191 results about "Message passing" patented technology

The invention relates to an unmanned aerial vehicle path planning method and system based on GNN and high-order security constraints. The method comprises the steps that a navigation scene where an unmanned aerial vehicle is located is represented as a heterogeneous directed graph, message passing and feature updating are conducted through the GNN, a risk-aware attention mechanism is introduced, and an interpretable decision result is output; a differentiable HoCBF-QP optimization layer is introduced, an original control command output by a strategy network is used as input, quadratic programming with high-order control barrier function constraints is solved online, minimum-amplitude safety correction is carried out on the control command, and an actuator control command meeting safety constraints is output; starting a HoCBF safety shield during operation so as to strictly ensure that all safety constraints are met before execution; a calculation task of the whole control cycle is modeled into a directed acyclic graph form, and parallel execution is carried out on heterogeneous multiple cores by utilizing a real-time scheduling strategy. The problem that unmanned aerial vehicle navigation control is not effective and unified in three aspects of structure, safety and scheduling is solved.

The invention discloses a transformer fault diagnosis and root cause positioning method based on a space-time diagram neural network, and relates to the field of transformer fault diagnosis, and the method comprises the steps: S1, carrying out the preprocessing of the structure information and DGA time series data of a transformer, and obtaining a topological network structure diagram and a DGA time series; s2, obtaining a spatial vector based on a message passing mechanism of a graph convolutional network; s3, a time sequence vector is obtained in combination with a Transform encoder and multi-head self-attention; s4, obtaining space-time fusion features; s5, constructing a multi-task prediction head based on the space-time fusion feature, the fault type historical data and the fault root cause; and S6, carrying out fault detection and outputting a corresponding fault type and root cause positioning result. According to the application, the accuracy of fault type identification can be remarkably improved, and accurate positioning of the fault root cause is realized.

One or more systems, devices, computer program products and / or computer-implemented methods of use provided herein relate to predicting an optimized result for a graph neural network (GNN). A system can comprise a memory configured to store computer executable components; and a processor configured to execute the computer executable components stored in the memory, wherein the computer executable components comprise: a fusion component that that models non-linear modality correlations within and across entities through Hirschfeld-Gebelein-Re'nyi maximal correlation (MaxCorr) embeddings that generates a multi-graph that preserves identities of modalities and entities; and a multi-graph neural network (MGNN) component for task-informed reasoning in multi-graphs, that learns parameters defining entity-modality graph connectivity and message passing in an end-to-end fashion.

The invention relates to the technical field of infrared light machine system thermal deformation prediction, in particular to a multi-material structure thermally induced stress deformation prediction method based on a graph neural network. The method comprises the steps of data set establishment, graph structure establishment, graph neural network model establishment and training and model and parameter optimization. Finite element nodes correspond to graph nodes, finite element edges correspond to graph edges, an encoder-message passing-decoder architecture model is established, and node states are updated through a three-layer physical symmetry message passing mechanism. Physical constraint loss including minimum displacement smoothness constraint and stress continuity constraint is innovatively added into a loss function. Compared with traditional finite element calculation, the method has the advantages that the speed is increased by more than 100 times, high hardware adaptability is achieved, the black box limitation of a data-driven neural network model is broken through, thermally induced stress deformation analysis caused by different material coefficients can be processed, the adaptability to geometric changes is high, and good engineering application value is achieved.

The invention relates to the technical field of building engineering construction management, and discloses a house steel building construction prediction progress and deployment system based on deep learning. According to the system, periodic stable paragraphs and non-periodic fluctuation paragraphs are recognized by analyzing the time sequence form of construction flow data, and construction links are stripped accordingly. And performing cross mapping on the hoisting event sequence in the link and the environmental monitoring reading of the associated link to generate a link toughness spectrogram representing the construction robustness. And determining a resource demand based on the spectrum graph, and forming a multi-dimensional resource demand vector, so as to drive a graph convolutional network to construct a dynamic construction deduction graph. And carrying out message passing and neighborhood aggregation on the graph, analyzing a key bottleneck path, and iteratively generating a progress prediction and resource allocation scheme. According to the method, the construction dynamic toughness can be evaluated, and accurate positioning and dynamic optimization of resource bottlenecks are realized.

