea conditions.