1506 results about "Network module" patented technology

The invention relates to a server cluster monitoring system based on multi-node collaboration and an implementation method thereof, a dynamic topology network module is configured to reconstruct a connection topology among monitoring nodes in real time according to node performance and link quality, support mixed configuration of a star type, a ring type and a net structure, and realize multi-node collaboration. Multi-dimensional data capture from a physical layer to an application layer is realized through a cross-level index acquisition module based on an integrated hardware sensor interface and a virtualization layer probe, and each node is enabled to perform collaborative reasoning through parameter encryption sharing through a decision model based on federated learning. A monitoring task fragmentation strategy is dynamically adjusted through an adaptive elastic fragmentation unit according to network delay and load fluctuation, and an abnormal event association rule base is updated in real time through an incremental knowledge graph construction unit. High availability and elastic expansion are realized through a multi-node collaborative architecture, the monitoring efficiency is improved in combination with dynamic load balancing and hybrid detection, and an intelligent multi-level response mechanism is constructed to guarantee the service continuity.

The invention relates to the technical field of high-frequency signal modulation, and discloses a high-frequency carrier synchronization signal modulation system. A carrier distortion compensation module of the system constructs a model based on a historical transmission data set, captures a phase jitter parameter, a spectrum leakage component and a modulation pulse sequence of a transmitting end carrier in real time, and outputs a reconstructed baseband parameter; the multi-dimensional distortion analysis module compares the reconstructed baseband parameter with a receiving end demodulation baseband parameter through composite difference detection, and generates a channel-level distortion coefficient tensor; the topological positioning network module is used for positioning signal out-of-step physical nodes and generating a probability distribution thermodynamic diagram by combining impedance characteristics of transmission nodes and signal path delay information; and the adaptive modulation strategy module starts a multi-band carrier injection mode for the high-probability out-of-step nodes according to the abnormal probability gradient of the thermodynamic diagram, and applies a phase disturbance test to adjacent transmission links. The system can improve the adaptability and accuracy of high-frequency carrier signal synchronous modulation.

The invention discloses an unmanned aerial vehicle autonomous navigation system based on a hierarchical reinforcement learning strategy. The unmanned aerial vehicle autonomous navigation system is suitable for a three-dimensional flight task in an unknown environment. The system comprises a state sensing module, a hierarchical strategy network module, a control execution module, a data classification module and a data playback module. The state sensing module extracts obstacle position information based on a deep neural network, and fuses the target, the obstacle position and the flight state to generate a state vector and a time sequence. The hierarchical strategy network adopts a high-layer DQN to generate a navigation intention, and a low-layer LSTM and PPO are combined to output a continuous control action; the control execution module adjusts the attitude of the unmanned aerial vehicle according to the instruction and performs closed-loop correction. The system introduces a double dynamic memory mechanism (DDM), improves strategy training efficiency and stability through experience classification and proportional sampling, and adopts a multi-target award function guide strategy to optimize convergence among task completion, obstacle avoidance safety and flight rationality. The system has good environmental adaptability and generalization ability, and is suitable for autonomous navigation tasks in complex scenes.

The invention discloses a fault diagnosis and remote monitoring system and method for a solar power supply system, and relates to the technical field of fault diagnosis of a solar system, and the system comprises a heterogeneous multi-mode sensing module which collects the multi-dimensional information of an assembly through a plurality of sensors; the memristor storage and calculation integrated unit is used for realizing data filtering and feature extraction; the multi-scale causal diagnosis engine is used for diagnosing faults by fusing deep learning and causal diagrams; a self-adaptive topology communication network ensures data transmission; a digital twinborn monitoring platform and visual operation and maintenance are adopted, and in addition, an intelligent evolution decision and self-reconfiguration sensor network module is further arranged, so that the intelligence and reliability of the system are improved. Through cooperation of multiple modules, accurate fault diagnosis and positioning are realized, the diagnosis time is shortened, stable data transmission is ensured, self-repairing and autonomous learning capabilities are provided, the operation and maintenance cost can be reduced, the power generation efficiency can be improved, and the reliability and economic benefits of a solar power supply system can be enhanced.

