69 results about "Temporal correlation analysis" patented technology

The invention relates to the technical field of pollutant tracing, and discloses a method and a system for tracing new pollutants in various environmental media based on machine learning. The method comprises the following steps: collecting multivariate environment data to construct a pollutant fingerprint database; performing space-time correlation analysis on the fingerprint database and the environment data, and reconstructing a transmission path; converting the data, the fingerprint database and the path diagram into source node fusion to construct an analytical model, and forming a contribution rate matrix; and positioning the pollution source through the three-dimensional features based on the matrix. According to the method and the device, an intelligent decision-making system based on machine learning can be constructed by integrating multi-source heterogeneous data under a complex environment background, automatic, standardized and precise traceability of new pollutants is realized, and the traceability efficiency and accuracy are improved.

The invention provides a crop monitoring system and method based on multispectral remote sensing and deep learning, and the system comprises a data preprocessing module which is used for carrying out the data preprocessing of a multispectral remote sensing image, and generating a standard reflectivity data set; the feature extraction module is used for extracting a high-dimensional spectral feature vector from the standard reflectivity data set through a multi-scale convolutional neural network; the time sequence dynamic analysis module is used for performing time sequence correlation analysis on the high-dimensional spectral feature vector through a long short-term memory network to generate a weighted time sequence feature vector; the physiological parameter quantification module is used for mapping the weighted time sequence feature vectors into quantitative indexes of crop physiological parameters; and the monitoring result generation module is used for performing dynamic deduction according to the quantitative index and generating dynamic trend prediction data of the crop growth state. The system can dynamically sense the growth stage characteristics of crops and adaptively adjust the spectral feature extraction strategy, thereby improving the crop monitoring precision in a complex agricultural environment.

The invention provides a network security protection method and system based on information fusion, and the method comprises the steps: firstly obtaining a multi-source heterogeneous data set, which comprises a traffic interaction data unit, an equipment log data unit and a protocol analysis data unit, of a target network, then carrying out the time sequence correlation analysis of the traffic interaction data unit, and generating a traffic behavior feature set; and executing state mode analysis on the equipment log data unit to generate an equipment operation feature set, and executing semantic recognition on the protocol analysis data unit to generate a protocol analysis feature set. Then, on the basis of a multi-dimensional feature fusion rule, cross-dimensional feature fusion processing is carried out on the feature set, and a network situation feature set is generated; and calling a threat identification model to carry out threat identification on the set, generating a threat identification result set containing threat type identifiers and influence range parameters, and finally generating a security response strategy set according to the threat identification result and issuing the security response strategy set to a security control node to execute protection operation, thereby effectively improving the network security protection capability.

The invention relates to the field of monitoring and early warning, in particular to a dynamic beam radar monitoring and linkage early warning method and system for a layered side slope of an expressway, and the method comprises the steps: carrying out the layered scanning of a layered geologic structure of the side slope, synchronously obtaining a phase coherent echo signal, carrying out the multi-threshold scattering point extraction, and carrying out the multi-threshold scattering point extraction; through analysis of a prior constraint model and a geological vegetation recognition network, interference signals caused by vehicle passing are eliminated to obtain a space-time coherent scattering point set, the space-time coherent scattering point set is input to a deformation calculation assembly line, differential interference measurement, adaptive atmospheric disturbance correction and slope structure parameter inversion are executed, and a displacement data stream is generated. And carrying out space-time correlation analysis on the layered inclination angle time sequence data and the meteorological and hydrological data, updating a slope stability evaluation index through a dynamic baseline, and generating an early warning instruction. According to the invention, a technical system from interference suppression and precise calculation to decision closed loop is formed, high reliability of road slope monitoring results is ensured, and intelligent support is provided for traffic safety and emergency management and control.

