1607 results about "Data Matrix" patented technology

To significantly improve the prediction accuracy, response speed and management efficiency of large river bank slope disasters, an integrated bank slope monitoring method based on multi-parameter collaborative recognition is proposed. The solution includes step S1 of synchronously collecting data on bank slope displacement, pore water pressure, inclination angle, vibration frequency and environmental temperature and humidity to form an original monitoring dataset and construct a multi-parameter collaborative recognition network; step S2 of using a multi-modal data fusion algorithm to generate a fusion data matrix including spatiotemporal correlation features and perform spatiotemporal data alignment and outlier cleansing; step S3 of combining a geomechanical parameter library and a past disaster case library to output a risk level map and perform dynamic risk assessment model analysis; and step S4 of triggering a multi-level early warning mechanism and generating linked control commands including treatment suggestions to perform multi-level early warning and linked control.

The invention relates to a dynamic risk control method and device, equipment and a storage medium. The method comprises the following steps: collecting and preprocessing multi-source data to obtain a standardized multi-dimensional data matrix; constructing a dynamic risk control model according to the standardized multi-dimensional data matrix, and calculating a risk control model parameter set; performing risk factor sensitivity analysis by using the risk control model parameter set and the standardized multi-dimensional data matrix to obtain a dynamic weight vector; executing iterative risk assessment based on the dynamic weight vector to obtain a comprehensive risk score; constructing a multi-layer threshold structure based on the comprehensive risk score and executing dynamic adjustment to obtain a personalized risk threshold; and according to the comprehensive risk score and the personalized risk threshold, triggering a risk control measure and executing a feedback mechanism to obtain a risk control execution result. The importance of different risk factors can be adjusted in real time, the market environment change is quickly responded, and the exploration capability of the system for unknown risks is enhanced.

The invention relates to the technical field of image data processing, and discloses a few-sample scene-oriented industrial product surface defect image analysis method, which comprises the following steps of: obtaining surface gray level image data of a product to be analyzed, calculating a structure tensor matrix and generating an anisotropy degree graph; searching similar blocks in a preset search neighborhood, and constructing a local texture data matrix; performing singular value decomposition on the local texture data matrix to extract a main subspace; constructing a projection operator and utilizing the projection operator to carry out orthogonal projection reconstruction on the local image block to generate a reconstructed background image block; according to the method, through an orthogonal subspace projection mechanism, good product textures and defect signals are separated, random noise is removed, meanwhile, high-frequency structural features are completely reserved, and the method is high in robustness, high in robustness and high in robustness. And the defect detection precision of a complex texture surface in a few-sample scene is improved.

The invention relates to the technical field of crack identification, and discloses a crack identification analysis method and system for a building shear wall, and the method comprises the steps: carrying out the multi-angle shooting and image standardization processing of the surface of the building shear wall, and obtaining a standardized image data matrix; performing multi-model degradation processing and multi-angle image combination to obtain target enhanced image data; inputting the image into a convolution denoising auto-encoder for noise separation to obtain a denoising feature image matrix; inputting a dynamic graph convolutional neural network to carry out local feature and global feature extraction to obtain a local crack feature matrix and a global crack feature matrix, and carrying out feature fusion to obtain a fused feature matrix; and inputting the twin metric learning network to carry out feature measurement and crack classification, and outputting a target crack classification result, thereby realizing effective capture of deep semantic information between crack areas of the building shear wall, and realizing efficient integration of crack features of different scales.

The invention provides an intelligent temperature field analysis-based heat dissipation optimization method for an IGBT (Insulated Gate Bipolar Translator) power module of an offshore flexible direct current converter valve. According to the method, an IGBT module space temperature data matrix and multi-point temperature sensor data are collected, and filtering processing is carried out through a multi-scale sliding window and a self-adaptive threshold value; establishing a multi-layer thermal network parameter model, and analyzing temperature dynamic change characteristics; layering the feature data according to the thermal response speed, and performing adaptive mapping and weight calculation; establishing a reinforcement learning model based on the heat dissipation efficiency index set to optimize a heat dissipation strategy; and predicting the temperature field distribution by using the graph structure neural network model. Accurate sensing, dynamic characteristic analysis, self-adaptive control and predictive maintenance of the temperature field of the IGBT module are realized, the heat dissipation efficiency and the temperature uniformity are improved, and the service life of equipment is prolonged.

