3105 results about "Network output" patented technology

A 3D target detection method based on multimodal fusion and a depth attention mechanism includes the following steps: obtaining and preprocessing original point cloud data and original image data; inputting the preprocessed point cloud data and image data into a 3D target detection network based on multimodal fusion and the depth attention mechanism, where the 3D target detection network based on multimodal fusion and the depth attention mechanism includes a generation phase for 3D bounding box proposals and a refinement phase for 3D bounding boxes, and the network outputs parameters and classification confidence of a target bounding box; training the 3D target detection network based on multimodal fusion and the depth attention mechanism; and processing the collected lidar point cloud data and image data by using the trained detection network, and outputting 3D target information, to realize 3D target detection.

The invention provides a network security protection method and system applied to regional digital and intelligent asset businesses, and the method comprises the steps: collecting asset data flows of a plurality of asset business nodes in a target region, carrying out the threat feature extraction of the asset data flows based on a preset threat knowledge graph, and obtaining a threat feature extraction result; generating a dynamic threat feature vector corresponding to the asset service node; inputting the dynamic threat feature vector into a pre-trained dynamic protection model, and outputting a real-time protection strategy adaptive to the asset service node through a multi-layer decision network in the dynamic protection model; performing strategy execution on the network flow of the asset service node based on the real-time protection strategy, generating a strategy execution result and feeding back the strategy execution result to the dynamic protection model; and performing adaptive optimization on decision parameters of the dynamic protection model according to a strategy execution result, and generating an updated dynamic protection model for a protection decision of a next round of asset business nodes.

The invention discloses a primary and secondary fusion complete ring main unit fault diagnosis method, and particularly relates to the technical field of power distribution fault diagnosis, and the method comprises the steps: collecting multi-path original data, carrying out the frequency domain and time domain combined calibration, carrying out the comprehensive evaluation according to two preset discrimination factors, namely, a data stability deviation amplitude and a multi-path waveform time deviation degree, and obtaining a fault diagnosis result. Two types of feature data sets are constructed subsequently, input data of two interference modeling networks are calculated respectively, then the interference modeling networks are input to output interference grade values, sampling precision dynamic adjustment and fault recognition strategy switching operation are executed according to the interference influence grade values, and diagnosis accuracy and stability in a complex interference environment are improved. According to the method, unified normalization processing of multi-path sensing data is realized, and the sensing accuracy of fault features is improved; through double-factor triggering and feature fusion evaluation, the stability of interference identification is enhanced; and sampling adjustment and strategy switching are executed based on the interference level value, so that the robustness and reliability of diagnosis are improved.

Systems and methods of the present disclosure include animating virtual avatars or agents according to input audio and one or more selected or determined emotions and / or styles. For example, a deep neural network can be trained to output motion or deformation information for a character that is representative of the character uttering speech contained in audio input. The character can have different facial components or regions (e.g., head, skin, eyes, tongue) modeled separately, such that the network can output motion or deformation information for each of these different facial components. During training, the network can use a transformer-based audio encoder with locked parameters to train an associated decoder using a weighted feature vector. The network output can be provided to a renderer to generate audio-driven facial animation that is emotion-accurate.

The invention discloses a monorail crane inspection robot intelligent test method based on data analysis, and relates to the technical field of intelligent detection, and the method comprises the following steps: synchronously collecting track images, point cloud and attitude data, carrying out time alignment and preprocessing, and outputting a standardized data packet; detecting an inspection target by using a YOLO detection network, and outputting a multi-scale feature vector in combination with a point cloud feature hierarchy extraction network and a time sequence convolutional network; predicting a fault development trend in combination with an improved A-star algorithm and a long short-term memory network, optimizing an inspection path through reinforcement learning, and outputting a maintenance decision scheme; the maintenance decision scheme is converted into a control instruction, the robot is driven to execute an inspection task and feed back the operation state in real time, incremental learning and point cloud reconstruction are combined, and a visual diagnosis report is output. According to the method, the dynamic threshold algorithm is adopted for self-adaptive analysis, and the key geometric indexes are calculated in combination with the cross-modal attention mechanism, so that the recognition capability of structural anomalies is improved.