The invention discloses a mining equipment state prediction method based on digital twinning and multi-modal fusion, and relates to the technical field of intelligent operation and maintenance, and the method comprises the steps: inputting a multi-modal alignment working condition window sequence into a digital twinning mechanism link, carrying out the same-window ideal response deduction, outputting an ideal multi-modal response, and constructing a twinning dynamic residual error; meanwhile, segmenting a residual structure event to generate a residual event token set; positioning a multi-modal data fragment based on the residual event token set, executing cross-modal attention alignment, and performing topology propagation aggregation in combination with a mechanical topology observation mapping table to generate a topology constraint fusion table set; and inputting the topological constraint fusion table set into the graph neural network, carrying out message passing in combination with a mechanical topological graph, outputting a component state and a complete machine state, and packaging the component state and the complete machine state into a mining equipment state prediction set. According to the method, structured analysis of the twinborn dynamic residual error is realized, and the method is used for accurately positioning an abnormal event and improving the sensitivity and timeliness of state prediction.

The invention discloses a three-dimensional geographic environment real-time intelligent deduction method based on a multi-modal large model, and relates to the technical field of computer vision. The method is used for solving the technical problem of unified modeling and real-time deduction of a dynamic object and a static environment in a three-dimensional geographical environment. The method comprises the following steps: firstly, resolving a camera pose through a motion recovery structure algorithm to generate a sparse point cloud, and separating a dynamic foreground object in a monitoring video to extract motion features; thirdly, initializing a three-dimensional Gaussian distribution set based on the sparse point cloud, extracting semantic features through a visual encoder, and mapping the semantic features to corresponding Gaussian distribution; thirdly, a topological graph structure of Gaussian distribution is constructed, motion features are used as initial excitation, and coordinate offset and appearance variation of each distribution are iteratively updated through message passing calculation; finally, Gaussian distribution attributes are dynamically updated, a continuous deduction image sequence is synthesized through micro-rasterization rendering, and high-reality real-time simulation of dynamic evolution of the three-dimensional geographical environment is achieved.

The invention provides a power grid fault propagation path identification method and system based on a graph neural network, and relates to the technical field of power grid fault identification, and the method comprises the steps: obtaining a power grid topological structure and fault observation data, constructing a direction perception graph neural network, achieving the one-way message passing based on potential energy difference, and obtaining a node potential energy value and embedded representation; edges are screened to generate a directed graph, and candidate paths are generated in the potential energy gradient direction; and verifying the satisfaction degree of the graph neural network evaluation path to the physical constraint through an invariant, and finally selecting the path with the minimum topological entropy. According to the invention, the accuracy and reliability of fault propagation path identification are improved.

The invention discloses an industrial product quality risk association method based on a graph neural network, and relates to the field of industrial manufacturing, and the method comprises the steps: collecting multi-source industrial data, carrying out the preprocessing of the multi-source industrial data, obtaining a standardized data table, and constructing an industrial element heterogeneous graph based on the standardized data table; inputting the industrial element heterogeneous graph into a graph attention network basic model for node representation learning, and setting a supervised learning task taking a product batch node in the industrial element heterogeneous graph as a prediction target and taking a historical quality detection result as a supervised label; and introducing a meta-path self-learning layer in a message passing process of the graph attention network basic model. According to the method, deterministic prediction is upgraded into probabilistic inference, internal confidence degree measurement is provided for each risk prediction value, and automatic, accurate and interpretable correlation analysis and traceability positioning of the industrial quality risk are realized.

The invention discloses a wind power plant data synchronous correction method based on view topology and a mask graph neural network, and belongs to the field of wind power plant data processing and artificial intelligence space-time sequence prediction.The method comprises the steps that firstly, historical space-time observation data of unit nodes are obtained, and a space-time feature tensor is constructed; generating a mask matrix; extracting space and time sequence waveform correlation characteristics of a plurality of unit nodes, and constructing a global multi-view adjacency matrix; inputting the spatio-temporal feature tensor and the global multi-view adjacency matrix into a spatio-temporal diagram neural network, performing blocking and shielding operation in a message passing stage of the network, extracting full-field features, and outputting an initial deduction sequence; and obtaining a boundary physical residual error, reversely compensating the boundary physical residual error to the initial deduction sequence, and generating and outputting final correction data. According to the method, test data high-fidelity error correction under high concurrency missing rate and strong noise interference is realized, and the space-time diagram calculation memory overhead of a bottom-layer deep learning framework is remarkably reduced by designing a static topology cache mechanism.

