316 results about "Network Convergence" patented technology

The invention provides an environment detection method and system based on a sample target detection model. The method comprises the following steps: synchronously acquiring an environment image, a video stream and physical parameters by using a multi-mode sensor; decomposing the data into image features and environmental parameter components through a dual-time sequence control signal, and realizing space-time alignment by adopting a linear phase filter; constructing a foreground region template based on the depth information, and generating target recognition feature representation containing an abnormal blurred target; adversarial training is carried out on the lightweight target detection network in combination with a transfer learning strategy, the network integrates convolutional features and a Transform attention mechanism, and the weight is dynamically adjusted through environmental parameters; fusing a target result and sensor data in real-time detection, and inputting a decision tree model for risk grading; and after the early warning is triggered, reconstructing a false detection sample through an online learning mechanism and iteratively optimizing the model. The system correspondingly comprises a multi-modal data acquisition module, a data enhancement and annotation module, a model training module, a real-time detection and fusion module and an early warning and optimization module. According to the invention, through multi-source data fusion, dynamic data enhancement and an adaptive compensation mechanism, the small target detection precision, the environmental adaptability and the real-time early warning capability are significantly improved.

The invention discloses a hyperspectral image classification method based on an S2CFM-spatial spectrum convolution fusion Mama network model, and the method employs a parallel double-branch structure to extract the spatial context information and spectral sequence features of a hyperspectral image, and finally integrates the features through a dynamic convolution fusion module, thereby achieving the classification of the hyperspectral image. The method solves the problem of unbalanced utilization of space-spectrum information in a traditional method, introduces a space spectrum convolution fusion Mama network, and fuses a multi-scale convolution block (MCB), a dynamic convolution block (DCB) and a space spectrum Mama block (S2MB); the method solves the problems that in the prior art, the capacity of CNN for capturing spectral information is relatively limited, and a complex spectrum-space characteristic relation in hyperspectral data is difficult to fully represent; the problems that in HSI data, due to the fact that the dimensionality is high and the sample size is limited, an over-fitting problem is prone to occurring, and the generalization performance of the HSI data is limited are solved through a Transformers-based architecture.

The invention relates to the technical field of intelligent manufacturing decisions, in particular to a digital twinning-based manufacturing system decision analysis method and system, and the method comprises the steps: deploying a plurality of Internet of Things sensors on a physical manufacturing system, and collecting a physical real-time data stream of equipment in real time; the method comprises the following steps: establishing a virtual data acquisition channel aligned with a physical manufacturing system clock, injecting a physical real-time data stream into a digital twinning creation model, and performing data preprocessing based on distributed edge calculation to delay and compress original data acquisition of the physical real-time data stream to 10ms level, the time sequence database and the NTP / GPS clock are synchronized to ensure the state alignment error lt of the physical-virtual system; compared with the prior art, the deep space-time prediction network is fused with a CNN-LSTM-attention mechanism, the accuracy of multivariable coupled KPI prediction is improved, in addition, model failure is recognized in real time through Page-Hinkley inspection, and a prediction error reaches a relatively stable state through an adaptive retraining mechanism.

The invention discloses a reservoir water regimen analysis method and system based on artificial intelligence, and the method comprises the steps: collecting original signals from multi-source monitoring indexes, such as water level, flow, rainfall and water quality, carrying out the standardized conversion through employing distributed calculation nodes, and forming a unified multi-source data set; based on this, using a feature extraction network to fuse upstream rainfall and reservoir flow, extracting space-time correlation features, and determining a short-term water level change trend; historical water quality abnormal data are integrated through a sequence prediction network, a time sequence is modeled, and potential pollution risks are judged; when the risk exceeds a threshold value, dynamically adjusting the weight of the prediction model, and generating an optimized water regimen simulation scene; finally, resource scheduling logic is fused, multi-scene risks are evaluated, and an optimization management strategy is output. Through deep fusion of spatial-temporal feature extraction and dynamic prediction, accurate water regimen prediction and flood control water supply decision support are realized, and the water resource management efficiency and the pollution prevention and control capability are improved.