The invention discloses a safety monitoring system of a high transverse support system for cable-stayed bridge man-shaped tower column construction, and relates to the technical field of bridge construction monitoring, the system comprises a creeping formwork integrated sensing module used for generating a point cloud model by using a mechanical arm integrated on a hydraulic creeping formwork platform and a laser radar scanning tower column curved surface, combining with a preset building information model coordinate, adaptively adjusting the mounting posture of the sensor, and outputting the mounting coordinate position of the sensor; the optical fiber sensing network module is used for collecting original strain and temperature data by using a distributed optical fiber sensor deployed along a main stress path of the support truss; an inertial navigation fusion positioning module; a digital twinning early warning module; and an edge calculation relay module. According to the invention, a full-process monitoring chain from data acquisition to risk early warning is constructed through cooperation of multiple modules, full-period and multi-dimensional dynamic control of construction of the human-shaped tower column high transverse support system is realized, and timely perception and overall control of potential risks are ensured.

The invention discloses a complex underwater side-scan sonar exploration detection method and device based on a multi-dimensional attention collaborative lightweight anti-noise detection framework, and the device comprises an underwater side-scan sonar imaging device which is used for obtaining a sonar image of a detected target; the computer is connected with the underwater side-scan sonar imaging equipment and comprises a backbone feature extraction network module which is used for processing an input sonar image through a multi-scale edge refining module and outputting a three-scale feature map; the check feature fusion network module is used for realizing cross-channel and cross-space information fusion through the focusing space adaptive local attention module, performing adaptive modulation and deep information aggregation on multi-scale features through a channel frequency aggregation and attention mechanism, and outputting three enhanced feature maps; and the YOLOhead detection head module is used for generating a target detection frame according to the enhanced feature map, and outputting a detection result after non-maximum suppression processing.

The invention relates to the technical field of warehouse-in and warehouse-out management, in particular to a second-hand car warehouse-in and warehouse-out management system and method. The system comprises a vehicle RFID tag module, an intelligent electronic price tag module, a warehouse-in management module, a warehouse-out management module, an inventory monitoring and alarming module, a multi-point RFID positioning network module and an inventory map visualization module, and a unique encrypted RFID tag can be configured for each second-hand vehicle; binding an intelligent electronic price tag for each second-hand vehicle, and receiving verification to generate a verification result; collecting label information when the vehicle enters the parking lot; the label information is verified when the vehicle leaves; receiving the verification result of the intelligent electronic price tag and the vehicle in-library data of the database to lock the position of the abnormal vehicle; dense RFID reader nodes are arranged in the market to collect and output positioning data; and receiving the positioning data and the vehicle state information, generating a real-time inventory distribution map, and providing a scheduling and site planning decision basis for a manager. The scheduling and planning efficiency of managers can be improved.

The invention discloses a lightweight multi-source unmanned aerial vehicle target detection method and system based on a DEYOLO framework, and relates to the field of target detection, and the method comprises the steps: obtaining an unmanned aerial vehicle visible light image and an unmanned aerial vehicle infrared image which are registered, and inputting the images into a pre-trained target detection model; the model comprises a double-flow feature extraction network module which is used for extracting an unmanned aerial vehicle visible light image and an unmanned aerial vehicle infrared image to obtain a visible light feature map and an infrared feature map; the bimodal adaptive feature weighting module is used for performing bimodal adaptive feature weighting and adding on the visible light feature pattern and the infrared feature pattern to obtain fusion features; the lightweight bimodal attention enhancement module is used for performing feature enhancement on the fusion features; and the detection head is used for detecting the enhanced features. According to the method, the calculation complexity is effectively reduced, and the detection precision and the reasoning speed of the model on the low-slow small target and the robustness of the model on a complex scene are remarkably improved.

