532 results about "Deep belief network" patented technology

The invention discloses a wind power plant booster station multi-source data fusion anti-misoperation locking intelligent decision-making and early warning method, and relates to the technical field of intelligent misoperation prevention of a power system, and the method comprises the following steps: collecting multi-source heterogeneous data, obtaining the data through a distributed sensor network, and carrying out the edge calculation preprocessing; performing data space-time alignment and fusion, performing equipment state evaluation, and constructing a deep belief network and Bayesian network hybrid model to calculate a health index; anti-misoperation rule modeling is carried out, and operation logic verification is carried out based on a Petri network and an expert knowledge base; risk early warning decision making: fusing multi-source early warning information to divide risk levels; intelligent locking control is carried out, and a locking strategy is optimized through reinforcement learning; and performing decision support and visualization, constructing a three-dimensional digital twinborn model, and displaying operation guidance and risk early warning in combination with an AR technology. Through multi-source data fusion and intelligent decision making, the anti-misoperation locking accuracy and efficiency are improved, and the safety and the operation and maintenance level of the booster station are remarkably enhanced by equipment fault early warning three months ahead of time.

The invention provides a die-casting die heat balance distribution optimization method and system based on an energy model, and relates to the technical field of die-casting dies, and the method comprises the steps: collecting heat distribution data, and building a heat energy transfer mapping relation; extracting space-time correlation features by using a graph attention network; constructing a heat distribution dynamic evolution model; constructing a temperature field predictor based on a deep belief network; training a predictor by using a multi-agent coevolution algorithm; constructing a temperature field optimization strategy network; generating an optimal temperature field control sequence; establishing a regional adaptive control strategy; constructing a temperature field controller based on deep reinforcement learning; and a dynamic fuzzy immune optimization algorithm is adopted to adjust cooling control parameters, and intelligent optimization control over heat distribution of the die-casting die is achieved.

The invention discloses an industrial robot health state monitoring method and system based on digital twinning, and relates to the technical field of equipment monitoring, and the method comprises the steps: collecting the real-time state data of an industrial robot through a plurality of sensors, and enabling the real-time state data to be matched and aligned with a three-dimensional simulation model, and constructing a digital twinning model; obtaining twinborn data through the digital twinborn model after the adaptive model parameter update, and fusing the twinborn data with the real-time state data to generate a multi-source heterogeneous data set; feature data representing the health state of the industrial robot is obtained through feature selection to construct health indexes; and constructing a health state evaluation model based on the deep belief network, and taking the current health index parameters as model input to obtain an industrial robot health state evaluation result. Multi-source heterogeneous data such as vibration data and electrical data are fused, the health state of the industrial robot is monitored and evaluated in combination with digital twinning, and a reliable reference basis is provided for state monitoring and maintenance of the industrial robot.

The invention discloses a substation equipment state monitoring and intelligent fault early warning method based on deep learning. The method comprises the following steps: S1, obtaining a preprocessed multi-source state data set; s2, generating a high-dimensional equipment state feature matrix; s3, a fault sensitive deep belief network model is adopted to form a preliminary fault state recognition result; s4, obtaining an optimized sensitive depth belief network model; s5, performing online analysis on the multi-source state data acquired in real time by using the optimized sensitive deep belief network model, generating a real-time fault prediction result of the equipment state, and classifying and grading fault risks; and S6, according to a real-time fault prediction result, triggering a remote fault early warning mechanism, and sending fault early warning information including a fault risk level, an early warning signal and an emergency processing suggestion to a substation operation and maintenance center. According to the invention, intelligent alarm linkage and hierarchical control of the scheduling system are effectively supported.

The invention relates to the technical field of cold-chain logistics monitoring, and discloses a temperature prediction method and system for a multi-modal AIGC cold-chain logistics monitoring platform, and the method comprises the steps: carrying out the multi-modal data collection and data fusion of a cold-chain logistics transportation process based on a cold-chain logistics monitoring platform, and obtaining a multi-modal fusion data matrix; inputting an AIGC model to carry out feature extraction and inter-modal feature weight calculation to obtain a multi-modal feature importance vector; performing cross-modal weighted fusion calculation and associated feature map construction to obtain a temperature state feature sequence; inputting a multi-modal deep belief network to carry out probability distribution modeling to obtain a temperature prediction probability distribution sequence; performing time sequence characteristic analysis to obtain a temperature prediction interval sequence; and performing dynamic threshold judgment to obtain a multi-stage temperature early warning trigger signal. According to the invention, the temperature prediction accuracy of the cold-chain logistics monitoring platform is improved.