The invention provides a computing power resource scheduling method and system based on cloud network integration. Selecting a computing power task to be scheduled as a current scheduling task, and generating a node resource adaptation matrix based on the real-time load data, the cloud network topological relation between the nodes and the dynamic bandwidth data; then calculating the lowest scheduling cost of each node according to the matrix, and determining a dynamic adjustment factor when a resource allocation conflict occurs in the current scheduling task; based on the lowest scheduling cost, the computing power demand scale and the data transmission estimated overhead, calculating the final scheduling overhead for scheduling the current scheduling task to each node; and finally, allocating tasks to a target node according to the final scheduling overhead, updating a running task queue, if a conflict occurs, calling a dynamic adjustment factor to execute resource reallocation, and updating the queue after the reallocation succeeds. And circulating the process until all tasks are scheduled. According to the scheme, optimal scheduling of computing power resources in a cloud network convergence environment can be realized.

The invention relates to a house building construction stage carbon emission dynamic estimation method and system based on full life cycle data, and the method comprises the steps: dividing a construction region based on a BIM model, laying a multi-source sensor network, fusing static BIM data and a dynamic Internet of Things monitoring flow, building a four-dimensional space-time label data set, and carrying out the construction stage carbon emission dynamic estimation based on a double-layer dynamic correction model. Kalman filtering is utilized to eliminate instantaneous interference, LSTM transfer learning is combined to predict mechanical efficiency attenuation, a dynamic correction coefficient matrix of a mechanical aging rate, operator skills and environmental factors is embedded, and a carbon emission value is calibrated in real time; when abnormal emission is detected, a key pollution source is traced and positioned through a graph neural network, a three-dimensional thermodynamic diagram is generated in the digital twinborn model, and component-level carbon flow analysis and early warning are performed, so that the carbon emission estimation precision is remarkably improved, the abnormal traceability time consumption is shortened, and the timeliness is remarkably improved.

The invention provides an RFID label positioning error correction method based on deep learning, and the method comprises the following steps: 1, deploying a multi-mode sensing network in a target region, synchronously collecting radio wave signals and environment auxiliary data of an RFID label, and constructing a space-time multi-dimensional feature data set; step 2, constructing a joint architecture hybrid model composed of a space-time Transform network and a generative adversarial network; according to the method, a space-time multi-dimensional feature data set is constructed by fusing RFID signals and environment auxiliary data through a multi-mode sensing network, adaptive parameters are dynamically generated in combination with a model-independent meta-learning algorithm so as to quickly respond to environment changes, multi-path signal correlation is captured by using a space-time Transform and generative adversarial network combined architecture, feature expression is optimized, and the robustness of the system is improved. The problems that a single signal feature is missing, model parameters cannot dynamically adapt to the environment and the anti-interference robustness of a traditional network is insufficient are effectively solved, and the effectiveness, the real-time performance and the precision of RFID label positioning in the complex environment are remarkably improved.

The invention discloses a multi-mode fusion driven multi-agent Transform collaborative power dispatching method and system, and the method comprises the steps: fusing three types of heterogeneous data, namely power grid topology, time sequence operation and equipment state, through a multi-mode projection network, and forming unified state representation; a Transform encoder is used for modeling a dependency and cooperation relationship between intelligent agents, and a mask decoder is used for generating a cooperation scheduling strategy in an autoregression mode; a strategy is evaluated and optimized by adopting a near-end strategy optimization algorithm and a joint reward function, and finally an instruction is converted into a control signal and a closed-loop learning mechanism is formed. The system comprises a multi-modal state perception and fusion module, a multi-agent collaborative representation module, a collaborative decision generation module, a joint strategy optimization and learning module and a scheduling strategy execution and feedback interface module. According to the method, the multi-source information utilization efficiency and the agent cooperation capability are effectively improved, and safe, stable and economical operation of the power grid under high-proportion new energy access is guaranteed.