The invention relates to a human shape posture recognition method and system based on image analysis, and the method comprises the steps: inputting the reference human shape data of a monitored object, and collecting the multi-modal data of an RGB image, an infrared image and inertial measurement data in a target scene in real time; space-time alignment processing is carried out, and corresponding features are fused; image space features are extracted, time sequence modeling is carried out on inertial data, and dynamic weighted fusion of two paths of network outputs is realized through a gating mechanism; human body basic joint points are positioned, and refined posture vectors including joint angles and limb relative positions are generated; according to attitude data and environment information collected in real time, adaptively adjusting an attitude classification threshold value and a similarity measurement standard, and predicting abnormal behaviors in a future time period; and when the abnormal behavior is predicted, triggering to execute a preset safety measure. Multi-modal data can be efficiently fused, attitude features can be accurately extracted, an identification strategy can be adaptively adjusted, and human shape attitude identification with behavior trend prediction capability can be realized.

The invention discloses a robot reinforcement learning control method and system based on a gating circulation unit, and relates to the technical field of artificial intelligence. Based on a reinforcement learning state machine, a trained student network is deployed to a real quadruped robot in a zero mapping manner, and movement control of the quadruped robot is realized; the training process of the student network is as follows: building a simulation training terrain environment of the robot, and setting different levels of terrain difficulty for each terrain; based on the distillation learning thought, establishing a teacher network and a student network based on a gating circulation unit, constructing a total loss function, and based on the constructed total loss function, fitting a motor joint angle output by the teacher network through an omnibearing simulation training terrain environment, a large-scale parallel training method and the student network; according to the robot reinforcement learning control method and system, robust motion of the robot in an unstructured terrain is realized, and the robot reinforcement learning control method and system have good anti-interference capability and self-recovery capability for a dynamic environment in which traditional control cannot be competent.

The invention discloses a high-voltage equipment monitoring system and method based on thermal imaging and dynamic sensing fusion of a power plant, and belongs to the field of high-voltage equipment monitoring. The edge intelligent processing module is used for outputting a real temperature field matrix, separating equipment vibration characteristics from environment noise and generating a fused characteristic vector; the multi-modal analysis module is used for inputting the feature vectors into a constructed equipment topological graph neural network and outputting a health index and an abnormal probability distribution diagram of each monitoring point; the environment coupling fault analysis module is used for generating a fault diagnosis report; and the dynamic early warning module is used for executing graded early warning according to the health index and the fault diagnosis report. The fault detection rate and the operation and maintenance efficiency can be improved.

The invention discloses a power transmission line inspection unmanned aerial vehicle obstacle intelligent detection and obstacle avoidance method. The method comprises the steps that multi-source sensing data is acquired, and alignment is completed through calibration and timestamp matching; heterogeneous data preprocessing and feature enhancement; constructing a high-precision environment fusing a geometric structure and a semantic tag, mapping a two-dimensional target detection result output by the recognition network to a three-dimensional coordinate system through spatial transformation, and fusing the two-dimensional target detection result with a point cloud structure to construct a semantic occupation grid map; performing preliminary route planning according to a preset power grid topological structure and task coverage requirements, and generating a barrier-free flight path covering the whole inspection area; reinforcing learning of a dynamic obstacle avoidance strategy; track dynamic reconstruction and energy consumption optimization scheduling are carried out; the technical problems that an existing technical system has defects in the aspects of obstacle recognition accuracy, complex environment adaptability, data fusion capacity and obstacle avoidance strategy intelligence, and the requirements for high-reliability, low-energy-consumption and high-efficiency unmanned aerial vehicle power transmission line inspection are difficult to meet are solved.

The present invention relates to the technical field of environmental perception in confined spaces, and discloses a multi-modal coupled perception method for target recognition and region segmentation in a confined space. The method comprises: firstly, constructing a 3D point cloud data processing network, a 2D point cloud data processing network, and an image data processing network; next, constructing a feature fusion device, and outputting a bird's-eye view incorporating multi-sensor information; then constructing a multi-scale feature fusion extraction network and a network output head, outputting a target recognition and region segmentation result, and designing a loss function to train a network weight; and finally, inputting 3D point cloud data, 2D point cloud data, and camera image data into a network model, performing inference to obtain a target recognition and region segmentation prediction result, and performing visual rendering on the prediction result. In the present invention, in view of the characteristics of a millimeter-wave radar, a multi-modal coupled perception network is constructed, so that effective information in mass point cloud data of the millimeter-wave radar can be deeply mined, thereby effectively improving the detection accuracy of target recognition.

