287 results about "Bayesian algorithm" patented technology

The invention relates to the technical field of state detection and fault diagnosis, in particular to an intelligent early warning and fault diagnosis system for a thermal power plant, which comprises a multi-source data acquisition module for acquiring data in real time; the edge computing node is used for performing noise filtering and abnormal value correction on the acquired data; the digital twin modeling unit is used for constructing a dynamic simulation model of the equipment based on a physical model and historical data; the hybrid analysis engine is used for positioning early abnormal detection and fault sources; the visual early warning interface is used for dynamically displaying the health state and the fault probability of the equipment and generating a graded alarm signal; according to the invention, the multi-source data acquisition module acquires equipment multi-dimensional signals in real time, after edge computing node filtering and denoising, a digital twin modeling unit constructs a precise simulation model, a hybrid analysis engine fuses LSTM and a Bayesian algorithm, fault features are deeply mined, data weights are optimized, and the fault detection accuracy is improved. According to the system, the accuracy and timeliness of diagnosis are remarkably improved.

The invention provides an energy storage system power distribution method based on battery pack health state prediction, and the method comprises the steps: constructing a hybrid neural network model for predicting the health state of a lithium ion battery through combining a convolutional neural network and a long short-term memory network, and optimizing the parameters of the hybrid neural network model through employing a Bayesian algorithm. The battery pack health state prediction precision of the model is improved; in combination with the provided lithium ion battery prediction model, a battery pack charging / discharging priority ranking rule based on an entropy weight method is provided; a battery pack power optimization distribution strategy is established by taking the consistency of the state of charge of the battery pack as an objective function and taking the state of charge and the state of health of the battery pack as evaluation indexes, so that energy optimization distribution of the energy storage system is realized, the service life of an old battery is prolonged, overcharge and overdischarge of a single battery are avoided, and balance of the state of charge of the battery pack is realized.

The invention discloses a heterogeneous sensor fusion method and system for dynamic covariance optimization, and the method comprises the steps: constructing a multi-source heterogeneous sensor network which comprises an underwater inertial navigation unit, a Doppler velocity sensor, an ultra-short baseline positioning system, a submarine topography matching device and a geomagnetic gradient detector; the method comprises the following steps: designing a distributed integrated navigation system by adopting a hierarchical fusion architecture, establishing a sensor confidence coefficient dynamic evaluation model based on online estimated error covariance matrix eigenvalue analysis, carrying out state prediction on a local filter level by applying Kalman filtering, and then carrying out measurement updating by adopting a novel variational Bayesian algorithm; a sensor autonomous switching and adaptive weighted dual-mode adjustment mechanism is developed on the main filter level, and self-healing improvement of navigation precision in a non-stationary environment is realized, so that the problems of dynamic reliability evaluation and fusion efficiency optimization in underwater multi-sensor multi-source navigation are solved.

The invention discloses an underground anti-seepage structure leakage monitoring method and system based on discrete time, and relates to leakage detection. The method comprises the following steps: collecting transient electromagnetic response data generated by an excitation signal; according to the initial conductivity parameter and the electrode position parameter of the monitoring area, establishing a three-dimensional geophysical model of the monitoring area through a full waveform inversion algorithm; obtaining electromagnetic abnormal data by using a finite element forward modeling algorithm; according to the temperature data, a distributed temperature field analysis method is adopted to calculate the space gradient and the time change rate of the temperature, and temperature abnormal data are obtained; according to the pressure data and time sequence change characteristics of the pressure data, determining pressure abnormal data; fusing the electromagnetic abnormal data, the temperature abnormal data and the pressure abnormal data by using a Bayesian algorithm to obtain fused data; and inputting the fusion data into a pre-trained machine learning model to obtain a leakage detection result. Aiming at the low dynamic leakage monitoring precision of the underground anti-seepage structure, the dynamic monitoring precision is improved.