The invention provides a humanoid robot inertial navigation and vision fusion positioning method, device and equipment. The method comprises the following steps: firstly, pre-evaluating the quality of IMU inertial data and visual SLAM data to generate a data credibility identifier; establishing a causal relationship chain between the data sources through time sequence correlation analysis; constructing a multi-strategy superposition state based on data credibility, and determining an adaptive fusion strategy through collapse judgment; constructing a data evolution path by using a causal relationship, and generating an expected behavior feature and a causal deviation feature; the fusion parameters are optimized according to the deviation characteristics, and a plurality of fusion positioning estimations with different weights are generated; and through space aggregation analysis and confidence weight calculation, selecting optimal positioning estimation and outputting a high-precision fusion positioning result. According to the method, deep understanding of sensor data, intelligent selection of fusion strategies and robust output of positioning results are realized, and the positioning performance of the humanoid robot in a complex environment is improved.

The invention relates to the technical field of power system management, in particular to a Beidou-based power grid emergency wireless command system, which comprises a Beidou positioning communication terminal, a multi-source data fusion terminal, an intelligent decision-making terminal, a heterogeneous communication terminal and a visual command terminal. The Beidou positioning communication module accurately obtains the position of the power equipment and transmits an encryption instruction; the multi-source data fusion module integrates power, weather and geographic information, and provides support for decision making through data cleaning and space-time correlation analysis; the intelligent decision-making module generates a multi-target optimization decision by applying an improved multi-target genetic algorithm based on a digital twinborn dynamic plan library and a deep reinforcement learning algorithm; the heterogeneous communication module integrates various communication units, realizes mode dynamic switching and bandwidth aggregation, and ensures stable communication. And the visual command terminal displays the power grid situation and efficiently issues an instruction by means of augmented reality and multi-level authority management. The power grid emergency response and command efficiency is greatly improved, and power supply stability is powerfully guaranteed.

The invention relates to the technical field of electrical load management, and discloses an electrical load spatial-temporal distribution modeling and adaptive optimization regulation and control system. The system comprises a load monitoring module, an optimization decision-making module, an exception handling module, a communication coordination module and a data tracing module. The load monitoring module collects load data by using a space-time correlation analysis technology; the optimization decision-making module adopts a dynamic clustering algorithm to generate a regulation and control strategy; the exception handling module corrects load exception in a graded manner based on a multi-scale coordination mechanism; the communication coordination module realizes instruction interaction through a hierarchical routing protocol; and the data tracing module generates a topology storage index by using a multi-dimensional feature coding algorithm. The system can accurately collect load data, reasonably distribute power, effectively process load abnormity, guarantee communication stability, facilitate data tracing, improve the operation efficiency and reliability of an electric power system, and meet the requirement of a modern electric power system for electrical load management.

The invention discloses a cloud network fusion data processing method and system, and particularly relates to the technical field of data processing. The method comprises the following steps: constructing a link semantic dynamic graph based on space-time correlation analysis by extracting dynamic semantic parameters of transmission links in a heterogeneous network; and meanwhile, performing multi-dimensional semantic analysis on the cloud data stream to generate a data stream semantic fingerprint. The method comprises the following steps: identifying a semantic conflict type through matching degree analysis, reversely analyzing a node switching sequence and bandwidth fluctuation characteristics of a transmission path for a fragmentation strategy mismatch scene, evaluating the matching degree of a link and data processing logic, and generating a semantic compatibility matrix based on a fragment recombination rule and aggregated context characteristics; and the matching degree and the compatibility matrix are input into a dynamic compensation model, a fragment recombination strategy and a priority remapping rule are generated, whether real-time reconstruction of a data processing engine is triggered or not is judged, dynamic adaptation of network transmission semantics and cloud computing logic is achieved, and the real-time performance of data processing and the resource scheduling efficiency in the heterogeneous environment are improved.

