766 results about "Online learning" patented technology

The invention provides an acoustic array adaptive calibration correction system applied to an underwater moving target, which relates to the technical field of marine equipment and comprises a multi-source excitation and environment perception module, an intelligent array perception and diagnosis module, an adaptive position inversion and uncertainty quantification module and a closed-loop calibration execution and self-learning optimization module. The multi-source excitation and environment perception module is responsible for providing reference signals required by calibration and establishing a correlation model of environment and formation distortion, and the intelligent array perception and diagnosis module realizes multi-modal data acquisition, array element health state monitoring and formation geometry self-perception. The adaptive position inversion and uncertainty quantization module completes signal processing, position estimation and error quantization propagation, and the closed-loop calibration execution and self-learning optimization module executes a compensation strategy, verifies a calibration effect and continuously optimizes system performance through online learning; the system solves the problem that a traditional method cannot process environment time varying, multi-sensor conflicts and uncertainty quantization.

The invention discloses an environmental data processing method and system based on ocean engineering, and relates to the technical field of data processing, and the method comprises the steps: receiving an original observation data flow through a multi-source data preprocessing module, and carrying out the dynamic noise filtering and abnormal value adaptive detection; fusing the multi-source heterogeneous data through a multi-scale data fusion module, and embedding the fused multi-source heterogeneous data into a marine kinetic equation as a soft constraint; non-linear evolution features are extracted from the fusion data through a feature extraction and state representation module, and a high-dimensional environment state vector is constructed; real-time prediction of model parameters is executed through online learning and an inference engine; and performing uncertainty propagation calculation on the processing flow through a confidence evaluation module and generating a final environment state report. According to the method, the adaptive capacity of data preprocessing can be remarkably improved, the physical consistency of multi-source data fusion is improved, the nonlinear evolution law of ocean phenomena is accurately captured, and continuous online optimization and edge side low-delay response of model parameters are achieved.

The invention discloses a thermal power plant whole-plant collaborative optimization system and method based on digital twin and AI algorithms, and belongs to the field of thermal power plant optimization control. The invention discloses a thermal power plant whole-plant collaborative optimization system and method based on digital twinborn and AI algorithms. The system comprises a data fusion processing module, a digital twinborn body construction module, a collaborative optimization and decision module, a strategy decomposition and execution module and an online learning and updating module. According to the method, the problems that the existing thermal power plant optimization control lacks global collaboration and is difficult to adapt to dynamic complex working conditions, and online self-evolution of a model and a strategy cannot be realized are solved; and a deep reinforcement learning algorithm is utilized to carry out multi-target collaborative optimization on the whole plant level, so that a global optimal control strategy which comprehensively considers the operation cost, the energy efficiency, the equipment service life and the environmental protection constraint can be dynamically generated, and the limitation of traditional decentralized control and static optimization is effectively overcome.

The invention provides an AI-based data cooling system with a self-adaptive regulation and control function, and relates to the technical field of data cooling, and the AI-based data cooling system comprises the following steps: collecting equipment operation parameters and operation environment parameters of database equipment; calculating a multi-dimensional load value of the equipment according to the standard operation parameters, and generating a heat dissipation strategy based on a preset AI customized model, the standard environment parameters and the multi-dimensional load of the equipment in combination with a preset temperature safety threshold; and the heat dissipation effect is judged, and the heat dissipation strategy is adjusted. According to the method, rapid closed-loop regulation and control are achieved through dynamic weight optimization and the BP neural network, CPU, memory and I / O multi-dimensional loads are accurately quantified, the temperature trend is pre-judged, and PUE and energy consumption of a data center are remarkably reduced by means of a hierarchical priority strategy; through an online learning model and execution deviation alarm and feedback optimization, manual intervention is reduced, the adaptability is improved, and the deployment cost is reduced through lightweight design.

