284 results about "Reference model" patented technology

The invention relates to the technical field of network security and data protection, and discloses a data leakage prevention method and system based on user behavior perception, and the method comprises the steps: obtaining historical operation data, and constructing a personalized behavior reference library; monitoring a current access behavior in real time by sliding a time window, calculating a deviation degree and triggering anomaly detection; performing multi-level feature analysis on the abnormal behavior and calculating a comprehensive abnormal score; dynamically adjusting the access authority according to the score, recording an abnormal behavior and carrying out relevance matching; optimizing the reference model through feedback learning; and evaluating the credibility and the risk level based on an accurate modeling result, and adaptively adjusting permission configuration. According to the method, the user behavior rule can be accurately captured, the data leakage risk can be efficiently identified, the access permission can be dynamically adjusted, the false alarm rate can be reduced, adaptive protection can be realized, and data security and business smoothness can be guaranteed.

The invention relates to the technical field of nondestructive testing, and particularly discloses an automatic detection system and method based on a titanium plate welding part, and the method comprises the steps: obtaining an original physical field signal of a to-be-detected part under the excitation of a single energy field, and extracting a space energy attenuation gradient and time phase lag distribution through wavelet packet decomposition and Hilbert transform; constructing a dynamic propagation model for describing a signal propagation path evolution rule, and performing space-time registration and vector difference calculation with a preset ideal reference model to generate a difference evolution graph; high-dimensional topological feature mapping, density clustering and multi-scale persistence analysis are carried out on the atlas, and a stable abnormal mode caused by defects is identified and confirmed; and backtracking a dynamic evolution path of an abnormal mode, extracting defect core parameters, and completing three-dimensional positioning, type classification and security level evaluation in combination with process information.

The invention relates to a power distribution network distributed energy bearing capacity assessment method and device. The method comprises the following steps: carrying out topology analysis on a network structure of a power distribution network to obtain an initial network topology model; obtaining a node dynamic feature data set based on the initial network topology model and the distributed energy access point data of the power distribution network; wherein the node dynamic characteristic data set comprises operation parameters of each node of the power distribution network in different load scenes; generating a parameter incidence matrix according to the node dynamic characteristic data set, and obtaining a bearing capacity reference model of the power distribution network according to the parameter incidence matrix and real-time data of the power distribution network in an operation state; wherein the parameter incidence matrix is used for quantifying the coupling degree between the operation parameters; and obtaining a risk distribution mapping graph according to the bearing capacity reference model, and identifying a potential overload area of the power distribution network based on the risk distribution mapping graph. According to the invention, power distribution network operation risk assessment can be accurately realized.

The invention provides a steel surface defect detection method and device, equipment and a storage medium. Relates to the technical field of image recognition. The method comprises the following steps: collecting steel surface defect images, and performing data enhancement processing on the steel surface defect images to obtain a data set after data enhancement; a backbone and neck network of a reference model YOLOv11s network is improved, an ECS-YOLOv11s model is constructed by adopting a multi-scale feature fusion mode, a data set after data enhancement is input into the ECS-YOLOv11s model to train and shoot and collect steel surface images in real time, the steel surface images are input into the trained ECS-YOLOv11s model, and a steel surface defect detection result is obtained. According to the method, the steel surface defects can be accurately and efficiently recognized, meanwhile, the needed calculation amount and parameters are reduced, and the requirement for deployment on mobile equipment can be met.

The invention discloses a roadside guardrail deformation detection method based on image and point cloud fusion and related equipment, and the method comprises the steps: collecting a guardrail region image through a high-definition camera carried by an unmanned plane, and synchronously collecting the point cloud data of a guardrail region through a laser radar; then, a joint calibration and iterative nearest algorithm is used for carrying out space-time registration on the guardrail area image and the point cloud data which are synchronously collected, and a multi-modal data set is generated, so that the problem of space-time dislocation caused by sensor movement is solved; an improved double-branch deep learning model is adopted to respectively extract image texture features and point cloud geometric features from a multi-modal data set, and the two features are fused to overcome a single-modal defect; and extracting the contour of the guardrail beam plate from the fusion feature map, aligning the contour of the guardrail beam plate with the reference model, and carrying out quantitative calculation to quantify the deformation degree of the guardrail and realize quantitative detection of the deformation of the guardrail.

