1832 results about "Sonar" patented technology

The invention provides an underwater target detection method based on multi-modal features and domain adaptation. The method comprises the following steps: S11, acquiring a sonar image, an optical image and environmental data; s12, extracting a sonar feature and an optical feature, encoding the environment data into an environment channel weight, and dynamically adjusting a fusion proportion of the sonar feature and the optical feature through the environment channel weight to obtain a fusion feature; s13, performing spatial attention calculation on the sonar features to obtain a spatial weight map, enhancing the optical features by using the spatial weight map, and performing forced alignment with the sonar features at the target edge; and S14, decoupling the fusion feature into a synthetic domain feature, decoupling the fusion feature and the environment data into a real domain feature, and gradually aligning the synthetic domain feature and the real domain feature through asymptotic domain alignment to complete construction of a target detection model. According to the invention, multi-modal data acquisition, dynamic feature fusion and decoupling and embedded real-time detection are combined, so that the precision of underwater target monitoring is remarkably improved.

The embodiment of the invention provides a swimming pool robot positioning and trajectory prediction method and system fusing sonar and vision. The method comprises the following steps: collecting terahertz sonar data for a target area; based on terahertz sonar data, constructing a motion track model of the swimming pool robot; acquiring multi-source image data by adopting a multi-spectrum and event camera collaborative acquisition strategy; a dynamic SLAM algorithm based on deep learning is adopted, dynamic objects in the swimming pool environment are recognized and processed in real time based on the multi-source image data, and the environment image data with the dynamic objects removed are adopted to obtain a swimming pool environment model; performing deep fusion on the motion track model and the swimming pool environment model through a knowledge graph network, and predicting the operation state of the swimming pool robot by adopting a quantum machine learning algorithm to obtain a panoramic model; and creating and updating a digital twinborn model corresponding to the panoramic model in real time. The real-time performance and accuracy of positioning and track prediction of the swimming pool robot are improved, and a user can conveniently maintain and manage the swimming pool robot.

The invention provides a multi-scale underwater fish school detection system and detection method based on an attention module, relates to the technical field of underwater detection, and performs multi-scale fusion on sonar signals and image information. The depth of a fish school is determined through a sonar, a sound wave feature vector is generated, an unmanned underwater robot is used for collecting a low-illumination image, edge features are generated in a grey-scale image, color features are generated in an HSV color space, and the edge features and the color features are corrected. Weighted fusion is carried out on the sound wave features, the edge features and the color features through a feature alignment and attention module, and a comprehensive feature vector is generated. And finally, constructing a fish school detection model by using a deep learning network based on the deep feature vector, and realizing real-time detection of fish school categories and quantity. According to the method, multi-scale information and an attention mechanism are utilized, and the accuracy and reliability of fish school detection are improved.

Disclosed in the present invention is a bridge scour curved surface morphological feature reconstruction method based on three-dimensional sonar point clouds, comprising the following steps: collecting point cloud data of a three-dimensional morphology of an underwater riverbed terrain near a bridge foundation, and acquiring original point cloud data of a complete morphology of an underwater riverbed; performing denoising and ball pivoting reconstruction preprocessing on the collected original point cloud data to complete preliminary reconstruction of point clouds; on the basis of the point cloud data having undergone preliminary reconstruction, performing point cloud binarization-based scour morphology recognition on the basis of a computer vision principle, calculating scour pit element classification values of all the point clouds, and recognizing scour pit point clouds; on the basis of the recognized scour pit point clouds, using a K-means clustering algorithm for clustering, and calculating the maximum depth of each pier scour pit; and on the basis of the obtained scour pit element classification values of all the point clouds, providing a curved surface reconstruction method based on scour recognition to perform high-precision curved surface reconstruction on the scour pits. The present invention can achieve high-precision scour pit morphology reconstruction.

The invention discloses an unmanned ship underwater obstacle avoidance system based on distributed wide-beam sonar, and the system collects original environment information through a wide-beam sonar group, carries out the dynamic noise reduction processing through adaptive filtering, and obtains environment detection information. And acquiring the motion state of the unmanned ship through a navigation compensation module, and performing motion error compensation on the environment detection information to obtain environment correction information. And constructing an ellipsoid space safety area based on the environment correction information, and calculating a safety navigation boundary in real time to obtain safety navigation information. The obstacle avoidance decision module generates a multi-level obstacle avoidance strategy according to the real-time navigation state and the safe navigation information, and the execution control module converts the strategy into an obstacle avoidance instruction and dynamically adjusts the output frequency to adapt to different navigation working conditions. The system effectively solves the problems that a traditional obstacle avoidance system is insufficient in detection precision and lags behind in response in a complex underwater environment, all-directional and high-precision control over underwater obstacle avoidance of the unmanned surface vehicle is achieved, and the real-time performance and environmental adaptability of the obstacle avoidance system are remarkably improved.