The invention relates to the technical field of image processing, and discloses a smart campus security monitoring method and system based on visual understanding. The method comprises the following steps: carrying out adaptive semantic segmentation on a campus scene image through priori knowledge of a campus functional region to obtain a campus functional region segmentation map; performing multi-dimensional identity feature extraction on the campus personnel according to the segmentation map to obtain a personnel identity detection result; the identity detection result is input into a campus behavior semantic perception network for abnormal behavior recognition, and an abnormal behavior recognition result is obtained; and according to the segmentation map, the identity detection result and the abnormal behavior identification result, performing comprehensive evaluation through a campus scene context sensing fusion algorithm to obtain a campus security monitoring decision result. The abnormal behavior detection method and device solve the technical problem that abnormal behavior detection in an existing campus security monitoring technology lacks spatial semantic correction and time sequence correlation analysis.

The invention relates to the technical field of learning optimization, in particular to a big data analysis-oriented deep reinforcement learning optimization algorithm, which comprises the steps of dynamic feature topological graph generation: performing time sequence correlation analysis on a big data stream input in real time to generate a dynamic feature topological graph; an enhanced state space is reconstructed, wherein the enhanced state space with space-time correlation characteristics is reconstructed through potential path mining; hierarchical decoupling training: asynchronous parameter updating is carried out by adopting a gradient isolation mechanism, and a strategy gradient flow and a value gradient flow are generated; multi-dimensional decision fusion: generating a multi-objective optimization decision through dynamic weight fusion; and feedback driving adjustment: according to the actual execution effect of the multi-objective optimization decision, reversely adjusting the construction threshold of the dynamic feature topological graph and the dimension parameter of the enhanced state space. According to the method, by constructing the dynamic feature topological graph, the time sequence dependency relationship in the big data flow can be captured in real time, the dynamic evolution process between the features is effectively reflected, and the flexibility and precision of feature modeling are remarkably improved.

The invention discloses an SER6 Pro antenna with adaptive beam forming capability, comprising: a generation module for generating an initial beam directional diagram based on spatial-temporal correlation analysis of multipath signals; the calculation module is used for updating beam direction parameters in real time by using a Doppler frequency shift estimation algorithm so as to adapt to Doppler frequency shift change of a high-speed mobile user; the suppression module is used for carrying out noise suppression on the beam signal in a frequency domain by adopting an adaptive filter; and the optimization module is used for dynamically adjusting the beam forming matrix and optimizing the beam direction and intensity through an iterative optimization algorithm. The method has the beneficial effects that the problem of inaccurate beam direction identification caused by excessive reflected and scattered signals in a complex multi-path propagation environment is solved; the problem of unstable beam tracking caused by significant change of Doppler frequency shift in a high-speed mobile user scene is solved; and the problem that the signal-to-noise ratio is reduced due to the strong external noise source in a high-interference environment is solved.

The invention discloses an AI-based urban traffic flow prediction and dynamic signal optimization method and system, and relates to the technical field of traffic management, and the method comprises the steps: obtaining real-time traffic data, historical flow data and external environment data of a target region, obtaining multi-source data, and constructing a space-time matrix corresponding to the target region according to the multi-source data; learning the space-time matrix by using a preset space-time fusion model, and outputting a prediction result of the traffic flow in a future preset time period through the space-time fusion model obtained by learning; wherein the space-time fusion model is a combined architecture of a graph convolutional network and a Transform network; and dynamically adjusting traffic signal control parameters in the target area through a multi-agent learning algorithm based on a prediction result. According to the method, closed-loop regulation and control of'data perception-prediction modeling-autonomous decision 'are formed, so that the limitation of spatial feature modeling staticization and time correlation analysis fragmentation of a traditional method is broken through, and the problem of regional imbalance caused by single-point optimization is effectively solved.