The invention relates to a UGT enzyme subtype substrate specificity prediction method and model. On the basis of a directional message passing neural network, graph structure characterization of a small molecule compound and features of specific protein binding sites of UGT enzyme are deeply fused, a bimodal prediction normal form of'molecule + protein binding sites' is designed, a deep learning model is constructed, conversion from compound center prediction to molecule-enzyme binding site comprehensive prediction is achieved, and the prediction accuracy is improved. And accurate classification prediction can be carried out on UGT enzyme substrates and non-substrates.

The invention relates to the technical field of battery thermal safety management, and discloses an energy storage battery thermal runaway intelligent early warning method and system based on machine learning, and the method comprises the steps: obtaining an energy storage system cooling layout parameter and a sensor data flow, generating a data missing mode recognition result containing a missing time period, a missing position and a missing type; probability distribution of temperature and flow physical quantity of the missing sensor is inferred through a message passing mechanism, and a numerical value distribution inference result of the missing sensor is output; posterior state distribution is calculated through Bayesian reasoning, and a virtual-real mixed thermal state estimation result is generated; and analyzing a thermal state estimation result based on a confidence coefficient weighted multi-objective optimization algorithm, constructing a multi-objective function including weighted risk minimization and cooling energy consumption cost minimization, and outputting a cooling control instruction. The technical problem that a traditional digital twinning system is highly dependent on data integrity is solved.

The invention relates to an Internet of Vehicles computing power scheduling method based on a graph neural network and deep reinforcement learning, and the method comprises the steps: S1, collecting the state information of network entities in the Internet of Vehicles and the association information between the entities in real time, and constructing a dynamic time-space attribute graph; s2, inputting the dynamic space-time attribute graph into a pre-trained graph neural network encoder, and outputting a node embedding feature set containing a high-order topological relation and global graph embedding features through multi-layer message passing and feature aggregation; s3, the node embedding feature set and / or the global graph embedding feature are / is used as the state of a deep reinforcement learning agent and input to a strategy network, the computing power scheduling action at the current moment is output, and the computing power scheduling action comprises the steps of assigning an unloading target node for a to-be-processed computing task and distributing corresponding computing and communication resources; s4, dispatching actions are distributed to the corresponding network entities to be executed, environment feedback is collected and used for model updating and next round of dispatching, and the method has the advantages of improving dispatching efficiency, adaptability and system energy efficiency and the like.

The invention relates to a microservice anomaly detection method and system based on a causal graph converter. The microservice anomaly detection method comprises the following steps: constructing graph data based on index data during microservice system architecture and operation; inputting graph data into a graph neural network of an anomaly detection model, performing multilayer message passing and feature aggregation on neighbor node features, and extracting local dependency features of nodes; converting node features extracted by the graph neural network into a sequence form, inputting the sequence form into a converter encoder of an anomaly detection model, and learning long-distance global interaction features between nodes through a self-attention mechanism; respectively calculating a causal attention mask and a non-causal attention mask based on output features of a converter encoder by using a causal attention learning module in the anomaly detection model, and softly dividing the original image into a causal representation image and a non-causal representation image; and reading the graph-level representation corresponding to the causal representation graph through the corresponding readout layer, and obtaining a micro-service anomaly detection classification result through the first classifier. Compared with the prior art, the method has the advantages that the microservice anomaly detection accuracy can be improved, and the like.

The invention provides a sewage plant water-energy-drug collaborative optimization method and system, and the method comprises the steps: obtaining the data of a technological process and a material transfer relationship of a sewage plant, constructing a graph network structure model with a technological unit as a node and material flow as an edge, and carrying out the preprocessing, thereby obtaining dynamic coupling graph structure data; a dynamic coupling graph neural network model containing a node feature coding layer, a time sequence coding module, a space message passing layer and an attention mechanism layer is constructed based on the data, and a prediction model capable of representing the dynamic coupling relation of the process unit is obtained through historical data training; then, a multi-objective optimization function which takes the lowest ton water treatment cost as an objective and covers water quality standard reaching, energy consumption and medicament dosage constraints is constructed; and in combination with the prediction model and the optimization function, the optimal operation parameters are solved through an optimization algorithm, and a whole-plant collaborative optimization decision scheme is generated. According to the invention, the dynamic coupling GNN prediction model and the virtual element multi-domain parallel optimization technology are integrated, and intelligent operation management of the sewage treatment plant is realized.

