29318 results about "Convolution" patented technology

Provided is a road crack detection method, a medium and a product. The lightweight YOLO-MCS road crack detection model is constructed based on an improved yolov8 network. A method of improving the yolov8 network includes: replacing a feature extraction network backbone with a lightweight convolutional neural network MobileNetV3, and embedding a Coordinate Attention Mechanism (CA) module in the lightweight convolutional neural network MobileNetV3; adding a small target detection layer and a Squeeze and Excitation (SE) module at a neck end; and introducing a loss function of power Intersection over Union (IoU) into a head prediction structure. The road crack detection method overcomes the problem that the existing detection algorithm has low detection precision for small cracks and is difficult to be applied to edge devices with limited computing resources.

The invention provides a dynamic path planning method and system in an intelligent traffic system, and relates to the technical field of intelligent traffic. Constructing a dynamic road network traffic capacity model based on a space-time diagram convolutional network; generating a multi-branch trajectory prediction result with a confidence score, adaptively starting an encryption parameter synchronization mechanism in combination with vehicle density, and generating a candidate path set through multi-agent collaborative game optimization; performing multi-dimensional deviation degree evaluation based on actual driving data and planning expectation; synchronously generating a multi-mode cooperative guidance signal; the system comprises a multi-source data fusion unit, a space-time modeling engine, a hierarchical decision-making system, a path verification and execution module, a closed-loop feedback controller, an event response system and a multi-mode man-machine interface. According to the method, the global resource utilization efficiency is improved through cooperation of data-driven modeling and hierarchical game decision, and the real-time performance, the safety and the system adaptability of path planning are improved through a closed-loop feedback and event response mechanism.

The invention discloses a tunnel multi-source fusion dynamic twin surrounding rock intelligent prediction and control method and system, and the method comprises the steps: collecting multi-source heterogeneous data in real time through intelligent drilling equipment, a distributed optical fiber sensing network and a mobile scanning device which are disposed on a tunnel construction surface; inputting the multi-source heterogeneous data into a space-time diagram convolutional network, constructing a space-time correlation model of geological features and construction disturbance parameters, and outputting a coupling feature matrix; based on the coupling characteristic matrix, simulating the dynamic response of the surrounding rock-support system through a streaming voxelization engine and a multi-physics coupling engine, and generating a risk evolution three-dimensional thermodynamic diagram; and inputting the risk evolution three-dimensional thermodynamic diagram into the deep reinforcement learning model, and dynamically optimizing to generate a construction parameter regulation and control instruction meeting a safety constraint condition. According to the technology, a full-link channel of'data perception-mechanical analysis-decision execution 'is opened in a closed-loop mode, and therefore the double risks of'data distortion misjudgment' and'response lag out-of-control 'of a traditional method are avoided.

Disclosed are a complex device fault diagnosis method and system based on multi-dimensional features, and the method comprises the following steps of: acquiring fault data of a target complex device, and carrying out input coding mapping and position coding; utilizing a multi-head attention mechanism and multi-head dilated convolution series connection, and acquiring fault features covering global and local deep information in combination with a feedforward neural network; fusing the extracted fault features to acquire a multi-dimensional feature vector; and acquiring a fault type probability score matrix by a classifier, and outputting a fault diagnosis result of the target complex device. The global modeling advantage of multi-head self-attention and the local multi-scale feature perception advantage of multi-head dilated convolution are fused, and a device fault diagnosis model in which a Transform model and the multi-head dilated convolution are mutually fused is established.