The invention discloses an epilepsy prediction method based on a self-adaptive space-time attention and dynamic fusion network, and relates to a brain signal preprocessing module, a context attention coding layer, a long-distance content dependence network, a self-adaptive time sequence state space modeling module and an epilepsy prediction module. The brain signal preprocessing module obtains corresponding time domain information, frequency domain information and an adjacent matrix; an adjacent matrix is regarded as a graph structure, the weight of each edge of the graph structure is input into a context attention coding layer, spatial features between channels are extracted, the weight is dynamically adjusted through aggregation of neighbor node information and attention, and a node feature matrix is output; inputting the node feature matrix into a long-distance content-dependent network to output global spatial features and corresponding time sequences; obtaining space-time dynamic fusion features through a self-adaptive time sequence state space modeling module; and inputting the space-time dynamic fusion features into an epilepsy prediction module and then outputting an epilepsy prediction result According to the invention, accurate prediction can be realized.

The invention provides an end-to-end automatic driving track evaluation method and system based on a world model, and the method comprises the steps: generating bird's-eye view state real-time information according to multi-mode sensor data obtained in a current automatic driving scene; inputting the aerial view state real-time information into a strategy network to obtain a plurality of real-time track anchor points output by the strategy network; according to the bird's-eye view state real-time information and the real-time track anchor point, constructing a real-time state-action pair, and inputting the real-time state-action pair into a bird's-eye view world model to obtain a predicted state-action pair output by the bird's-eye view world model; according to the real-time state-action pair and the predicted state-action pair, the predicted driving track corresponding to the predicted state-action pair is evaluated, and an evaluation result of the predicted driving track is obtained. According to the method, the predicted driving track can be evaluated more accurately, and the safety and reliability of the automatic driving system are improved.

The invention relates to the technical field of power system dispatching, and discloses a multi-agent reinforcement learning active power distribution network area coordination method and system, and the method comprises the steps: dividing a power distribution network into a plurality of areas, and each area is managed by an agent; collecting observation information; inputting the observation information into an upper reinforcement learning strategy network, and outputting control parameters; inputting the control parameters into a target function of the lower-layer local physical optimization model, and solving an output setting point of the equipment under the condition of meeting the safety operation constraint; constructing a De-POMDP problem, and obtaining a reward signal of each agent; a sequential updating mechanism is introduced, global network parameters are optimized, and corresponding decisions are obtained; and inputting the multi-agent decision into the global active power distribution network model to obtain the total operation cost, feeding back the total operation cost as an award to the reinforcement learning strategy network, updating global network parameters, and converging to obtain an optimal decision. According to the invention, regional wind-solar-storage multi-energy scheduling can be effectively optimized, and energy balance in the region is realized.

The invention discloses a lithium ion battery health state evaluation method and device based on deconstruction physical information, a medium and a product, and relates to the technical field of lithium ion battery health state evaluation, and the method comprises the steps: extracting a multi-dimensional health factor, inputting the multi-dimensional health factor into a deep physical information neural network fusing a self-attention mechanism module and a Koopman neural operator module, and obtaining a deep physical information neural network; and outputting the SOH estimation value. By extracting the universal health factors suitable for multiple working conditions, the problem that the universality of the health factors is insufficient is solved; a self-attention mechanism is utilized to enhance features and reduce redundancy, and the perception ability of the model to key information is enhanced; physical information is deconstructed by means of a Koopman neural operator, a physical mechanism of battery degradation is fused into the model, and the physical interpretability of the model is enhanced; the deep physical information neural network is fused with multi-dimensional information for estimation, individual differences and complex working conditions of different batteries are effectively dealt with, and therefore high-precision and high-robustness lithium ion battery SOH estimation is achieved.

The invention relates to the technical field of electric drive transmission system service life prediction, and discloses an AI-based electric drive transmission system comprehensive service life prediction method, which comprises the following steps: acquiring electric drive system operation parameters and mechanical part degradation data; arranging the data into a system operation full-period input tensor and a component degradation full-period input tensor, and respectively extracting multi-order feature tensors through a bidirectional recurrent neural network and a gated time convolutional network; performing cross-modal fusion by using a cross attention fusion network in combination with physical constraints to obtain a system-component degradation fusion feature vector; and after dimension reduction, inputting a multi-layer perceptron network output life prediction value, and generating a residual service life interval with confidence in combination with historical cases. The method integrates multi-source data, realizes cross-domain feature dynamic association and physical constraint fusion, improves the precision and reliability of life prediction, is suitable for intelligent operation and maintenance of the electric drive system, and provides a scientific basis for equipment maintenance.