The invention relates to the technical field of industrial digital twinning, in particular to a digital twinning-oriented real-time data synchronization and consistency verification method, which comprises the following steps of: S1, acquiring multi-source heterogeneous data from a physical entity and a service system, and performing timestamp alignment based on a unified time reference to generate a standardized data stream; and S2, based on the standardized data stream, carrying out data cleaning, aggregation and preprocessing, verifying the integrity and time sequence of the data stream through a transmission verification mechanism, and outputting high-fidelity credible data. According to the method, a bidirectional consistency verification mechanism between a physical entity and a digital twinborn model is constructed, real-time deviation is quantified into a loss function, an online learning engine is driven to adaptively adjust physical parameters in the model, and a complete closed loop from data acquisition to parameter optimization is formed; the digital twinborn model can continuously adapt to dynamic conditions such as material aging and working condition change of a physical entity, and the tedious process that a traditional system depends on manual regular calibration is avoided.

The invention provides a filter stick defective product sorting method for reinforcement learning self-adaptive grabbing, and relates to the technical field of filter stick sorting. The defects of the filter stick are recognized through a multi-view visual module, image coordinates are compensated in real time in combination with the speed of a conveying belt, and the image coordinates are accurately mapped to a three-dimensional working space of a mechanical arm; then, defect poses, production line states and mechanical arm parameters are input to a reinforcement learning module, so that the optimal grabbing action and clamping pressure are output, and efficient sorting of the driving mechanical arm and the soft clamping jaw is achieved; and meanwhile, the feedback evaluation unit acquires a grabbing result through a sensor, generates a reward signal optimization strategy network, and realizes continuous online learning. The technical problems that in a high-speed flexible production line, a traditional sorting system is insufficient in grabbing precision and high in false grabbing rate due to the fact that visual recognition and a mechanical grabbing strategy are disjointed are solved. According to the invention, the collaborative precision of defect identification and grabbing and the sorting efficiency in the filter stick production line are obviously improved.

The invention relates to an underwater wireless sensor network path sensing routing method based on deep reinforcement learning, which comprises the following steps that: firstly, a node constructs and periodically updates a transmission preference model based on local and neighbor node interaction information; secondly, deploying a deep reinforcement learning model at each underwater sensor node to perform distributed routing strategy learning; and finally, generating a global guide vector by the sink node according to the routing path information of the received data packet, reversely spreading the global guide vector to the source node, fusing the global guide vector with a local transmission preference vector of the node to generate a guide reward, optimizing the deep reinforcement learning model, and updating a routing strategy. According to the method, the problems of difference and complexity of underwater transmission tasks can be solved, and the network data transmission efficiency and the overall service quality are improved in combination with local preference and global guidance while the node online learning is kept to adapt to the dynamic underwater environment.

The invention relates to the technical field of online education, and discloses an online course learning management method based on a knowledge graph. The method comprises the following steps: acquiring multi-modal learning behavior data of a learner, and extracting a deep learning state vector reflecting knowledge understanding depth, learning input degree and cognitive confusion through semantic fusion; and dynamically calculating and updating the logical relationship strength among the knowledge points in the course knowledge graph by using the vector, so that the knowledge structure can adaptively evolve along with the actual cognitive state of the learning group. And generating a real-time personalized learning path based on the updated knowledge graph and the current state vector of the learner. Meanwhile, according to cognitive confusion features in the state vector, intervention measures such as pushing of remedial resources, adjusting of content sequence or starting of self-adaptive testing are triggered in real time. According to the method, the dynamic optimization of the knowledge graph and the accurate and immediate response of learning intervention are realized, and the adaptability and management efficiency of online learning are improved.

The invention provides a cardiovascular trend prediction method and system based on time sequence medical health data, and relates to the technical field of medical health data analysis. The method comprises the following steps: collecting time sequence medical health data of a patient through a multi-source sensor, wherein the time sequence medical health data comprises dynamic physiological indexes such as heart rate, blood pressure and oxyhemoglobin saturation; performing time calibration and feature extraction on the acquired multi-source data; constructing a time sequence feature model based on the time sequence features, and fusing the time sequence feature model with the static information of the patient to generate a comprehensive feature vector; using a deep learning model to train historical data, and learning a dynamic change rule of cardiovascular health indexes; predicting the change trend of the cardiovascular health indexes in real time, and evaluating the risk level of cardiovascular diseases; the model parameters are optimized through online learning, the prediction precision is improved, the change trend of cardiovascular health indexes can be predicted in real time, and support is provided for early discovery and personalized medical treatment of cardiovascular diseases.