The invention discloses a karst development area geological disaster identification method and system based on artificial intelligence, relates to the field of geological disaster early warning and risk assessment, and solves the problems that it is difficult to integrate geology and related data, it is difficult to construct a model to predict disaster categories based on historical disaster cases and real-time monitoring data, and the risk assessment efficiency is improved. The technical problem of lack of association of a prediction result with a geographic space to generate a risk distribution map and dynamically update a high-risk area is solved; comprising the following steps: introducing multi-source heterogeneous data, and combining historical geological disaster cases; preprocessing the data; extracting underground water level change rate, soil humidity and vibration frequency characteristics; combining a plurality of features into a feature matrix, and projecting the feature matrix to a principal component space; after training the model by using a random forest algorithm, optimizing the constructed model by combining cross validation with a Bayesian algorithm; the model prediction result is converted into a risk level value through a mapping rule; and generating a risk level distribution map based on the GIS data.

The invention discloses a shield tail sealing failure intelligent judgment method and device. The method comprises the steps that gap data of a duct piece and a tail shield, external soil mass pressure data and grease state data are obtained; inputting the gap data into a shield attitude abnormity early warning model, and outputting a first prediction result; inputting the external soil body pressure data into an external soil body abnormity early warning model, and outputting a second prediction result; the external soil body abnormity early warning model is used for determining an external soil body pressure sudden change turning point; inputting the grease state data into a grease abnormity early warning model, and outputting a third prediction result; the grease abnormity early warning model is used for determining whether the grease contains water, whether the grease temperature is abnormal and whether the grease pressure is abnormal according to the grease state data; and based on a Bayesian algorithm, carrying out fusion processing on the first prediction result, the second prediction result and the third prediction result, and outputting a comprehensive prediction result. The early warning accuracy of the shield tail sealing failure can be improved.

The invention provides a network information operation and maintenance system based on AI multi-modality, and belongs to the technical field of network information operation and maintenance. Heterogeneous operation and maintenance data such as network flow, equipment state, audio alarm and thermal imaging are acquired through an acquisition unit, and various features are extracted in parallel by using a multi-modality feature extraction module to form a unified multi-dimensional feature vector; a hierarchical anomaly detection architecture is established, lightweight and deep anomaly detection models are deployed on an edge side and a cloud end respectively, different modal features are intelligently fused through an attention mechanism by adopting a multi-modal feature fusion model, and a detection threshold is optimized in real time according to a network state by using an adaptive threshold dynamic adjustment Bayesian algorithm. And a multi-modal fusion decision engine is constructed to perform weighted fusion on the anomaly detection result and dynamically adjust the modal weight, so that the technical problem of insufficient accuracy of multi-modal operation and maintenance data fusion processing is solved.

The invention discloses a Bayesian algorithm-based swivel bridge spherical hinge structure optimization design method, which is characterized in that a parameterized model of a swivel bridge spherical hinge structure is constructed, and a finite element simulation technology and a Bayesian optimization algorithm are combined, so that multi-target global optimization design is realized. The method specifically comprises the following steps: establishing a refined finite element model of the swivel bridge spherical hinge; defining input design variables (spherical radius, supporting radius, pin roll radius and the like) and output optimization targets (maximum contact stress, horizontal and vertical friction moment); adopting Latin hypercube sampling (LHS) to generate a plurality of groups of initial parameter combinations; dynamically selecting a high-value parameter combination through a Bayesian optimization framework to carry out finite element simulation; training a Gaussian process agent model and carrying out iterative optimization; and quantizing the parameter sensitivity and outputting a Pareto optimal solution set. According to the method, the simulation frequency can be remarkably reduced, the design efficiency is effectively improved, and the problem that traditional experience design is prone to falling into local optimum is solved.

