1740 results about "Network module" patented technology

The invention relates to the technical field of tunnel engineering construction, and discloses an intelligent material transportation and safety monitoring system and method for shield construction, and the system comprises a visual perception unit, a sensor network module, an AI analysis center module, a safety decision module and a human-computer interaction interface. According to the invention, data acquisition is carried out through the visual perception unit and the sensor network module, multi-target detection operation is carried out on image frames through the AI analysis center module after target identification and track prediction, target types, space coordinates, contour boundaries and confidence coefficients are identified and extracted, and safety judgment and early warning output are carried out. According to the invention, by integrating the multi-view camera equipment and the UWB, GNSS and other sensors and adopting a deep learning target detection algorithm, high-precision identification and continuous tracking can be carried out on construction site personnel, equipment, segments and other key objects, and accurate input is provided for subsequent risk analysis.

The invention discloses a cooperative monitoring device and method for a large deep foundation pit complex supporting system, and relates to the technical field of foundation pit supporting. The device comprises a multi-dimensional sensor network module, a BIM-GIS digital twin platform module, an intelligent analysis and early warning module, a construction collaborative decision module, a data backup and recovery module and a remote monitoring and management module. The method comprises the following steps: step 1, carrying out multi-source data space-time registration; step 2, dynamically constructing a digital twinborn model; step 3, coupling risk assessment; step 4, construction collaborative optimization; according to the technical scheme, the method comprises the following steps of data processing, data quality control and system performance evaluation, through three innovations of deep coupling of multi-source data, dynamic model correction and intelligent collaborative decision making, a'monitoring-analysis-decision-execution 'full closed loop is constructed, technical breakthroughs are achieved in complex working condition adaptability, early warning real-time performance and construction safety, and the method has remarkable engineering application value.

The invention relates to the technical field of aircraft intelligent detection and maintenance systems, and discloses an aircraft defect intelligent evaluation system and method based on multi-modal fusion, and the system comprises a multi-modal data collection module, a tensor construction and decomposition module, a meta-prototype relation network module, a multi-target game optimization module, and a closed-loop feedback module. The method comprises the steps of constructing a five-order feature tensor through multi-modal data synchronous acquisition and space-time alignment, extracting low-rank features through hypergraph block item decomposition, dynamically generating a defect prototype set in combination with meta-learning, generating a maintenance decision by adopting a Nash equilibrium strategy and fusing multi-constraint conditions, and optimizing system parameters through closed-loop feedback. The whole-process intelligentization of aircraft defect detection and maintenance is realized; according to the method, high-precision defect detection is realized through multi-modal data fusion and hypergraph modeling, an intelligent decision is generated in combination with dynamic prototype learning and multi-target game optimization, and continuous self-optimization is performed by means of a closed-loop feedback mechanism, so that the operation and maintenance efficiency and safety of the aircraft are improved automatically in the whole process.

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 energy management and carbon accounting, in particular to an intelligent carbon emission monitoring system and method based on the Internet of Things, and the system comprises a distributed sensing network module which collects the energy consumption and emission data of an independent accounting unit in real time; the edge computing module is deployed at a local edge computing node to preprocess the data acquired by the distributed sensing network module; the cloud co-processing module receives the preprocessed data and carries out dynamic accounting and multi-source data fusion; the carbon accounting model module automatically matches accounting requirements according to the industry to which the enterprise belongs and generates a monitoring point layout scheme; and the intelligent visualization module is used for generating a multi-dimensional carbon emission data analysis chart and a compliance report meeting MRV requirements based on data of the edge calculation module, the cloud co-processing module and the carbon accounting model module. Full-process automatic management from data acquisition, real-time monitoring to verification is realized, and the accuracy, integrity and traceability of carbon emission data are ensured.