The invention focuses on enhancing indoor positioning and navigation through advanced synchronous fusion methodologies that integrate various technologies, including Inertial Navigation Systems (INS), Inertial Measurement Units (IMU), LiDAR, stereo vision, and Sonar. This comprehensive system aims to achieve high-precision data collection with centimeter-level accuracy, crucial for creating detailed three-dimensional indoor maps. A significant aspect of this innovation is its ability to address privacy concerns by incorporating measures that abstract sensitive segments of the environment when necessary, ensuring personal privacy is maintained during data collection. Additionally, the system tackles challenges such as voids in stereo imaging and temperature variations in ultrasound and LiDAR measurements through sophisticated algorithms and corrections, including back propagation techniques that utilize stereo depth data. By employing particle swarm optimization and Neuro-Fuzzy algorithms, the framework enhances the accuracy and reliability of navigation in complex environments, making it particularly beneficial for emergency responders and personal navigation in unfamiliar settings.

The invention discloses an integrated measurement method and system for hydrological elements in a high-salinity and high-sand environment, and relates to the technical field of hydrological monitoring, and the method comprises the steps: correcting the theoretical signal receiving strength of each sonar through an established sound attenuation model, and then calculating an effective signal-to-noise ratio, thereby achieving the measurement of the underwater topography in the high-salinity and high-sand environment. According to the method, a dynamic weight fusion algorithm is adopted to perform data fusion on the water depth data of each sonar to obtain fused water depth data, and an inversion method based on residual error minimization is adopted to perform iterative optimization on model parameters, so that the accuracy is relatively high. When the water velocity and the flow rate are measured in the high-salt and high-sand environment, iterative decoupling is carried out based on the sediment particle motion comprehensive model to obtain the sediment particle velocity, then the water velocity is updated based on the measured apparent velocity and the difference value, and after the updated water velocity is converged, the flow rate is calculated. And the accurate water flow rate can be calculated by combining the flow cross section area. The measurement precision of the unmanned ship on the hydrological elements in the saline-alkali area can be improved.

The invention discloses an underwater propeller control method and system based on water body environment analysis. The method comprises the following steps: acquiring image data and laser point cloud data of a target water body, and constructing a three-dimensional environment model; initial position information and a target position of the underwater propeller are obtained, and a working path is generated based on environment model analysis; doppler sonar data on a path are collected, water flow information is analyzed, and a deviation correction control instruction is generated; and the instruction transmission quality is analyzed, and an optimal transmission scheme is determined. According to the method, dynamic modeling and analysis of a complex water body environment are realized by fusing multi-source environment sensing data, the path planning precision and autonomous control capability of the underwater propeller are improved, and the method is suitable for precise navigation and dynamic obstacle avoidance scenes in complex underwater operation tasks.

The invention discloses a sonar target recognition system based on a residual network, and the system comprises a sonar preprocessing module which is used for collecting and preprocessing an original sonar echo signal; the frequency spectrum construction module is used for generating a multi-channel frequency spectrum image; the spectrum enhancement module is used for performing spectrum enhancement processing; the residual feature extraction module is used for extracting sonar target feature representation; the label screening module is used for calculating a label credibility score and constructing a label training set; the joint training module is used for combining the label training set and the real labeling samples to form a joint training set and executing iterative optimization of the SonarResBlock model; and the identification output module is used for performing reasoning identification by using the updated model and outputting a category label of the sonar target. According to the method, multi-class spectrum construction and a residual attention mechanism are fused, accurate sonar target recognition is achieved, and the method has the advantages of being comprehensive in modeling, high in robustness and efficient in training.

The invention belongs to the technical field of underwater topographic survey, and particularly relates to an underwater topographic survey system based on multi-sensor data fusion, which comprises a multi-beam sounding sonar, a laser radar sensor, an ultrasonic bathymeter, an optical fiber hydrophone, a side scan sonar and a data processing and fusion module. The invention further relates to an underwater topographic survey method, and the method adopts a Kalman filtering data fusion algorithm. According to the invention, multiple types of sensors such as a multi-beam sounding sonar, a laser radar, an ultrasonic bathymeter, an optical fiber hydrophone, a side-scan sonar and the like are integrated into the same system for the first time, and an acoustics, optics and mechanics multi-dimensional data acquisition system is formed.