The invention relates to the technical field of material nondestructive testing, in particular to a CFRP wing skin damage positioning system and method based on multi-modal signal processing and Bayesian optimization DSCN, and the method comprises the steps: carrying out permutation entropy analysis and Higuchi fractal dimension analysis on a signal data set received by a sensor; performing time-frequency feature extraction on the sensor receiving signal data set deviating from the reference; performing damage feature screening on the signal data in the effective time period; training the DSCN structure to obtain an initial CFRP wing skin damage positioning prediction model; performing hyper-parameter optimization on the initial CFRP wing skin damage positioning prediction model according to a Bayesian algorithm; and performing damage positioning prediction on a to-be-detected sample according to the final CFRP wing skin damage positioning prediction model to obtain a corresponding CFRP wing skin damage positioning result. According to the method, effective damage features can be accurately and efficiently extracted from complex signals, and the accuracy and efficiency of CFRP wing skin damage positioning are remarkably improved.

The invention discloses an IGBT residual life prediction method based on variational Bayes and a mixed Wiener process, and belongs to the technical field of IGBT residual life prediction, and the method comprises the following steps: S1, giving out the definition of the mixed Wiener process, and building a degradation model to describe the degradation track of an IGBT; s2, performing off-line parameter estimation based on a variational Bayesian algorithm by using a prior sample; s3, selecting an optimal model in the degradation models according to an automatic correlation determination method; s4, selecting a prior sample which is most similar to the test sample at the current moment; s5, updating the mean value and variance of the weight vector of the test sample on line; and S6, solving a probability density function of the residual life of the mixed Wiener process in the sense of the first arrival time, and estimating the residual life value of the IGBT at each moment. According to the IGBT residual life prediction method based on the variational Bayes and the mixed Wiener process, the degradation mode can be automatically determined, the fitting precision of an IGBT degradation track is improved, the requirement for specialty is reduced, and the universality of the model is improved.

The invention provides a Bayesian earth sound parameter inversion method. The method comprises the following steps: acquiring earth sound observation data and earth sound synthesis data; constructing a plurality of KRAKENC earthquake sound forward modeling models corresponding to the hierarchical model of the earthquake sound observation data; according to the earth sound observation data and the earth sound synthesis data, adopting a Wasserstein measurement form to determine the index likelihood distribution of a plurality of KRAKENC earth sound forward modeling models; according to the selected index likelihood distribution and prior distribution, calculating posterior probability distribution of the geoacoustic observation data by using a Bayesian algorithm; and carrying out random sampling processing on the posterior probability distribution by using a Markov chain Monte Carlo simulation algorithm to obtain random sampling data points, calculating sampling expectation values corresponding to the random sampling data points, and determining a Bayesian earth sound inversion result corresponding to the earth sound observation data according to the sampling expectation values. The accuracy of sedimentary layer attenuation inversion is improved, and the uncertainty of waveform inversion is remarkably reduced.

The invention belongs to the technical field of robot pose positioning, and discloses a positioning and mapping method and system based on multi-source data. The method analyzes the multi-source SLAM scheme. Secondly, how to establish a laser inertial odometer by using an extended Kalman filtering algorithm is proposed, inter-frame matching of laser point cloud is realized, and a laser radar grid map is established; acquiring three-dimensional image information by using a depth camera, extracting ORB features of the image, solving pose information of the depth camera through a PnP algorithm, and converting the pose information into two-dimensional point cloud data; and finally, by improving a Bayesian algorithm based on multi-source data, constructing a raster map by using the multi-source data. According to the invention, the sensor with low cost is used to realize good positioning and composition effects.

The invention provides a shaft paraffin removal period prediction method, and belongs to the field of petroleum and natural gas industry. The method comprises the following steps: firstly, collecting wax deposition experimental data of the carbon dioxide flooding production well under a simulated working condition and calculating a wax deposition rate experimental value; secondly, preprocessing the sample data; constructing an initial random forest regression model, and optimizing hyper-parameters in the model by using a Bayesian algorithm; training the optimized random forest model by using the processed sample data of the carbon dioxide flooding production well under the simulated working condition; then wax precipitation real-time data of the working condition of the carbon dioxide flooding production well is obtained; inputting real-time wax deposition data into the trained random forest model, and predicting a real-time wax deposition rate; and finally predicting the paraffin removal period according to the paraffin deposition rate. By adopting the method, the prediction precision of the wax deposition rate can be improved, and accurate guidance is provided for determining the paraffin removal period of the shaft.