The present invention relates to the field of smart city management technology, and specifically to a dynamic aggregation and decision support system for urban physical examination spatiotemporal data, including a data acquisition module, a data preprocessing module, a spatiotemporal data aggregation module, an indicator calculation module, a dynamic analysis module, and a decision support module; wherein: the data acquisition module is used to collect multi-source heterogeneous original urban operation data; the spatiotemporal data aggregation module aggregates data according to a specified time window and spatial unit; the indicator calculation module extracts core indicators that reflect the health status of the city; the dynamic analysis module predicts the future change trend of the core indicators; the decision support module generates an optimization plan for urban governance strategies. The present invention accurately predicts the trend of urban operation and generates targeted governance optimization plans through the dynamic integration and spatiotemporal correlation analysis of multi-source heterogeneous data, significantly improving the comprehensiveness of urban physical examinations and the scientific nature of decision support.

The invention relates to the technical field of medical image information processing, and discloses a medical image information management system based on wisdom medical treatment, which comprises a scene perception preprocessing module, a cross-modal attention fusion module, a weak supervision annotation module, a comparative analysis module, a collaborative report generation module, a knowledge graph reasoning decision module and a consultation collaborative platform module. The image quality is improved through scene adaptive preprocessing; a hierarchical cross-modal attention mechanism is adopted to realize multi-modal feature alignment and fusion; lesion labeling is carried out based on a cascade weak supervised learning strategy; obtaining a focus evolution trend through time sequence correlation analysis; generating a standardized diagnosis report by using a visual language collaborative network; providing treatment scheme recommendation based on individualized knowledge graph reasoning; and a multidisciplinary consultation cooperation platform is constructed. According to the method, the scene adaptability of image quality evaluation is improved, the multi-modal semantic alignment capability is enhanced, the dependence of focus labeling on a fine sample is reduced, and dynamic disease monitoring and individualized diagnosis and treatment decision support are realized.

The invention discloses a distributed photovoltaic fire early warning method, and relates to the technical field of fire early warning, and the technical scheme is characterized in that the method comprises the steps: collecting the current, voltage and infrared temperature matrix of a photovoltaic module through a detection module; the data collected by the detection module is analyzed based on the space-time correlation analysis module, the dynamic weight coefficient of the current is output in real time, and a weighted feature vector is generated through dynamic fusion; the position P of the photovoltaic module is obtained through the positioning module, and a space-time correlation matrix between the photovoltaic modules is calculated through the space-time correlation analysis module; analyzing the weighted feature vector and the space-time incidence matrix based on an LSTM network, and outputting a risk score R (t) of the photovoltaic module; and triggering a grading analysis response according to the risk score. According to the invention, through multi-source detection, dynamic analysis and grading correspondence, efficient and accurate photovoltaic fire early warning is realized.

The invention discloses a multi-temporal-spatial-state main multi-source collaborative modeling method and device. The method comprises the following steps of S1, performing hierarchical processing on multi-temporal-spatial-state data; s2, performing multi-time-space state feature extraction and correlation analysis on the processed data to form a multi-time-space correlation matrix; s3, performing main multi-source collaborative modeling based on the multiple time-space incidence matrixes and outputting a result; and S4, predicting and generating a scheduling scheme by using an output result. During work, on the basis of multi-time-space state data, through combination of multi-time-space correlation analysis and a main model-collaborative sub-model collaborative modeling method, global and local features are integrated, and through dynamic weight adjustment, accurate prediction and optimization of the operation state of the power distribution network are realized, and finally, comprehensive support is provided for scheduling, optimization and emergency response.

The invention discloses an event-visible light combined video enhancement method for cross-modal spatial-temporal correlation analysis, and the method comprises the steps: 1), generating a corresponding dynamic event stream frame through an event camera simulation model, and dividing a data set; (2) a Feature Extractor module based on UNet is constructed, and feature extraction is carried out; 3) constructing a cross-modal reconstruction unit based on BCPS, and recovering contour information of the visible light video frame; 4) constructing a space domain noise filtering network VSNF and a time domain noise filtering network VTNF, and performing feature analysis respectively; 5) constructing a UNet-based feature fusion module, and generating a denoising result conforming to human visual perception characteristics; and 6) designing a loss function, and achieving an optimal balance state through multiple times of loop training. The method belongs to the technical field of image processing, and solves the problems of incomplete dynamic feature extraction, insufficient time domain information utilization and low overall visual quality of a video in a denoising process in the prior art.