The invention relates to the technical field of model construction, and discloses a neural network-based frozen soil unfrozen water content detection model construction method and system. The method comprises the following steps: carrying out segmented sampling test on a clay sample in a temperature interval of 0 DEG C to-20 DEG C to obtain a multi-dimensional original data set, and carrying out standardization and principal component analysis on the data set to obtain a standardized feature vector; and performing three-stage classification marking on the feature vectors to obtain a training data matrix. A deep neural network is adopted to carry out five-fold cross validation training, and a prediction model of three hidden layers is constructed. And performing correction calculation on model output according to soil mineral composition and porosity parameters, and finally identifying an abnormal value through root-mean-square error analysis and a three-time standard deviation principle to obtain a standardized prediction result. According to the method, the mapping relation between the thermal parameters and the unfrozen water content is established, correction is carried out in combination with the soil body characteristic parameters, and the technical problem that the prediction precision of the unfrozen water content is not high in the prior art can be solved.

The invention relates to an intelligent curtain wall energy-saving control method and system based on deep learning. The method comprises the following steps: acquiring temperature data, illumination data and energy consumption data of each hierarchical region of a curtain wall system to obtain a sensor data matrix; a curtain wall energy consumption residual value is calculated, time sequence segmentation and K-means clustering are carried out, and an energy consumption feature vector and an energy consumption mode feature database are obtained; setting a state space, an action space and a reward function, and training the initial deep reinforcement learning model; self-adaptive droop coefficient adjustment is carried out on the curtain wall control area, the shading coefficient, the opening degree of a ventilation opening and the temperature of a hollow layer are adjusted, and energy-saving control parameters of all the areas are obtained; and executing multi-objective optimization control, and carrying out online updating on the initial deep reinforcement learning model to obtain a target deep reinforcement learning model. According to the invention, a regional and hierarchical control strategy is adopted, the influence of the building orientation and the floor height is fully considered, and refined control management is realized.

The invention relates to the technical field of strength detection, and discloses radiator strength detection equipment and a detection method. The method comprises the following steps: carrying out adaptive wavelet denoising and structural association mapping on collected multi-scale structural feature data and multi-environment coupling material feature data of a radiator to be detected, and carrying out multi-dimensional feature extraction, space-time alignment and interactive mapping on an obtained fusion data set to obtain a multi-physical field coupling data matrix; carrying out physical field control equation set separation iteration solution and heat dissipation cyclic load and environmental action calculation on the coupling data matrix to obtain a damage evolution state; and performing multi-dimensional damage sensitive area identification based on the damage evolution state, generating a risk distribution map, performing failure comparison and life calculation based on historical failure data of the same type of radiators, and generating an intensity comprehensive detection result. Through multi-physical field coupling analysis and multi-dimensional damage evaluation, accurate detection of the strength state of the radiator is realized, and the accuracy of structural reliability evaluation is improved.

The invention relates to a high-precision multi-channel phased array radio measurement calibration method and a high-precision multi-channel phased array radio measurement calibration system. The method comprises the following steps: carrying out electromagnetic characteristic modeling on N array element channels and an antenna housing of the multi-channel phased-array antenna to obtain a channel measurement model; carrying out electromagnetic field numerical calculation on the multi-channel phased-array antenna to obtain an initial error data matrix; mapping the initial error data matrix to a two-dimensional weight matrix, and performing optimal matching solution on the two-dimensional weight matrix to obtain a theoretical calibration coefficient matrix; connecting the standard gain antenna and the multi-channel phased-array antenna by adopting a vector network analyzer, and performing far-field scanning measurement on the multi-channel phased-array antenna to obtain actually measured amplitude-phase characteristic data; and performing weighted least square iterative calculation on the actually measured amplitude-phase characteristic data and the theoretical calibration coefficient matrix to obtain a target calibration compensation coefficient. According to the invention, accurate measurement of the amplitude-phase characteristics of the multi-channel phased-array antenna is realized, and the stability of the calibration process is improved.