The invention relates to the technical field of underwater robots and high-precision positioning, and particularly discloses a high-precision positioning system for collaborative operation of an underwater robot cluster. The system comprises a multi-source fusion positioning base station network module, a cross-medium cooperative positioning engine module, a cluster relative positioning subsystem module, a dynamic environment perception compensation module, an elastic positioning fault-tolerant system module and a cooperative positioning decision center module. An absolute positioning reference is constructed through a multi-source fusion positioning reference station network, a cross-medium cooperative positioning engine is combined to realize accurate pose calculation, a cluster relative positioning subsystem is utilized to establish a dynamic topological relation between robots, an environment perception compensation and elastic fault-tolerant mechanism is introduced, and finally resource configuration is optimized through a cooperative decision center. The method solves the problem of high-precision positioning of robot cluster collaborative operation in a complex underwater environment, and can be widely applied to the fields of ocean exploration, underwater engineering and the like.

The invention discloses an image recognition system for industrial part defect detection, and particularly relates to the field of part defect detection, which comprises a multi-axis controllable light source array module, a high-speed polarization camera module, an edge computing node module, a double-branch semantic segmentation network module and a physical constraint post-processing module, according to the invention, through combination of time-sharing stroboscopic illumination and polarization image sequence acquisition, multi-dimensional perception of surface topography and material differences is realized; generating an elevation map and a normal map by using photometric stereo solution, constructing a differential rendering layer reverse matching CAD model, and extracting flash sensitive features; a double-branch U-Net network is adopted to fuse geometric and polarization characteristics, the characterization capability is enhanced through a trans-attention mechanism, and a pixel-level mask is output; and finally, mapping a two-dimensional result to a three-dimensional coordinate system by means of calibration parameters, carrying out geometric verification in combination with a tolerance zone and a height threshold value, and automatically generating a structured defect report containing position, size, grade and visual information.

The invention discloses a time-space alignment-based vehicle-road cloud integrated end-to-end automatic driving device and method, and aims to solve the problems of limitation of a single vehicle intelligent end-to-end algorithm and incompatibility of fusion after vehicle-road collaborative perception. The device comprises a roadside device and a vehicle end, the roadside device extracts roadside features and transmits the roadside features, and the vehicle end compensates transmission delay through a space-time alignment network module, projects the roadside features to a unified BEV space, and inputs the roadside features into a prediction planning network module after dynamic fusion. The method comprises the steps of road side processing, vehicle end processing, space-time alignment, feature fusion and end-to-end planning, and multi-task loss function optimization is adopted. According to the invention, deep fusion of vehicle and road information is realized, heterogeneous sensor scenes are adapted, the vehicle end load is reduced, the long-tail scene sensing and planning precision is improved, and the reliability and safety of automatic driving are enhanced.

The invention discloses a large language model reasoning acceleration method and system based on dynamic sparsity, and the method comprises the steps: adding a parallel bypass prediction path on an original main calculation path of a network module supporting dynamic simplification of a structure of an original target large language model for the original target large language model; embedding a predictor for selective activation in the bypass prediction path, the predictor being used for generating a network sub-module to be activated according to an input vector of the network module so as to obtain a target large language model supporting two working modes of a dense mode and a sparse mode; when the sparse mode needs to be executed, a predictor embedded in the bypass prediction path is activated to obtain a fast reasoning result; and when the dense mode needs to be executed, closing the predictor embedded in the bypass prediction path to obtain a comprehensive reasoning result. The method aims at solving the problems that in the large language model reasoning process, video memory occupation is too high, and time consumption is too large, and optimal balance of calculation efficiency and resource consumption is achieved.

The invention is suitable for the technical field of material mechanics and engineering, and provides a multi-axial fatigue life prediction method and device and computer equipment, and the method comprises the steps: obtaining original data from a multi-axial fatigue test database, and obtaining target features based on the original data, designing a plurality of initial multi-axial fatigue life prediction equations based on a semi-empirical multi-axial fatigue life prediction method, constructing a corresponding neural network architecture according to each initial multi-axial fatigue life prediction equation, and training the neural network architecture in combination with the target features and the physical constraint loss function to obtain a target neural network; and performing interpolation sampling on each network module of the target neural network to construct an enhanced data set, extracting an interpretable quantization equation of each network module through symbolic regression based on the enhanced data set, combining the interpretable quantization equations, performing generalization screening, and outputting a final multi-axial fatigue life prediction equation. And precision, interpretability and generalization are considered, and engineering application requirements are met.