The invention discloses a traffic accident detection method based on FFC and GCSA models. The method is innovatively improved based on a YOLOv8 network model. Firstly, a multi-scale feature fusion module FFC is designed in Backbone to replace an original C2f module, and the capability of fusing the multi-scale features of the network can be further improved on the premise of not increasing the network calculation amount, so that the network can fuse the multi-scale features on the level of finer granularity; then, a GCSA attention mechanism is introduced between a C2f module and a Deect module of a Neck layer, and the recognition capability of the model for key features in a complex environment is remarkably enhanced; and finally, establishing a loss function Focal-EIoU Loss for the improved YOLOv8 network structure, so that the network classification detection capability is improved, and the generalization capability of the model is improved. In a specific implementation process, a traffic accident image data set covering multiple scenes is constructed, and specialized data preprocessing is performed; then, end-to-end training and parameter optimization are carried out on the Traffic-YOLO network model obtained after improvement; and finally, integrating the optimized model to a traffic accident detection system for real-time target detection. Compared with the prior art, the method effectively improves the accuracy and robustness of traffic accident detection in a complex scene, and has important practical significance.

The invention discloses a vehicle monitoring method based on frame difference and deep learning fusion, and relates to the technical field of vehicle monitoring, cameras and environment sensors are deployed in a monitoring area, and videos and multi-source data are acquired by means of vehicle-road cooperation; a self-adaptive frame difference method is used, morphology and optical flow estimation are matched, a threshold value is determined according to the environment, and vehicle features are extracted; constructing a deep convolutional neural network with an attention mechanism, and training a model by using various data in combination with migration and reinforcement learning; fusing the two types of features based on a graph attention network to form high-quality fusion features; a space-time diagram convolutional network is combined with an LSTM to track a vehicle and predict a trajectory, a behavior pattern library is constructed to judge abnormity, and classification analysis is performed in combination with an SVM and a knowledge graph. According to the invention, the frame difference and deep learning are fused, the monitoring accuracy is improved, and the vehicle can be accurately identified and detected; the real-time performance is enhanced, the data is quickly processed, and the environmental influence is reduced; traffic management is assisted, and a safe and efficient traffic environment is created.

The invention discloses a wind turbine generator state monitoring method driven by network fusion of a knowledge graph and a space-time diagram. The method comprises the following steps: S1, collecting time sequence SCADA data and wind power text data of a wind turbine generator; s2, constructing the wind power text data into a wind power operation and maintenance knowledge graph; s3, generating time sequence diagram data by querying a wind power operation and maintenance knowledge graph and combining the preprocessed SCADA data; s4, carrying out normal behavior modeling on the time sequence diagram data by utilizing the time-space diagram neural network model, predicting each node in the diagram data in the healthy operation time period of the unit in the normal behavior modeling process, and calculating the maximum absolute value of the difference between the predicted value and the actual value of each node as the maximum absolute value of the difference between the predicted value and the actual value; the maximum absolute error is used as a health threshold value of each node to perform state monitoring; in the state monitoring stage, the matching condition of the mapping information of each node in the graph structure in the monitoring result of the real-time data and the fault transmission chain is compared, the health state of the unit is judged, and the fault early warning time is determined. According to the invention, the accuracy and robustness of the monitoring result are enhanced.

The invention discloses a tunnel pavement concrete early-age strength prediction method based on multi-network fusion modeling. The method comprises the following steps: S1, continuously and equally dividing a tunnel center line according to a certain interval; s2, only keeping a left-right adjacent segment relation for the segment, and calculating a direction weighted thermal gradient, a direction weighted humidity gradient and a direction weighted traffic disturbance gradient based on the state vector; s3, writing the state vector of each segment into a sliding window with a set time length at a fixed sampling period; s4, inputting the dynamic graph input tensor into a space-time diagram neural network; s5, comparing the prediction sequence with a preset strength threshold value, identifying potential weak segments, and calculating risk confidence in combination with the gating coefficient; and S6, writing the maintenance instruction packet into a corresponding PLC channel. Potential weak sections can be recognized, spraying, heat preservation curtains and ventilation equipment can be linked, and local precise maintenance and batch open traffic unified management are achieved.