The invention discloses a terminal meter reliability dynamic evaluation method, system and device based on multi-source data features and a medium, and relates to the technical field of terminal meter fault prediction.The method comprises the specific steps that multi-source data of a metering terminal are obtained, and the multi-source data are integrated to form a structured feature matrix; and introducing a mixed feature screening mechanism to carry out mixed feature screening to obtain a key feature set of the terminal meter. And carrying out weight distribution by adopting a Bayesian algorithm to obtain a comprehensive weight. And constructing a comprehensive reliability scoring model, and outputting a comprehensive reliability score of the terminal meter. And dynamically setting a risk threshold according to the environmental parameters, and outputting a comprehensive risk level of the terminal meter. According to the method, terminal meter reliability dynamic evaluation under multi-source data fusion is realized, the accuracy of reliability evaluation is improved through dynamic feature screening and an adaptive weight adjustment mechanism, and fault risks and operation and maintenance weak links under different scenes are effectively identified.

The invention discloses an intelligent alarm research and judgment and safety operation system combined system and method, and the system comprises an alarm classification device which is used for receiving alarm information and original logs from a safety information and event management system, and classifying alarms into a class A, a class B and a class C; the small model research and judgment module is used for processing the A-type alarms and calculating a false alarm probability through local endogenous information matching and a naive Bayes algorithm; the large model research and judgment module is used for processing the B-type alarms and generating a research and judgment result based on the extracted alarm vulnerability information and a preset question template; the manual research and judgment module is used for processing the C-type alarms and alarms which cannot pass through small model research and judgment or large model research and judgment; and the alarm memory is used for storing research and judgment results and mark information of all alarms. According to the method, the workload of a security analyst is reduced, the alarm average response time is prolonged, and the number of alarms processed manually is reduced on the premise that the missing report rate is not obviously increased.

The invention relates to the field of coal mine geological disaster monitoring, in particular to a coal mine surface slope remote sensing data fusion monitoring method and system, and the method comprises the steps: collecting multi-source data through a satellite-unmanned aerial vehicle-ground three-stage network, and carrying out the cleaning, correction and standardization preprocessing; utilizing an improved LSTM model which introduces an attention mechanism and a geological parameter correction item to predict slope displacement and risk levels; distributing monitoring resources through a PSO (Particle Swarm Optimization) algorithm, dynamically adjusting an equipment state through a fuzzy PID (Proportion Integration Differentiation) algorithm, and fusing multi-source data through a Bayesian algorithm to generate a high-dimensional matrix; and finally, storing data based on the alliance chain and performing early warning based on a dynamic threshold value. The system correspondingly comprises six core modules. The problems of narrow coverage, poor timeliness and low data utilization rate of traditional monitoring are solved, millimeter-level precision monitoring is realized, the early warning response is less than or equal to 5 minutes, the cost is reduced by more than 40%, and the method is suitable for safety and ecological monitoring of various coal mine slopes.

The invention belongs to the technical field of medical health monitoring, and provides a human health prediction method and system based on facial video physiological signal detection, and the method comprises the steps: collecting a facial video stream, and extracting time sequence physiological signals such as heart rate, HRV, respiratory rate and the like through an rPPG algorithm; constructing a graph database individual health portrait in combination with multi-scale time sequence alignment; adopting a dynamic threshold algorithm to detect instantaneous anomaly, and fusing nonlinear dynamics and waveform morphological characteristics to quantify anomaly; constructing a hybrid model, extracting space-time and high-order features, and modeling multi-parameter interaction; a prediction result is dynamically corrected based on a Bayesian algorithm, and health risk layering is realized through clustering; and outputting the visual health report. Through non-contact monitoring, multi-modal fusion and edge-cloud collaborative architecture, the problems that traditional equipment is low in compliance, non-contact technology is insufficient in precision and prediction is shallow are solved, dynamic health prediction and closed-loop management are achieved, and the system is suitable for scenes such as remote monitoring and chronic disease screening.