The invention relates to the technical field of water quality monitoring, and discloses a water quality monitoring method and system based on edge calculation. According to the method, a water quality sensor array is deployed at an edge node, multi-dimensional water quality parameters of a target water area are collected in real time, and an original water quality data flow is generated. Performing space-time correlation analysis on the original data stream, identifying the change trend of the water quality parameters in time and space dimensions, and generating a preprocessed data set with a timestamp and a position mark; a dynamic water quality evaluation model is constructed based on the data set, and model parameters are updated in real time by utilizing the computing capability of edge computing nodes. Inputting water quality parameters collected in real time into the model, detecting abnormal water quality fluctuation and generating an abnormal water quality event report. And triggering a traceability analysis process according to the report, and determining a potential source of the abnormal water quality event in combination with historical water quality data and environmental factor data. The method is high in real-time performance, efficient in data processing, capable of accurately tracing, capable of effectively improving the water quality monitoring level and capable of guaranteeing the safety of water resources.

The invention relates to the technical field of unmanned aerial vehicle sensor anomaly detection methods, and particularly discloses an unmanned aerial vehicle flight control system data anomaly detection method based on a CNN-KFU multiple regression model. In unmanned aerial vehicle flight data, correlation of different degrees often exists among data, and firstly, a correlation analysis method is utilized to select a data set having relatively high correlation with target data; secondly, a multiple regression neural network model, namely CNN-KFU, for fine-grained spatial-temporal correlation analysis is designed based on 1D CNN and KFU, the CNN-KFU is used as a feature extractor of data, correlation of flight control data in time dimension and spatial dimension is fully learned, and the model is enabled to better understand data features. And finally, calculating the deviation between the regression residual error of the test data and a threshold value to realize abnormity judgment. The objective of the invention is to solve the problem that in the prior art, parameter selection is lack of effectiveness, and time-space relationship knowledge learning is insufficient, so that the anomaly detection capability is low in a complex flight scene.

The invention relates to the technical field of traffic management, in particular to a traffic video event detection method and system based on space-time correlation analysis, and the method comprises the steps: obtaining traffic video data, traffic text description data and traffic equipment state data, carrying out the preprocessing of the data, and unifying the format; extracting space and time characteristics of the video frame sequence, calculating a target space-time association weight by means of a space-time attention mechanism, and establishing a space-time association model; identifying a traffic event according to a model rule to obtain a preliminary result; the preliminary detection result is verified and supplemented through text association matching and image feature matching in combination with user query, a final event detection result is obtained, and the space-time association model is updated; and presenting a final event detection result to a user in a visual form. According to the method, multi-modal traffic data can be fused, the traffic incident detection precision in a complex scene is improved, a model can be optimized in combination with user requirements, a result is visually presented, and efficient traffic management is assisted.

The invention discloses a research and judgment method, system and equipment for four disordered problems of water conservancy rivers and lakes, and particularly relates to the field of research and judgment of water conservancy rivers and lakes, and the method comprises the steps: constructing a multi-source heterogeneous data set, and extracting dynamic environment features to generate a feature data set of a target water area; deploying a lightweight recognition engine at an edge computing node to perform dimension reduction on the features to generate four types of lightweight feature packets; a multi-dimensional decision graph is generated through space-time correlation analysis; and finally, the visual early warning platform is driven to realize dynamic visualization of the four disordered problems. According to the method, the system and the equipment for studying and judging the four-disorder problem of the river and the lake in the water conservancy, automatic alignment and efficient fusion of multi-source data are realized by controlling the space-time deviation within a threshold value, and the manual intervention requirement and the preprocessing computing resource consumption are remarkably reduced; the model parameter adjustment frequency is reduced through a radiation correction coefficient and a dynamic weight distribution strategy; and through space-time correlation analysis, a multi-dimensional scientific basis is provided for decision making, and the treatment efficiency is optimized.

