269 results about "Static model" patented technology

The invention relates to the field of road compactness monitoring, in particular to a road compactness real-time regulation and control method and system based on digital twinning, and the method comprises the steps: collecting vibration acceleration, temperature and position data, and generating a time-space aligned multi-source fusion feature data set after processing; inputting a pre-trained LSTM model to construct a dynamically updated digital twinborn body, and outputting a three-dimensional compaction energy spectrum; dispersing the atlas and calculating parameters, and generating a compaction degree deviation matrix; a regulation and control instruction is generated and issued based on matrix optimization; and according to the measured data and the predicted value residual error, triggering re-optimization and calibrating the sensor. According to the method, the problems of non-uniform compaction quality and over-high energy consumption caused by poor adaptability, decision lag and error coupling of a traditional static model are solved.

The invention discloses a modeling analysis method for optimizing an urban water supply pipe network, and belongs to the technical field of intelligent water affairs, and the method comprises the steps: building a comprehensive pipe network database, collecting hydraulic parameters through Internet of Things equipment, and fusing the hydraulic parameters with GIS topological data; constructing a dynamic hydraulic simulation model, coupling real-time data of a pressure sensor with an EPANET model, and correcting a friction resistance coefficient of a pipe section; a hybrid optimization algorithm architecture is designed, a double-target genetic algorithm is adopted for old pipe network transformation, and a constrained particle swarm algorithm is adopted for new pipe network planning; executing multi-stage optimization calculation, generating a pipe diameter feasible solution space in combination with geographical constraints, and iteratively outputting a scheme meeting a pressure threshold value; and generating a pipe network optimal configuration scheme, and outputting an engineering implementation list through spatial overlay analysis and valve regulation logic. According to the method, the problem of modeling distortion caused by a multi-source data island is solved, the defect that a static model is difficult to adapt to dynamic water demands is overcome, and the economical efficiency and the engineering implementability of a pipe network optimization scheme are remarkably improved.

The invention relates to the field of financial science and technology, and discloses a financial risk dynamic assessment system and method based on artificial intelligence. The system comprises a multi-source heterogeneous data acquisition module which acquires transaction data, public opinion texts and association maps in real time; the adaptive feature engineering module dynamically screens key risk factors; the dynamic risk map construction module calculates a risk conduction coefficient through a map neural network; the multi-modal AI analysis engine cooperatively runs a time sequence prediction model, a text mining model and a graph calculation model; a risk conduction simulator quantifies a systematic risk path. The problems of data splitting processing, model static solidification and correlation risk quantification deficiency in the prior art are solved, the false alarm rate is reduced to 12%, the response speed reaches 90 seconds, the prediction deviation is reduced to 22%, and an interpretable supervision report is generated.

The invention relates to the technical field of water quality monitoring, in particular to an automatic water quality monitoring method and system.The method comprises the steps that multiple pieces of collected water quality monitoring data are combined pairwise, dynamic coupling strength is calculated, a topological network atlas is generated, and automatic extraction and structural characterization of the dynamic coupling relation among complex water quality parameters are achieved; the limitation of dependence on manual feature recognition traditionally is overcome; secondly, matching the topological network atlas with a preset pollution mode feature library, dynamically determining a newly added abnormal mode, and outputting an abnormal feature code set, thereby solving the key defect that a static model cannot recognize an unknown pollution mode; and finally, a water quality monitoring and early warning signal is output by fusing the pollution diffusion prediction result and the abnormal feature code set, so that bidirectional verification of data driving and a mechanism model is realized, and the early warning accuracy of a water quality abnormal phenomenon is remarkably improved.