The invention relates to the technical field of backhaul monitoring, in particular to a backhaul link monitoring method and system applied to a 5G base station, and the method comprises the steps: collecting physical signal statistical data, backhaul service data and network topology data of a backhaul link in real time; according to physical signal statistical data, a physical layer entropy value is calculated through a Shannon entropy formula, and recessive degradation characteristics of a physical layer are quantified; a pulse neural network space-time coding mechanism is used to generate business layer anomaly prediction parameters, and cross-layer anomaly prediction is realized; according to service types and priorities, constructing a time-varying service awareness reference model by adopting a chaos kinetic equation to serve as a dynamic judgment reference; when the return state is abnormal, combining the physical layer entropy and the network topology data to construct a feedback correction loop, and generating a self-adaptive protection strategy; according to the method, advanced prediction and accurate positioning of recessive degradation of the backhaul link are realized, and the self-healing capability and the service quality guarantee level of the backhaul link in a multi-service scene are improved.

The invention relates to the technical field of refrigeration house energy-saving control and digital twinning, in particular to a refrigeration house fan energy-saving operation method and system, and the method achieves the whole-field temperature deduction of a sensor-free area by constructing a CFD reference model and simulating and predicting the three-dimensional transient airflow and temperature distribution in a refrigeration house. Model parameters are calibrated through measured data, and the order of the model is reduced by adopting intrinsic orthogonal decomposition and Galerkin projection, so that the calculation amount is remarkably reduced, and online optimization is supported. And in combination with a data assimilation algorithm, the prediction result of the reduced-order model is continuously corrected, and the adaptability to environment change and system aging is improved. The optimization control stage takes minimization of the total energy consumption of a fan as a target, solves an optimal fan control sequence under the hard constraint that the whole-field temperature does not exceed the cargo safety upper limit and does not exceed the cargo safety lower limit, and adopts a rolling time domain mode for execution to realize collaborative optimization of safety and energy conservation.

The invention discloses a chemical plant safety early warning and multi-dimensional correlation analysis method and device and a storage medium. By collecting equipment operation parameters, personnel operation and environment data, a reference model library is constructed to realize dynamic threshold early warning; after the early warning is triggered, calculating a first correlation index, a second correlation index and a third correlation index respectively by adopting time sequence similarity analysis, historical statistical analysis and process knowledge graph reasoning; and positioning the core inducement through multi-index weighted fusion. The problems that a traditional method is poor in early warning adaptability, weak in system collaboration and insufficient in tracing depth are solved, and accurate early warning, deep tracing and closed-loop management are achieved.

The invention relates to the technical field of risk assessment optimization, and discloses a risk assessment method based on statistical model optimization. The method comprises the following steps: acquiring a running state data set of a target object containing multi-dimensional monitoring index time sequence data; and inputting the operation state data set into a pre-trained reference risk assessment model, and generating an initial risk score and risk distribution characteristics. And iteratively adjusting parameters of the reference risk assessment model through a dynamic correction algorithm according to the generated risk distribution characteristics, and generating an optimized risk assessment model. And adopting the optimized risk assessment model to re-assess the same operation state data set, and outputting a corrected risk score and a key risk area identifier. According to the method, the risk distribution characteristics of the specific data of the target object under the reference model are analyzed, and the model parameters are dynamically adjusted, so that the risk assessment standard better fits the actual risk mode, the accuracy and pertinence of risk identification are improved, and a more reliable basis is provided for a risk management and control decision.