The invention discloses a comprehensive pipe gallery fire positioning method based on modal recognition and a Bayesian algorithm, and the method comprises the steps: firstly, determining a comprehensive pipe gallery disaster condition for a space scene, and building a comprehensive pipe gallery fire numerical calculation model based on a computational fluid mechanics method; secondly, a physical field modal reduced-order model is constructed based on time slice data, and nonlinear modal recognition of physical information such as temperature, carbon dioxide and carbon monoxide in the utility tunnel during a fire disaster is achieved; thirdly, performing nonlinear modal feature recognition on features of physical information such as temperature, carbon dioxide and carbon monoxide by using a neural network driven by physical information; and finally, based on a Bayesian reasoning algorithm method, carrying out fire position rapid positioning. According to the method, the machine learning theory is fused, and the accuracy, interpretability and timeliness of the model are improved. The method has an important practical application value for rapid prediction and disaster source positioning of the comprehensive pipe gallery fire, and especially can rapidly respond in an emergency, thereby providing support for disaster management.

The invention discloses an AI data processing adaptive acceleration system based on a Bayesian algorithm, which belongs to the technical field of data processing and computing, and specifically comprises the steps of positioning a target operator, creating a data processing pipeline monitoring thread, collecting target data and hardware resource information and storing the target data and hardware resource information as current configuration information, and starting an automatic optimization function. The method comprises the following steps: collecting operator information, marking bottleneck operators, setting iteration times to carry out hyper-parameter search on the operator information, updating current configuration information into new configuration information by utilizing a result of each hyper-parameter search, guiding to adjust operators on a data processing pipeline by utilizing the new configuration information, and after executing the iteration times, carrying out data processing on the operators on the data processing pipeline. And the optimal hyper-parameter is screened out and stored in a local file, and is directly called and the operator is adjusted when an assembly line is started next time, so that the data processing speed during AI model training can be effectively improved.

The invention relates to the technical field of medical detection, in particular to a cervical cancer screening system based on risk HPV (human papillomavirus) expansion typing, and a risk assessment module provides solid technical support for individualized CIN2 + / 3 + risk assessment by using a Bayesian network and a Cox proportional risk model. By dynamically acquiring key data such as HPV types, cytological results, patient ages and infection duration, the Bayesian algorithm is beneficial to constructing individual specific risk models, and real-time risk division is carried out. The Cox regression model predicts accumulated risks in three years, dynamically adjusts a risk assessment threshold value and refreshes the weight of an input variable in real time in combination with a machine learning mechanism, and the composite model structure enables the risk assessment to be more flexible and ensures the scientificity of a management decision.

The invention discloses a telescope parameter efficient optimization method and system based on a Bayesian algorithm and a fluctuation optical TTL coupling noise calculation model, and aims to solve the problem that a fluctuation optical high-precision calculation module is used for improving TTL coupling noise calculation precision in an existing telescope parameter optimization method. And due to frequent calling of a high-time-consumption module, the optimization time is sharply increased, and the efficient design requirement of a space gravitational wave detection task is difficult to meet. According to the method, on the basis of the principle of a Bayesian optimization algorithm, potential optimal to-be-evaluated telescope parameters are searched through an agent model, a collection function and the optimization function of Zermarkes software; and calculating TTL coupling noise of the telescope to be evaluated by combining a light field propagation calculation method based on a wave optics theory with a light field-phase resolving method, carrying out iterative optimization on telescope parameters, and outputting optimal TTL coupling noise and optimal telescope optical parameters.