The invention relates to a water conservancy equipment service life prediction and fault monitoring method. The water conservancy equipment service life prediction and fault monitoring method comprises the steps of performing comprehensive digital modeling on water conservancy equipment, determining a fault sensitive area and a key monitoring point, generating a sensor deployment scheme, preprocessing analog and simulated sensor data, and ensuring that the data is comprehensive and targeted; performing multi-domain fusion feature extraction, deep feature learning and correlation analysis on the data, screening out important features to form a feature subset, and capturing equipment fault features in all directions; a mixed life prediction model is constructed, parameter initialization, pre-training and formal training are completed, a multivariate Gaussian mixture model and a deep belief network are constructed, and then a fault monitoring model is obtained; sensor data arranged according to a deployment scheme is obtained in real time, features are extracted after preprocessing, real-time feature vectors are input into a life prediction model and a fault monitoring model respectively, life prediction and fault monitoring of the water conservancy equipment are achieved, powerful decision support is provided for equipment maintenance, reliable operation of the water conservancy equipment is guaranteed, and fault loss is reduced.

The invention provides a method and a system for identifying and cleaning abnormal data, which relate to the technical field of data processing, and are used for identifying and cleaning abnormal data by acquiring real-time data flow, determining a self-adaptive threshold value by using a trained Gaussian mixture model and detecting abnormal data points. A deep belief network and long and short term memory network composite model is adopted to carry out deep feature learning and anomaly verification, and high-level feature representation and anomaly degree quantitative evaluation results are obtained; and evaluating a conditional dependency relationship among the abnormal data points by using the probability graph model, constructing a target probability dependency graph, and generating an abnormal data point recognition result. Based on an identification result, a reward mechanism excitation algorithm is applied to optimize a cleaning strategy; according to the method, the to-be-determined abnormal region is identified, the multi-modal fusion technology is introduced to perform correlation analysis, and the data in the to-be-determined abnormal region is judged and cleaned based on the analysis result to obtain the target cleaning strategy, so that the abnormal data identification and cleaning efficiency and accuracy are improved, and the method has relatively high adaptive capability and expansibility.

The invention relates to the technical field of aircraft structure detection, and discloses an aircraft structure crack intelligent identification method based on deep learning. The method comprises the following steps: acquiring original vibration response signals and electromagnetic field distribution data on the surface and inside of an aircraft structure in parallel through a multi-source sensor network; synchronously processing the data by using a multi-scale convolutional neural network, and extracting time-frequency domain abnormal fluctuation features and space magnetic field distortion features; constructing a cross-modal correlation model, analyzing a topological dependency relationship of the two types of features through a graph attention mechanism, and generating a fused damage sensitive feature vector; inputting the vector into a pre-trained deep belief network to obtain a probability distribution mapping relation for different crack types; and according to the mapping relation, carrying out adaptive weighted fusion on original multi-sensor data, inhibiting environmental noise and structural background interference, and separating and reconstructing an accurate three-dimensional morphology map of the target crack. According to the method, multi-source data information can be effectively fused to improve the accuracy of aircraft structure crack identification.

The invention relates to the technical field of water quality detection, and discloses a water quality pollutant detection method, system and equipment based on spectral analysis, and the method comprises the following steps: carrying out real-time spectral data acquisition on a water body sample in a vehicle driving process through a multispectral sensor array in a vehicle-mounted water quality detection device; obtaining a water body spectrum three-dimensional data cube; carrying out anti-vibration wavelength calibration and ambient light source interference elimination processing to obtain a preprocessed spectrum data set; performing standard multivariate decomposition processing and horizontal local constraint optimization of a pollutant target wave band on the preprocessed spectrum data set to obtain enhanced feature fingerprint spectrums for different types of water quality pollutants; and inputting the enhanced feature fingerprint spectrum into a deep belief network model to perform pollutant feature matching analysis to obtain various pollutant types and corresponding concentration values in the water body sample, thereby effectively eliminating ambient light changes and other background interferences, not only determining the pollutant types, but also accurately quantifying the concentration values.