The invention belongs to the field of visual tracking, and relates to a multi-target visual tracking method based on cooperation of a dynamic neural field and a neural network, which takes a cross-modal cooperation architecture as a core and comprises a dynamic neural field module based on multi-target trajectory maintenance and shielding matching and an improved MoESDQ neural network module. Meanwhile, a collaborative decision-making mechanism is designed, when the activation peak value of the dynamic neural field is attenuated to a preset threshold value, neural network feature matching is triggered, and disappearance target reproduction correlation is achieved based on cosine similarity. The objective of the invention is to solve the visual tracking capability under the condition of scene and target motion change in a monitoring range, for example, under an intelligent traffic intersection scene. The problems of high ID switching rate, multi-target misassociation and low tracking precision under a real-time tracking background caused by scene change or frequent shielding of vehicles and pedestrians, similar target appearances, transient disappearance and reproduction of the targets and sudden illumination change are solved.

The invention discloses a satellite orbit forecasting method based on deep learning physical constraint loss, and the method comprises the following steps: 1, carrying out the normalization preprocessing of input data, forming a training data set and a test data set, and constructing batch processing training data; and 2, performing dimension expansion on sample data points in each window in the batch processing data formed in the step 1, constructing a multi-dimensional feature space of the sample points, and forming a batch processing input data format capable of being introduced into the model. And 3, performing forward reasoning on the batch data formed in the step 2 by using a model, and obtaining a batch processing orbit prediction value output by the model at the next moment through a CNN lightweight spatial-temporal feature extraction module and a BiLSTM bidirectional time sequence neural network module. And 4, taking the track prediction value obtained in the step 3 and the truth value label in the training set obtained in the step 1 as input, calculating to obtain a loss value of a current training iteration batch through a multi-random learning loss module fusing physical constraints, and performing reverse updating of model parameters to complete model training. And step five, through the steps two to four, performing reasoning verification on the model by using the test set formed in the step one, and comparing with a truth value in the test set to obtain a model test result.

The invention discloses a multivariable time sequence prediction method and system based on an implicit neural network. The method comprises the following steps: 1) collecting data and preprocessing the data; 2) performing window division on the standardized or normalized multivariable time sequence and determining the length of a to-be-predicted window; 3) performing variable correlation coding on the input window to obtain a variable-level feature vector; 4) the implicit neural network based on time attention predicts target parameters by using the variable features in the step 3), and implicit neural representation of the target sequence is modeled through the parameters; 5) taking the output of the implicit nerve representation and the original input window as the input of the multi-head attention predictor, and obtaining a prediction result through cross-sequence cross attention calculation performed in the implicit space and multi-layer perceptron conversion output dimension; and 6) training and optimizing model parameters, calculating a mean square error of a prediction result and a real result, taking the mean square error as a loss function, carrying out back propagation to optimize trainable parameters of the variable correlation coding module, the implicit neural network module multi-head attention predictor and the multi-layer perceptron, and then repeating the steps 3) to 6) to obtain the multi-head attention predictor. Until the preset number of iterations is reached or the error of the model on the verification set meets the requirement of early stop; and 7) performing prediction by using a model of training convergence, and performing reverse normalization on a prediction result to obtain a final prediction result. The method has good generalization, and meanwhile, the interpretability of the attention mechanism is remarkably improved by generating the hidden space characteristics of the trend component and the season component.

The invention relates to the technical field of radio frequency generator circuits, and provides a phase-locking frequency-stabilizing multi-core control radio frequency system, which processes I / Q signals and constructs a multi-core task allocation and cooperation mechanism through a digital baseband processing module, and performs pre-distortion processing and system scheduling. The double-closed-loop control module is used for stabilizing fundamental frequency, correcting temperature drift and compensating and adjusting frequency swing amplitude; the hybrid power amplification module is used for performing multi-stage hybrid power amplification signal processing and temperature monitoring through a driving stage and output stage combined topology; and the feedback sampling network module collects output signals in real time through a directional coupler and feeds back, adjusts and precisely controls the frequency stability according to the output signals.