The invention discloses a mining rock mass structure degradation monitoring method and system based on deep learning, particularly relates to the technical field of mine safety monitoring, and is used for solving the problems of monitoring lag and misjudgment caused by the fact that an existing static model cannot automatically adapt to rock mass damage dynamic evolution. The method comprises the following steps: constructing a dynamic damage incremental data set by collecting multi-source heterogeneous monitoring data under mining disturbance in real time, extracting newly-added damage features, and calculating a distribution offset degree between the newly-added damage features and historical features; when the deviation degree exceeds the limit, verifying and screening a damage feature subset according with a mechanical law based on a rock constitutive equation, and blocking non-physical noise interference; a geological structure evolution mode is matched through damage path dependence modeling, and a potential damage path thermodynamic diagram is generated in combination with a space gradient; performing cross-stage association on the thermodynamic diagram and a historical feature library by adopting a knowledge distillation mechanism to generate a dynamic weight matrix fused with a mining time sequence; and finally, updating the damage assessment model through a parameter reweighting mechanism to realize adaptive assessment of the rock mass degradation risk.

The invention provides a mine water disaster monitoring and early warning method and system based on multi-source heterogeneous data fusion, and the method comprises the steps: collecting multi-source data of a mining area, carrying out the time-space alignment of the multi-source data, and generating a data set, the multi-source data comprising remote sensing data; preprocessing the data, inputting the preprocessed data into a multi-modal fusion network, and extracting surface water body distribution, lithologic permeability, underground water level and structural fracture characteristics to obtain a three-dimensional hydrogeological static model; the hydrological numerical model based on physical driving is coupled with the static model, and the dynamic model is used for simulating the dynamic change of an underground water flow field and a pollutant diffusion path; based on the dynamic model updated in real time, multi-target collaborative evaluation is carried out to evaluate the mining area water resource, ecological and social collaborative effect; and calling an unmanned aerial vehicle to inspect a leakage position or a settlement position in the hydrogeological risk map based on a multi-target collaborative evaluation result. According to the method, the prediction accuracy is improved through the multi-source data.

The invention discloses a power distribution network fault diagnosis method and device based on a large model, a terminal and a medium, and relates to the technical field of power distribution networks. According to the scheme provided by the invention, on the basis of acquired operation data such as topology, electrical quantity and operation environment of a power distribution network, real-time topology dynamic change of the power distribution network is reflected by constructing a dynamic graph attention network model; and multi-modal data features are fused by using a cross-modal attention mechanism, the interference of multi-modal data distribution difference on feature extraction is eliminated, and the robustness of the model to fault diagnosis operation in a complex fault mode is enhanced, so that the problems of fault misjudgment and missed judgment caused by insufficient fusion of a static model and multi-modal data in a traditional method are solved, and the fault diagnosis accuracy is improved. And the power distribution network fault diagnosis accuracy is improved.

The invention discloses a train dispatcher behavior anomaly detection system based on LSTM-FCN and a dynamic intervention method thereof, and relates to the technical field of intelligent monitoring. Scheduling operation time sequence data, environment state data and physiological monitoring data are collected in real time, a space-time joint feature vector is constructed, and a train dispatcher behavior anomaly detection result is obtained. The LSTM-FCN hybrid network is used to extract time sequence dependence features and spatial pattern features, and an attention weight matrix generated by physiological data and a compensation factor matrix generated by environmental parameters are combined to dynamically calculate a comprehensive abnormal probability value; and when the probability value exceeds a self-adaptive adjustment threshold value, triggering a hierarchical intervention mechanism based on the driving scheduling knowledge graph to realize progressive intervention from interface prompting to manual takeover. By fusing multi-modal data and self-adaptive dynamic compensation, the problem of poor adaptability to complex scenes due to adoption of a static model in traditional train monitoring is solved, and the accuracy and intervention timeliness of abnormal behavior detection of the train dispatcher are remarkably improved.