The invention relates to the technical field of generator state monitoring, in particular to a leakage detection method and system for an ORC generator set, and the method comprises the steps: firstly, synchronously collecting system key operation parameters and environment concentration data; then, matching the pressure value with a pre-generated and load-divided leakage-free reference model, and calculating a theoretical pressure value and a real-time deviation; and a three-dimensional state judgment matrix is innovatively constructed and applied to perform combined logic judgment on a pressure deviation level and an environment concentration level, so that step-by-step diagnosis from micro-leakage early warning to serious leakage alarm is realized. After the leakage is confirmed, the leakage rate can be estimated, and the possible leakage area can be positioned in an assisted manner. According to the method, early-stage, sensitive, automatic and intelligent detection and diagnosis of leakage of the ORC generator set are realized, and the operation safety and the maintenance efficiency of the set are remarkably improved.

The invention discloses a data center dynamic air-conditioning load rapid calculation method, which comprises the following steps of: 1, summarizing data center cold load influence factors as an input condition of a calculation model; 2, constructing a standardized data center reference model based on building energy consumption simulation software; 3, based on the building geometrical characteristics and thermal performance of the target data center, correcting the enclosing structure load of the reference model by adopting an area correction method, and constructing an enclosing structure load rapid calculation model; 4, automatically resetting an internal heat source load calculation result, and constructing an internal heat source load rapid calculation model; 5, correcting the fresh air load of the reference model by adopting a volume correction method based on the geometric characteristics of the target data center building, and constructing a fresh air load rapid calculation model; and step 6, forming a target data center dynamic air-conditioning load rapid calculation method, and obtaining a hourly cooling load prediction result required for covering the whole year or a design stage.

The invention relates to the technical field of power system equipment state monitoring and fault diagnosis, in particular to a GIS basin-type insulator operation state evaluation method and system, and the system comprises an asset information and baseline modeling module which is used for building a high-fidelity multi-physics field finite element reference model and generating a defect state-external representation mapping data set; the physical information driven agent model generation module is used for constructing a neural network agent model fusing physical law constraints; the real-time data acquisition and feature extraction module is used for acquiring and processing online monitoring data such as UHF, gas, temperature and vibration; the state inversion and digital twinning calibration module is used for inverting internal defect parameters by adopting a Bayesian inference and MCMC method so as to realize real-time calibration of the model; and the evaluation diagnosis and life prediction module carries out fault mode identification and residual life prediction based on the calibration model.

The invention discloses a voice-driven mechanical element modeling method and system. A user inputs a natural language instruction containing a design intention into the CAD system through voice, and the natural language instruction is analyzed into a structured operation instruction; meanwhile, selecting a reference model, generating a geometric code corresponding to each surface based on a local geometric attribute corresponding to each surface of the model, and constructing a geometric structure coding matrix; predicting each machining surface in the machining features by using the machining surface prediction network to obtain a sequence formed by all machining surface IDs of the machining features in sequence, and recording the sequence as a machining surface ID sequence; and finally, executing API (Application Program Interface) calling of the CAD platform, and finally obtaining a model of the target mechanical element. According to the method, by connecting the high-level design intention and the bottom-level geometric operation of a designer, the tedious interaction and cognitive burden caused by manual selection and operation of low-level geometric elements (points, edges and surfaces) in traditional direct modeling is avoided, and the design efficiency is remarkably improved.

The invention discloses an abnormal data real-time filtering method and system based on edge computing in a dynamic environment system, the method is executed by an edge computing gateway, sliding window weighted average preprocessing is equivalently realized by adopting integer shift operation, and the single computing overhead is controlled within 50 clock cycles; dynamically and adaptively adjusting dynamic reference model parameters based on the ratio of the network load to the sensor sampling frequency; performing multi-stage anomaly filtering of a hard threshold value, a mutation rate and a statistical interval on the data through a three-stage pipeline judgment structure executed by atomization; an FPGA hardware queue manager independent of a main processor bypasses a TCP stack to push abnormal data at the highest priority, and redundant data is stored in a zero-copy annular buffer area managed by DMA. According to the invention, the problems of intranet congestion, server I / O bottleneck and alarm delay under the centralized architecture of the traditional dynamic loop system are solved, and the fault, fault, fault, fault, fault and fault are realized on resource-limited platforms such as Cortex-M4 and the like; the average alarm delay is 8 milliseconds; and the data compression rate is more than 90%.