The invention relates to a microchip appearance defect detection method based on a convolutional neural network. The microchip appearance defect detection method comprises the following steps: acquiring a high-resolution microscopic image and carrying out adaptive brightness equalization processing; labeling defect features in the pre-processed image by adopting a layered labeling strategy, and dividing defects into a surface deformation class and a material anomaly class by coarse-grained classification labeling; a double-branch lightweight convolutional neural network model is constructed based on the annotation data, a first branch extracts global semantic features, and a second branch extracts local detail features. In the model training, a defect sensitivity loss function is adopted for optimization, and defect area attention, edge preservation and category balance loss items are included, so that the small-size defect detection capability and the boundary positioning precision are improved, and the problem of sample imbalance is solved. And finally, a detection result including defect types, position coordinates and confidence scores is generated by inputting a to-be-detected preprocessed microscopic image, and the defect detection performance with high precision and strong pertinence is achieved.

The invention discloses an industrial robot real-time adaptive control method and system based on digital twinning, and relates to the technical field of industrial robots. The digital twin engine module runs a high-fidelity dynamics simulation model and an environment interaction model, performs real-time state estimation, abnormal working condition recognition and twin parameter dynamic updating, is seamlessly integrated with the control execution module, and provides decision support with high robustness and high adaptability for an industrial scene; the adaptive control module performs online rolling optimization on a control strategy based on a deep reinforcement learning algorithm, generates joint space trajectory correction, tail end precision compensation and dynamic load adaptability optimal instructions, and realizes parameter adaptive setting through fuzzy logic or a neural network; and the fault diagnosis module performs multi-scale time sequence analysis by using an LSTM and convolutional neural network fusion model, detects position offset, moment sudden change or temperature overrun and other abnormalities, and triggers emergency shutdown, sound-light alarm and an adaptive recovery strategy.

The invention relates to the field of power equipment data processing, in particular to a biomass power generation combustion parameter deep learning method and system, and aims to solve the problem of phase mismatch caused by sampling frequency difference and clock reference offset of multi-source heterogeneous time sequence data. A parallel multi-scale convolution and bidirectional long-short-term memory network hybrid model is constructed, transient fluctuation and long-period trend features are extracted, and combustion stage feature weights are dynamically distributed through a gating attention mechanism. The optimization control module generates a multi-target constraint condition, an operation instruction is output in combination with a fuzzy inference engine, and a digital twin platform simulates an extreme working condition to enhance model robustness. A closed-loop feedback mechanism dynamically adjusts model parameters through combustion efficiency monitoring data and simulation results, and a two-stage fault-tolerant strategy realizes sensor abnormity compensation and historical control strategy backtracking. The problem of asynchronous data stream feature misalignment is effectively solved, and the combustion efficiency prediction precision and the control decision reliability are improved.

Disclosed in the present application is a skeleton detection and fall detection method based on improved spatio-temporal adaptive graph convolution. The method comprises the steps of: S1, collecting image data to acquire data of each image frame; S2: using a pre-trained yolov5 target person detection model to detect whether a target person is present in the data of each image frame, and if a target person is present, turning to step S3, and if no target person is present, ending the process; S3: for each detected target person, using a Deepsort target tracking algorithm to perform target tracking to obtain a tracking result, calculating the similarity to obtain the result of target association, and updating trajectory information of each target person; and S4: performing pose recognition on each target person on the basis of the trajectory information, using a spatio-temporal adaptive graph convolutional network to extract a feature vector of a pose, and using a classifier to perform human body behavior classification and recognition, in order to determine whether the target person has experienced a fall incident. The method achieves higher accuracy and robustness.

The invention discloses an underground construction decision-making method based on three-dimensional geological modeling and risk hot area identification, and relates to the field of fusion of artificial intelligence and geological engineering. The method comprises the following steps: firstly, acquiring drilling data, geological radar images and seismic reflecting layer information, constructing a three-dimensional geological voxel model with spatial topology constraints, and accurately describing a geological unit structure by adopting an irregular grid mode; and then, extracting a time sequence characteristic index under construction disturbance, forming a continuous time sequence characteristic vector, inputting the continuous time sequence characteristic vector into a convolutional recurrent neural network model with a space attention aggregation mechanism and a deep memory unit, and predicting a risk heat value of each space position. And on the basis, through heat gradient clustering and neighborhood consistency analysis, a dynamic high-risk hot area is identified, and a risk hot area map is constructed. And finally, in combination with the construction stage, the equipment plan and the sensor feedback information, constructing a multi-target auxiliary decision function, and generating a construction decision result including operation path reconstruction, rhythm adjustment and power limit and control suggestions.