The present application discloses a safety monitoring and management method and system for an intelligent box with an integrated lock, which is used to enhance the safety protection ability of the intelligent box and eliminate potential safety hazards. The method of the present application includes: the edge computing unit obtains multi-modal sensor data of the box in real time; the edge computing unit performs real-time analysis on the multi-modal sensor data according to a preset abnormal threshold to detect and respond to single-point abnormal events of the box; the edge computing unit performs local primary feature extraction on the multi-modal sensor data and uploads the extracted primary feature vectors to the fog computing node; the fog computing node performs high-level feature extraction and spatio-temporal correlation analysis on the primary feature vectors uploaded by all boxes in the regional network to identify whether there are group safety risk events; if so, the fog computing node dynamically adjusts the safety policy level of all boxes in the regional network to the highest level.

The invention relates to the technical field of induced draft fan bearing seats, and discloses an induced draft fan high-temperature-resistant bearing seat structure and thermal state monitoring algorithm integrated system which comprises a bearing seat body. Four corner areas of the bearing seat body are respectively provided with a fixing hole used for being fixed with a base, and the center of the bearing seat body is provided with a circular bearing mounting hole; according to the induced draft fan high-temperature-resistant bearing seat structure and thermal state monitoring algorithm integrated system, the annular liquid storage cavity structure provides an optimal measurement point for the temperature sensor while actively dissipating heat, high unification of the heat dissipation efficiency and accurate monitoring is achieved, and secondly, through time sequence correlation analysis of temperature and vibration signals, a multi-parameter fusion diagnosis algorithm is used for diagnosing the heat dissipation efficiency of the bearing seat structure and the thermal state monitoring algorithm. In addition, localization processing is combined with the self-adaptive learning function, the anti-interference performance and long-term stability of the system are enhanced, and meanwhile the maintenance process is simplified through remote parameter configuration.

The invention relates to the technical field of equipment log association analysis, and discloses a network security equipment log association analysis method based on a deep learning algorithm, which comprises the following steps: firstly, acquiring log data from network security equipment in real time through a log data acquisition tool supporting Syslog and SNMP protocols; cleaning, formatting and standardizing the collected original log data, and converting the log data in different formats into a uniform data structure; the method specifically comprises the following steps: standardizing field names and data types; data analysis is carried out, and feature analysis is carried out on the collected timestamps, IP addresses, port numbers, request types and response code data; the BERT model comprises an application layer, and the application layer outputs the results of the associated log entries recognized by the output layer and the association analysis. The mass data processing efficiency is improved, the correlation analysis accuracy is enhanced, the space-time correlation analysis capability is enhanced, and the adaptive learning capability is improved.

The invention provides an intelligent behavior identification and analysis method and system. The method comprises the following steps: segmenting preprocessed video stream data by using a semantic segmentation technology to obtain animal monomers, and respectively extracting spatial-temporal characteristics and overall dynamic characteristics of an animal group; inputting the spatio-temporal characteristics and the breeding environment semantic information into a monomer behavior semantic recognition model to obtain monomer behavior semantic characteristics, performing spatio-temporal correlation analysis on each monomer behavior semantic characteristic to calculate behavior interaction strength among different animal monomers, and constructing a group behavior correlation matrix according to each behavior interaction strength; and inputting the overall dynamic characteristics and the group behavior association matrix into a group behavior semantic recognition model to obtain a group behavior classification result, and generating prompt information. According to the method, key associated information such as group stress and ingestion competition can be effectively captured, and accurate identification and analysis of individual behaviors in a group behavior scene are realized.