The invention discloses an asynchronous task message passing method, device and equipment based on an MCP protocol and a storage medium, is applied to a calling end registered as an MCP endpoint, and relates to the technical field of computer networks, and the method comprises the following steps: establishing a full duplex communication session with an execution end based on instance information issued by a service registration center, establishing task semantic information based on the initial task request by using an MCP protocol layer; a target task request is sent to the execution end through the session, and the execution end executes a task by using the Nacos service according to the target task request to generate an event flow. And when the network connection is abnormal, the calling end locates the position of the event successfully received last time based on the global unique event identifier of the event stream, generates a reconnection request and issues the reconnection request to the execution end, and the execution end returns the event stream in sequence according to the reconnection request. And the calling end sends the confirmation instruction to the execution end, the execution end generates the event confirmation sequence number and returns the event confirmation sequence number, and the calling end judges that task message transmission is completed after receiving the sequence number, so that the task message transmission efficiency is improved.

The invention discloses an intelligent substation state evaluation method and system based on digital twinning, and relates to the technical field of state evaluation, and the method comprises the steps: firstly constructing a heterogeneous knowledge graph capable of precisely mapping a physical entity logic relation based on the ontology definition, asset information and topological data of a substation; then, massive real-time fast-change data streams are introduced into the atlas framework, and node states are dynamically mapped by using a time sequence feature coding technology; and a complex message passing and aggregation mechanism is carried out in the graph structure through the relation perception graph neural network, and node embedding representation with local personality and global generality is generated. And finally, synchronously finishing equipment risk prediction at a micro level and total-station comprehensive evaluation at a macro level based on the high-dimensional representation, and carrying out path backtracking and cause analysis on a high-risk state based on map relevance. Therefore, the problem of equipment health and system operation state separation can be solved, and intelligent substation panoramic state perception and risk early warning with interpretability can be realized.

The invention relates to the cross technical field of material calculation and machine learning, and discloses a magnesium alloy grain boundary segregation site determination method based on a physical information graph neural network, and the method comprises the following steps: extracting initial geometric structure information of a target grain boundary site and adjacent atoms thereof, and obtaining feature vectors of initial nodes and edges; performing message passing on the initial node and the edge feature vector based on a mathematical analysis form and an update function embedded with physical information to obtain an updated node feature vector; carrying out aggregation processing on the updated node feature vectors to generate a grain boundary structure descriptor used for representing the local atomic environment of the grain boundary site; and inputting the grain boundary structure descriptor into a pre-trained machine learning regression model to obtain a solute segregation performance predicted value of the target grain boundary site. According to the method, the calculation of segregation energy is converted into efficient machine learning prediction from high-cost physical simulation, and the calculation efficiency is greatly improved.

The invention discloses an AI-driven big data blood relationship and quality collaborative treatment method and system, and the method comprises the steps: constructing a dynamic blood relationship knowledge graph through a graph neural network based on collected original data, and carrying out the blood relationship reasoning and business index mapping through a message passing mechanism; according to the dynamic consanguinity knowledge graph, combining field semantics, consanguinity topology and data features to generate a quality rule, positioning a data exception root cause through a causal inference model, and outputting a governance decision basis; an operation and maintenance strategy model is constructed through a reinforcement learning algorithm, a dynamic blood relationship map change state, quality rule violation details and a cluster resource load condition are taken as inputs, data exception recovery efficiency, rule false alarm rate control and manual intervention frequency reduction are taken as optimization objectives, and targeted repair actions are dynamically matched and executed. According to the method, the problems of difficulty in tracing, quality rule static lag, difficulty in root cause positioning, dependence on labor in operation and maintenance and high cost caused by blood relationship fragmentation in traditional data management are solved.

The invention discloses a three-dimensional point cloud semantic segmentation method and device. The method comprises the steps of obtaining three-dimensional point cloud data to be segmented; and inputting the semantic tag into a pre-trained segmentation model to obtain the semantic tag. The segmentation model adopts a local geometric enhancement module, a dynamic attention module and a feedforward network which are connected in sequence. The core of the method is that anisotropic graph message passing is carried out through a graph neural network, and local geometric features are explicitly enhanced; and through a grouping vector attention mechanism, a position modulation item based on a relative position between points and a density modulation item based on a local density are introduced in a combined manner, and an attention weight is dynamically adjusted, so that adaptive feature aggregation of a point cloud heterostructure and complex geometry is realized. And the segmentation precision and contour sharpness in sparse and dense mixed regions and high-curvature boundaries are effectively improved.