The invention relates to a side cloud collaborative adaptive workflow scheduling method and system, and belongs to the technical field of distributed computing and artificial intelligence. The method comprises the following steps of: firstly, in a macroscopic candidate screening stage, reducing problem granularity through task clustering, and obtaining balance between utilization and exploration based on a weighted distance probabilistic preferential strategy; then, in a collaborative scheduling decision-making stage, a global network state diagram is constructed through a graph neural network, deep spatial features of nodes and neighborhoods of the nodes are extracted, context-aware state representation is formed, and a reinforcement learning agent makes an optimal collaborative decision in multiple options such as local execution, edge migration or cloud unloading according to the state representation; and finally, in a local adaptive optimization stage, performing fine-grained optimization after the task is issued, dynamically adjusting a scheduling frequency and a multi-target weight through an online learning mechanism, realizing balance between a task deadline and a resource utilization rate, and ensuring efficient and robust execution of a node level.

The invention provides a rice irrigation online learning forecasting method and system, the method is realized according to a pre-constructed physical mechanism-neural network hybrid model based on physical mechanism model prediction and neural network error correction fusion, and the method comprises the following steps: S1, obtaining real-time environment data of a current decision period of a target rice field; s2, on the basis of the real-time environment data of the current decision period, forecasting a paddy field water layer depth predicted value of the next decision period through a physical mechanism-neural network hybrid model, and generating an irrigation drainage forecast in combination with a crop irrigation drainage mode; s3, real-time environment data of the target rice field in the next decision period after irrigation drainage forecast is executed are obtained, training samples are constructed and put into an experience playback pool, and the physical mechanism-neural network hybrid model executes online learning based on the experience playback pool; and S4, when the next decision cycle starts, returning to S2 until a preset stop condition is met.

The invention relates to a real-time process monitoring method based on data analysis, and the method comprises the following steps: S1, building a three-dimensional component priority evaluation model based on a component operation scene type, a real-time resource occupancy rate and a data dependence degree, and dynamically matching an acquisition strategy; s2, a cleaning rule is adapted according to a data source, a feature extraction dimension is adjusted in combination with process dynamic features, and an improved time sequence decomposition algorithm is used for separating data trends, fluctuations and abnormal residual errors; s3, constructing an exclusive baseline sub-model by using an online learning algorithm according to a scene label, and establishing a scene switching mechanism; s4, in combination with component interaction anomaly features, an anomaly level is judged through a mixed detection model; s5, on the basis of exception processing and user feedback, constructing an error correction model optimization parameter; and S6, generating a report containing an abnormal propagation path, and triggering hierarchical collaborative response of the associated component. The invention aims to solve the problems of single acquisition dimension, no scene adaptability in preprocessing, incomplete abnormal detection and the like in the existing monitoring technology.

The invention discloses a special gas cylinder state real-time monitoring and abnormal behavior recognition system, which belongs to the technical field of gas cylinder safety monitoring, and comprises a gas cylinder state data acquisition module for continuously acquiring the pressure, the temperature, the position and the gas concentration of a gas cylinder in real time within one second; the gas cylinder digital twinning module constructs a gas cylinder virtual three-dimensional digital model based on gas thermodynamics physical constraints, realizes double-source fusion of physical constraints and actually measured data by establishing an equivalent mapping relation between the virtual model and a gas cylinder real-time state, and performs adaptive correction on the equivalent mapping relation based on a deviation decomposition attribution mechanism; the deviation decomposition attribution mechanism divides deviations into random errors, systematic accumulated deviations and abnormal deviations, and differential correction strategies are adopted for different types; the equivalent mapping dynamic updating unit continuously optimizes a mapping function through an online learning algorithm, so that the model has a self-evolution capability; and conversion from passive monitoring to active prediction is realized.