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 relates to the technical field of hydropower engineering, and discloses a single-core self-healing type looped network networking method and system, and the method comprises the steps: dividing a whole network into a plurality of sub looped networks; each sub-ring network operates independently; the light switch in each sub-ring network adopts an A / B end connection mode; reversely connecting the B end of the last measuring point to the A end of the initial measuring station by using an optical fiber to form a closed physical structure; configuring a protocol on the switch, and controlling a data flow path through the protocol; different sub-ring networks are connected through RJ45 ports, and a CAT5E shielded twisted pair or an Ethernet interface is used; when a certain node or link fails, the protocol automatically triggers a switching mechanism; the master station optical transceiver monitors the states of all nodes in real time and displays fault points through a network management interface. The system comprises a sub-ring network module, a control data flow module and a fault point display module. The problems that a traditional networking method of hydropower engineering is poor in reliability, and self-healing cannot be achieved after an intermediate node is disconnected are successfully solved.

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 an industrial equipment early warning system and method, and the system comprises a multi-mode sensing network module which collects equipment operation data in real time, and carries out the preprocessing of the equipment operation data; the feature extraction module is used for performing feature extraction on the operation data of the multi-source equipment; the data fusion module is used for carrying out feature fusion on the extracted features and generating equipment health state feature vectors; the health state evaluation module is used for analyzing the feature vectors, evaluating the current health state of the equipment and predicting the change trend of the future 12-24 hours; the service life prediction module is used for predicting the residual service life of the equipment based on the historical operation data and the current state data of the equipment and generating a maintenance suggestion according to a prediction result; and the model optimization module is used for carrying out optimization processing on the optimized life prediction model. According to the invention, accurate prediction of the residual service life of the equipment can be realized.

The invention discloses a new energy automobile body frame lightweight design method based on digital twinning, and relates to the technical field of new energy automobile body structure design and computer-aided engineering simulation, and the method comprises the following steps: S1, building a digital twinning body connected with a physical automobile body sensing system; s2, a dynamic precision topology network module is used for dynamically dividing a simulation precision area of the vehicle body frame according to the mechanical energy transmission path and the real-time sensing data. According to the new energy automobile body frame lightweight design method based on digital twinning, intelligent allocation of computing resources is realized through a dynamic precision topology network, and the computing burden of multi-physics coupling simulation is effectively reduced while precise prediction of a key structure is ensured; the sharp contradiction among the model precision, the real-time response and the optimization efficiency is effectively solved, and effective closed-loop iteration of the lightweight design is achieved under the complex constraint condition.

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 package full life cycle tracing system based on a block chain and the Internet of Things. The system comprises a package identification module which generates a unique digital identity and binds a block chain account; according to the multi-source information acquisition module, an embedded sensor network monitors the packaging state in real time; the data uplink processing module is used for spatio-temporal data enhancement and block chain transaction construction; the alliance chain network module is used for distributed account book management and consensus verification; the life cycle tracing module is used for full-cycle data visualization; and the closed-loop recovery verification module is used for carrying out recovery processing digital authentication. The system has the advantages that through deep fusion of the block chain and the Internet of Things, a full-life-cycle credible tracing closed-loop system is constructed, the problem that data of a traditional tracing system is easily tampered is solved, logistics optimization suggestions and quality early warning are generated in real time, and the packaging recovery rate is improved.

The invention provides a magnetic particle imaging resolution improving method and system based on frequency domain information filtering, and relates to the technical field of magnetic particle imaging. Comprising the following steps: inputting original magnetic particle imaging data into a Transform model, and selectively filtering frequency domain information in the magnetic particle imaging data through a fusion frequency domain discrimination feedforward network module in an encoder to obtain the output of the encoder; inputting the output of the encoder into a bottleneck layer, aggregating global and local information through a multi-scale attention mechanism module, and then selectively filtering frequency domain information in the magnetic particle imaging data again to obtain the output of the bottleneck layer; inputting the output of the bottleneck layer into a decoder with the same structure as the bottleneck layer to obtain deep features; inputting the deep features into a convolutional layer to obtain a residual image; and calculating the sum of the original magnetic particle imaging data and the residual image to obtain a reconstructed image. According to the invention, the overall imaging resolution of the MPI image under the low-gradient field acquisition condition is 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 provides a self-adaptive collaborative acoustic environment active treatment system and method. The system comprises a multi-dimensional environment sensing network module, an intelligent voiceprint recognition and sound field prediction module, an active noise control module, a central intelligent collaborative regulation, diagnosis and self-learning module and a passive acoustic intervention module. The multi-dimensional environment sensing network module collects multi-dimensional sensing data in real time; the intelligent voiceprint recognition and sound field prediction module outputs a voiceprint recognition result and a noise source space coordinate and predicts a sound field evolution trend; the active noise control module outputs a residual noise signal; the central intelligent cooperative regulation, diagnosis and self-learning module outputs an active and passive cooperative control instruction set; the passive acoustic intervention module controls broadband noise to block or change its propagation path. According to the invention, through a dual-channel self-learning mechanism of the deviation diagnosis capability, continuous evolution of system performance can be realized according to a deviation autonomous optimization acoustic model and a control strategy, and accurate, efficient and prospective active treatment is carried out on a complex noise environment.