The invention relates to a landslide susceptibility evaluation method considering InSAR and a multi-stage optimization random forest model. According to the method, non-landslide points are selected through multi-factor control and spatial stratified sampling, feature factors are selected by using a random forest classifier in combination with a Pearson's correlation coefficient matrix and a VIF method, a random forest model is optimized based on a Bayesian algorithm, finally, the performance of the model is evaluated through multiple indexes, and susceptibility indexes are divided into five grades. Compared with the prior art, the method not only takes the earth surface deformation rate identified by InSAR as a characteristic factor, but also performs quantitative analysis on the characteristic factor and the susceptibility zoning result, verifies the consistency of the two factors, can effectively improve the precision of a landslide susceptibility evaluation model, provides important reference for landslide disaster prevention and reduction research, and has a wide application prospect. The method is especially suitable for areas with frequent geological disasters such as southwest regions in China.

The invention discloses a reasoning and interaction system based on multiple dimensions. According to the inference system based on multiple dimensions, the complete process from multi-source data acquisition to inference result output is realized. The acquisition module is responsible for collecting out-hospital examination information and in-hospital examination information of a patient. And the pruning module predicts a targeted set by utilizing the interactively collected patient information and a preset diagnosis knowledge base, dynamically prunes the full-amount question-examination thinking sub-trees according to the targeted set, and optimizes the pruned question-examination thinking sub-trees. And the feature extraction module extracts key features from the interactively collected out-of-hospital and in-hospital question examination information based on the optimized question examination thinking sub-tree. And finally, the inference module inputs the key features into a pre-trained diagnosis model, and the model is combined with a Bayesian algorithm, a deep learning algorithm and a clinical decision consensus to output a final inference result. The problem that dynamic adaptation and efficient and accurate reasoning of multi-dimensional data cannot be achieved on a task set with specific requirements in the prior art is effectively solved.

The present invention provides a method and system for processing bill of quantities based on dual parsing correction, which relates to the technical field of data processing. The method includes: obtaining a bill of quantities; converting the paper-based bill of quantities into an electronic version; extracting multiple recognized engineering categories of the target bill of quantities and the recognized quantities of each recognized engineering category based on an object detection algorithm; extracting the initial text of the target bill of quantities in combination with the Bayesian algorithm; performing semantic parsing on the initial text in combination with a large language model that uses dynamic context tokens as input data, and outputting the semantic text of the target bill of quantities; aligning each recognized engineering category and each parsed engineering category to the target entity; comparing the recognized quantity and the parsed quantity belonging to the same target entity; in the case where the comparison results are all consistent, outputting the semantic text as the processing result of the bill of quantities, otherwise, marking the comparison difference results in the semantic text. The compilation efficiency and accuracy of the bill of quantities are improved.

The invention discloses an engineering structure performance state inversion method, a safety early warning method and a safety early warning system based on engineering skin. The inversion method comprises the following steps: acquiring multi-source data acquired by multiple types of sensors arranged on a to-be-monitored engineering structure; preprocessing the multi-source data; fusing the multi-source data by adopting multi-rate Kalman filtering based on a neural network to obtain multi-source data with a unified time step; taking the data of the plurality of flexible piezoelectric sensors after the unified time step as model input, inputting the data into a trained neural network-based key point engineering demand parameter inversion model, and performing inversion to obtain engineering demand parameters of a plurality of key points of the engineering structure; and correcting an inversion result by using a Bayesian algorithm in combination with data of corresponding time steps of the external source sensor. According to the method, the key point engineering demand parameters can be quickly inverted, the inversion efficiency is high, and the precision is high.

The application provides a weak fault feature extraction method for an autonomous underwater vehicle propeller, and belongs to the technical field of underwater vehicle fault diagnosis, and comprises two parts: fault feature enhancement and feature fusion. First, the application optimizes parameters by judging the Gaussianity of all modes of multi-source state signals and control signals through negative entropy, completes noise reduction, and extracts and enhances fault features based on a modified Bayesian algorithm. Then, the feature signals are divided into multiple time intervals, the faults occurring in each interval are taken as focal elements, all signals except the longitudinal velocity are subjected to first feature fusion, the first fusion result is subjected to second fusion with the feature signal of the longitudinal velocity, the fault features are further enhanced, and the monotonicity between the fault features and the fault degree is presented. The application can provide a basis for subsequent fault detection and identification, and is particularly suitable for state monitoring of autonomous underwater vehicle propellers.