The invention discloses a gas molecule smell prediction method and system based on an isotropic graph neural network, and relates to the technical field of tobacco production equipment.The method comprises the steps that an SMILES expression of gas molecules is converted into a molecular graph structure containing atomic features and edge features and three-dimensional space coordinates through DGL-LifeSci and RDKit toolkits; then inputting the data into an EGNN isotropic graph neural network, aggregating neighborhood information through a message passing mechanism, and synchronously updating node features and coordinate features; a plurality of EGNN layers are stacked for deep feature extraction, and high-dimensional node representation and final coordinate values are obtained; performing global pooling through an MLPReadout module to obtain a global molecular representation vector of a fixed dimension; and finally, mapping the vector to a 138-dimensional space through a full connection layer, processing through a Sigmoid function to obtain an odor probability vector, and finally judging and outputting a specific odor category through a threshold value.

The present disclosure provides a Boolean formula unsatisfiability core prediction method based on hypergraph modeling. A CNF formula generated by a software and hardware formal verification problem coding in the field of electronic design automation is received from the outside, input into a hypergraph representation learning model, and modeling for solving a SAT problem corresponding to the software and hardware formal verification problem is obtained. The model is constructed in the following manner: first, SAT problem representation based on hypergraph is performed. Specifically, the CNF formula is modeled as a clause-literal hypergraph by using a SAT problem modeling method based on hypergraph and a message passing method based on hypergraph, and a clause correlation graph is further constructed to obtain problem representation. Then, a polarity-aware variable decomposition method is applied to the clause correlation graph, and the problem representation is structured and modeled. The hypergraph representation learning model is trained by using a training method based on polarity-aware consistency constraints, and is integrated with a SAT problem solver, so that the model can be used to solve the problems that the existing graph neural network-based SAT learning method has in the aspects of polarity modeling and high-order structure expression.

The invention discloses a point cloud-based suction pose calculation method and device and a medium, and the method comprises the steps: collecting point cloud data corresponding to a to-be-sucked article in real time, and carrying out the preprocessing of the point cloud data, and obtaining node data and adjacent data corresponding to the node data; acquiring a graph neural network model; space geometric information is introduced into a message passing and attention calculation mechanism in a graph convolution operator to calculate and construct an SSFConv layer, a feature extraction layer in a graph neural network model is replaced by the SSFConv layer, and an absorption pose calculation model is obtained; and inputting the node data and the adjacent data into a suction pose calculation model for calculation to obtain a suction pose corresponding to the to-be-sucked article. According to the invention, the accuracy and robustness of the suction pose can be improved, so that the suction effect is improved.

The invention discloses a channel management method and system based on a red-black isolation architecture, and relates to the technical field of channel management, and the method comprises the following steps: configuring strategy information of opposite-end equipment in a red area, triggering a channel management event based on the information, generating a control message by a channel management module of the red area, and sending the control message to the opposite-end equipment; sending the control message to an isolation unit for legality verification, and forwarding the control message passing the verification to a black area; and the control message is analyzed in the black area, a channel management message is assembled according to the opposite terminal equipment information and the instruction, link establishment or link disassembly operation is executed, and a result is sent to the opposite terminal equipment in the red area. The invention solves the technical problems that the prior art depends on a single channel type to carry out communication, the channel management control data lacks security protection and the operation flexibility is insufficient, and achieves the effects of realizing security channel management under multiple channel types and trigger modes based on a red-black isolation architecture and multiple trigger mechanisms, and improving the safety of communication. And the safety and the flexibility of the channel management operation are improved.

The application provides a low-density parity-check code decoding method and device based on a graph neural network, which comprises the following steps: step 1, constructing a factor graph comprising variable nodes, check nodes and edge relationships, and mapping log-likelihood ratio information of a received signal to initial embedding of the variable nodes; step 2, generating message features according to node embedding, node degree and iteration step length, and constructing attention weights for each edge to measure the importance of the message; step 3, inputting the message features and the attention weights into a gated recurrent unit to update the residual of the edge weight, and feeding back the updated edge weight to the graph structure; step 4, weighting and aggregating the messages from the adjacent nodes according to the edge weight, calculating the updated embedding of the variable nodes and the check nodes, and performing gated modulation combined with the check result; step 5, repeating steps 2 to 4 until a preset iteration number or a decoding convergence condition is reached, and mapping the final variable node embedding to a decoding result to realize LDPC code word recovery. By introducing the attention mechanism and the gated residual update into the message passing process, the application realizes adaptive modeling of the contribution degree of different edge messages, dynamically remembers the historical state, thereby improving the decoding performance and the convergence speed; meanwhile, the application can effectively reduce the bit error rate and is suitable for high-speed reliable data transmission scenarios in a 5G / 6G wireless communication system.