The invention provides a water area monitoring system for cooperative operation of an unmanned aerial vehicle and an unmanned ship based on a Mesh ad hoc network. The water area monitoring system comprises the unmanned aerial vehicle, the unmanned ship, a Mesh ad hoc network module, a cooperative control system and a shore end control system, according to the unmanned plane, wide-area patrol and image acquisition, airspace and wide-area water area information is acquired through a sensor, fixed-point acquisition and water area information acquisition are realized through an unmanned ship, and data interaction is realized by relying on nodes of a Mesh ad hoc network. Through the multi-hop relay and dynamic routing technology of the Mesh ad hoc network, autonomous and reliable communication in a scene without a fixed base station is realized, and the communication coverage range and survivability are improved; on the basis of distributed task allocation and real-time data interaction, the equipment cooperation efficiency is remarkably improved, the response delay is shortened, and efficient completion of tasks in a complex environment is guaranteed.

The invention discloses a side information enhancement sequence recommendation method and system based on causal intervention depolarization, and relates to the technical field of recommendation. According to the method, the recommendation accuracy and robustness are improved by capturing the evolution laws of the user interests on different time scales. By introducing a trainable frequency domain filtering weight, noise interference is effectively suppressed, and the stability and generalization ability of user interest representation are enhanced. The influence of false correlation is eliminated by introducing a learnable causal mask matrix and a differential fusion mechanism, depolarization of systematic interference factors is realized, and the fairness and causal rationality of a recommendation result are improved. And specialized modeling of different user behavior modes is realized through the global-local double-gating hybrid expert network module, so that the expandability and the response speed of the system are improved. And deep interaction of cross-modal features is realized through a dual-path feature weighted fusion module, so that the comprehensiveness of user interest description and the personalized level of recommendation are remarkably improved in a multi-source information fusion scene.

The invention relates to the technical field of intelligent agricultural planting and breeding, and discloses a digital intelligent agricultural planting and breeding combined system which comprises a multi-source sensing module used for collecting environment data, biological sign data and equipment operation data through a planting area sensor, a breeding area sensor and a circular processing equipment sensor; the data verification module is used for dynamically verifying the collected data based on a preset agronomic mechanism model; the hierarchical digital twinning module is used for carrying out collaborative decision making in a three-level architecture of the edge computing node, the local server and the cloud platform and generating an optimization instruction; a virtual-real decision engine module; and a closed loop execution network module. According to the invention, a lightweight twinborn model is deployed through the edge layer to realize millisecond-level equipment control and guarantee timely response of extreme working conditions, the field area layer coordinates planting and breeding material circulation through a dynamic optimization algorithm, and the cloud layer integrates climate data to generate a carbon sink strategy of block chain evidence storage. And the real-time decision-making precision, the resource utilization efficiency and the carbon economic value are improved through three-level cooperation.

The invention discloses a neural disease diagnosis system based on space-time attention and dynamic field self-adaption. The method belongs to the technical field of cross-modal medical data adaptive analysis. The technical problem that a brand new system capable of simultaneously fusing multi-modal information and modeling multi-scale spatial-temporal features and having dynamic field adaptive ability is urgently needed to improve the accuracy and generalization ability of intelligent diagnosis of multi-site nerve diseases is solved. The system comprises a data preprocessing module for extracting a standardized time sequence of a brain region from fMRI time sequence data; the two-channel feature coding network module obtains global features through an attention mechanism; according to the feature fusion and classification module, a main task classifier executes a main task and predicts whether a to-be-tested person suffers from nerve diseases or not, and a domain task classifier executes a domain task and predicts a site to which the to-be-tested person belongs; and the dynamic balance training module adjusts the dynamic balance of the main task and the domain task through a dynamic balance control strategy.