The invention discloses a source load storage dynamic strategy verification method based on double-layer reinforcement learning, and the method comprises the following steps: S1, collecting the operation data of a source load storage system, and constructing a standardized operation data set; s2, constructing a double-layer reinforcement learning model, generating a global scheduling strategy by an upper-layer strategy network, and outputting an action decision strategy by a lower-layer strategy network; s3, performing joint training on the double-layer reinforcement learning model by adopting a strategy gradient optimization method, and outputting a scheduling strategy; s4, introducing an integral gradient method to analyze a scheduling strategy, and constructing a key scheduling state node set; s5, optimizing the generation logic of the global scheduling strategy to obtain an optimized double-layer reinforcement learning model; s6, constructing a plurality of source-load-storage system operation scenes to form a typical operation scene set; and S7, deploying the optimized double-layer reinforcement learning model in the typical operation scene set, and outputting a strategy verification result. According to the invention, through combination of double-layer reinforcement learning and an integral gradient method, source-load-storage dynamic strategy verification is realized.

The invention discloses a 3D object reconstruction method combining multi-view fusion and a neural network, and the method comprises the following steps: collecting a multi-view image of a target object, carrying out the geometric calibration and view parameter calibration, and generating a standardized image sequence; inputting the image sequence into a feature extraction and voxel fusion module to obtain a preliminary three-dimensional space representation body as a coarse reconstruction model; performing uncertainty evaluation on the coarse reconstruction model, generating a voxel-level confidence coefficient heat map, and dividing the voxel-level confidence coefficient heat map into a plurality of confidence coefficient intervals; based on the confidence interval, constructing an adaptive repair network with a multi-scale residual path, and outputting and activating different repair paths as required by using a path gating mechanism; and fusing the residual output of each repair path with the coarse reconstruction model to generate an optimized final three-dimensional reconstruction model. According to the method, the risk of excessive repair or error repair can be effectively reduced, the adaptability of the model to complex areas such as sheltered areas is enhanced, and the integrity and precision of the whole three-dimensional reconstruction model are improved.

The invention provides a scene adaptive projection vehicle lamp system based on deep reinforcement learning and a control method, and relates to the technical field of intelligent vehicle lamps and automatic driving perception systems. Comprising a multi-modal sensing module, a feature fusion module, a strategy generation module and an execution module. The multi-mode sensing module is used for collecting environment state data and performing primary processing to form an environment data information flow; the feature fusion module is used for generating a unified environment feature vector for the environment data information flow; the strategy generation module is used for receiving the environment feature vector and generating a vehicle lamp adjustment strategy through multi-layer neural network calculation; evaluating a result obtained by executing the vehicle lamp adjustment strategy based on the vehicle lamp, and optimizing strategy parameters of the strategy network based on a PPO algorithm; the execution module is used for controlling the vehicle lamp according to the vehicle lamp adjustment strategy output by the strategy network. The intelligent level of the vehicle lamp is remarkably improved, and the system is widely applied to night driving assistance, urban interaction prompt and low-visibility driving scenes.

The invention discloses an electric power system short-term load prediction method based on TCN-BIGRU-CBAM, and the method comprises the steps: obtaining a standard load time series data set as input data, and carrying out the preprocessing of the input data; establishing a time convolutional network TCN model, and extracting a long-term dependency relationship in the time sequence; establishing a two-way gating cycle unit network BIGRU, and outputting two-way time characteristics; constructing a convolutional block attention module (CBAM), and obtaining a four-dimensional feature map subjected to channel and space attention enhancement; and establishing a full connection layer, mapping the time sequence characteristics to a scalar through linear transformation, and outputting a power load prediction value of a target time step. According to the method, the problems of information loss, difficulty in high-dimensional feature extraction and the like of a traditional short-term load prediction model in complex time sequence modeling are effectively solved, the precision and the stability of short-term load prediction are remarkably improved, and the method has relatively high practical value and popularization potential.

The invention discloses an electric power analysis method and system based on artificial intelligence, and relates to the technical field of electric power system intelligent analysis. Establishing a hierarchical depth map neural network model, and setting a cross-layer information interaction channel to connect each sub-network; executing a bidirectional knowledge distillation algorithm, extracting a rule set from neural network output, and forming a parameter-rule bidirectional mapping matrix; deploying a federal reinforcement learning architecture, performing parameter aggregation on the local models on the distributed power nodes, and generating a power system state evaluation result and a risk coefficient matrix; and starting the self-repairing intelligent agent network, calculating a regulation and control parameter set of the multilevel power system, and outputting a regulation and control instruction. According to the invention, through the hierarchical depth map neural network and a cross-layer information interaction mechanism, collaborative optimization among all levels of the power system is realized, and the operation efficiency and stability of the system are improved.