The invention relates to the technical field of Bluetooth earphones, and discloses a Bluetooth earphone automatic pairing method and device for multi-terminal switchover, and the method comprises the steps: carrying out the equipment information scanning of a preset region range of a Bluetooth earphone, obtaining an equipment identifier, a signal intensity value and an equipment state parameter, and storing the equipment identifier, the signal intensity value and the equipment state parameter in a priority database; inputting a double-layer deep belief network to perform feature mapping calculation to obtain an equipment connection score; establishing a first equipment priority queue and performing dynamic updating calculation to obtain a second equipment priority queue; distributing independent signal processing channels for parallel processing to obtain effective connection equipment; performing periodic acquisition, and generating a switching instruction when a difference value exceeds a preset threshold value; according to the method and the device, the probability of switching failure is effectively reduced, and the stability of automatic pairing of the multi-terminal switching Bluetooth headset is improved.

The invention provides a distributed BMS battery active equalization type safety management method and system, and the method comprises the steps: obtaining the state information and performance change trend corresponding to each single battery through real-time monitoring, constructing a target battery pack topological structure model, combining a reinforcement learning algorithm, generating an intelligent agent model, and employing the intelligent agent model and a fuzzy logic controller to achieve the active equalization type safety management of a battery pack. Determining an energy flow management scheme; based on the feedback data and historical data of the energy flow management scheme, using a deep belief network to construct an anomaly detection model, based on the anomaly detection model, generating a risk assessment report, and constructing a security record platform based on the block chain technology to obtain security record information; optimizing each model parameter based on the risk assessment report and the security record information, and generating a security management system in combination with a transfer learning algorithm and a quantum computing method; and high-precision monitoring, intelligent electric quantity balance regulation and control, anomaly detection, risk management and continuous optimization of the distributed BMS battery system are realized.

The invention provides a transformer substation fault intelligent analysis and diagnosis method and system based on big data, and the method comprises the steps: obtaining the surface and internal temperature data flows of all power equipment in a transformer substation, and the environment temperature and humidity data flow of the transformer substation in the operation environment of the transformer substation; performing cross-time-scale dynamic coupling on the temperature data stream and the environment temperature and humidity data stream to generate a heterogeneous temperature characteristic stream; based on the heterogeneous temperature characteristic flow, dynamically adjusting an association rule of the temperature anomaly of the power equipment and the operation state of the transformer substation; performing cross-device coupling analysis on the heterogeneous temperature characteristic flow through a deep belief network to generate a dynamic conduction topological structure; and generating a transformer substation fault diagnosis result in combination with the adjusted fault association rule and the dynamic conduction topological structure. According to the invention, the early warning accuracy and diagnosis efficiency of the substation fault are improved.

The invention provides a water source detection method and system based on an unmanned aerial vehicle, electronic equipment and a storage medium, and relates to the field of water source detection. The method comprises the following steps: collecting multi-source heterogeneous data; the method comprises the following steps: preprocessing multi-source heterogeneous data to obtain multi-scale feature data, and establishing a multi-dimensional hydrogeological feature space; and inputting the multi-dimensional hydrogeological feature space into a preset deep belief network, and generating a probabilistic distribution diagram of the hydrogeological elements in the detection area. And updating preset hydrogeological conceptual model parameters based on the hydrogeological element probability distribution map, inputting the multi-source heterogeneous data into the corrected hydrogeological conceptual model, outputting spatial and temporal distribution characteristic data, and generating a water source potential partition map through multi-criterion evaluation. And determining a high potential area according to the water source potential partition map, performing encryption detection on the high potential area to obtain encryption detection data, and determining an optimal water source point position coordinate based on the encryption detection data. According to the technical scheme, the accuracy of water source detection based on the unmanned aerial vehicle is improved.

The invention relates to the technical field of burn wound treatment, and discloses an intelligent burn wound dynamic monitoring and evaluation system. The system comprises a data acquisition module for acquiring real-time physiological data of a burn wound by using a multi-source sensor; the multi-modal feature fusion module is used for generating wound comprehensive state features based on a deep belief network; the dynamic evaluation module outputs a wound healing level and a risk early warning signal through a pre-trained collaborative evaluation model; the optimization decision generation module is used for constructing a multi-target dynamic optimization model to adjust a treatment scheme according to risk early warning; and the hierarchical execution control module realizes distributed execution of treatment instructions through a hierarchical control architecture. The system can comprehensively monitor the state of the wound surface, accurately evaluate the healing risk, optimize the treatment scheme and accurately execute the treatment scheme, effectively improve the treatment effect of the burn wound surface, reduce the infection risk and shorten the healing period, and has important clinical application value.