The invention provides a distributed service intelligent master selection method and system based on double-engine cooperation, and relates to the technical field of intelligent master selection, and the method comprises the steps: collecting the processing capability index, the network throughput and the resource utilization rate of a service node to construct a performance data matrix, and generating an intelligent identification code based on a node scoring function and a physical clock value; nacos and Redis signals are monitored through a double-layer event monitor, the optimal incremental step length is determined according to the score sequence distribution trend, and a target score is generated to construct a dynamic priority sequence; and periodically selecting a main node and a preheating standby node, and when the main node fails, starting increment state synchronization based on Redis affairs after voting arbitration confirmation, so as to realize main and standby non-inductive switching. According to the method, the election accuracy of the main node and the switching reliability are improved, and the system interruption risk is reduced.

The invention discloses a remote printer monitoring and fault prediction system based on the Internet of Things, and relates to the technical field of the Internet of Things and artificial intelligence, and the system comprises a data collection module which is used for collecting equipment state data of a remote printer in real time and carrying out the preprocessing of the equipment state data; the data processing module is used for integrating the preprocessed equipment state data into a data matrix and a label vector; the model construction module is used for outputting a final feature set by using a random forest model and combining a Gumbel-Sigmoid activation function; and the fault prediction module is used for constructing a fault prediction model by using the bidirectional LSTM to output the predicted fault probability of the current time point and dividing a fault interval data pool. By introducing the combination of a random forest algorithm and a Gumbel-Sigmoid activation function, a feature selection process can be automatically optimized, a feature set which is crucial to fault prediction can be accurately screened out, and a bidirectional LSTM model is adopted to capture time sequence information, so that the fault prediction precision and the real-time response capability are remarkably improved.

The invention discloses an intelligent operation and maintenance management system and method based on a charging pile, and belongs to the technical field of fault early warning, and the method comprises the steps: building a unified time sequence operation data matrix through collecting multi-source state data generated in the operation process of the charging pile; key features are extracted to construct feature vectors, and a multi-classification neural network model is utilized to evaluate a health state; a micro-degradation evolution path model is constructed in combination with the health trend in the continuous observation period, and a fault prediction curve is generated; performing similarity matching on a prediction result and a fault prior curve library, calculating a risk weight coefficient, identifying potential fault nodes and outputting an early warning list; constructing a regional task scheduling graph based on the high-risk pile position, fusing geographic position, power level and residual life information, and optimizing to generate an operation and maintenance path and a resource configuration scheme; according to the method, the fault prediction accuracy and operation and maintenance efficiency of the charging pile can be remarkably improved, and intelligent operation and maintenance and response optimization are realized.

The invention discloses a time sequence data management method of an edge computing gateway, which relates to the technical field of edge computing and industrial Internet of Things, and comprises the following steps of: respectively recording a communication bandwidth occupancy rate, a buffer area residual rate and a scheduling thread occupancy rate of the edge computing gateway in a preset fixed time period; and constructing a resource use original data matrix covering all time points in the fixed time period. According to the method, by periodically monitoring the resource use state and fusing the high-priority task scheduling performance, the scheduling resource abnormal occupancy index is dynamically generated, and intelligent sensing and scheduling optimization of the edge computing gateway on the resource pressure are achieved. When the abnormal index is increased, the system automatically triggers buffer area redistribution and low-optimal task data compression, data writing and scheduling real-time performance of key tasks are guaranteed preferentially, the problems of task starvation and data loss are effectively avoided, and the stability and the response capability of the system in a high-pressure environment are improved.