The invention relates to the technical field of course analysis management, in particular to a course analysis management system based on deep learning. The method has the advantages that multi-modal data deep analysis realizes full-dimensional analysis of unstructured data by integrating a 3D-CNN model, a Transform architecture and a BERT model and synchronously extracting an attention hot area, a voice emotional state and a text knowledge point association network of a classroom video; nonlinear behavior modeling adopts an LSTM network and time convolutional network fusion model, a knowledge internalization path and forgetting curve prediction are dynamically generated, parameters are optimized in combination with incremental learning, and a transition rule across knowledge points is captured; a teaching scene-evaluation threshold mapping table is constructed based on a reinforcement learning algorithm through dynamic decision and resource collaboration, collaborative optimization under multi-campus data privacy protection is achieved in combination with a federated learning framework, GPU computing nodes are dynamically allocated through a heterogeneous resource scheduling engine, and the analysis efficiency is improved.

The invention relates to the technical field of online approval management, and discloses an online employee approval management system based on an edge calculation model. An employee terminal data acquisition layer of the system captures a multi-modal examination and approval data flow based on a priority dynamic focusing mechanism, generates an examination and approval behavior characteristic thermodynamic diagram through an edge characteristic pyramid network, and divides an abnormal region; the examination and approval knowledge graph construction layer loads a domain rule base, extracts an entity relationship through semantic dependency analysis, and constructs an examination and approval rule path graph with a weight; the map path cross validation layer synchronizes an edge node clock, and generates approval risk confidence through multi-head map attention network fusion data; the dynamic strategy optimization layer converts the risk confidence into an executable strategy and issues the executable strategy to an edge execution engine; and the approval efficiency feedback layer monitors the flow state and generates an efficiency index to dynamically optimize a data acquisition strategy. According to the system, precision, high efficiency and dynamic optimization of approval management are realized.

The invention discloses an expressway congestion prediction method and system based on fusion of a cellular transmission model and a space-time convolutional network. According to the method, an expressway is divided into continuous cellular units, speed and density data of each cellular in multiple periods are collected, and a space-time input sequence is constructed. Local state correlation between cells is extracted through spatial convolution, and then a causal convolution network is used for modeling a time evolution trend of a traffic state, so that joint prediction of speed and density in a plurality of time steps in the future is realized. According to the invention, the spatial discretization idea of the cellular transmission model and the feature extraction capability of the convolutional neural network are combined, so that the provided method not only retains the interpretability of traffic flow physical evolution, but also has the capability of learning a nonlinear complex mode; the method is suitable for application requirements of traffic situation monitoring, intelligent scheduling, congestion management and the like in various expressway operation scenes.

The application discloses a channel estimation method for a millimeter wave frequency division duplex massive MIMO system based on compressed sensing and deep learning, and belongs to the technical field of wireless communication.The technical scheme is as follows: a received pilot signal is processed by using a compressed sensing method to extract a preliminary CSI matrix; a convolutional neural network and a long short-term memory network are combined to extract spatial features and capture time correlation; the preliminary estimated CSI matrix is input into a ConvLSTM layer, and the ConvLSTM network fuses time correlation information to improve the estimation accuracy of the CSI; the same padding, ReLU activation function and filter with appropriate size are used to obtain the same size as the input data; and dimension transformation and inverse normalization are used to obtain the final CSI estimation result.The application has the beneficial effects that the method for channel estimation by using compressed sensing and deep learning aims at reducing the overhead of channel estimation and improving the estimation accuracy in a time-varying channel, reduces the overhead of downlink training and uplink feedback, and improves the channel estimation accuracy in the time-varying channel.

The invention relates to an underwater visible light signal recovery method based on transfer learning, and aims to solve the problems of signal noise, distortion and communication performance reduction caused by disturbance of water turbidity, flow velocity, ambient light intensity and the like on an underwater visible light communication (UVLC) system. In combination with transfer learning and a generative adversarial network (GAN), data are acquired through a self-developed hardware platform, background data are generated through MATLAB simulation, simulation and real image features are fused by using a conditional generative adversarial network (cGAN) to generate simulation data, signal recovery capability is trained by using a U-NetGAN model, and finally the system is deployed at a receiving end. Compared with the prior art, the scheme overcomes the problems that traditional modulation is poor in adaptability under disturbance of water turbidity, flow velocity and the like and is difficult to deal with a complex underwater environment; the defects that a deep learning method depends on large-scale data and cross-scene generalization is weak are overcome. Through the combination of transfer learning and GAN, the UVLC system communication performance is significantly optimized, the delay is low, the complexity is low, and actual deployment requirements are better met.