The invention relates to a knowledge graph semantic enhanced embedding optimization method based on a dynamic memory network, and belongs to the technical field of knowledge graph logic query questions and answers. Explicit modeling and dynamic updating of a historical logic mode are realized by constructing a structured dynamic memory network; a nested structure and a long-term dependency relationship in complex logic query are effectively captured, the semantic understanding and generalization ability of a model to diversified structure combinations is remarkably improved, basic semantics, logic structures and memory features are dynamically fused, a gated memory updating strategy is introduced, a memory calling path is clear in the reasoning process, and the reasoning efficiency is improved. And the optimization behavior is traceable, so that the interpretability and robustness of the model are enhanced, and the embedding space optimization effect is remarkable and has interpretability. And finally, on the premise that an original upstream encoder does not need to be modified, reasoning enhancement is realized through an external dynamic memory network module, the proportion of updated parameter quantity is small, the calculation overhead is low, and the method is suitable for efficient deployment of various reasoning platforms.

The invention relates to a video snapshot compression imaging reconstruction method and system. The method comprises the following steps: inputting a video frame sequence and a time-varying mask set thereof into a measurement model to obtain initial estimation; constructing a reconstruction network which comprises a feature extraction module, a gating residual network module and a video reconstruction module; the feature extraction module comprises two three-dimensional convolution layers, each three-dimensional convolution layer is connected with an activation function, and the feature extraction module extracts initial features from the initial estimation; inputting the initial features into a gating residual network module, and outputting reconstruction information features; and the video reconstruction module fuses the reconstruction information features, and performs up-sampling and detail refining to reconstruct a video sequence. According to the method, on the premise that parameters and computing power are hardly increased, ghosting and flickering are effectively restrained, the stability of long-time reconstruction is improved, and an effective scheme is provided for SCI reconstruction with the high compression ratio, the super-definition resolution ratio and the long sequence.

The invention belongs to the technical field of unmanned aerial vehicles, and particularly relates to an intelligent aerial 3D printing and spraying system and method based on an unmanned aerial vehicle cluster, and the system comprises a spatial three-dimensional laser ranging scanning modeling module for generating a real-size scene model, a three-dimensional positioning network module, and a three-dimensional positioning network composed of a plurality of laser radar arrays. Wherein the laser radar or the wireless positioning beacon array is arranged on a working plane to construct a three-dimensional space coordinate reference system; the printing module is integrated on the unmanned aerial vehicle, compared with traditional high-altitude operation, the construction efficiency is improved, the constraint of tedious procedures such as scaffold building and manual high-altitude operation is thoroughly eliminated, the unmanned aerial vehicle cluster can be rapidly deployed in a short time, and operation tasks such as large-area single-color or full-color spraying, repairing, modeling and printing are efficiently completed with high precision; the project construction period is greatly shortened, the comprehensive construction cost is reduced, the safety construction level is improved, the engineering income is improved, and the construction accident risk is reduced.

The invention provides an automatic engineering main body structure construction progress detection method based on unmanned aerial vehicle vision, and the method comprises the steps: collecting a construction site high-resolution image through an unmanned aerial vehicle, constructing a data set, carrying out the labeling preprocessing, and converting the data set into a YOLOv12 recognition format; a YOLOv12 model (including replacing an A2C2f module with an A2C2fMcva module, replacing a C3k2 module with a C3k2-SLBlock module, and replacing a neck network Concat module with a GDSA feature fusion module) is improved, and an optimal detection model is obtained through training; shooting a construction picture in real time by using an unmanned aerial vehicle, segmenting a construction region through a model, judging a current activity based on construction sequence coding, and calculating a construction activity area; and calculating a progress correction coefficient in combination with CAD software, and finally obtaining the construction progress P. The method realizes automatic and accurate detection of the construction progress, and is suitable for complex construction scenes.