The invention relates to an internet big data extraction method and device, equipment and a storage medium, and the method comprises the following steps: carrying out distributed crawler collection on an internet data source, obtaining original network data, and converting the original network data into a structured data matrix; and performing multi-level semantic analysis on the matrix, constructing a semantic feature map, and performing topic segmentation and classification to form a topic domain knowledge tree. Association rules in the knowledge tree are further mined, and an implicit knowledge network is constructed. Performing semantic decomposition and expansion on query conditions based on the network to generate expanded query data, and performing similarity matching with the knowledge network to obtain a candidate data set; and finally, performing multi-factor sorting and extraction on the candidate data, and outputting target data, thereby solving the technical problem that in the second-hand car market, due to wide data sources and fuzzy semantics, an existing system has relatively large deviation when performing price prediction and maintenance cost analysis.

The invention provides a real-time deep sea subsurface buoy monitoring system, which belongs to the technical field of deep sea measurement, and comprises a control chip, a multi-parameter sensor array, a data storage device and a power supply, high-precision monitoring is realized through the following steps: recording ocean data acquired by a multi-parameter sensor; correcting the sound wave propagation model and calculating the relative position of the subsurface buoy; constructing a three-dimensional data matrix and realizing data compression; identifying abnormal data by using a matrix disorder index; processing the time sequence data by adopting a sliding window weighted average method and eliminating jump; carrying out distributed preprocessing on the multi-source heterogeneous data and carrying out parallel processing by applying a matrix partitioning technology; accumulated errors are corrected by combining historical data and applying a Kalman filtering algorithm, and the problems of environment interference and sensor drift are solved through a deep sea environment disturbance compensation network model and a self-adaptive weighted error optimization function.

The invention discloses a fresh food quality monitoring method fusing fresh food after-ripening characteristics and logistics data, and relates to the field of food science and technology, and the method comprises the steps: collecting logistics environment data, logistics process data and fresh food ontology data in real time through a distributed sensor network; time stamp synchronization and space coordinate mapping technologies are adopted, space-time alignment is carried out on heterogeneous data with different sampling frequencies, and a unified data matrix is established; the method comprises the following steps: establishing a variable parameter dynamical model comprising variety difference factors, harvest maturity and environment interaction coefficients based on post-harvest physiological mechanisms: dynamically updating model parameters of various varieties in different logistics scenes through a federated learning framework crossing supply chain nodes; when the quality attenuation curve predicted in real time deviates from a preset threshold value, graded early warning is triggered, and logistics parameter adjustment suggestions are generated. According to the invention, full-link accurate management and control of fresh products from a supply chain to a consumption terminal is realized through multi-dimensional technology collaboration.

The invention discloses a reservoir dam safety monitoring method and system based on edge calculation, and relates to the technical field of hydraulic engineering safety monitoring, and the method comprises the steps: obtaining monitoring data by each edge calculation node, carrying out the preprocessing, and generating a standardized data matrix; establishing a reference database, executing anomaly detection, and generating a labeling time sequence data matrix; performing multi-scale decomposition on the labeled time sequence data matrix, and constructing a node response feature matrix; the central processing unit receives data of each edge computing node, analyzes a multi-parameter spatial propagation mode by constructing a parameter-spatial correlation matrix, and obtains a spatial correlation feature matrix; establishing a Bayesian risk assessment model, predicting a dam risk level and outputting a risk evolution trend; and issuing a differentiated early warning instruction according to the risk assessment result. Through a distributed architecture combining edge calculation and central processing, real-time monitoring, intelligent analysis and accurate early warning of the dam safety state are realized, and the monitoring efficiency and the risk identification accuracy are improved.

The invention discloses a contract filing method, system and device based on automatic recognition and a medium, and the method specifically comprises the steps: taking a contract document uploaded by a user as input, and extracting contract key data; inputting the signature area coordinate, the signature date metadata and the clause keyword into a space-time correlation model to generate a context enhanced candidate contract number set; inputting the candidate contract number set into a preset knowledge graph, and outputting a target contract number; inputting the distribution characteristics of the clause keywords into a bidirectional long-short-term memory network classifier for processing, and constructing a multi-dimensional metadata matrix in combination with the target contract number; and inputting the desensitized contract text content and the multi-dimensional metadata matrix into a file DNA atlas generator, and generating a unique feature code by fusing a semantic embedding vector and a document structure fingerprint. The efficiency bottleneck and accuracy problems of a traditional archiving mode are solved, and the efficiency, accuracy and compliance of contract archiving are remarkably improved.