The invention relates to a large-scale road network traffic control method based on a deep reinforcement learning large model, and belongs to the technical field of intelligent traffic control. The method comprises the following steps: sensing real-time multi-modal road network information including urban road intersections, highway entrance ramps and emergency lanes, and generating a space-time fusion representation vector representing a current traffic network state by fusing a space diagram construction method and a time sequence embedding method; the space-time fusion representation vector and historical state memory are spliced to serve as input, a backbone network of a pre-training large language model is used for state feature distillation so as to enhance state representation, and a traffic control decision is output through a strategy network with a layered action space; through cross-modal knowledge migration and a progressive course learning strategy, a training process of a deep reinforcement learning algorithm is guided and optimized so as to improve model training efficiency and generalization ability. According to the method, the generalization performance and the accuracy of the control strategy are improved while the real-time response speed is ensured.

The invention discloses a feature integration method for interactive convolution and dynamic focusing of infrared images. The feature integration method comprises the steps that infrared image pairs with different resolutions in various real scenes are obtained through an infrared camera; performing degradation preprocessing on a part of original high-resolution images to obtain low-quality high-resolution images to form a mixed low-resolution data set, and dividing the processed data set into a training set and a test set; constructing a double-layer feature extraction module for feature modeling; training a network by using the processed training set, and optimizing a loss function; and inputting a low-resolution infrared image into the trained network, and outputting a high-resolution reconstruction result. According to the method, local and global features are fused, so that the super-resolution reconstruction quality of the infrared image in complex scenes such as low contrast and fuzzy edges is remarkably improved, and meanwhile, relatively high calculation efficiency is kept.

The invention discloses a corrugated pipe inner wall multi-type flaw detection method based on deep learning, and the method comprises the following steps: S1, collecting an initial corrugated pipe inner wall image and corrugated pipe inner wall images in different illumination environments, and generating an original image; s2, preprocessing the original image to generate a preprocessed image; s3, extracting surface geometric overall features of the inner wall of the corrugated pipe from the preprocessed image through a pre-trained ResNet101 network; s4, inputting the preprocessed image and the surface geometric overall features into an improved StyleGAN3 network to generate an enhanced image; s5, inputting the enhanced image into the multi-scale adaptive deep network, and outputting a defect detection result; and S6, performing post-processing on the flaw detection result, and outputting a final flaw detection result. According to the method, deep learning and geometric characteristic embedding technologies are adopted, so that the defects of the inner wall of the corrugated pipe are accurately detected, and the method has the advantages of high precision, high robustness and comprehensive adaptability.

The invention relates to a traffic prediction method based on dynamic graph space-time correlation and adaptive adversarial training. The method comprises the following steps: acquiring a dynamic graph space embedding representation by learning dynamic graph data capture by utilizing an adaptive graph convolutional network; capturing the dynamic graph data according to the time attention network to obtain a dynamic graph time embedding representation; obtaining dynamic graph embedding; after dynamic graph embedding is used as initial embedding and the last preset adversarial node embedding is defined as context node embedding to be used as input of a strategy network, an adversarial reward function and a loss function are set, then the strategy network is trained, and an updated dynamic graph is output according to the trained strategy network. And performing spatial correlation capture and temporal correlation capture on the updated dynamic graph to obtain a traffic prediction result corresponding to the current network equipment. By adopting the method, data pollution and node abnormity can be effectively handled, and traffic prediction can be realized by adapting to continuously changing network conditions.

The invention relates to the technical field of power transmission line detection, and discloses a power transmission line key component defect identification method based on cloud edge cooperation. The method comprises the following steps: acquiring a multi-source inspection data set consisting of a power transmission line component image acquired by an unmanned aerial vehicle, edge end sensor data and a cloud historical defect database; at the edge end, extracting component region features through an image preprocessing algorithm, and generating environment correlation parameters by using a multi-modal feature fusion algorithm; and at the cloud, performing space-time correlation analysis on the historical defect database to generate a part defect evolution graph. And inputting the information into a cloud edge collaborative recognition model to obtain a component defect feature vector, constructing a multi-stage defect recognition network through a dynamic optimization algorithm, and outputting a component defect classification result and confidence. According to the method and the system, the accuracy, the real-time performance and the reliability of defect identification of the key component of the power transmission line are improved, and the method and the system have good application prospects.