The invention relates to a full-convolution deep-convolution generative adversarial network fusion process constraint-based artificial intelligence pressure-resistant shell design method, which comprises the steps of constructing a simulation model, the method comprises the steps of setting a pressure-resistant shell shape parameter range and step length and a pressure-resistant shell material, setting a rib parameter range and step length, performing simulation software modeling, and calculating the volume, the weight and the maximum pressure-resistant value of the pressure-resistant shell. Constructing a data set, and generating a plurality of basic samples according to the parameters of the simulation model; an AI model is constructed, the AI model is a full-convolution deep-convolution generative adversarial network architecture, the AI model comprises a forward prediction model and a reverse design model, the forward prediction model comprises three convolution layers of a full-convolution structure, and the reverse design model comprises three transposed convolution layers of the full-convolution structure; training and optimizing the AI model; and intelligently designing the pressure-resistant shell by using the AI model. The design efficiency is improved, the feasibility of the design scheme is high, and the withstand voltage value prediction precision and the parameter generation accuracy are improved.

The invention relates to a multi-network convergence gateway system supporting a satellite, a cellular and a wide-narrow band ad hoc network, and the system comprises a satellite communication module which is used for carrying out the communication connection with a satellite, and receiving and transmitting a satellite signal; the cellular communication module is used for communicating with a cellular network base station; the wide-narrow band ad hoc network module is used for constructing an ad hoc network in a local area to realize communication between nodes; the data processing module is used for uniformly processing data from the satellite communication module, the cellular communication module and the wide-narrow band ad hoc network module; and the power management module is used for managing and controlling a power supply of the whole system. The method has the beneficial effects that fusion of various communication networks can be realized, communication requirements in different scenes are met, and the power consumption of the system is reduced.

The invention discloses an intelligent storage environment lightweight efficient target detection method based on YOLO11 improvement, and belongs to the technical field of image processing. Aiming at the problems of target shielding, illumination change and limitation of computing resources and storage space on mobile equipment deployment in carton detection in a storage environment, target detection image data is loaded by using a database and is converted into a YOLO format, and a training set and a test set are divided; performance optimization is realized through the following improvements: a multi-dimensional cooperative attention module is introduced before a spatial pyramid pooling module of a backbone network; the neck network is fused with a weighted bidirectional feature pyramid network and a multi-dimensional cooperative attention module, and feature interaction between levels is enhanced; an original large detection head is removed from the detection head, medium and small targets are focused, parameter quantity and background interference are reduced, feature representation is optimized, detection precision and calculation efficiency in a storage scene are balanced, and the method is suitable for real-time detection and efficient operation of a mobile device on cartons in a storage environment.

The invention discloses an electric vehicle man-machine cooperative scheduling strategy for multiple scenes of an electric power traffic coupling network, and aims to solve the problem of electric vehicle charging optimization scheduling caused by deep coupling of an electric power system and a traffic system in different scenes. The method comprises the steps that firstly, topological information and behavior characteristics are fused through a graph generative adversarial network, a graph structured model is constructed, and an electric power traffic coupling operation scene is generated; secondly, establishing a multi-objective optimization mechanism by utilizing hierarchical reinforcement learning, constructing an electric vehicle charging optimization scheduling finite Markov decision model in a conventional scene and a fault scene, and designing an algorithm based on knowledge distillation to solve a scheduling strategy; and finally, realizing strategy migration of charging redistribution and path emergency adjustment in a fault scene by combining a man-machine cooperative regulation and control technology and fusing a user instruction. Experimental results show that the strategy can effectively improve the toughness of the power grid, relieve traffic congestion, reduce charging queuing time and increase user satisfaction.