The invention relates to the field of fault early warning, in particular to a wind power fault dynamic early warning method and system based on multi-source heterogeneous data fusion. According to the method, multi-source data such as SCADA operation data, CMS vibration monitoring data and meteorological environment data of a wind turbine generator are collected in real time, standardization processing is carried out, and a multi-dimensional feature vector is constructed. And generating a fusion data set by using an adaptive weighted fusion algorithm, constructing a fault prediction model based on a deep convolutional neural network, and outputting a health state assessment value and a fault risk level in real time after historical fault sample supervised training. And when the risk level exceeds a threshold value, generating an early warning signal containing a fault type and a positioning and repairing suggestion, dynamically adjusting a monitoring parameter weight, iteratively updating a model, and realizing adaptive optimization of an early warning strategy. The problem that an existing method depends on single data source and multi-source data fusion is solved, and accurate dynamic early warning is achieved.

The invention provides a supply chain multi-dimensional fluctuation prediction and inventory optimization method based on artificial intelligence, and relates to the technical field of supply chain management, and the method comprises the steps: obtaining multi-dimensional data, carrying out the preprocessing of the multi-dimensional data, generating a standardized time series data set and a knowledge graph, carrying out the multi-scale decomposition through wavelet transformation, and extracting fluctuation features; and constructing a state matrix by combining a graph attention network and a multi-head self-attention mechanism, predicting a risk conduction path based on historical fluctuation pattern matching and a graph convolutional network, and generating a risk prevention and control scheme. According to the invention, the fluctuation characteristics and the risk conduction path in the supply chain system can be accurately identified, and the early warning accuracy and the response timeliness are improved.

The invention provides an intelligent rehabilitation training method and system based on artificial intelligence and virtual reality, a user wears an intelligent wearable device to collect multi-modal data such as electroencephalogram, myoelectricity, physiological features and motion signals, the multi-modal data is preprocessed and then input into an artificial intelligence training model, and key features are extracted and fused by using a graph convolutional network and an attention mechanism algorithm. And constructing a digital twinborn model by using the fusion features, performing real-time dynamic mapping and predictive simulation, and generating a customized training scheme by means of a reinforcement learning algorithm in combination with a rehabilitation target and a physical state of the user. A user is trained in the virtual reality interaction model, the system monitors actions and physiological states in real time, the digital twin model synchronously acts, and the scene is dynamically adjusted. After training, the rehabilitation effect is evaluated according to the physiological indexes, the motion data and the twinning optimization analysis result, and an optimization training scheme and a digital twinning model are fed back. Precision, individuation and intelligentization of rehabilitation training are achieved, and the training effect and quality are improved.

The invention discloses a machine vision-based resistor disc defect online detection system and a grading method, relates to the technical field of industrial machine vision detection, and solves the defect problems in the aspects of multi-scale defect dynamic perception, cross-level feature interaction and process adaptive optimization in the prior art. According to the scheme, metal reflection interference is inhibited through Retinex illumination correction and a combined denoising model; adopting a deformable convolution kernel and cavity space pyramid pooling to realize gradient entropy driving dynamic sensing of the multi-scale defect; constructing a bidirectional cross-layer attention network to realize early fusion of high-resolution details and high-level semantics; modeling local-global feature physical association based on a graph attention network and a self-supervised message passing mechanism; integrating reinforcement learning and a memristor random calculation unit to form a closed-loop parameter optimization system; according to the method, the multi-scale defect detection precision, the cross-modal feature fusion efficiency and the system adaptive capacity under complex working conditions are remarkably improved.