The invention relates to a quick river flood forecasting method based on a physical information neural network, and belongs to the field of river flood forecasting. The method comprises the following steps: on the basis of a traditional physical information neural network (PINN), introducing a boundary condition parameter as an input variable, and enabling the PINN to learn a flood wave propagation rule under different boundary conditions. Furthermore, on this basis, a physical information neural network flood fast forecasting framework (RFF-PINN) integrated with a hydrodynamic method is provided, a numerical solution based on grid discretization is reconstructed into a continuous function in a time-space domain through a piecewise polynomial interpolation method, residual error loss between network output and a hydrodynamic model simulation value is constructed, and therefore, a flood fast forecasting result is obtained. The network parameters are optimized in cooperation with the PDE loss, and the problem that the network parameter optimization effect is reduced due to the fact that the PDE loss of the complex flow state area is difficult to converge is solved. The method has the beneficial effect that the water depth change process of each section of the river channel under any boundary condition can be accurately and quickly predicted.

The invention provides a reinforcement learning path planning method for multiple unmanned vehicles in an intelligent factory. The method comprises the following steps: building a feeding path planning simulation environment; taking each unmanned vehicle as an intelligent agent, interacting the intelligent agent with the environment to extract information, and constructing a state space, an action space and a reward function of the Markov decision model according to the information; building an IPPO algorithm network, and training the strategy of the Markov decision model based on the IPPO algorithm network and the reward function; during training, a strategy network loss function with a rollback strategy is obtained through improvement by combining cutting loss with KL divergence in a mode of introducing hyper-parameters; and determining the current state at each moment according to the actual current position of the unmanned vehicle, inputting the current state into the strategy network, and outputting the current action to be executed by the unmanned vehicle. The method is high in convergence speed, stable in strategy updating, high in exploration capacity, capable of effectively reducing path blockage and high in environment adaptability.

The invention discloses a quasi-brittle material damage field inversion method based on a physical information neural network. The method comprises the steps of data acquisition and processing; presetting initial damage field data, and taking the modulus of each unit in the initial damage field data as an independent to-be-inverted parameter; taking the position information of each node in the space as the input of a neural network, processing through a hidden layer of the neural network, and taking displacement data corresponding to the position information as network output data; constructing a loss function of a neural network according to the preprocessed displacement data, network output data and a mechanical law; and performing training optimization on the initial damage field data by using a loss function of a minimized neural network, optimizing hyper-parameters of the neural network by adjusting weights of control item loss, boundary item loss and data item loss until a preset convergence condition is met, and determining target damage field data. According to the method, the dependence of a neural network model on a data set is remarkably reduced, and the inversion result is ensured to have relatively high physical interpretability.

According to the invention, based on deep learning target detection, automatic identification of power transmission line insulator defects is realized. The method comprises the following steps: firstly, acquiring and preprocessing an aerial image, and then inputting the aerial image into a backbone network integrated with S-CBAM attention, an FPN + PAN + GSConv lightweight neck network and a detection head additionally provided with a small target detection branch; the model adopts an SGD optimizer, is matched with cosine annealing learning rate scheduling, and is trained by using CIoU loss, Focal Loss and binary cross entropy. After training is completed, the model is exported as a TensorRT engine and deployed in embedded equipment, and forward reasoning is accelerated. And for the new image, the network outputs the candidate box and the category confidence, and after NMS screening, a final defect detection result is obtained.

The invention relates to a ship detection method for a complex synthetic aperture radar (SAR) scene, and belongs to the technical field of remote sensing image target detection.The method comprises the steps that an obtained high-resolution synthetic aperture radar image is input into a DPM-YOLO ship detection network, a ship target detection effect picture is output, the DPM-YOLO ship detection network is improved based on a YOLOv11 network, and the ship target detection effect picture is obtained; a DPSConv module is introduced into a backbone network to capture multi-scale context information by using a receptive field while keeping fine feature details, and a PromptFusionMod module is introduced into a neck network to perform multi-modal feature fusion through four processing stages of space compression and prompt fusion, an efficient attention mechanism, a lightweight multi-layer perceptron and output fine processing. And the original detection head is replaced by the MscaleASFHead detection head. Compared with the prior art, the method has the advantages that fine-grained feature extraction, cross-scale semantic alignment and lightweight deployment can be considered, and ship detection precision and robustness in a complex sea condition scene are improved.