A sonar transducer mount and aiming system for attachment to an electric trolling motor, which includes a rotary actuator assembly and a rotating shaft. The rotary actuator assembly includes a housing that is secured to the electric trolling motor and a rotating coupler is rotationally driven. The rotating shaft is connected to and rotates with the rotating coupler and includes a sonar transducer mounting point. The rotating shaft of the sonar transducer mount and aiming system and the electric trolling motor shaft have a common axis of rotation and are configured to rotate independently from one another about the common axis of rotation.

The invention discloses an image enhancement method based on multi-modal enhanced grid masking and fast Fourier convolution, and the method comprises the steps: S1, collecting the foresight sonar data of an underwater typical target, and making an initial data set; s2, performing data enhancement in a multi-mode shielding mode on the original foresight sonar image; s3, performing data enhancement of a traditional image transformation mode on the multi-mode shielding frame enhanced image, simulating changes of illumination, noise, visual angles and the like in different environments, and generating diversified training data; s4, constructing an image enhancement network based on fast Fourier convolution, and improving the processing and enhancement capability of the occlusion region by using a global receptive field; and S5, enhancing the image by using the trained model to obtain a clear target occlusion image with rich details. According to the method, through the data enhancement method in combination with the multi-mode shielding mode and the network based on the fast Fourier convolution, the image enhancement quality and efficiency of the severely shielded target of the forward-looking sonar are remarkably improved, and the method has good generalization ability and practical value.

The invention discloses a robust autonomous navigation and obstacle avoidance method for an underwater detection robot, and relates to the technical field of underground space intelligent identification and navigation.The method comprises the steps that through the multi-sensor fusion technology, a three-dimensional point cloud data set and a depth image data set of an underground environment are synchronously collected through a sonar and a stereoscopic vision system; the method comprises the following steps: constructing original geometric morphology data of an underground space, providing basic information for subsequent data processing, constructing a dynamic updating mechanism according to an initial navigation path data set, monitoring underground environment change and structural state through real-time sensor data, and regularly updating risk level values. If the risk level change exceeds a preset range, triggering path recalculation to ensure adaptation to underground environment change; the robust autonomous navigation and obstacle avoidance method of the underwater detection robot has important application value in underground engineering fields such as mines and tunnels, and provides technical support for intelligent management and safe operation of underground space.

A sonar transducer mount and aiming system for attachment to an electric trolling motor, which includes a rotary actuator assembly and a rotating shaft. The rotary actuator assembly includes a housing that is secured to the electric trolling motor and a rotating coupler is rotationally driven. The rotating shaft is connected to and rotates with the rotating coupler and includes a sonar transducer mounting point. The rotating shaft has a tubular shape with a through bore that is configured to receive at least a portion of an electric trolling motor shaft in a co-axial arrangement. The size and shape of the through bore is designed so that the electric trolling motor shaft may be positioned within the through bore in clearance fit such that the rotating shaft of the sonar transducer mount and aiming system is free to rotate independently of the electric trolling motor shaft.

The invention provides an underwater robot intelligent navigation and environment sensing system based on a multi-sensor fusion collaborative technology. The system integrates a plurality of sensors such as sonar, optical, electromagnetic and the like, and realizes comprehensive data acquisition and real-time perception of an underwater environment. By applying advanced algorithms such as Kalman filtering and a neural network, the system performs synchronization, preprocessing and deep fusion on multi-source data, and the consistency and accuracy of information are remarkably improved. In addition, the system also has adaptive navigation and environment perception capabilities, can dynamically adjust a navigation path and a perception strategy according to fused data, and adapts to a complex and changeable underwater environment. And the intelligent decision support system provides decision assistance for an operator in combination with an environment perception result and a task target. And due to the design of a user interaction and monitoring interface, the usability and real-time monitoring capability of the system are ensured. According to the implementation of the invention, the precision and efficiency of the underwater robot in tasks such as monitoring and exploration are greatly improved.