The invention discloses a complex scene target detection method based on a model dynamic joint mechanism, and the method comprises the steps: carrying out the preliminary detection through an RT-DETR model, retaining more potential targets through dynamic threshold adjustment, and projecting a generated detection frame to a feature space of an improved YOLOv12 model through dual-mode feature mapping; the improved YOLOv12 model integrates an SEAM attention module and a rejection loss function so as to enhance feature representation and positioning compactness of an occluded target. Then, a model joint mechanism is adopted to process preliminary results of the two models; through difficult case mining and online learning, missing detection targets are supplemented, and the RT-DETR model is optimized; and intelligently fusing the detection results of the two models through dynamic weight distribution based on scene complexity and hierarchical fusion of a decision tree. And finally, post-processing is carried out by using an improved non-maximum suppression algorithm, and mistaken deletion is reduced. According to the method, the problems of missing detection, false detection and inaccurate positioning of the target in a complex scene are effectively solved, and the recall rate and the accuracy rate of detection are remarkably improved.

The invention discloses an intelligent monitoring and early warning system and method for project progress and cost, and relates to the technical field of constructional engineering management. The streaming data fusion module adopts an Apache Flink engine and applies a dynamic time warping algorithm to carry out time alignment on multi-source asynchronous data to realize semantic unification; the space-time diagram neural network prediction module constructs a space-time association diagram, integrates global features such as weather and supply chain fluctuation, and adaptively learns an influence weight by using a graph attention mechanism; the self-adaptive early warning module adopts a Bayesian online learning framework, an early warning threshold value is dynamically adjusted according to a historical false alarm rate and a missing report rate, the method comprises the steps of data acquisition, fusion, mapping, joint prediction and self-adaptive early warning, the problem of data islands is solved, complex space-time association is accurately captured through a space-time diagram neural network, and real-time early warning is achieved. Joint prediction of progress and cost risk is realized, false report and missing report are reduced, and real-time performance, accuracy and decision-making efficiency of engineering management and control are improved.

The invention relates to the field of vehicle control, and particularly discloses a tractor hybrid power cooperative control method, system and device and a medium, and the method comprises the steps: collecting state parameters of a whole vehicle, an agricultural implement and a power system in real time, employing a fusion rule and a real-time optimized energy management strategy to analyze an operation mode, and calculating an initial power distribution target; dynamic coordination is carried out by taking optimal system efficiency and battery state maintenance as targets, smoothness verification and closed-loop feedback correction are carried out on an output instruction, and a final control instruction is generated, issued and executed; the system correspondingly comprises a perception analysis module, a decision making module, a coordination verification module, an execution module and a learning evolution module. By constructing full-link closed-loop control, self-adaptive dynamic optimization and reliable cooperation of the power system are achieved, the online learning ability is achieved, the problems that in a traditional method, control is extensive, response is delayed, and self-adaptability is lacked are effectively solved, and the operation economical efficiency, smoothness and long-term adaptability of the tractor are improved.

The invention relates to the technical field of ship energy efficiency management, and discloses an energy efficiency improvement method and system based on course-speed-trim collaborative optimization, which constructs a course feature code based on navigation environment forecast information and electronic chart information, and combines real-time state information and decision variables of a ship to improve the energy efficiency of the ship. Generating voyage number accumulated energy consumption expectation by using a ship energy consumption prediction model fused by physical information; taking expectation minimization as a target, coupling navigation time constraints, host working condition constraints and ship stability safety boundaries, constructing a three-variable collaborative optimization model of the route path, the planned navigational speed of each route segment and the planned trim value, solving the model, and outputting a collaborative optimization scheme; and on-line parameter adaptive updating is performed on the model based on real-time data during navigation, and dynamic re-planning is triggered. The global voyage number energy consumption optimization is realized through a three-variable collaborative optimization framework and physical information fusion prediction, and the adaptability and robustness of an optimization scheme in a dynamic environment are improved by means of an online learning and rolling optimization mechanism.