The invention discloses a government affair data processing method, system and device and a storage medium, and relates to the field of intelligent government affair decision, and the method comprises the steps: generating a tamper-proof block chain evidence storage triple through a multi-chain collaborative evidence storage mechanism based on a structured policy vector and government affair data; performing real-time decision matching by adopting a cosine similarity algorithm according to the block chain evidence storage triad, calculating a similarity value of the government affair item state vector and the structured policy vector, and generating a decision execution record when the similarity value reaches a policy compliance reference requirement; based on the decision execution record, starting a multi-chain collaborative auditing mechanism, identifying and positioning illegal operation nodes and generating an auditing report; according to the audit report, the audit data and the policy efficacy weight are optimized through a policy analysis engine, and a government affair data optimization proposal is generated; the policy knowledge graph is constructed by fusing the aging characteristics and the regional parameters through a dynamic quantization algorithm, and the structured policy vector is generated, so that the efficacy evaluation deviation of a static model is effectively solved.

The invention relates to the technical field of railway contact networks, and provides a railway contact network icing thickness prediction method and system. The method comprises the following steps: inputting meteorological environment parameters into a machine learning model, and carrying out dynamic calibration on icing medium parameters based on the meteorological environment parameters by utilizing the machine learning model to obtain calibrated icing medium parameters; obtaining an icing growth coefficient based on the meteorological environment parameters, the conductor physical characteristic parameters and the calibrated icing medium parameters; and inputting the calibrated icing medium parameters and the icing growth coefficient into a Makkonen model to obtain an icing thickness prediction value. According to the technical scheme provided by the invention, the key icing parameters are dynamically calibrated through machine learning, and the computational logic of the Makkonen model is optimized, so that the icing thickness prediction precision under complex meteorological conditions is improved, and the problem of prediction failure caused by insufficient environmental adaptability of a traditional static model is solved.

The invention relates to the technical field of artificial intelligence processing, in particular to a manufacturing and processing system based on artificial intelligence simulation control parameters. According to the manufacturing and processing system, three-dimensional space-time coding is carried out on vibration, temperature and deformation time-varying signals through a multi-mode sensing module; generating a composite feature body including an equipment rigidity distribution matrix, a thermal deformation gradient vector and a material residual stress tensor, and solving the problems of spatial-temporal asynchronization and physical field feature splitting of multi-source data; the parameter resolving module constructs a parameter incidence matrix based on a fractal neural network, combines dynamic constraint conditions of thermal deformation gradient vectors, performs multi-objective optimization on a rigidity distribution matrix and residual stress tensor, generates an initial parameter solution set for eliminating time-lag deviation, and breaks through the nonlinear coupling optimization bottleneck of a traditional static model; and the state dissociation module calls a historical wear feature library to construct a performance attenuation reference surface, and tool accumulated wear and instantaneous thermal deformation disturbance are synchronously inhibited through convolution operation and projection correction of a dynamic compensation factor.

The invention relates to the technical field of intelligent water affair and urban water supply system informatization, in particular to a water supply pipe network hydraulic model calibration and leakage locating method and system, and the method comprises the steps: obtaining the pressure and flow data of a plurality of monitoring points in a pipe network in real time; taking the model as a boundary condition to drive a hydraulic model to carry out real-time simulation, and calculating a theoretical value; calculating a residual error between a theoretical value and an actual value of the monitoring point; judging a triggering model calibration event or a leakage suspicion event based on a residual error abnormal mode; if calibration is triggered, inverting and updating global parameters of the model through an optimization algorithm to realize self-calibration; if leakage is triggered, a suspected area is determined by combining pressure space distribution analysis, and a leakage pipe section is accurately positioned through analog simulation and correlation analysis. Through closed-loop feedback of real-time data and the model, the model can adapt to changes of a pipe network system, dynamic self-calibration of the water supply pipe network hydraulic model is achieved, and the problem of precision attenuation of a traditional static model is solved.

The embodiment of the invention discloses a large model continuous evolution method and system based on multiple modalities, and the method comprises the steps: constructing a real-time access channel of multi-source heterogeneous data, so as to update knowledge, and obtaining a data set from an updated database; based on a dynamic feedback closed-loop mechanism, training a large model by adopting a data set, performing self-correction on the model through user feedback, and outputting the corrected large model and an incremental data set; implementing an anti-forgetting continuous learning scheme on the corrected large model by adopting the incremental data set to enable the large model to learn and consolidate knowledge; s3, performing knowledge fine tuning on the large model output in the step S3 by adopting an efficient knowledge fine tuning technology; and based on the results obtained in the steps S2 to S4, carrying out multi-modal collaborative optimization on the large model, and comparing the learning effects of the large model obtained in the steps. The problems that in existing large model development, the iteration capacity of a static model is lost, the multi-modal feature fusion efficiency is low, and a man-machine cooperation closed loop is not formed yet are solved.