The invention discloses a product collaborative design management method and system based on data driving, and relates to the technical field of product design management, and the method comprises the steps: constructing a double-flow heterogeneous quantitative collection network; establishing an incidence matrix and calculating dynamic coupling strength among the parameters; designing a recursive deep belief network based on the incidence matrix and the dynamic coupling strength, encoding product structure parameters and design process data into a probability graph model, and constructing a design knowledge base; dynamically distributing the design rules in the design knowledge base by adopting a swarm intelligent optimization algorithm, generating a collaborative decision-making unit, and establishing a constraint propagation link; and generating a multi-target collaborative optimization scheme group, and screening an optimal scheme group based on Pareto frontier. According to the invention, omnibearing acquisition of product structure parameters and design flow data is realized through the double-flow heterogeneous quantitative acquisition network, and the data integrity is improved.

According to the cooling tower early fault early warning method based on vibration state monitoring, vibration signals and working condition labels of key parts of the cooling tower are synchronously collected through multiple channels, and data quality is improved through preprocessing operation such as band-pass filtering and normalization; time-frequency features are extracted in a multi-scale mode through self-adaptive variational mode decomposition and wavelet packet transformation, signal complexity is quantized through energy entropy, and weak fault detection capacity is enhanced; the obtained features are input into a deep belief network after being subjected to principal component analysis dimensionality reduction, and automatic classification and recognition of the equipment operation state are achieved; dynamic early warning grade adaptation is carried out according to an identification result in combination with a working condition label, the environmental adaptability and stability of early warning are effectively improved, the method further has the functions of early warning sample recording and periodic model iterative optimization, and the fault identification precision and robustness in a complex noise environment are remarkably improved.

The invention provides a satellite attitude control system fault diagnosis and fault-tolerant reconstruction method and system, and relates to the technical field of satellites, and the method comprises the steps: obtaining attitude data through a Kalman filtering state observer, building a fault diagnosis model, generating a residual sequence, and carrying out the adaptive dynamic threshold calculation to obtain a fault feature vector; and inputting the feature vector into a pre-trained deep belief network for fault diagnosis, and determining the fault type and degree. According to a diagnosis result, a mixed integer programming model considering attitude control precision and actuator power constraint is established, an improved genetic algorithm is adopted for solving, an actuator reconstruction scheme and controller parameters are obtained, and fault-tolerant control is achieved. According to the invention, faults can be diagnosed rapidly and accurately, fault-tolerant reconstruction is carried out according to fault types and degrees, the reliability and stability of a satellite attitude control system are effectively improved, and the satellite attitude control precision is ensured.

The invention belongs to the technical field of metallurgical equipment intelligent control and digital twinning, and provides a metallurgical equipment twinning HMI control system based on multi-source data, and the system comprises a multi-source data collection module which is used for collecting the multi-source data; the data fusion processing module is used for performing data fusion processing on the multi-source data by adopting a space-time alignment algorithm and a feature extraction network; the digital twinborn modeling module is used for constructing a metallurgical equipment digital twinborn model by utilizing an improved deep belief network algorithm based on the fusion processing data; the HMI interaction module is used for dynamically presenting the fusion processing data and the operation state data of the metallurgical equipment digital twinning model based on the output of the digital twinning modeling module; and the intelligent control module is used for performing closed-loop control on the metallurgical equipment by adopting a self-adaptive predictive control algorithm. According to the invention, full-process intelligent management of the metallurgical equipment can be realized, and the operation efficiency, the control precision and the reliability of the metallurgical equipment are remarkably improved.

An apparatus including a Deep Belief Network is configured to receive, via a processor, input data. The processor is caused to initialize, based on the input data, weights for a learning model of the DBN. The processor is further caused to generate, via the learning model, a representation of the input data. The weights, the input data, and the representation is to be transmitted to a quantum compute device. The processor is caused to receive sampled values from the quantum compute device using an optimization function associated with the quantum compute device. The processor is further caused to update, based on the sampled values, the weights to train the learning model to produce a trained learning model. The trained learning model is configured to generate an updated representation of the input data. The processor is further caused to generate, via a regression layer, output data based on the updated representation.