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 an intelligent sand excavation supervision system based on multi-source data fusion, and relates to the technical field of machine learning, and the system collects target river reach data in real time through a multi-source sensing network module; the spatial-temporal feature fusion module generates a dynamic state fingerprint matrix; the adaptive baseline monitoring module establishes and dynamically updates a normal state baseline under multiple conditions, and triggers an abnormal disturbance alarm by calculating a mahalanobis distance between a real-time fingerprint and the baseline and combining collaborative deviation verification of acoustics, turbidity and water flow characteristics, and the multi-task analysis module adopts a parallel neural network architecture, so that a multi-task analysis result is obtained. The illegal operation type probability, the strength estimation value and the environment disturbance level are synchronously output; the three-dimensional visualization early warning module generates an early warning interface based on the analysis result; the dynamic knowledge management module and the self-adaptive optimization module are used for improving the analysis accuracy and continuously optimizing the system performance by using historical experience; the method has the advantages that abnormal disturbance events such as illegal sand excavation and the like can be accurately and intelligently supervised in real time, and powerful capability is provided.

The invention provides a lightweight low-light target detection method and system, and relates to the technical field of image processing, and the method comprises the steps: obtaining a low-light image data set; labeling the low-light image data set; yOLOv8s is used as a framework, a lightweight target detection model is constructed, and the lightweight target detection model comprises a multi-scale phantom convolution module, a backbone network module, a neck network module and a detection head module; inputting the marked low-light image data set into a lightweight target detection model for training; obtaining a to-be-detected low-light image; and inputting a to-be-detected low-light image into the trained lightweight target detection model, and outputting a target detection result of the to-be-detected low-light image. According to the method, the target detection precision and speed can be improved, the robustness of the detection model is enhanced, a scene with a high real-time requirement is met, and the recognition capability of the model in a complex environment is improved.

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 relates to the field of community old-age care, and discloses a community old-age care-oriented medical-care-and-care-combined data intercommunication and service coordination system, which comprises a sensing module used for acquiring physiological data of old people, old-age care service data, environment data and service demand information to form multi-modal information; the network module is used for carrying out multi-modal information transmission, protocol conversion and edge calculation preprocessing to obtain processed data; and the data module is used for constructing a standardized data lake according to the processed data by adopting a unified data standard and a main data management technology, and carrying out fusion storage, treatment and safety protection to obtain multi-source information. Multi-modal information is collected to provide a data basis for cross-mechanism cooperation, data transmission and preprocessing are performed, and a standardized data lake is constructed through a unified data standard and main data management, so that medical institutions, pension institutions and community grids can share global data such as health states, service records and the like of old people in real time.

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 settlement monitoring system based on computer vision, and relates to the technical field of infrastructure monitoring, the settlement monitoring system comprises a settlement monitoring platform, the settlement monitoring platform is in communication connection with an image acquisition module, a sensor network module, a data fusion analysis module, a settlement abnormity identification module and a settlement early warning module, the modules are in electric signal connection; and the image acquisition module is used for monitoring a foundation area of the infrastructure by using a plurality of cameras deployed in a monitoring area to obtain image data of the infrastructure. Through combination of the image acquisition module and the sensor network module, comprehensive coverage and accurate monitoring of an infrastructure foundation area are realized, a plurality of cameras are utilized to carry out omnibearing and multi-angle image acquisition, dead-corner-free monitoring is ensured, physical parameter data of a foundation are acquired in real time through multiple types of intelligent sensors, and the monitoring precision is improved. Monitoring comprehensiveness and accuracy are obviously improved, and potential safety hazards caused by monitoring blind areas are effectively avoided.

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.