The invention discloses a B5G base station T / R assembly health measurement method and system based on sparse projection and a hidden Markov model, and the method comprises the steps: collecting the multi-source operation data of a T / R assembly, and constructing a multi-dimensional operation parameter time sequence; a sparse projection matrix is constructed through covariance analysis and eigenvalue decomposition, and high-dimensional operation parameters are mapped into low-dimensional sparse health eigenvectors; training a hidden Markov model based on the feature sequence in the normal state, fitting an observation probability by using a Gaussian mixture model, and establishing a normal state reference model; calculating a KL distance between the current feature sequence distribution and the reference distribution, and mapping the KL distance into a normalized health degree index; and adaptively determining a state division threshold value by using a K-means clustering algorithm to realize health state grading of the T / R assembly. According to the method, environmental noise is effectively stripped through sparse projection, the dynamic reference model is utilized to adapt to complex working conditions, and online sensing and accurate evaluation of early weak degradation of the B5G base station assembly are realized.

The invention relates to a self-correction hybrid power regulation method based on working condition compensation. The method comprises the following steps: monitoring and collecting a group of system real-time data streams; accessing a three-dimensional mapping model and indexing a group of load segmentation thresholds matched with the real-time system working conditions; generating a power reference value and a real-time power calculation value respectively by using the real-time data and the load segmentation threshold value; judging whether interval offset occurs or not based on the change trend of the real-time system load, and resetting the real-time power calculation value by using the power reference value when the interval offset occurs; monitoring a correction offset generated during resetting, and performing three-dimensional mapping on the model based on the correction offset; and outputting the reset real-time power calculation value as a final power regulation instruction. The method can utilize the high resolution characteristic of real-time parameters, and also can periodically correct accumulative errors through a reference model capable of being adaptively updated, so that high-precision and long-period stability can be realized at the same time under complex and changeable working conditions.

The invention relates to the technical field of Beidou reference correction, in particular to a Beidou-based space-time reference dynamic correction method. The method comprises the following steps: firstly, collecting Beidou multi-frequency-point observation data, and preprocessing by adopting a Kalman filtering algorithm; then, based on the preprocessed data, a base station network time synchronization mechanism is established by using Beidou satellite signal propagation time difference, spatial reference data of different base stations are integrated through a multi-sensor fusion algorithm and a least square method, and smoothing processing is performed by using a spatial interpolation algorithm; thirdly, selecting an optimal baseline combination based on a space-time synchronization result, constructing a difference observation equation of a Beidou multi-frequency carrier phase and a pseudo range, fixing integer ambiguity by adopting an LAMBDA algorithm, and establishing a unified space-time reference model; and finally, resolving the clock error of the high-precision receiver by utilizing the double-difference integer ambiguity constraint, generating a correction parameter, and dynamically adjusting and updating the correction parameter by adopting a model algorithm. According to the invention, high-precision dynamic correction of the space-time reference is realized.