The invention discloses an intelligent power distribution network line state real-time monitoring, analysis and evaluation system, and relates to the technical field of power system monitoring and control, the intelligent power distribution network line state real-time monitoring, analysis and evaluation system is constructed, data is collected in multiple dimensions, features are extracted through edge calculation, data is screened, a dynamic threshold model is constructed at a cloud end, and abnormity is identified. The method has the advantages that a three-dimensional digital twin network is constructed based on GIS data and an SCADA system through the power grid topology modeling module, and a unique'topology fingerprint 'containing electrical connection, physical position and logic control relation is generated for each piece of equipment; an upstream and downstream equipment list, a load influence range and a power flow transfer path are marked, and an association state evaluation module adopts a graph convolutional neural network and can accurately capture electrical coupling, physical proximity and historical fault association effects among equipment.

A method is provided for improving image classification accuracy in few-shot learning scenarios, where only a limited number of training examples are available. The method combines the use of Gabor filters and convolutional neural networks (CNNs) to extract detailed texture and orientation features from images. These features are then enhanced through global average pooling, aggregated into comprehensive feature vectors, and refined using an attention mechanism that identifies and emphasizes the most relevant features for classification. Masks generated from this attention process selectively enhance critical features, which, after optional re-encoding, are used to train a classifier via a metric learning approach. This method aims to increase feature separability and classification performance, facilitating more accurate classification of new images with minimal training data.

The invention discloses an electric power capital construction process early warning method and system based on a high-precision three-dimensional model, and relates to the technical field of electric power capital construction, and the method comprises the steps: collecting multi-source data of an electric power capital construction site, and constructing a high-precision three-dimensional model comprising equipment space coordinates, construction time sequence labels and environmental parameters; inputting the space-time diagram into a space-time diagram convolutional network, outputting a risk propagation probability matrix of a three-dimensional space and a construction time sequence dimension, and identifying high-risk nodes and associated construction stages; and dynamically marking root cause coordinates and a risk diffusion range in the high-precision three-dimensional model, generating an early warning instruction containing a visual path, a root cause report and a disposal priority, and pushing the early warning instruction to a terminal in real time through an edge node. Based on the hierarchical space-time attention-physical constraint graph convolutional network, the inter-node cross-stage association weight is dynamically allocated, the convolution kernel parameters are optimized in combination with the physical connection strength, and the space-time association of high-risk node identification is significantly improved.

The invention provides a power prediction precision improvement method and system for a wind and light station, and relates to the technical field of new energy power generation, and the method comprises the steps: obtaining the historical power, weather and equipment operation data of the wind and light station through a data preprocessing module, and carrying out the time sequence decomposition, spatial interpolation, abnormal value detection and correction, and obtaining the fusion feature data. And constructing a deep learning prediction model based on the fused feature data, extracting spatial features by using a convolutional neural network, processing the spatial features by using a long-short-term memory network to obtain an initial prediction result, introducing an attention mechanism to perform weight allocation to obtain weighted features, and combining to obtain power prediction data. And judging the weather type according to the real-time meteorological condition, and correcting by adopting the matched correction model when the extreme weather is identified. And finally, an error compensation model is constructed based on historical prediction errors for compensation, a final power prediction result is obtained, error correction is performed according to actual power data, and compensation model parameters are updated.

The present invention discloses a safety risk analysis system and method based on multimodal data processing; it relates to the field of industrial automation and information technology; the purpose of the present invention is to specifically target high-risk scenarios of hazardous chemical enterprises, and provide a safety risk analysis system and method based on multimodal data processing, which is based on deep learning technology, comprehensively considers the changes in spatiotemporal characteristics, can monitor and evaluate the safety risks of hazardous chemical enterprises in real time, and automatically integrates multimodal data such as monitored videos, sensor data, and operation logs. The spatial features are extracted through convolutional neural networks, and the time series data is processed using recurrent neural networks and long short-term memory networks, and further feature extraction and fusion are performed. The key risk factors are also identified through the attention mechanism, thereby achieving a comprehensive and accurate safety risk assessment, thereby providing real-time warnings for safety managers to ensure that potential safety hazards are discovered in a timely manner.