The invention relates to the technical field of point cloud processing, and discloses a point cloud data processing method, system and device for industrial three-dimensional model construction. The method comprises the following steps: carrying out denoising and down-sampling processing on original point cloud data of an industrial part to obtain preprocessed point cloud data, calculating a local geometric descriptor, converting the local geometric descriptor into an industrial feature recurrent plot through a recurrent plot algorithm, inputting the recurrent plot into a convolutional neural network to extract a high-dimensional geometric feature vector, and mapping the feature vectors into B-spline curved surface control parameters through a deep belief network, and performing point cloud reconstruction quality evaluation according to the control parameters to obtain geometric accuracy error data and curved surface reconstruction integrity data. According to the method, the problems that in existing industrial three-dimensional model construction, a point cloud data processing method lacks intelligent feature recognition, the reconstruction precision is insufficient, and manufacturing constraints are not fully considered are solved, and the recognition accuracy of geometric features of complex industrial parts and the precision of three-dimensional model reconstruction are improved.

The invention relates to the technical field of electromagnetic interference signal processing, and provides a grading method and system for partial discharge live detection electromagnetic interference signals of a traction substation. The method and the device are used for solving the problems of difficulty in accurately classifying various types of electromagnetic interference signals, difficulty in adapting to changes under different working conditions, poor adaptive adjustment capability and insufficient adaptability in the prior art. The method comprises the following steps: constructing a dynamic graph model to process an electromagnetic interference signal data stream, and generating fusion data; carrying out real-time anomaly detection on the data, and carrying out adaptive context awareness classification in combination with reinforcement learning and a deep belief network; extracting space-time spectrum characteristics of the electromagnetic interference signals, constructing an interactive expert system, generating target parameter configuration, and obtaining a preliminary grading result; and adjusting each algorithm parameter to generate a final grading result. According to the technical scheme provided by the invention, an efficient and intelligent electromagnetic interference signal processing method is provided, the accuracy and the reliability of a grading result are ensured, and the efficiency and the effect of electromagnetic environment management are improved.

The invention discloses a method for managing medical risks, and particularly relates to the technical field of medical management, and the method comprises the steps: S1, deploying a multi-modal noninvasive biosensor, and collecting the physiological data of a patient; s2, integrating data sources, and performing cleaning and standardization processing to ensure data consistency and accuracy; s3, performing feature extraction and correlation analysis by using a deep belief network and a graph neural network, and identifying a potential risk mode; and identifying a potential risk mode through high-dimensional feature extraction and complex correlation analysis. And by utilizing self-supervised learning and a generative adversarial network, hidden risks can be efficiently detected, and potential health problems can be warned in advance. A personalized risk assessment and multi-level response mechanism provides accurate intervention measures for each patient, and the quality and efficiency of medical services are improved. Meanwhile, according to the method, continuous data collection is achieved through the noninvasive sensor network, it is guaranteed that the patient is not interfered in the monitoring process, and the comfort level and compliance of the patient are improved.

The invention discloses a coal mine underground navigation control system and device based on big data, and particularly relates to the technical field of underground navigation control. The underground roadway waveguide effect grade is judged by monitoring underground radio signals in real time and recognizing a signal reflection mode by combining wavelet transform with a convolutional neural network; meanwhile, three-dimensional point cloud data of the underground roadway are processed through multi-scale curvature analysis and a DBSCAN clustering algorithm, and division of a structure mutation region is achieved; determining a navigation error level according to the waveguide effect level and a structure mutation result, and when the navigation error level reaches a second level or a third level, analyzing historical navigation trajectory data by using a dynamic time warping algorithm, and evaluating a current navigation path deviation degree; comprehensive analysis is carried out through the deep belief network, the reliability of the navigation control system is evaluated, whether a path re-planning instruction is triggered or not is judged, and the underground navigation precision and safety are improved.