The invention provides a tunnel static excavation digital twin operation method and system and a computer readable storage medium, and the method comprises the steps: inputting the feature data of a rock mass in front into a pre-trained tunnel surrounding rock grade prediction module, enabling the tunnel surrounding rock grade prediction module to output a static excavation mode, and carrying out the construction according to the static excavation mode, the method comprises the steps that a surrounding rock grade prediction module is established, a real-scene model is established based on the three-dimensional laser scanning technology in the excavation process, then the real-scene model and a pre-established BIM reference model are aligned to form an over-excavation and under-excavation analysis model, then an over-excavation and under-excavation area is obtained through the over-excavation and under-excavation analysis model, and the surrounding rock grade prediction module and the over-excavation and under-excavation analysis module are linked in real time, so that the surrounding rock grade prediction accuracy is improved. According to the method, excavation deviation data and surrounding rock grades are automatically synchronized to a BIM reference model, support parameters are dynamically adjusted, model precision is continuously optimized by utilizing construction feedback data, a digital twin model covering a static excavation construction period of a tunnel is formed, tunneling efficiency, construction safety and resource utilization rate are further improved, and engineering cost is reduced.

The invention discloses a hydropower engineering electromechanical equipment installation detail control method based on a three-dimensional laser scanning technology, and the method comprises the steps: S1, setting and determining the instrument parameters of a three-dimensional laser scanner, and collecting the point cloud data of a target region through the three-dimensional laser scanner; s2, remotely reading the point cloud data through a computer, uploading the point cloud data to a cloud database in a file stream form, and storing the point cloud data; s3, performing iterative fitting on the plane model by using a random sample consensus algorithm RANSAC and removing inner points, fitting a target ball model by multiplexing the RANSAC algorithm in the residual point cloud data after the plane model is removed, and screening target ball parameters with the maximum number of inner points; s4, constructing a combined reference model based on the electromechanical equipment to be installed and the virtual target ball, and performing coordinate deviation value comparison with the actually measured target ball model to obtain a deviation value; and S5, generating an installation detail adjustment scheme according to the coordinate deviation value, and sending the adjustment scheme to a mobile client of the field installation personnel.

The invention relates to the technical field of motor rotor production monitoring, in particular to an intelligent monitoring method and system for motor rotor production based on the Internet of Things. The method comprises the following steps: collecting equipment operation data of motor rotor production equipment; obtaining a reference model and a health data subset based on the health multi-dimensional sequence data set; obtaining a multi-dimensional mean vector based on the average condition of the multi-dimensional data vectors in the sliding time window; acquiring a working condition fluctuation index; determining the corresponding sliding time window as a working condition stable window based on the working condition fluctuation index; constructing a temporary model of each working condition stable window, obtaining average path similarity, and calculating a drift quantitative index of data in each working condition stable window; and when the drift quantitative index is greater than a preset drift threshold value, an updated isolated forest model is constructed, abnormity monitoring is performed on the multi-dimensional data vector, an abnormity score is calculated, and early warning information is sent, so that the intelligent level and the operation and maintenance efficiency of motor rotor production monitoring are improved.

The invention relates to the technical field of vehicle fault diagnosis, and discloses a vehicle anomaly detection system and method based on multi-modal data analysis, and the system builds a time zero point alignment relation between control domain data and a high-frequency vibration signal through a hardware synchronous triggering unit by using a level pulse; performing angular domain resampling on the non-stationary vibration signal by adopting a coarse-fine coupling phase locking technology and combining rotating speed polynomial fitting and instantaneous frequency ridge line extraction; the system constructs a virtual reference model by using a deep neural network, and deduces a predicted ideal angular domain characteristic spectrum of a current working condition according to a dynamic state vector; and on the basis, calculating the residual error of the actual spectrum and the predicted spectrum, removing noise through order correlation mask filtering, and judging abnormity based on the mahalanobis distance of a residual error vector and a statistical threshold value. The method effectively solves the problems that the signal is not stable and weak fault features are difficult to extract under the variable speed working condition, and improves the detection accuracy.