The invention relates to the technical field of smart traffic, and discloses a smart traffic monitoring system and method based on multi-source data fusion, and the system comprises a multi-source data collection module, a spatial-temporal feature fusion engine, a hierarchical decision core, a decision execution module, and an online learning module. The method corresponds to the system. According to the method, heterogeneous traffic data are unified under the same time-space reference through a multi-modal fusion technology, and comprehensive and accurate road network state feature representation is constructed; the hierarchical decision-making core forms a closed-loop decision-making link from event identification to control strategy generation through close cooperation of an event sensing layer and a regional optimization layer, and realizes rapid response and accurate control of traffic abnormity; on-line learning continuously optimizes decision logic based on complete historical operation data so as to adapt to a continuously changing traffic environment; finally, the accuracy of traffic state perception and the timeliness of decision response are improved, and reliable technical guarantee is provided for efficient management and control of intelligent traffic.

The invention discloses a deep reinforcement learning optimization method for injection molding process parameters, and belongs to the technical field of intelligent manufacturing. The method comprises the following steps: constructing a dynamic causal graph network through information entropy flow analysis and transfer entropy calculation, and revealing a causal relationship and time delay characteristics among process parameters; manifold learning is adopted to map a high-dimensional parameter space to a low-dimensional manifold, and Riemannian metric guide optimization search is constructed based on the quality gradient; generating enhanced state representation fusing causal association and manifold geometric information; identifying a production element state and selecting a corresponding optimization strategy; a geodesic line is planned in a manifold space to obtain an optimal parameter adjustment path; historical experience is utilized through memory retrieval and case adaptation; cross-task knowledge migration is realized; adopting a depth deterministic strategy gradient algorithm to optimize the decision; and online learning is realized through elastic weight consolidation. According to the method, the problems of black box decision, slow convergence, difficulty in knowledge reuse and the like in the prior art are solved, the optimization efficiency and the interpretability are improved, and the method has the capability of quickly adapting to new tasks.

The invention discloses an educational resource recommendation method and system based on artificial intelligence. The method comprises the following steps: acquiring audio data, interaction data and task data acquired by a user terminal; performing feature extraction on the audio data, the interaction data and the task data to obtain an emotion feature vector, a learning rhythm vector and a content feature vector; inputting the emotion feature vector and the learning rhythm vector into a pre-constructed emotion recognition model to obtain a psychological state vector; the cognitive load is calculated based on the learning rhythm vector and the content feature vector, and then the cognitive load is corrected through the psychological state vector; matching a state interval of the corrected cognitive load according to a preset threshold interval; and according to the state interval, adjusting a difficulty coefficient of the recommended course, rearranging a course content sequence and an auxiliary learning prompt, generating structured data, and outputting the structured data as an intelligent auxiliary learning recommendation result. According to the invention, online learning interactivity and teaching quality in rural and remote areas are effectively improved.

The invention belongs to the field of artificial intelligence, particularly relates to an agent strategy generation and online optimization method based on dynamic scene perception, and aims to solve the problems that in a dynamic environment, strategy response is slow, optimization is difficult under sparse rewards, and online learning is unstable. The method comprises the following steps: constructing a multi-modal fused dynamic scene semantic perception module, and generating a high-dimensional scene representation; historical behaviors and environment contexts are fused through an attention mechanism, and an initial probabilistic strategy is output; executing an action and collecting real-time feedback to form an experience tuple; performing incremental strategy updating by adopting a non-parametric Bayesian framework and combining with a multi-peak exploration operator; a Lyapunov stability criterion and a strategy distillation mechanism are embedded to guarantee convergence robustness. According to the scheme, strategy generation within 50 milliseconds is achieved, the convergence speed of sparse reward tasks is increased by three times, strategy fluctuation is controlled within 8%, the system availability reaches 99.5%, and the real-time decision-making capacity and group cooperation efficiency of an intelligent agent in a complex dynamic scene are remarkably improved.