The invention discloses a VGA (Video Graphics Array)-based 5G miniature optical transceiver module self-calibration method, which belongs to the technical field of optical transceiver module self-calibration, and comprises the following steps: S1, establishing a self-calibrated benchmark reference value through an initialization module and collecting environment parameters and benchmark optical parameters; s2, dynamically collecting and receiving optical power and environment change data, and judging whether deviation exceeds a threshold value or not to trigger model retraining by collecting actual operation data of environment parameters and driving parameters and combining a neural network model prediction target value; integration of a new data set and re-fitting of a non-linear relation enable the model to continuously adapt to the influence of long-term factors; key parameters such as a gain coefficient or a temperature compensation curve of a proportional-integral-differential control algorithm are dynamically corrected, long-term precision and reliability of a self-calibration system are guaranteed, and the problem of calibration failure caused by failure of a static model is avoided.

The invention relates to the technical field of data processing, in particular to an artificial intelligence-based person and post matching system, which comprises an acquisition module, a judgment module, an evaluation module, a determination module, an adjustment module, a correction module and a matching module. The method comprises the following steps: acquiring various key data, judging concerned posts in combination with browsing frequency and browsing speed according to keywords of resumes and recruitment, evaluating recruitment indexes and resume indexes by utilizing a model, and determining a candidate post list in combination with historical training frequency and historical promotion speed; the resume index or the similarity threshold value is dynamically adjusted according to the delivery and interview success rate of the candidate post list, the candidate post list is corrected according to the number of times of adjustment, and the recommended post is matched, so that the recommendation result better fits the target and the post, the matching accuracy and effectiveness are improved, and the user experience is improved. The problems of inaccurate matching and slow response speed caused by incomplete data acquisition and excessive dependence on a static model are effectively solved.

The invention provides an AI-driven industrial decarburization process control method and system based on feedback regulation, and relates to the technical field of industrial control, and the method comprises the steps: executing industrial decarburization process monitoring, and obtaining a process operation data stream sequence; performing process working condition time sequence iterative analysis; matching is carried out in a pre-constructed causal knowledge base; traversing the associated causal clue set to perform historical data backtracking exception investigation to obtain an exceptional associated causal clue set and an exception degree set; and performing feedback control scheme identification to obtain a target feedback control scheme, generating a feedback adjustment instruction, and issuing the feedback adjustment instruction to the control execution module to execute the target feedback control scheme. According to the method and the device, the technical problem that in the prior art, due to the fact that static model prediction or empirical rule-based judgment is mainly adopted, real-time tracing and dynamic intervention of process-level carbon emission abnormity are difficult to achieve, and the carbon emission control effect in a complex environment is not ideal is solved, and the control effect of the industrial decarburization process is improved.

The invention discloses an offshore wind turbine foundation scouring full-period intelligent monitoring method and system based on multi-source data fusion and a dynamic coupling model, and relates to the technical field of intelligent monitoring, and the method comprises the steps: deploying a multi-source monitoring module, and constructing a finite element model; carrying out load calculation and parameter inversion; and training full-cycle dynamic updating of the washout failure function model. According to the method, a self-adaptive Kriging-Bayesian method is adopted, a Bayesian inversion framework and a self-adaptive agent model are fused to solve optimal soil body parameters, full-period model dynamic updating based on dynamic monitoring data is achieved, a multi-fidelity deep kernel learning model is adopted, three types of data are fused into a training set, full-period intelligent monitoring of offshore wind turbine foundation scouring is achieved, and the method has the advantages of being simple in structure, convenient to operate and high in practicability. The dynamic identification of soil parameters is realized by combining a self-adaptive inversion framework with a displacement error closed-loop optimization mechanism, and the technical problem that a traditional static model cannot adapt to the spatial-temporal variability of seabed geology is solved.