The invention provides a parallelization boundary perception cloud or shadow rapid segmentation method, and belongs to the technical field of image processing, and the method comprises the steps: giving a remote sensing image global observation value and a preset unary potential function of a cloud / shadow coarse mark, and carrying out the iterative segmentation through employing a parallelization boundary perception segmentation method; the initialization of a Gaussian KD tree is carried out; iteratively using the following steps to carry out conditional random field parallelization rapid message passing, class compatibility transformation of non-normalized probability, local updating of non-normalized probability and probability normalization; and after iterative convergence, optimal classification is obtained. According to the method, the sensitivity to the low-level visual features of the region of interest in the image is enhanced, the segmentation model is guided to perform accurate segmentation on the edge of the target of interest, and the target edge is fully compact and sharp in segmentation prediction; and designing a Gaussian KD tree-based parallelization model implementation method to solve the problem of rapid calculation of a boundary perception segmentation model.

A video prediction technique generates a motion graph based on given video frames. The motion graph includes spatial edges and temporal edges. Each spatial edge describes a same-frame semantic relationship between two graph nodes that are associated with a same video frame. Each temporal edge describes an interframe relationship between two graph nodes of temporally neighboring frames. The temporal edges include backward temporal edges and forward temporal edges. The technique further includes generating initial motion feature information associated with the graph nodes in the plural given video frames, and updating the motion feature information by performing message-passing operations. The technique decodes the motion feature information into dynamic vector information. The technique then predicts and synthesizes a subsequent video frame based on the given video frames and the dynamic vector information.

The invention provides a pixel-level spatial resolution multi-energy X-ray material identification method and system, which is combined with a graph neural network to realize pixel-level material identification, and comprises the following steps: acquiring multi-energy X-ray image data of a sample; selecting a pixel region as an analysis unit, and constructing an energy-space diagram, including defining each pixel point of each energy interval as a node of the energy-space diagram, and establishing a first class of edges connecting adjacent nodes on the space and a second class of edges connecting nodes of the same pixel point space coordinate but in different energy intervals; and inputting the energy-space graph into a pre-trained graph neural network model so as to generate feature representation capable of representing material attributes of the pixel region through multiple rounds of message passing and aggregation, and outputting material categories through a classifier. According to the method, the spatial information and the energy spectrum information are deeply fused, so that the accuracy, the robustness and the data utilization efficiency of classification of low-atomic-number and near-density materials are remarkably improved, and meanwhile, the dependence on an accurate physical model is reduced.

The invention discloses a gene regulatory network prediction method and system based on explicit correlation modeling, and the method comprises the steps: obtaining a gene expression matrix of single-cell RNA sequencing data and an adjacent matrix of a prior regulatory graph constructed based on prior knowledge, and inputting the matrixes into a graph neural network model; wherein the graph neural network model is configured to perform explicit modeling on a link in the prior regulation and control graph through an intra-layer message passing space and an inter-layer message passing space so as to obtain link representation; predicting whether a regulation relation exists between the gene pairs through a classifier on the basis of link characterization so as to deduce a gene regulation network; wherein the architecture of the graph neural network model is adaptively determined through an automatic architecture search algorithm according to input data. According to the framework provided by the scheme, modeling link representation is displayed in the message passing process, the regulation and control relation of the gene pair is inferred by MLP based on link embedding, utilization and organization of complex connection information of the prior regulation and control graph are enhanced from the source, and the inference accuracy is effectively improved.

The application discloses a kind of typhoon disaster under graph neural network induced active power distribution network dynamic reconstruction system, including graph neural network module, pre-processing filtering module, post-processing selection module, optimization solving module and scene generation module.System is dynamically simulated topological reconstruction by switch gate message passing mechanism, adopts topology-independent local predictor to realize the expansion of cross-network configuration, in combination with pre-filtering non-critical switch and post-processing confidence selection, under the premise of guaranteeing physical feasibility, GNN prediction is combined with MIP optimization.In the actual measurement of IEEE 33 node system, 1.64 times of calculation speed is realized, only 0.67% average optimality gap is generated, effectively solve the problem of low computational efficiency of traditional method, significantly improve the resilience level of power distribution network in response to extreme weather.