An application system fault prediction method based on an association rule and a deep learning integrated model, the method comprising: collecting historical fault data of an application system; performing data preprocessing on the collected historical fault data to obtain a data matrix, and then converting the data matrix into a data form suitable for analysis by an association rule algorithm and a deep learning algorithm; performing feature extraction on the data matrix to obtain effective fault-related features; establishing an association rule model and a deep learning LSTM model; fusing outputs of the association rule model and the deep learning LSTM model to form a multi-layer decision tree model; and predicting a fault by combining the association rule model, the deep learning LSTM model, the multi-layer decision tree model, and current state data of the application system, and obtaining a fault prediction result via weighted voting. The present invention achieves accurate fault prediction and early warning for an application system, and enhances the accuracy and robustness of fault prediction by introducing optimizations for a deep learning LSTM model.

The invention relates to the technical field of coal mine safety monitoring, and discloses a coal mine heterogeneous data visualization processing method combined with artificial intelligence, and the method comprises the steps: collecting multi-source heterogeneous data above and under a coal mine to construct a real-time heterogeneous data matrix; feature categories are divided based on data dynamic relevance, and stable data areas are screened through a dynamic analysis window to generate an optimization matrix; performing pattern recognition on the unstable region to extract an abnormal data cluster, and calculating an abnormal feature factor of a data point; analyzing the feature distribution difference to generate a stable feature index, and calculating an abnormal risk value in combination with the distance, the abnormal feature factor and the stable feature index; and mapping the center coordinate of the stable region to a three-dimensional space of the coal mine, and positioning a key information region in combination with the abnormal risk value. An apparatus includes a memory, a processor, and a computer program. The coal mine heterogeneous data processing efficiency and the safety monitoring accuracy are improved, intelligent positioning of the key information area is achieved, and powerful support is provided for coal mine safety production.

The invention relates to the field of optical energy storage technology, and discloses a method for predicting the state of charge of an optical energy storage battery based on CNN-LSTM-SA. The key points of the technical solution include the following steps: collecting all state data of an optical energy storage battery; standardizing the state data to obtain a standardized state data matrix, performing feature extraction, and obtaining a time series data matrix; inputting the time series data matrix into a convolutional neural network to extract a spatial feature vector sequence; inputting the spatial feature vector sequence into a long short-term memory network to establish a model of the time dependence of the battery state of charge, and obtaining time-varying trend data; taking the spatial feature vector sequence and the time-varying trend data as inputs, citing them for processing by an attention mechanism, and obtaining a feature output after attention weighting; and calculating a state of charge prediction value by applying a weighted fusion algorithm based on the spatial feature vector sequence, the time-varying trend data, and the feature output after attention weighting.

The invention discloses an LSTM-COF-based power equipment data anomaly detection method and system, and relates to the technical field of power equipment state monitoring, and the method comprises the following steps: collecting historical data, and constructing a three-dimensional data matrix; predicting equipment parameters at the extreme temperature through an LSTM model; compressing the features, quantifying the covariance deviation degree between the features in combination with a correlation abnormal factor algorithm, and detecting abnormal points; the system integrates a data collection module, a data preprocessing module, a data prediction module, a detection model generation module and a visualization module. According to the method, the multi-dimensional historical operation data of the power equipment is collected, the equipment parameters in the extreme temperature environment are predicted by using the LSTM model, the principal component analysis dimensionality reduction and correlation abnormal factor algorithms are combined, insulation degradation type and electrical connection type faults can be dynamically identified, the data distribution change is adapted through the incremental learning mechanism, and the fault diagnosis accuracy is improved. The problems of low high-dimensional data processing efficiency and poor anomaly detection adaptability due to manual experience dependence in a traditional method are solved.