The present application provides an anti-interference tracking method and system based on target infrared imaging features. Among them, a continuous infrared image sequence of a target object at different time points is acquired; spatio-temporal correlation analysis is used to determine the potential motion trajectory of the target object in the infrared image sequence; a dynamic weight map is generated based on the potential motion trajectory, wherein the dynamic weight map adaptively adjusts the importance of each pixel according to the changes of background noise and target features; the dynamic weight map is combined with the infrared image sequence to strengthen the target area and suppress the non-target area, obtaining a strengthened infrared image sequence; a multiple hypothesis tracking strategy is adopted to perform real-time positioning of the target object in the strengthened infrared image sequence, and the dynamic weight map is updated to maintain continuous tracking of the target object. The technical solution provided by the present application can improve the tracking accuracy.

The present application relates to the technical field of fire alarm, and discloses a fire alarm linkage method and system applied to an intelligent lock. The method includes: performing communication pairing and data exchange between the intelligent lock and the fire alarm system to obtain local sensing data and fire situation monitoring data; performing multi-source fusion and spatio-temporal correlation analysis to obtain a comprehensive fire situation assessment result; constructing an adaptive decision-making model and a differential response strategy; performing task decomposition and collaborative execution to obtain an intelligent lock linkage control instruction set and obtain an execution effect evaluation index; performing real-time monitoring and edge computing analysis on the execution effect evaluation index and environmental parameter change data to obtain a target feedback data stream; performing knowledge graph reasoning on the target feedback data stream to obtain decision model update parameters, and updating the adaptive decision-making model based on the decision model update parameters to obtain a target decision-making model. The present application realizes the intelligent linkage between the intelligent lock and the fire alarm system.

The invention discloses a natural gas pipeline failure risk assessment method and system based on data driving, and relates to the technical field of pipeline safety. The method comprises the following steps: firstly, calculating and correcting the failure probability by establishing a pipeline failure probability evaluation model, extracting key features by constructing a corrosion and design five types of failure factor index systems and principal component analysis, and calculating the failure probability by utilizing an improved correction coefficient formula; secondly, establishing a consequence evaluation model based on a risk matrix, and realizing differentiated evaluation of failure consequences in different geographical environments by combining GIS data; setting an online learning mechanism, and automatically updating a risk matrix when sensor data triggers a threshold value; the problems that a traditional method is high in subjectivity, insufficient in data fusion and low in simulation precision under complex conditions are solved, the accuracy and dynamic adaptability of risk assessment are improved through machine learning and space-time correlation analysis, accurate decision support is provided for pipeline operation and maintenance, and the safety accident rate is effectively reduced.

The application discloses a ship lock concrete structure durability analysis method and system under the coupling action of multiple factors, which comprises the following steps: acquiring internal structure images of different erosion areas of a ship lock concrete test piece; identifying and quantitatively analyzing the internal structure images of different erosion areas by a deep learning image segmentation algorithm to generate an erosion structure factor set; calculating environmental characteristics corresponding to multiple environmental parameters by a multi-physical field coupling inversion algorithm; constructing a three-dimensional microstructure model of different erosion areas; dynamically simulating the three-dimensional microstructure model according to the environmental characteristics; performing spatio-temporal correlation analysis on simulation result data by a hypergraph neural network to generate a prediction result; and comparing an expert knowledge base and performing construction maintenance based on text information of the prediction result by an Euclidean distance similarity algorithm. The application introduces high-precision three-dimensional model multi-factor coupling simulation, and improves the ship lock concrete structure analysis precision through high-precision coupling prediction of the hypergraph neural network.

The present application relates to dynamic time warping and graph neural network technology, in particular to a load data space-time correlation analysis method based on space-time graph neural network, which solves the technical problem that the accuracy improvement space of the traditional wind-solar-power prediction method is limited due to single consideration factor, and discloses the content of using space-time graph neural network to analyze the space-time correlation of load data, first using the FastDTW algorithm to analyze the space-time correlation of the obtained load data, constructing a correlation matrix, and finally using the obtained data set to train multiple independent parallel space-time graph neural networks to obtain the space-time characteristics of the load data and provide high-quality basic data for prediction.