The invention relates to the technical field of communication, in particular to a three-network convergence communication terminal system based on core size level heterogeneous integration and an implementation method, and the system comprises a radio frequency transceiving core particle, a baseband processing core particle, a storage core particle, a control scheduling core particle and a power management core particle. According to the invention, systematic linkage optimization of cross-domain parameters is realized through a core size level heterogeneous integration and state space cooperation mechanism, and real-time channel state information directly drives a scheduling algorithm to solve in a global state space. According to the method, the problems of low energy efficiency utilization rate, lagged resource scheduling response, low power consumption and the like of a terminal in a multi-network concurrency and switching scene due to the fact that a multi-network communication module is discrete and a cross-hardware-level dynamic coordination mechanism is lacked are effectively solved, and the service life of the terminal in a multi-network concurrency and switching scene is prolonged. And therefore, the problems of limited terminal volume, high power consumption and poor service continuity can be solved.

The provided are a federated reinforcement learning (FRL) end-to-end autonomous driving control system and method, as well as vehicular equipment, based on complex network cognition. An FRL algorithm framework is provided, designated as FLDPPO, for dense urban traffic. This framework combines rule-based complex network cognition with end-to-end FRL through the design of a loss function. FLDPPO employs a dynamic driving guidance system to assist agents in learning rules, thereby enabling them to navigate complex urban driving environments and dense traffic scenarios. Moreover, the provided framework utilizes a multi-agent FRL architecture, whereby models are trained through parameter aggregation to safeguard vehicle-side privacy, accelerate network convergence, reduce communication consumption, and achieve a balance between sampling efficiency and high robustness of the model.

The invention discloses a weighing sensor life degradation modeling method based on a bimodal LSTM network, and belongs to the technical field of industrial automation control systems, and the method comprises the steps: obtaining the data of a weighing sensor, generating a bimodal original data set, and carrying out the denoising processing to obtain a bimodal denoised data set; the method comprises the following steps: constructing a dual-channel LSTM-DC-CNN network, fusing stress time sequence data and environment parameter data, performing time sequence feature extraction to obtain a stress degradation feature vector and an environment coupling coefficient vector to generate a fusion degradation feature vector, performing feature enhancement processing on the fusion degradation feature vector, and performing path optimization to generate a life degradation stage judgment result. And a preset historical degradation database is combined to generate a remaining service life index of the weighing sensor. According to the method, two-channel time sequence feature extraction, a dynamic fusion mechanism and an empirical mode compensation technology are adopted, the prediction precision and reliability can be remarkably improved, and efficient and intelligent evaluation of the remaining service life is achieved.

The invention discloses a method for establishing a reinforcement learning network security attack and defense double-agent control strategy model, which is suitable for high-security network environments such as an electric power monitoring system and the like. The model realizes a dynamic attack and defense decision through a double-agent collaborative architecture: an attack end agent adopts a three-level CNN to mine network topology spatial-temporal characteristics, and extracts association information of five-dimensional dynamic matrixes such as node states, region levels and defense slots; the defense end intelligent agent combines a KL divergence adaptive penalty mechanism to optimize a PPO algorithm, and dynamically adjusts the exploration intensity by monitoring strategy distribution offset in real time. And introducing a CLIP truncation function to constrain the strategy update amplitude, and realizing priority protection and resource elastic scheduling of the core control area in combination with an attack and defense reward function. The model supports hundred-level node scale deduction, effectively solves the problems of response lag, unknown node sensing delay and slow large-scale network convergence of a traditional static rule, and meets the real-time attack and defense requirements of a power system under the principles of'security partitioning, network specialization, transverse isolation and longitudinal authentication '.

The invention discloses a communication analysis processing method and device based on dual-mode heterogeneous communication network convergence, and relates to the technical field of communication processing, and the method comprises the steps: generating a coupling feature vector through obtaining the real-time operation data of HPLC and HRF in a converged communication system, and predicting the interfered frequency point and time period of the future HRF through a short-time prediction model; screening a clean frequency band candidate set based on a prediction result, and calculating a coupling strength index and an adjacent interference index of each candidate frequency band to obtain a candidate front value; according to the method, the frequency band with the maximum candidate front value is selected as the target communication frequency band in the future preset time window, and the HRF link is concentrated to the frequency band before interference occurs, so that cross-medium interference possibly occurring in the future can be predicted in advance, potential influences are actively avoided before interference occurs, and the interference performance is improved. Risks of data error codes, link interruption and switching delay caused by radiation of HPLC harmonic waves to an HRF communication band are effectively reduced, and continuity and reliability of communication are improved.