The invention discloses an automatic order sending recommendation integration system based on a knowledge graph, and relates to the technical field of intelligent recommendation and resource integration. The problems of poor data real-time performance, model staticization, low recommendation accuracy and the like exist in the prior art. According to the invention, operation and maintenance targets, fault features, resource attributes and historical cases are integrated in real time through a dynamic knowledge graph construction module, and a hierarchical multi-modal knowledge network is constructed; the conflict detection module is combined with a rule engine and a probability graph model to detect logic and semantic conflicts; the real-time inference engine realizes multi-constraint path search and multi-target optimization recommendation based on a graph neural network, and outputs a combination scheme of engineers, spare parts and tools; and the feedback closed loop module updates the knowledge graph and recommendation strategy parameters through a reinforcement learning algorithm. The method breaks through the limitation of a traditional static model, remarkably improves the real-time performance, accuracy and dynamic adaptability of order sending recommendation, and is suitable for scenes of enterprise I operation and maintenance, intelligent customer service, logistics scheduling and the like.

The invention belongs to the technical field of dynamic network risk prediction based on knowledge graph driving, and discloses a dynamic network risk prediction method and system based on knowledge graph driving, and the method comprises the steps: firstly obtaining a network security event and a context to construct a knowledge graph, and then detecting entity semantic drift through a preset rule and a deep semantic model, and carrying out node splitting, fusion, renaming or label updating and other structural remodeling on the knowledge graph based on a detection result, and finally carrying out risk prediction by utilizing a graph neural network model. The problem that in a traditional method, a static model cannot adapt to dynamic semantic changes is solved, the recognition capacity of a novel attack mode is improved, the risk detection false report and missing report rate is reduced, and the risk prediction efficiency is improved.

The invention belongs to the technical field of network security, and provides a network threat real-time detection and defense method and system based on artificial intelligence. The method comprises the steps of multi-modal data acquisition and preprocessing, dynamic graph feature engineering and knowledge graph collaborative fusion, dual-adaptive model training and optimization, streaming real-time detection and anomaly scoring, DRL-driven hierarchical defense response and automatic disposal, and feedback-driven model adaptive updating and block chain auditing. According to the method, a mixed model of OS-ELM + dual-adaptive ridge regression + federated learning is designed, the training speed is higher than that of CNN, and over-fitting / under-fitting is avoided by dynamically adjusting a regularization coefficient; the federal learning realizes data local training and parameter uploading, and solves the problem of privacy disclosure; knowledge distillation enables the model volume to be reduced, edge equipment deployment is adapted while the accuracy is maintained, and the generalization ability is obviously superior to that of a traditional static model.

The invention discloses a low-carbon transformation method, system and device for a building air conditioning system. The objective of the invention is to solve the problems of static model, single target, one-sided evaluation and non-standardized process in the existing reconstruction technology. According to the method, building multi-dimensional data are collected; constructing a building energy consumption prediction physical simulation model coupled with a user behavior prediction model based on machine learning to dynamically reflect a real operation condition; a multi-dimensional objective function is defined, and a Pareto optimal transformation scheme set is generated; constructing an evaluation model based on an analytic hierarchy process and a fuzzy comprehensive evaluation method, and calculating a comprehensive evaluation value of each scheme; and selecting an optimal scheme according to the comprehensive evaluation value, and generating a detailed implementation report. The method can scientifically and efficiently determine the global optimal transformation strategy considering energy conservation, carbon reduction, comfort and economy, and significantly improves the scientificity and comprehensive benefits of building transformation decision.