The invention discloses a concrete internal defect quantitative detection method and system based on reflected waves, and belongs to the technical field of nondestructive testing. A reflected wave data matrix is obtained through multi-angle excitation and synchronous receiving; calculating energy characteristics of each channel, and constructing an energy response residual field; extracting waveform offset, spectrum jitter and phase change caused by defects by adopting a disturbance comparison algorithm to form a disturbance feature vector set; a defect-response function curved surface is further constructed, a defect topological structure is inversed based on gradient and curvature analysis, and defect geometric parameters are output; and finally, inputting the multi-moment defect parameters into the recurrent neural network, and predicting a defect evolution path and a failure risk. The method has high resolution and trend prediction capability, and is suitable for detection and early warning of concrete structures in bridges, tunnels and nuclear power projects.

The invention discloses a method and system for predicting the service life of a fire valve, and relates to the field of prediction maintenance, and the method comprises the steps: obtaining a multi-dimensional monitoring data matrix which comprises the sealing performance data, operation torque data and corrosion degree data of the fire valve continuously monitored in a preset time period; determining a parameter incidence matrix according to the multi-dimensional monitoring data matrix; determining a plurality of principal component vectors and corresponding characteristic values according to the parameter incidence matrix through a principal component analysis algorithm, and determining a current health state score of the fire valve according to the characteristic values corresponding to the plurality of principal component vectors; determining a degradation law function of the fire-fighting valve according to the historical operation record of the fire-fighting valve; and predicting the service life of the fire valve according to the current health state score and the degradation law function. According to the scheme, the accuracy of life prediction of the fire valve is improved, and the problem that the accuracy of life prediction of the fire valve is low is solved.

The invention discloses an intelligent operation and maintenance scheduling and resource optimization method and system for a new energy power station, and belongs to the technical field of data processing and management.The method comprises the steps that real-time power generation data, equipment sensor data, weather forecast data, a power grid scheduling instruction and electricity market electricity price information of the new energy power station are obtained; a unified data matrix is generated through space-time alignment processing to execute bidirectional feedback prediction, and a corrected power generation plan is generated; a cooperative scheduling decision is generated through a multi-target dynamic balance algorithm, and a personnel dispatching scheme and a material allocation path are generated through real-time path planning; and generating a historical decision data set based on the execution result and the actual execution deviation, and adjusting prediction parameters and scheduling parameters through an incremental learning model. A closed-loop optimization method combining data fusion, collaborative prediction, multi-target scheduling and adaptive learning is adopted, global collaborative optimization of multiple factors such as power generation, operation and maintenance, energy storage and markets can be achieved, and the economic benefit and the intelligent level of overall operation of a power station are improved.

The invention provides an intelligent classification method for Beidou positioning data, and relates to the technical field of Beidou positioning data classification, and the method comprises the steps: obtaining the Beidou positioning data of a monitoring target; performing standardization processing, abnormal value processing and time sequence alignment processing on the acquired Beidou positioning data to generate a preprocessed time sequence data matrix; constructing a classification model; performing feature extraction, including time feature extraction and spatial feature extraction, on the preprocessed time sequence data matrix by using a spatial-temporal feature extraction module to obtain a time feature vector and a spatial feature vector respectively; carrying out fusion processing on the time feature vector and the space feature vector by adopting a spatial-temporal feature fusion module, and constructing a spatial-temporal joint feature; and inputting the spatio-temporal joint features into a classification module, and obtaining a classification result through feature conversion, attention weight calculation and feature aggregation. According to the invention, accurate identification and classification of the motion state of the monitored target are realized by establishing a data processing and classification framework of the system.