The invention discloses a wide-area landslide rapid identification method based on an interpretable intelligent algorithm, and relates to the field of remote sensing science and technology, and the method comprises the steps: building a dual-channel feature extraction architecture through multi-source spatio-temporal data fusion and knowledge graph dynamic weighting: capturing image local textures through a lightweight CNN, modeling geological spatial correlation through a graph convolutional network, and carrying out the recognition of the landslide. Combining the SHAP value and causal reasoning to generate an interpretable contribution degree thermodynamic diagram and a rule chain; a knowledge graph bidirectional verification system is introduced, spatial logic contradictions are verified by using prior rules, and co-evolution of a model and a rule base is triggered based on misjudgment samples; outputting a multi-dimensional credibility report, quantifying uncertainty by Monte Carlo Dropout, and customizing interpretation granularity according to roles; a terrain-adaptive block-stream processing architecture is adopted, and edge lightweight deployment and federated learning are combined, so that wide-area real-time early warning and model dynamic updating are realized. According to the scheme, the limitation of a traditional black box model is broken through, and a disaster prevention closed loop with physical driving, transparent decision and second-level response is formed.

This invention relates to a gait emotion recognition method, system, storage medium, and computer device based on spatiotemporal graph convolution. The method includes the following steps: S1, data augmentation by reversing the temporal direction of gait; S2, obtaining deep emotion features and prior emotion features respectively through a spatiotemporal graph convolutional network and prior feature statistical methods; S3, performing nonlinear mapping on the prior emotion features using a feature mapping layer; S4, inputting the fused features of the deep emotion features and prior emotion features into an emotion classifier to obtain the emotion category. The feature mapping layer of this invention achieves more effective feature fusion by performing nonlinear mapping on prior features; it also introduces causal temporal convolution to replace general temporal convolution, effectively extracting fine-grained temporal features by enhancing temporal correlation and cross-period feature fusion. Furthermore, a walking direction recognition auxiliary task is designed to accelerate the training and convergence speed of the model, enhancing the ability to extract temporal-dependent features and the performance of emotion recognition.

The invention provides a power grid fault waveform identification and intelligent relay protection rapid control method and system, and relates to the technical field of electric power, and the method comprises the steps: collecting the voltage and current waveform data of a power grid, carrying out the digital filtering and noise elimination processing, carrying out the Fourier transform and wavelet transform, extracting the time domain and frequency domain features, and constructing a combined feature vector. And a deep learning model including a convolutional neural network and a long-short-term memory network is used to identify and evaluate the type, position and amplitude of the power grid fault based on the feature vector database. And then, a multi-target particle swarm optimization algorithm for constructing a target weight matrix based on historical fault data is adopted to optimize fault isolation time, a power supply recovery rate and system stability to obtain a control strategy, and a relay protection device setting value is adjusted according to the control strategy to execute fault isolation and power grid topology reconstruction.

The invention provides a knowledge graph construction and product recommendation method and system based on user data, and relates to the technical field of artificial intelligence, and the method comprises the steps: constructing an initial knowledge graph through user historical behavior data, generating an optimization graph through a multi-layer neural network comprising a multi-granularity layer, a graph attention layer and a graph convolution layer, and performing bidirectional random walk sampling based on real-time behavior data of a target user to obtain a related sub-graph, calculating a product node importance score, and performing sorting pushing by adopting a multi-target optimization algorithm. According to the method, multi-dimensional accurate description of user interests can be realized, the recommendation accuracy and diversity are improved, and meanwhile, the commercial value is considered.