The invention relates to the technical field of target detection and deep learning, in particular to an image small target detection method based on an improved YOLOv11 algorithm. Aiming at the problems of insufficient features, background confusion, scale change, limited computing resources and the like in small target detection, YOLOv11n is taken as a reference model, a multi-branch feature extraction module (CFE) and a sparse attention mechanism-based context capture module (CBF) are innovatively introduced, and efficient multi-scale attention (EMA) and a scale dynamic loss function (SIIOU) are combined. According to the main technical scheme, the method comprises the following steps: integrating a CFE module in a backbone network to enhance the small target feature extraction capability; long-distance context semantic information is captured by using a BiFormer attention mechanism through a CBF module; eMA is introduced into the neck network to establish short-range and long-range dependence; and dynamically adjusting the weight by adopting an SDIOU loss function so as to improve the small target sensitivity. According to the method, the feature extraction effect of the image can be remarkably improved, the detection precision is improved, meanwhile, the parameter quantity is only 2.46 M, and the method is suitable for real-time application scenes such as unmanned aerial vehicles, aerospace and detection.

The invention relates to the technical field of data processing and intelligent environment control, in particular to a sleep environment feedback control data processing method based on cognitive behavior therapy logic, which comprises the following steps: a reference model construction step: acquiring a non-contact multi-mode time sequence signal, and reconstructing a reference signal balance curve to construct a target signal manifold model; a simulation flow generation step of converting the preset interference characteristics into signal modulation operators and injecting the signal modulation operators into the model to generate a simulation signal flow; a double-track difference calculation step: executing double-track difference operation to respectively extract residual features representing system deviation and theoretical interference; a similarity judgment and control step: calculating the topological similarity of the residual features in a time-frequency domain, judging a deviation dominant type, generating a corresponding control instruction, and driving an execution mechanism to act; according to the method, psychological anxiety and environmental discomfort are effectively distinguished by using a double-track differential mechanism, and accurate attribution analysis of sleep interference sources is realized.

The invention discloses an engineering construction site real-time three-dimensional modeling method based on an unmanned aerial vehicle aerial image, and relates to the technical field of computer vision, and the method comprises the steps: collecting inclined image data and high-frequency pose data, obtaining sparse key point features, depth semantic features and high-frequency time sequence features, generating a three-dimensional space point cloud model, and recognizing a low-confidence region. And comparing the three-dimensional space point cloud model with the semantic tag with a dynamic semantic three-dimensional model of a previous period as a reference model to identify a semantic change area and semantic state conversion conforming to preset construction logic, constructing a dynamic semantic three-dimensional model of a current period, and generating an unmanned aerial vehicle flight parameter adjustment instruction. According to the method, the three-dimensional modeling quality is improved through cross-view semantic consistency verification, progress changes are interpreted based on construction logic, a building information model and time sequence prediction are combined, and high-confidence data support is provided for construction site management by solving a multi-objective optimization function and deciding unmanned aerial vehicle collection operation.

The invention relates to the technical field of fire safety and simulation training, and discloses a rule-driven fire-fighting real smoke and real fire training simulation system, which comprises a data acquisition and modeling module, a rule driving module, a rendering output module and a training evaluation module. The data acquisition and modeling module is used for acquiring initial fire data and constructing a reference model of smoke diffusion and fire spreading; the rule driving module simulates the non-synchronous evolution process of the fire through a particle simulation algorithm, a time coordination rule and a feedback loop algorithm; the rendering output module is used for integrating the environment rendering data and the multi-factor propulsion mode and generating a training effect evaluation index; and the evaluation optimization module judges whether the simulation precision of the reference model reaches a preset standard or not according to the training effect evaluation index until a simulation result meeting a precision requirement is obtained. According to the invention, the reality and accuracy of fire-fighting simulation training are improved.