The invention discloses a lithium battery thermal runaway prediction and multistage response system based on AI intelligent evaluation, and the system comprises a multi-sensing monitoring module, an AI prediction evaluation module, a thermal runaway risk evaluation module, a safety response control module, and a safety execution module. Through fusion of multi-dimensional sensing data and an artificial intelligence algorithm, real-time prediction and evaluation of the thermal runaway risk of the battery are realized, and graded safety response measures are actively triggered at the early stage of thermal runaway. And aiming at different risk levels, the system automatically executes corresponding multi-level protection actions. The system also has online learning and model adaptive optimization capabilities, and can continuously improve the prediction accuracy and response efficiency along with the change of the state of the battery. And the thermal runaway early warning sensitivity and the response timeliness are remarkably improved, and the method has an intelligent level and engineering practicability and can be widely applied to the field of lithium battery safety management of electric vehicle battery packs, energy storage power stations and the like.

The invention discloses an air conditioner host load regulation and control parameter self-adaptive learning method. The method comprises the steps that multi-source real-time data of an air conditioner host is obtained and preprocessed; generating a steady-state identification sequence by adopting layered progressive steady-state analysis, wherein the short-term analysis adopts self-adaptive window variance calculation based on the instantaneous change state of the system; based on the steady-state identification sequence, constructing an event causal relationship graph by adopting an improved causal test algorithm, and determining causal association between regulation and response; integrating the causal atlas, and generating a self-adaptive regulation and control strategy library capable of online learning through density clustering and regression modeling; and responding to a power grid dispatching instruction, and matching and generating an optimal regulation and control instruction sequence from the strategy library. According to the method, through the technical means of hierarchical progressive steady-state analysis, improved causal test, density clustering and regression modeling, an online learning strategy library is constructed, the precision of steady-state detection and load prediction can be improved, and the generalization and self-adaption capability of the model under complex working conditions can be enhanced.

The invention provides a lightweight configurable cue word labeling method and system for a Web system, and relates to the technical field of Web front-end development and man-machine interaction, and the system comprises a front-end labeling plug-in module, a cue word content service module, a cue word management module and an intelligent recommendation module. The front-end labeling plug-in captures text content selected by the user by monitoring a global shortcut key, and allows the user to add prompt words of a text, a rich text or a link type; the prompt word content service module provides an API (Application Program Interface) to realize persistent storage of data; the prompt word management module provides a unified management interface for an administrator; and the intelligent recommendation module automatically judges the prompt word display priority through a candidate recall and sorting algorithm based on the user click behavior data, and continuously optimizes the recommendation result by using an online learning mechanism. The method is integrated to an existing Web system in a non-intrusive mode, business core codes do not need to be modified, the use threshold of the system is remarkably lowered, and precipitation and sharing of business knowledge are promoted.

The invention relates to the technical field of intelligent manufacturing and precision machining, and discloses a skylight guide rail clamp clamping force intelligent regulation and control method and system.The skylight guide rail clamp clamping force intelligent regulation and control method comprises the steps that multi-dimensional sensing data of a skylight guide rail clamp is obtained and preprocessed; acquiring a force displacement data pair and identifying a flexibility coefficient of the guide rail; the elasticity modulus is inversely calculated through the flexibility coefficient, and temperature correction is carried out; calculating theoretical stress distribution and a displacement field, and fusing and correcting the theoretical stress distribution and the displacement field with measured data of the sensor; evaluating stress safety, deformation stability and vibration stability; the current clamping force distribution is adjusted; the clamping force adjustment amount is calculated and converted into a control instruction for adjustment, the guide rail is machined, and quality detection is conducted; updating the quality prediction model, predicting tool wear and calculating compensation; according to the invention, through an online learning and adaptive optimization mechanism, the system can continuously learn and evolve and automatically adapt to changes of production conditions.

The invention relates to the technical field of industrial automation and machine vision, and particularly discloses a baked porcelain plate surface defect online detecting and sorting system based on machine vision. The system comprises an automatic feeding module, a multi-modal image acquisition module, a central data processing module and an intelligent execution sorting module which are arranged in sequence, synchronously acquiring surface information by adopting three imaging units of a bright field, a dark field and a 3D outline; constructing a multi-modal feature fusion defect classification model based on deep learning, and realizing feature fusion through a cross attention mechanism; the integrated model online learning unit is used for realizing incremental learning by adopting an elastic weight consolidation algorithm; the intelligent execution sorting module plans a track according to the defect position and performs sorting through a self-adaptive vacuum chuck array; the device realizes comprehensive detection of various defects such as scratches, pits and chromatic aberration, has the beneficial effects of high detection precision, strong self-adaption, avoidance of secondary damage and the like, and improves the production efficiency and the product quality.