The invention provides a multi-level attribution and recommendation method and system for medical management decisions, and relates to the technical field of medical management decisions, and the method comprises the steps: extracting graph node evolution characteristics through a multi-level medical data knowledge graph and a decision knowledge base by employing a time sequence diagram convolutional network, constructing a decision influence propagation graph through a cross-layer interactive attention network, and carrying out the analysis of the decision influence propagation graph; calculating the contribution degree of each decision node to the medical effect, generating an attribution analysis result, determining a decision influence hierarchical system according to the attribution result, and generating and evaluating candidate decision paths in combination with a multi-objective optimization network, a hierarchical reinforcement learning network and a Monte Carlo search tree network. In conclusion, accurate attribution analysis and multi-objective optimization of the management decision can be realized, the hospital resource allocation efficiency is effectively improved, the operation cost is reduced, scientific decision support is provided for a hospital management layer, and the hospital fine management level and the overall operation efficiency are remarkably enhanced.

The invention discloses a mixed tower structure full-life damage intelligent sensing array early warning system, which relates to the field of mixed tower structure detection and comprises a multi-modal data collection module, an array topology optimization module, a self-adaptive signal processing module, a digital twin life prediction module, a grading early warning module and a visualization system. The multi-modal data collection module comprises a multi-modal sensor array, a self-powered module and a wireless transmission module. According to the invention, a full-scale sensing network is constructed, full-dimension damage perception from distributed monitoring to sudden damage capture and structural modal analysis is realized, wavelet transform and blind source separation are combined to eliminate environmental noise interference, a damage characteristic ultrasonic attenuation coefficient, an acoustic emission energy spectrum peak value, optical fiber strain gradient anomaly and vibration modal frequency deviation are extracted, and the detection accuracy is improved. And classification and positioning of damage types and intelligent diagnosis of severity levels are realized through a convolutional neural network and long and short memory neural network hybrid model, and a closed-loop processing flow from data acquisition to feature analysis is formed.

The invention discloses an underground oil and gas well fault prediction method based on a multi-modal space-time diagram neural network, and aims to solve the problems of insufficient multi-modal feature coupling, weak space-time correlation modeling, poor real-time performance and the like of a traditional method. The method is characterized in that multi-frequency sensor data features and maintenance log semantic knowledge are respectively extracted through a time expansion convolutional network (TCN) and a BERT-BiLSTM model, and a cross-modal gating attention mechanism is designed to realize heterogeneous data dynamic fusion; an equipment space topological graph is constructed based on Delaunay triangulation, dynamic causal association between nodes is quantized in combination with transfer entropy to generate a time graph, and a fault propagation path is jointly modeled through residual space-time graph convolution; a hierarchical prediction module is constructed by adopting a bidirectional LSTM and a graph attention network (GAT), short-term fault classification and long-term equipment residual life prediction are respectively realized, and the fault prediction precision and industrial landing feasibility under complex working conditions are effectively improved.

The invention relates to an unmanned aerial vehicle intelligent dynamic path guidance method and system based on deep reinforcement learning. The method comprises the steps of obtaining three-dimensional terrain point cloud and obstacle information of a flight area, constructing an environment topological structure diagram, extracting features through a three-layer diagram convolutional network, and generating high-dimensional environment feature representation. And a deep reinforcement learning state space is constructed, and a multi-target reward function is designed. And initializing the deep reinforcement learning network by using [-0.1, 0.1] uniformly distributed random parameters to generate an initial path scheme. Optimizing through a dynamic planning algorithm, adjusting a node sequence according to a path length and a task dynamic threshold value, and calculating a target function value. And judging whether the current path scheme reaches the optimal balance point, if not, adjusting the weight of the reward function by using a gradient descent method, and regenerating the path scheme until the path scheme is optimal. And finally, converting the scheme into a waypoint coordinate and speed instruction, performing real-time monitoring during flight, and triggering re-planning when an obstacle exceeds a safety threshold, so as to achieve the purposes of safe flight of the unmanned aerial vehicle in a complex environment and the like.