The invention relates to the field of high-voltage cable fault diagnosis, and discloses a high-voltage cable insulation fault intelligent diagnosis method and system based on multi-information fusion, and the method comprises the following steps: S1, obtaining the operation multi-source data of a high-voltage cable, and constructing a multi-source original data matrix; s2, preprocessing to obtain a time-space aligned standardized data matrix; s3, performing feature extraction to obtain a multi-dimensional feature vector, and learning internal association between features by using a multi-modal deep network to obtain a joint multi-modal feature; s4, constructing a fault type identification model based on Bayesian reasoning and Monte Carlo sampling, and obtaining a fault type classification result; s5, in combination with deep learning and a physical model, obtaining a fault occurrence interval, positioning information and a fault level; and S6, based on a fault type classification result, a fault occurrence interval and positioning information, obtaining a fault level, and carrying out early warning pushing on a generated diagnosis report. According to the invention, high-precision identification, positioning and risk assessment of high-voltage cable insulation faults are realized.

The invention provides a wind tunnel health monitoring data mining method, medium and system, and belongs to the technical field of wind tunnel health monitoring data mining and processing, and the method comprises the steps: collecting a plurality of sensing signals to construct a monitoring data stream, and carrying out the filtering and noise reduction processing to obtain preprocessed data and an abnormal data set; and starting a GPU and CPU processing stream to receive the preprocessed data and the abnormal data set, performing component decomposition to obtain a steady-state data matrix, a dynamic data matrix, an abnormal feature matrix, a parameter data vector and an abnormal parameter vector, establishing a data mining feature equation set, and calculating a wind tunnel operation state evaluation result by using the wind tunnel operation state evaluation equation set. And generating a wind tunnel operation characteristic matrix and a wind tunnel state early warning index, and outputting an early warning signal according to a comparison result of the early warning index and a preset health threshold value. The technical problem that potential fault symptoms cannot be better found due to the fact that wind tunnel health detection data cannot be rapidly and efficiently mined and analyzed from the two aspects of steady state and dynamic state at present is solved.

The invention relates to a water conservancy facility operation and maintenance method based on multi-source data, and the method comprises the steps: collecting multi-source heterogeneous data of a water conservancy facility, and obtaining a standardized multi-dimensional data matrix; multi-modal features of the standardized multi-dimensional data matrix are extracted through a graph neural network fusion algorithm, and a fusion feature vector is obtained; performing fault diagnosis on the fusion feature vector through a knowledge graph reasoning algorithm automatically constructed by a domain ontology to obtain fault diagnosis information; based on the fault diagnosis information, performing facility state evolution analysis through a space-time coupling degradation prediction model to obtain a space-time degradation prediction result; according to the space-time degradation prediction result, state evaluation of the water conservancy facilities is carried out through a dual-objective optimized dynamic weight distribution algorithm, and an operation and maintenance state evaluation result is obtained; and on the basis of the operation and maintenance state evaluation result, performing cross-basin cascade fault prevention and control on the water conservancy facilities to obtain a cascade fault prevention and control scheme. The method improves the prediction precision of the degradation of the water conservancy facilities, and enhances the anti-risk capability of the water conservancy infrastructure.

The invention relates to pipeline circumferential weld detection, and discloses a pipeline circumferential weld defect detection method and system based on deep learning, multiple sensors are arranged on the surface layer of a pipeline to collect multi-modal signals, an inertial measurement device is combined to carry out pose correction, and a multi-modal time sequence data matrix is constructed; performing preprocessing and segmentation, calculating to obtain a dynamic reference band, and outputting upper and lower bounds; performing broken line fitting on each segment to extract a phase change factor triple, and comparing with a reference band to screen event candidate segments; constructing a multi-segment time domain coupling relation graph based on the candidate segments, and generating a dominant response mode candidate set; inputting a multi-branch time sequence coding network to extract a three-mode feature and generate a time sequence fusion feature; and performing similarity matching with a defect prototype library to obtain a defect category probability sequence, performing single-mode ablation and time sequence playback verification to obtain a high-confidence index, mapping the high-confidence index to a spatial position, and outputting a defect category and severity in combination with a feature index. According to the method, high-precision defect detection and reliable classification under the trenchless condition can be realized.