The invention belongs to the technical field of information, and particularly relates to a material set state early warning model based on spatio-temporal characteristics and an attention mechanism, and the model comprises a multi-source data collection and preprocessing module which is used for integrating plan-inventory-supply chain-transportation-production full-link data; the Transform prediction module is responsible for outputting a prediction result; the dynamic optimization module is used for dynamically adjusting parameters such as an early warning threshold value, a time window length and a feature weight through a reinforcement learning mechanism, and forming a'prediction-optimization-re-prediction 'closed-loop feedback mechanism; and the grading early warning output module is used for generating grading early warning grades according to the prediction result and the optimization parameters. According to the model, dynamic early warning of the complete set of states of complex product materials is achieved by accurately capturing the spatial and temporal change rule of the material states, the problems of evaluation lag, data island and static model stiffness of a traditional method are solved, and the prediction accuracy and timeliness are remarkably improved.

The invention relates to the technical field of data testing, in particular to a testing method and system based on large model multi-modal generation and dynamic verification, and the testing method based on large model multi-modal generation and dynamic verification comprises the following steps: initializing a testing system, deploying a pre-trained large model, and generating testing data through the large model; dynamically detecting the generated test data through a preset abnormal mode knowledge base, and feeding back an abnormal result; and according to an abnormal result, reasoning and positioning an abnormal root cause through a preset causal reasoning model, and carrying out interpretable causal analysis output. According to the method, an iteration mechanism of test data generation, detection and feedback can be established, the generation work of the test data is reversely optimized through the abnormal result, all the generated test data can be ensured to pass basic verification, the compliance of the test data is ensured, dynamic detection is performed through the preset abnormal mode knowledge base, and the test efficiency is improved. Compared with a traditional static model, the method is higher in detection accuracy and processing efficiency.

The invention discloses a non-living aquatic product supply chain quality deterioration visual early warning method, and belongs to the field of non-living aquatic product dynamic monitoring, and the method comprises the following steps: S1, synchronously collecting the physical appearance, quality indication labels and environmental parameters of non-living aquatic products, and constructing a multi-dimensional data set; s2, extracting complementary features, and outputting weighted fusion features; s3, establishing a residual shelf life prediction model, and obtaining a residual shelf life prediction value and a confidence interval; s4, based on the residual shelf life prediction value, constructing a supply chain digital twinborn body, and mapping a physical entity state in real time; and S5, continuously optimizing parameters of the residual shelf life prediction model. By adopting the non-living aquatic product supply chain quality deterioration visual early warning method, multi-modal feature deep interaction, digital twinborn visualization and adaptive iteration are fused, a data acquisition-feature fusion-prediction early warning-model evolution closed loop is constructed, and the limitation of a traditional single-modal and static model is broken through.

The invention belongs to the technical field of low-code development platforms, and particularly relates to a low-code platform model construction and dynamic execution method and system based on a hybrid DSL (Digital Subscriber Line), and the method comprises the steps: describing static model information in an application by using a structure DSL in a declarative grammar; defining a behavior DSL in a mounting mode under a corresponding element of the structure DSL; analyzing the structure DSL into a meta-model object tree in the platform, and converting the behavior DSL into an executable expression tree / intermediate representation; jointly driving the meta-model object tree and the expression tree / intermediate representation by utilizing a template engine, and automatically generating at least one application code in a front-end page, a back-end interface and a database script; a common structure DSL and a behavior DSL are combined and packaged into a scene template, and the scene template is stored in a template library so as to be reused by different service scenes, and modularization and templating of service modeling are realized. The complexity of the system is reduced, and the development efficiency and quality are improved.

The invention discloses an automatic blasting scheme optimization system device, and particularly relates to the technical field of intelligent blasting analysis and processing, which comprises a parameter acquisition module, a data processing module, an optimization algorithm module, a simulation verification module, a dynamic control module, a communication module, a safety protection module and a man-machine interaction module, a visual interface is provided for parameter input, scheme adjustment and three-dimensional dynamic display of simulation results, and multi-terminal synchronous operation and remote cooperative control are supported; according to the invention, multi-source sensor groups such as a vibration sensor and a geological radar are integrated, wavelet transform and Kalman filtering algorithms are combined, dynamic acquisition and space-time alignment of parameters such as an internal structure and water content of a rock mass are realized, and a three-dimensional geological model constructed by a data fusion unit can update a rock mass damage state in a blasting process in real time, so that the blasting accuracy is improved. The method has the advantages that the limitation of a traditional static model is broken through, the precision of explosive load calculation is remarkably improved, and dynamic adaptation of complex geological conditions is supported.