The invention relates to an intelligent fish blocking and ship passing system based on multi-mode AI fusion and self-adaptive control, and belongs to the field of water conservancy projects and intelligent control. Aiming at the problems that a traditional electric fish blocking device is low in ship communication efficiency, poor in environmental adaptability and high in maintenance cost, a multi-mode sensor (laser radar, sonar, infrared thermal imaging and the like) fusion technology is adopted, and a reinforcement learning optimization proportion-integral-differential (PID) control parameter and a graph neural network (GNN) path planning algorithm are combined. All-weather high-precision sensing and dynamic gate regulation and control are realized; and equipment faults are predicted through a long short-term memory (LSTM) model, so that the shutdown risk is reduced. According to the system, the ship dredging efficiency is improved by 25%, the accident rate is reduced by 70%, the maintenance cost is reduced by 40%, the system adapts to extreme environments, and intelligent water conservancy construction is supported.

The invention discloses a seabed sonar image recognition system based on a graph neural network, and the system comprises the following modules: an image collection module which is used for collecting an original sonar image and constructing an original sonar image data set; the preprocessing module is used for generating a de-noised sonar image data set; the three-dimensional landform structure modeling module is used for constructing a three-dimensional landform structure diagram; the graph structure coding module is used for obtaining multi-scale landform semantic feature representation; the decoding and evaluation module is used for reconstructing a preliminary seabed landform semantic segmentation map through jump connection and calculating a fitness vector; the optimization scheduling module is used for obtaining an optimized submarine landform semantic segmentation map; and the post-processing and output module is used for generating a final segmentation result and obtaining a landform category identification result. According to the method, the problems of fuzziness and fracture of a traditional convolutional neural network on a sea ditch-sea mountain-hill complex nested landform boundary are effectively solved.

The invention discloses a seabed target sonar detection method based on an adversarial network, and the method comprises the steps: S1, collecting deep sea sonar original data, and carrying out the preprocessing of the data, and obtaining a standardized sonar tensor; s2, taking the standardized sonar tensor as training input, and training an improved StyleGAN-3 model in combination with an environmental parameter vector; s3, calling the improved StyleGAN-3 model, and outputting a weak target feature tensor; s4, constructing a sonar detection network; s5, outputting an optimal detection parameter set; and S6, loading the optimal detection parameter set to the sonar detection network, performing target judgment on the weak target feature tensor, and outputting a target confidence value, a three-dimensional space positioning result and a target motion track. Compared with a traditional method, the method has the advantages that in a deep sea scene, the positioning error and the target trajectory loss rate are greatly reduced, the method has excellent online tracking and dynamic situation awareness capabilities, and a solid technical support is provided for ocean monitoring, security and emergency command application.

The invention provides an underwater sonar target detection system and method. The underwater sonar target detection system comprises an optical fiber hydrophone array module which comprises a plurality of optical fiber hydrophone units, each unit comprises an optical fiber Bragg grating sensor and a sound pressure signal demodulation device, and the optical fiber hydrophone array module is used for collecting underwater sound wave signals in real time and converting the underwater sound wave signals into first electric signals; the sonar transmitting-receiving array module comprises a broadband sonar transmitter, a multi-beam receiver and a signal preprocessing circuit, and is used for actively transmitting a frequency modulation continuous wave signal, receiving a target reflection echo and generating a second electric signal; and the multi-mode signal fusion processing module comprises a high-speed data acquisition card, a self-adaptive noise suppression unit and a time-frequency analysis unit. The underwater sonar target detection system and method provided by the invention have the advantages of relatively high reliability, relatively high detection performance, relatively accurate cross-modal signal fusion and capability of performing intelligent target identification and tracking.

The invention relates to the field of intelligent detection, and discloses a breakwater structure rapid scanning diagnosis method based on an unmanned aerial vehicle, and the method comprises the following steps: 1, collecting the multi-modal data of an overwater structure and an underwater structure of a breakwater through a sensor carried by the unmanned aerial vehicle; step 2, carrying out space-time alignment processing on the multi-modal data to generate fusion point cloud data; 3, constructing a multi-dimensional tensor representing damage features based on the fused point cloud data; step 4, uploading the damage classification result to a cloud; 5, dynamically adjusting the scanning path planning of the unmanned aerial vehicle according to the damage classification result and the real-time environment parameters; and 6, outputting a three-dimensional visualization result containing the damage position, the damage type and the emergency scheme. Through cross-medium cooperative acquisition of the millimeter wave radar, the sonar and the multispectral sensor, the coverage range and the information dimension of damage detection are expanded, and reliable data are provided for breakwater structure monitoring in a complex marine environment.