The invention relates to a meteorological deduction method and device fusing physical constraints and a neural network, and the method comprises the steps: obtaining multi-source meteorological data, and constructing a spatial-temporal feature input tensor; the spatio-temporal feature input tensor is subjected to standardization processing and then input into a deep learning network model, and a future weather prediction result is obtained; the model extracts time sequence evolution features and space attention features through a neural network module and a space attention module respectively, and integrates the time sequence evolution features and the space attention features in a splicing form; for a forecast task of a future gamma day, a deep learning network model and a physical mode are adopted for prediction respectively, and a splicing time point is determined according to an error minimum principle, so that splicing of prediction results is carried out; when the physical mode is used for prediction, the improved regional numerical weather prediction model is used as a basis, atmospheric basic equation sets are integrated, and weather prediction at future moments is carried out. Compared with the prior art, the method has the advantages that the atmospheric physical law and data driving advantages are fused, and the extreme weather prediction precision and stability are improved.

The invention provides a well wall crack detection method and device and a storage medium. The detection method comprises the following steps: S1, constructing a data set image; s2, a detection model MSCI-RTDETR is constructed; s3, training the model; and S4, testing the model. S2 comprises the steps of S21, constructing a feature extraction backbone network module; the backbone network module is composed of an automatic edge detection module and a feature extraction module KAN-Transform in sequence; s22, constructing a hybrid encoder module, wherein the hybrid encoder module is formed by splicing a same-scale feature interaction module AIFI and a cross-scale feature interaction module PAC-APN; s23, constructing a decoder module, wherein the decoder module is composed of a Wise-IoU perception query selection module; and S24, obtaining the final output of the model. According to the detection method, accurate detection of the well wall crack is achieved in a multi-scale fusion mode, the problems that an existing crack detection method is complex in calculation and insufficient in detection precision are solved, and underground casualties and equipment losses are avoided.

The invention discloses a digital twinning multi-agent reinforcement learning intelligent decision-making system and method with a secure memory playback mechanism, and the system comprises a digital twinning module which is used for constructing a virtual model and synchronizing the virtual model with a physical entity in real time; the multi-agent reinforcement learning module is used for carrying out strategy learning based on a constrained Markov decision process and balancing performance and safety through a Lagrange multiplier; the safe memory playback module is used for weighting and playing back the experience samples according to the risk and the timeliness so as to improve the learning safety; the reversible grey influence network module is used for causal modeling and reasoning and enhancing decision interpretability; the double-loop self-constraint control module ensures that a control action is always in a physical safety boundary through a barrier function and safety projection; and the convergence and stability criterion module is used for verifying strategy security convergence and system asymptotic stability. According to the method, the problems of strategy border crossing, virtual-real mismatching and the like in the high-risk manufacturing process are solved, and multi-target optimal control under the safety constraint is realized.

The invention belongs to the technical field of signal processing, and particularly relates to a coherent light high-speed transmission signal processing method based on deep joint compensation, which comprises the following steps of: performing fine frequency offset and inter-carrier interference joint preprocessing on a coherent light receiving sampling sequence; obtaining a pre-processing output sequence and at least one estimation parameter derived from fine frequency offset and inter-carrier interference combined pre-processing; inputting the preprocessing output sequence into a diffusion type score guide joint compensation network module to obtain a deep joint compensation sequence; performing online judgment and decoding on the deep joint compensation sequence, and adaptively updating internal parameters of the diffusion type score guide joint compensation network module when a preset adaptive updating condition is met; according to the invention, the symbol residual error can be obviously reduced, the forward error correction gain can be improved, and the stability and robustness of the system under high-order modulation, high symbol rate and long-distance link scenes can be enhanced.

The invention provides an image text description generation method, electronic equipment and a readable storage medium. According to the method, the object perception prototype learning module and the global context feature extraction module are introduced, so that fine-grained information and global semantic understanding in the image are effectively balanced. The visual backbone network module can extract multi-scale and multi-level image features and perform fusion, thereby enhancing the expression ability of the image features. The object perception prototype learning module further extracts an object prototype from the fusion features to ensure that the model can accurately capture key objects and attributes thereof in the image, and the global context feature extraction module ensures that the overall context of the image is fully understood. On the basis, the encoding and decoding module combines the global context and the object prototype to generate the text description, so that the semantic splitting phenomenon in the traditional method is avoided, and the detail information in the image is effectively reserved, thereby improving the accuracy and integrity of the image description.