The invention discloses a wind power plant booster station misoperation-preventive locking intelligent decision-making method based on multi-source data fusion, and relates to the technical field of misoperation-preventive locking decision-making. Multi-source data such as electrical equipment states, environmental parameters and equipment appearance images are collected and preprocessed; extracting multi-dimensional features, and constructing a space-time incidence matrix; constructing a power equipment knowledge graph, and converting safety regulations into rules and reasoning; a three-branch neural network is constructed, multi-modal features are fused, and a decision model is trained; according to the risk assessment value and the dynamic threshold value, an anti-misoperation locking decision is executed, a permission or locking instruction is output, and an operation log is recorded. By fusing multi-source data and combining the knowledge graph, deep learning and other technologies, the wind power plant booster station anti-misoperation locking intelligent decision is realized, the fault early warning accuracy and decision efficiency are improved, the system flexibility and interpretability are enhanced, and safe and reliable operation of the booster station is guaranteed.

The invention discloses a social group discovery system based on fused semantic information. The system comprises a presentation layer, a presentation layer, a service layer and a data layer. The presentation layer supports checking of a group division result; the display layer displays a user structure network, group dynamic division and group characteristic indexes through a visual tool; the service layer is composed of a semantic tag generation module, a user structure analysis module, a social group division module and a social group analysis module, semantic and structural features are fused through a graph attention network, and accurate group division is realized in combination with an adaptive embedded graph aggregation algorithm; and the data layer stores the original data set of the social platform and the processed data. The system inputs user texts into a large language model to generate semantic tags, node embedding is generated by calculating node association weights, group division is completed by combining an adaptive embedding graph aggregation algorithm, and finally group characteristics are quantitatively analyzed from the aspects of cohesion, conductivity and the like. The system is suitable for scenes such as vertical domain community mining.

The invention discloses a method for predicting the remaining service life of a control moment gyroscope based on parameter fusion, and relates to the technical field of health management of spacecraft attitude control systems. According to the method, optimal fusion of measurement parameters and implicit parameters is realized through adversarial learning feature extraction and a channel attention mechanism, and the method is particularly suitable for high-precision residual life prediction of the spacecraft control moment gyroscope under variable working conditions. The method comprises four main steps of data preparation and multi-source input, adversarial learning feature extraction, SE-Attention feature fusion and three-stage training optimization. In the data preparation step, original time sequences of voltage and current of a rotor motor are collected through a built-in electrical sensor of a CMG, and key physical parameters of a full-film lubrication friction coefficient, lubricating oil viscosity, a bearing clearance and contact stiffness are inverted based on an electromechanical coupling model; in the adversarial learning step, a game framework of a feature extractor and a working condition discriminator is constructed, and working condition-independent robust feature extraction is realized through a gradient inversion layer; in the SE-Attention feature fusion step, importance weights are adaptively distributed to different feature channels through an extrusion-excitation mechanism; and the three-stage training optimization step adopts a preheating-confrontation-fine tuning strategy to ensure the network convergence. The method solves the problem of domain adaptation, has the technical advantages of strong robustness, high precision, strong generalization, interpretability and self-adaptation, and can realize high-precision RUL prediction under variable working conditions.

The invention discloses a loader remote intelligent control system based on multi-network fusion and modular design, and relates to the technical field of loader remote control, and the loader remote intelligent control system comprises an equipment end, a remote control end and a cloud server end; the equipment end comprises the following hardware modules: a hardware sensing module which comprises a multi-type sensor array and a data acquisition unit and realizes real-time acquisition of mechanical parameters, environmental parameters and attitude data; and the main control processing module integrates a CPU (Central Processing Unit) and an FPGA (Field Programmable Gate Array) acceleration unit, is internally provided with a QNX real-time operating system, and is used for data preprocessing, control logic execution and hardware drive management. Through a remote intelligent control scheme, an operator can operate and control equipment in a safe area, the operation safety is improved, the operability and flexibility of the equipment are enhanced, modular design is adopted to facilitate installation, maintenance and rapid deployment, and a multi-network fusion architecture ensures stable data transmission in different environments; the low-delay and accurate control technology realizes the undifferentiated response speed of remote control and field operation.