The invention discloses a seabed sonar image processing method based on semantic segmentation. The method comprises the following steps: S1, obtaining preprocessed sonar image blocks; s2, generating a submarine landform boundary priori map corresponding to the preprocessed sonar image blocks pixel by pixel; s3, an improved U-Net double-branch semantic segmentation network is constructed, the improved U-Net double-branch semantic segmentation network comprises a semantic branch and a boundary branch, and a landform mutual feedback gating module is configured in each scale jumper connection layer; s4, obtaining a fusion feature map; s5, deploying to the autonomous underwater vehicle to form an onboard reasoning model; and S6, performing online semantic segmentation reasoning on the preprocessed sonar image block acquired in real time by using the onboard reasoning model, and outputting a semantic category diagram and a boundary vector diagram corresponding to the preprocessed sonar image block. According to the method, the average mIoU index of the model is improved in a small-target and multi-category hybrid scene.

The invention discloses a robot target identification method and system based on multi-source data driving, and relates to the technical field of intelligent robot environment awareness, and the method comprises the steps: inputting a dynamic environment vector into an LSTM network, and outputting the real-time fusion weight of vision, sonar and laser radar through an activation function; performing weighted fusion on vision, sonar and laser radar based on real-time fusion weights, constructing a causal graph neural network, separating false correlation features through anti-fact intervention samples, and outputting causal feature vectors; and inputting the causal feature vector into a pre-trained lightweight target recognition model for target classification, and when a new scene is detected, triggering knowledge base retrieval and comparative distillation to generate a recognition confidence coefficient. According to the method, the causality and correlation in the multi-modal sensor data are effectively distinguished by constructing the causality graph neural network and introducing an anti-fact intervention mechanism, so that the recognition accuracy and generalization ability of the model in a complex dynamic environment are improved.

The invention discloses an interactive multi-model underwater maneuvering target tracking method and system based on a pure azimuth second-order EKF. The method comprises the following steps: establishing a discrete state space model of a pure azimuth target tracking system; performing second-order linearization on the pure azimuth measurement model; calculating mixed input of a sub-filter corresponding to each model in the model set of the interactive multi-model algorithm; estimating a target state through parallel filtering of the azimuth-pure second-order EKF sub-filter corresponding to each model in the model set; updating the probability of each model in the model set; and combining the estimation results of all the sub-filters to obtain a final estimation result of the target state. According to the method, the target tracking precision can be improved, the problem of highly nonlinear measurement of the UUV on a target detection and tracking system through a passive sonar is effectively solved, good real-time performance is achieved, and real-time tracking of the UUV on the motion state of the underwater maneuvering target is achieved through adaptive matching of the real motion of the target through the interactive multi-model algorithm.

The invention discloses a net cage fish school number estimation method based on fish school density, and the method comprises the steps: obtaining a sonar image corresponding to the rotation scanning of a target net cage by a sonar through a step S1 and a step S2, and extracting the fish school number corresponding to each sonar image based on image recognition; a linear correlation curve # imgabs2 # of the effective area # imgabs0 # and the sampling depth # imgabs1 # of the netting in water and a nonlinear correlation curve # imgabs5 # of the fish school density # imgabs3 # and the sampling depth # imgabs4 # are obtained through the step S3, finally, integration is conducted on the two curves according to intervals through the step S4, the fish school number of each interval is calculated in a layered mode, and the estimated value # imgabs6 # of the net cage fish school number in the target net cage is obtained through accumulation. The method fully considers the non-uniformity of the fish school density and the net cage netting area along with the depth change, can improve the measurement accuracy of the net cage fish school number, and has the advantages of high accuracy and efficient, rapid and convenient implementation.

The invention discloses a marine surveying and mapping method based on multi-beam sounding correction, and belongs to the technical field of marine surveying and mapping. The method comprises the following steps: acquiring sounding echo signals, sound wave propagation time delay data and temperature data through a multi-beam sonar array, an acoustic chromatography transceiving array and a laser Raman probe; and fusing the data to construct a dynamic refractive index field model, correcting sound ray refraction distortion by adopting an adaptive variable step size algorithm, carrying out weight allocation and data fusion on space-time adjacent beams to obtain high-confidence water depth, and generating an isobath topographic map. The problem of refraction distortion is solved through multi-source data fusion, the sound ray tracking step length is dynamically optimized, noise interference is suppressed through weighted fusion, and the precision and reliability of topographic surveying and mapping in complex environments such as a deep sea hydrothermal region are remarkably improved.