The invention discloses an intelligent sports event decision-making system based on causal-driven multi-modal fusion and spatio-temporal dynamic reasoning. The system comprises a multi-modal causal data acquisition and preprocessing module; a causal-oriented multi-modal knowledge graph construction and updating module, wherein the causal-oriented multi-modal knowledge graph construction and updating module is provided with a causal structure learning algorithm and an online learning framework; a space-time perception hybrid agent module; the causal constrained dynamic decision optimization module is provided with a deep reinforcement learning algorithm; and the interpretability analysis and visualization module is used for receiving the decision strategy sent by the space-time perception hybrid agent module, generating decision explanation according to the decision strategy and visually presenting the decision explanation. The objective of the invention is to construct an intelligent system capable of providing high-precision, interpretable and adaptive decision support by integrating causal reasoning, multi-modal learning and reinforcement learning, so as to significantly improve scientificity and effectiveness of sports event analysis and decision.

The invention discloses a digital twinborn model construction and life prediction method for pressure vessel defect data, and belongs to the technical field of pressure vessel safety assessment, and the method comprises the following steps: a defect topological graph construction and feature extraction step: converting defect space distribution into a graph structure, and extracting features by adopting a graph attention network; a crack propagation physical constraint modeling step: predicting a defect propagation behavior by adopting a physical information constraint neural network; an uncertainty quantification and reliability evaluation step: calculating a confidence interval and a failure probability of the residual life by adopting a Monte Carlo Dropout method; the model parameters are dynamically adjusted through an online learning mechanism, high-precision real-time prediction of defect evolution and reliability evaluation of the residual life are achieved, and the calculation efficiency is improved by more than two orders of magnitude compared with a traditional finite element method.

The invention discloses an industrial network fault intelligent diagnosis method and system based on multi-source data, and the method comprises the steps: synchronously collecting data from a plurality of data sources of an industrial network, and extracting a time sequence statistical feature, a flow entropy feature and a protocol conformity feature to form a multi-dimensional feature vector; establishing a dynamic baseline model by adopting a sliding window online learning method, and calculating a comprehensive anomaly score for anomaly detection; the fault suspicion degree is calculated based on the equipment incidence matrix and the fault propagation model to realize fault source positioning; carrying out fault type identification and root cause analysis by adopting Bayesian reasoning and a knowledge rule base; and outputting a structured diagnosis report containing the fault source, the type, the root cause and the disposal suggestion. According to the invention, early warning, accurate positioning and intelligent diagnosis of industrial network faults are realized, and the operation and maintenance efficiency, safety and reliability of the industrial control network are significantly improved.

The invention relates to the technical field of intelligent scheduling and management and control of a harbor storage yard, and discloses a dynamic self-adaptive intelligent scheduling method of the harbor storage yard, and the method constructs a closed-loop process including environmental anomaly collaborative diagnosis, scheduling strategy dynamic reconstruction, and scheme execution and feedback based on a storage yard three-dimensional digital twinborn model and a multi-objective optimization scheduling model. The method comprises the following steps: collecting operation physical sign data of a plurality of devices in real time, and carrying out collaborative analysis and reasoning on the operation physical sign data, a device performance baseline and a historical environment event database, so as to diagnose hidden physical anomalies; according to the abnormal type and the task attribute, the weight or constraint of the optimization model is dynamically adjusted, and a self-adaptive scheduling scheme is generated; and finally, continuously updating the baseline library and the event library by executing feedback to realize online learning and optimization of the system. According to the method, the defects of a traditional scheduling method in the aspects of three-dimensional visualization, multi-objective optimization and dynamic response of environment anomalies are effectively overcome, and the intelligent level, safety and efficiency of port storage yard operation are remarkably improved.