The invention discloses a parameter optimization method and system for dynamic coupling of a roller press, and the method comprises the steps: constructing the interaction among all parts through a knowledge graph in the dynamic coupling process of the roller press; establishing a synchronous link between nodes in the knowledge graph by using a Bayesian algorithm to obtain an optimized knowledge graph; in the working process of the roller press, matching corresponding coupling parameters in the optimized knowledge graph by setting output parameters of the roller press; when any coupling parameter fluctuates, other coupling parameters are optimized and adjusted through the optimized knowledge graph, so that the fluctuating parameter is compensated; and parameter optimization in the dynamic coupling process of the roller press is realized. According to the method, the coordination and response speed of parameter adjustment are improved, the problems of quality fluctuation and high energy consumption caused by coupling imbalance are remarkably reduced, intelligent, high-precision and high-stability operation of the rolling process is achieved, and the method has good engineering practical value and popularization prospects.

The invention discloses a dam interior and exterior deformation monitoring method and system based on deep fusion of finite element and GNSS (Global Navigation Satellite System) monitoring. According to the method, surface displacement observation data are obtained through a GNSS receiver, a finite element model is constructed, and the mechanical response of the finite element model under hydrostatic pressure, temperature and seismic load is simulated. According to the first layer, parallel primary fusion is conducted on GNSS data and finite element output through Kalman filtering, particle filtering, a neural network and a Bayesian algorithm; in the second layer, weights are dynamically distributed on the basis of mean square errors of all algorithm results in a sliding window and reference data, and a high-precision displacement estimation value is generated through weighted integration. The system evaluates data quality and model confidence in real time, dynamically optimizes weight distribution, performs early warning based on multistage thresholds of displacement, speed and acceleration, and finally studies and judges structural risks through time sequence decomposition and abnormal mode recognition. According to the invention, the overall precision and reliability of dam deformation monitoring are significantly improved.

The invention discloses an electric power field operation safety monitoring method and system based on AI driving. The method comprises the following steps: synchronously acquiring voice, operation video and equipment state identification information, and de-noising to generate a multi-modal sequence; using a multi-modal cross reconstruction model to reconstruct other modals for any modal, and identifying suspicious fragments according to reconstruction errors; multi-layer consistency matching is executed on the suspicious fragments, and the consistency matching degree and mismatch attribution are calculated through time soft alignment, semantic embedding unification and semantic graph reasoning; dispersing the voice, action and equipment state elements into an event sequence, and matching the event sequence with a preset process causal graph to position an abnormal event; and finally, abnormal nodes and induced nodes are analyzed in combination with a Bayesian algorithm, and whole-process safety monitoring is realized. According to the method, password inconsistency, action out-of-order, object mismatching and equipment response abnormity in electric power operation can be intelligently identified and traced, and the real-time performance and accuracy of operation safety are improved.

The invention discloses a gas cylinder state on-line monitoring method and system based on a Bayesian network, and relates to the technical field of on-line monitoring, and the method comprises the following steps: determining a to-be-detected gas cylinder, deploying a plurality of sensors on the to-be-detected gas cylinder, and setting a radio frequency identification tag; multiple types of real-time data of the gas cylinder to be detected are obtained based on multiple sensors, and timestamp alignment and normalization processing are carried out; constructing a topological network based on the characteristics of the multiple types of real-time data, and determining topological network nodes; constructing a gas cylinder state monitoring model by using topological network nodes based on a variational Bayesian algorithm; inputting the various indexes of the gas cylinder to be detected into the gas cylinder state monitoring model to identify the risk of the gas cylinder to be detected; and acquiring a risk identification result of the to-be-detected gas cylinder, writing the risk identification result into the radio frequency identification tag, and when the risk identification result is that the to-be-detected gas cylinder is abnormal, pushing the risk identification result and a tag code of the radio frequency identification tag to a maintenance terminal.