The invention discloses an underwater sonar image recognition method and system based on improved YOLOv8. The method comprises the following steps: constructing a network model based on a YOLOv8 model, a multi-dimensional parallel attention mechanism and a contrast learning architecture; obtaining a training sample, training the network model by using the training sample to obtain a training recognition result, calculating a training loss value by using a comparison loss function and a YOLOv8 loss function, optimizing weight parameters, and outputting the trained network model through repeated iteration; acquiring a sonar monitoring image of the monitoring area acquired by the underwater sonar equipment, and inputting the sonar monitoring image into a preset network model to obtain an underwater target detection result; according to the invention, the characterization capability and generalization performance of the network model are improved through a multi-dimensional parallel attention mechanism and a comparative learning architecture, so that the network model can identify target details more accurately in an underwater complex environment.

A system and method for materials recovery using a mobile materials recovery facility (MMRF) are provided. The presently disclosed subject matter aims to replace manual sorting lines and techniques with a mobile, robotized sorting line to automate the separation by using, for example, cameras, artificial intelligence assisted hyperspectral material recognition algorithms, and / or other sensor technologies (such as optical, RADAR, SONAR, and / or LIDAR), for treatment and removal of contaminations in the recycling, organics and residues streams.

The invention belongs to the technical field of point cloud data processing, and discloses a point cloud smooth fitting method based on local density parameter adjustment and intensity optimization, and the method comprises the steps: obtaining original point cloud data, carrying out the preprocessing, carrying out the local density calculation, carrying out the dynamic adjustment of a search radius strategy, and carrying out the dynamic extension of a neighborhood, and after boundary judgment, performing boundary protection mechanism or joint weight calculation and updating smooth fitting on boundary points to obtain a point cloud visualization result graph after fitting reconstruction. The method effectively overcomes the defects of sparse point cloud smoothing, noise robustness, intensity feature retention, boundary feature fuzziness and the like in the prior art, can dynamically adapt to sparsity and non-uniform distribution of the point cloud, and remarkably improves the precision of smooth fitting of the point cloud and the optimization capability of intensity information. A more accurate and efficient technical scheme is provided for topographic surveying and mapping, underwater target detection and environment modeling of the forward-looking three-dimensional sonar.

The invention belongs to the technical field of hydraulic engineering measurement, and discloses a seawall measurement method and system based on multi-source data fusion, and the method comprises the steps: collecting geological data and hydrological data through a data collection module; the route planning module formulates a route; the overwater data acquisition equipment and the underwater data acquisition equipment are used for monitoring; the auxiliary equipment provides a high-precision positioning reference; the meteorological data module obtains meteorological data; the data processing module processes the data; the three-dimensional modeling module carries out point cloud registration and DEM model construction; the comprehensive analysis module performs comprehensive evaluation and predicts potential problems and risks; when an abnormal condition or a potential risk is monitored, the early warning module gives an alarm. Multi-source data acquisition equipment such as unmanned aerial vehicle aerial survey, a laser radar, a multi-beam depth finder, a side-scan sonar, a shallow profiler and a micro-motion exploration instrument are integrated, seawall overwater and underwater full-dimensional data acquisition, processing, modeling and volume calculation are realized, and high precision and reliability of measurement results are ensured.

The invention discloses a submarine searching sonar buoy array position optimization method based on a non-dominated sorting genetic algorithm NSGA-III, and the method comprises the steps: introducing a time scale factor in combination with the initial and maneuvering positions of a submarine, and obtaining a position probability distribution function of the submarine after maneuvering; a buoy position is generated in the whole search area according to probability distribution, more initial array position individuals are generated near a high-probability area, and the exploration tendency of a population to a key area is improved; when reference lines are selected during non-dominated sorting, fusion density estimation is added, so that the reference lines at individual sparse positions are denser; when the Pareto front is selected to be reserved, a reduced-proportion front-edge reservation method is selected, and except for the first front edge, subsequent individual reservation is gradually reduced in a reduced-proportion mode until the population scale is reached; introducing a gene adaptation entropy crossover threshold in the crossover part, adopting a priority retention strategy for the parent with high fitness, and then performing crossover operation on the remaining part; and the potential sonar buoy array position optimization is realized.