The invention discloses a primary and secondary fusion ring main unit fault rapid isolation method and system, and relates to the technical field of power distribution network automation. The method comprises the following steps: acquiring topological characteristics of each node of the ring main unit and performing validity verification to generate an effective topological fingerprint; constructing a dynamic time sequence fault tree model based on the topological fingerprints, and obtaining a minimum cut set with time sequence constraints through space-time decoupling; based on the minimum cut set, a fault isolation strategy is generated through reinforcement learning, and safety verification is carried out; and based on the isolation strategy passing the verification, pre-judging a future topology state through topology deduction and generating a trigger signal. Through dynamic topological feature extraction and verification, reliable basic data is provided for the primary and secondary fusion ring main unit, and the adaptive capacity of the primary and secondary fusion ring main unit in a topological change scene is enhanced; by means of dynamic time sequence fault tree modeling, the fault evolution law is accurately captured, the limitation of a traditional static model is broken through, and the accuracy of fault positioning is improved.

The invention relates to the technical field of energy conservation, in particular to an intelligent management system for electric appliance efficiency improvement and carbon emission reduction, which comprises a data acquisition and monitoring module, a data analysis and evaluation module, an intelligent optimization control module and a user interaction and management module, compared with the problems of low precision and poor real-time performance caused by adoption of a static carbon emission factor method in the prior art, the technical breakthrough is realized through hybrid modeling: Monte Carlo simulation generates million-level working condition samples based on Latin hypercube sampling, and high-fidelity physical constraints are constructed in combination with an energy flow balance equation; the defect of insufficient sample coverage of a traditional method is overcome; the BP neural network captures a process-power grid-environment nonlinear coupling relation through thousand groups of sample training, a dynamic weight adjustment mechanism responds to power grid carbon intensity fluctuation in real time, and the limitation that a static model cannot adapt to real-time working conditions is broken through; the confidence interval output mechanism quantifies the prediction uncertainty, and compared with traditional point estimation, the decision reliability is improved.

The invention discloses a load transfer method, system, equipment and medium considering new energy and load power fluctuation, and belongs to the technical field of relay protection, and the method comprises the steps: taking a switch motion moment as a first stage of load transfer, taking a set time after the switch motion as a second stage of load transfer, building a dual-stage load transfer model, and taking the set time as a second stage of load transfer; obtaining a load transfer scheme; double-stage constraint verification is executed, and operation constraint verification is carried out on the load transfer schemes of the first stage and the second stage; introducing a constraint out-of-limit penalty factor, and quantifying the degree of the load transfer scheme deviating from the constraint condition; constructing a load transfer scheme comprehensive evaluation function, and performing weighted integration; and optimizing the load transfer scheme comprehensive evaluation function by adopting an improved binary particle swarm algorithm, and determining an optimal load transfer scheme. According to the method, the limitation of a traditional static model is overcome, and the problem of operation constraint violation caused by photovoltaic output change is avoided.

The invention discloses a ground vegetation leaf area index remote sensing inversion method based on a remote sensing image. The method comprises the following steps: data acquisition and preprocessing; performing multi-scale space-time non-local filtering fusion; dynamic feature extraction; carrying out transfer learning fine tuning; time sequence deep learning integration; and model output and post-processing. According to the invention, through multi-source space-time fusion and dynamic feature distribution, vegetation LAI inversion with high resolution and high continuity is realized; the transfer learning and the time sequence deep network enhance the adaptability of the model to a new region and time sequence change; the stability and reliability of large-scale application are guaranteed through full-process automation and uncertainty evaluation, and the model is obviously superior to an existing single-source or static model.