The invention relates to the technical field of air tightness detection, in particular to an air tightness detection method and system for a plastic pipe connecting piece, and the method comprises the steps: obtaining real-time pressure data and associated temperature data of the interior of a detected plastic connecting piece in an inflation and pressure maintaining process; inputting the real-time pressure data into a temperature and pressure coupling model for pressure value compensation correction to obtain a compensated pressure value only reflecting the leakage effect; performing time sequence change analysis on the compensated pressure value, and identifying and determining a starting time point when the pressure enters a stable state; extracting the dynamic attenuation characteristic of the compensated pressure value; and performing matching degree calculation on the dynamic attenuation characteristics and the reference model of the leakage-free basis behavior to generate an air tightness detection result of the plastic pipe connecting piece. According to the invention, the problem of interference of non-leakage factors such as environment temperature in air tightness detection is effectively solved, the inhibition capability of interference of non-leakage factors such as temperature is enhanced, and the accuracy and reliability of a detection result are improved.

The invention belongs to the technical field of building energy conservation, and provides a roof system energy efficiency optimization management method and device based on digital twinning. The method comprises the following steps: acquiring real-time monitoring data, determining a digital twinborn body, and determining an energy consumption evaluation index; calculating a comprehensive energy consumption value to determine a target control parameter generation optimization scheme; a control instruction is generated and sent to the execution terminal; calculating a difference coefficient to calibrate the digital twin; and performing energy-saving transformation and equipment updating by taking the calibrated digital twin as a reference model. According to the invention, accurate monitoring and optimal control of the energy consumption of the roof system can be realized, the energy utilization efficiency is improved, and the building operation cost is reduced.

The invention belongs to the technical field of verification of an electric digital integrated module, and provides a verification method and system for a reusable storage module based on a UVM (Universal Verification Module), and the method comprises the steps: simulating a multi-host concurrent access scene through a UVM component, and generating and synchronously outputting an excitation signal to a to-be-verified storage module and a reference model; acquiring a reference operation result and an actual operation result generated by the to-be-tested storage module according to the excitation signal; according to the design function points of the to-be-verified storage module, the actual operation result and the reference operation result are compared and verified, and a verification result is obtained; if the verification result is that at least one design function point in the actual operation result and the reference operation result is inconsistent, it is judged that the function of the to-be-verified storage module is abnormal in the multi-host concurrent access scene, and key signal waveform data and key log data of the to-be-verified storage module are recorded and reported. According to the scheme, the comprehensiveness and the accuracy of verification are improved, and the function reliability and the verification efficiency of the storage module in a complex concurrent environment are improved.

The invention relates to a photovoltaic power prediction method based on a multi-task neural network and physical constraints, and aims to solve the problem that a traditional prediction model is difficult to give consideration to physical rules and dynamic meteorological characteristics, and the method comprises the steps: carrying out the deep fusion of a data-driven feature extraction module, a physical constraint module and a time reasoning module; a multi-task neural network framework combined with physical information is constructed, and high-precision site-level prediction of photovoltaic power on the time scale of 4 hours and 15 minutes is achieved. Experimental results show that compared with a reference model, the prediction precision of the method is improved by 5.5%-38.6% within the prediction intervals of 4 hours and 15 minutes, the problem of uncertainty of photovoltaic power prediction under meteorological disturbance is effectively solved, and reliable technical support is provided for new energy grid-connected regulation and control.

The invention relates to a limited space operation safety monitoring method based on multi-sign parameter intelligent judgment, which comprises the following steps of: training a single-class support vector machine model by utilizing historical data, and establishing a normal physiological state multi-dimensional reference model under each operation content; the method comprises the following steps: acquiring current operation content in a limited space, determining a vital sign parameter set needing to be monitored, and collecting real-time vital sign data of an operator through a user terminal; calculating a comprehensive abnormal score AS of the real-time vital sign data, and when the comprehensive abnormal score AS exceeds a dynamic threshold value delta, marking the data as comprehensive abnormal data; marking the vital sign parameter with the maximum contribution degree absolute value in the abnormal parameters as a key vital sign; and sending alarm information to a monitoring terminal, wherein the alarm information comprises the identifier of the key vital sign. By comprehensively analyzing the real-time vital signs and comparing the real-time vital signs with the dynamic threshold value, the accuracy of abnormal person recognition is effectively improved.