The invention discloses a railway track damage detection method, and belongs to the technical field of railway track detection. According to the method, an image acquisition module and an ultrasonic detection module are installed at the bottom of a track detection vehicle, the detection vehicle is controlled to run, and track top face and side face image sequences and ultrasonic reflection signals are acquired; preprocessing the image, and respectively inputting the image into a deep convolutional neural network model and a support vector machine classifier to obtain a crack identification result and a wear level; processing an ultrasonic reflection signal, and judging a layering defect; and finally fusing the data, marking a damage position and generating a structured detection report. According to the method, the problems of incomplete detection, low precision and the like in the existing railway track damage detection are solved, efficient detection of track surface cracks, side abrasion and internal layering defects is realized through collaborative acquisition of the multi-modal sensor, intelligent algorithm processing and data fusion, and the comprehensiveness and reliability of detection are improved.

The invention relates to the technical field of power dispatching, in particular to a digital twin energy management method and system for source-network-load-storage cooperative dispatching, and the method comprises the steps: collecting source-network-load-storage multi-dimensional space-time operation data, and extracting space-time coupling features through a graph convolution-long and short-term memory network; establishing a simulation model of a digital twin environment, simulating an uncertain operation condition by using a Monte Carlo scene generator, and processing a power flow constraint by using a second-order cone relaxation technology; training an energy storage scheduling agent in a digital twin environment, and learning an energy storage charging and discharging strategy through a near-end strategy optimization algorithm; designing a source-network-load-storage hierarchical collaborative optimization framework, optimizing power output and load distribution by using an improved particle swarm optimization algorithm on the upper layer, and solving power flow distribution by using an alternating direction multiplier method on the lower layer; and establishing a self-adaptive feedback correction mechanism, and dynamically adjusting a cooperative scheduling strategy. According to the invention, intelligent collaborative scheduling of source network load storage is realized, and the operation efficiency and stability of a power system are improved.

The invention relates to the technical field of fault prediction, and provides a fault prediction method for a multi-modal cross-attention enhancement graph neural network, and the method comprises the steps: collecting the data of equipment; performing adaptive enhancement and normalization processing on the image data, performing sliding window segmentation, standardization and noise suppression on a time sequence numerical signal, and performing semantic vectorization coding on a maintenance log text; extracting low-dimensional spatial features of image data by using the pruned lightweight convolutional neural network, connecting time sequence features of modeling time sequence numerical signals in series, extracting context semantic expressions of maintenance log texts, integrating the features into multi-modal data, alternately taking each modal feature as Query and the other modal features as Key and Value, and obtaining multi-modal data; calculating attention weight and performing weighted fusion; constructing a modal node weighted graph, and performing inter-node feature propagation through a multi-layer graph attention network; and a residual service life regression prediction module and a degradation level classification module are deployed in parallel, and fault early warning is completed through multi-task joint optimization.

The invention discloses a power load prediction method and system based on a meteorological prediction model, and relates to the technical field of load prediction, and the method comprises the following steps: obtaining historical power load data and corresponding multi-dimensional meteorological data, constructing a meteorological coupling effect analysis model, calculating a dynamic coupling weight matrix among the meteorological parameters through an attention mechanism network; performing feature fusion on the coupling weight matrix and the multi-dimensional meteorological data through a gating circulation unit to generate a space-time coupling feature vector; establishing a power load prediction model, and extracting a short-term fluctuation feature and a long-term trend feature of the power load from the space-time coupling feature vector based on a deep residual network architecture and a parallel convolution channel; the dynamic coupling weight matrix is updated based on prediction error back propagation, and adaptive adjustment of the meteorological parameter coupling relation is achieved. According to the method, dynamic fusion of the spatial-temporal characteristics is realized through the cross gating unit, so that the model can perform power load prediction by using spatial-temporal information, and the prediction precision is improved.