The invention provides a full-link electricity consumption monitoring method, system and equipment based on intelligent Internet of Things, and relates to the technical field of power system management. The method comprises the following steps: acquiring operation data acquired by an intelligent sensor group deployed at a power network node in real time, and executing localized carbon flow accounting according to the operation data through an edge computing node; constructing a joint probability model based on Monte Carlo simulation and a deep belief network, and generating a node carbon flow density matrix under multiple scenes; dynamically updating an electricity-carbon conversion coefficient according to real-time energy structure data, and calculating node-level carbon emission: optimizing a power grid topology and an energy storage scheduling strategy by adopting a double-delay depth deterministic strategy gradient algorithm TD3 and taking a carbon flow density matrix as a constraint condition; and generating an intelligent report including a carbon footprint thermodynamic diagram, emission reduction potential evaluation and block chain evidence storage. According to the invention, the capability of multi-target collaborative optimization of the security and economy of the power grid can be improved.

The invention relates to the technical field of tunnel monitoring, and discloses a tunnel fan health diagnosis and early warning system and method based on multi-source fusion, comprising a sensing layer, a data acquisition and transmission layer, a data processing and fusion layer, an intelligent diagnosis and early warning layer and an application layer which are arranged in sequence from bottom to top by adopting a layered architecture, all the layers cooperate to achieve tunnel fan collision safety and equipment health two-dimensional management and control. Vibration, displacement, strain, temperature and power multi-source monitoring data are fused, single-parameter monitoring limitation is broken through, wind turbine typical faults such as bearing damage, coupling misalignment and foundation looseness and specific risks such as over-limit vehicle collision are covered, and a full-dimension monitoring system is constructed. By means of a deep belief network (DBN), a convolutional neural network (CNN) and an MATLAB core algorithm, and in combination with a fault-feature mapping library and a multi-evidence combined judgment mechanism, the fault diagnosis accuracy is greatly improved.

The invention provides an electromechanical equipment fault prediction method and system based on multi-source information fusion, and the method comprises the steps: collecting operation data, including vibration data, temperature data and current data, during the operation of electromechanical equipment; performing feature extraction on the operation data based on a principal component analysis algorithm to obtain a fusion feature vector; inputting the fusion feature vector into a fault prediction model based on a deep belief network, and outputting a prediction result; wherein the deep belief network adopts a small-batch stochastic gradient descent algorithm combined with an adaptive learning rate adjustment strategy during training; and judging whether the electromechanical equipment has a fault hidden danger or not according to the prediction result. According to the method, the relevance between different types of data is mined, and the defect of low prediction precision is overcome.

The invention discloses a pseudo-satellite layout optimization method based on a deep belief network and a particle swarm, and relates to the technical field of base station deployment optimization, and the method comprises the steps: firstly constructing a non-exposed space pseudo-satellite base station layout constraint index; secondly, determining a pseudo satellite base station layout optimization performance evaluation index; then constructing a pseudo satellite base station layout optimization mathematical model; training the collected data based on a deep belief network to generate a DBN model; the training process comprises an unsupervised pre-training stage and a supervised fine tuning stage; and finally, based on a DBN-PSO algorithm, obtaining an optimal layout scheme of the pseudo-satellites in the current environment. According to the method provided by the invention, by comprehensively evaluating the layout performance of the pseudo satellite and combining the advantages of unsupervised learning and supervised learning, the efficiency of the optimization process is improved, the resource consumption is reduced, the optimal layout scheme under various constraint conditions is realized, and the overall efficiency of a navigation system is improved.

The invention discloses a predictive cruise control method and system for a commercial vehicle. The method comprises the steps that road gradient information provided by a high-precision map and a target cruise vehicle speed corrected by a deep belief network driving style model are obtained to serve as input parameters; according to the rotating speed and the torque of the engine, a weighted moving average algorithm is adopted to carry out averaging processing on the power value within a short period of time, and the current engine power is generated; on the basis of an automobile power balance equation, according to the current position and the slope value of the front road, the driving power requirement of the next slope section is predicted; and in combination with the efficient output power interval of the engine, the recommended gear and the optimal accelerator opening degree of the next slope section are generated according to different power demand conditions. Therefore, according to the predictive cruise control method for the commercial vehicle, the gears and the accelerator can be adjusted in a self-adaptive mode according to the road gradient and the driving habit, the driving efficiency and the fuel economy are improved, and the individuation of the driving experience is enhanced.

The invention discloses a deep learning-based network public opinion monitoring method and system, and relates to the technical field of network public opinion data processing, and the method comprises the steps: carrying out the preprocessing and feature extraction of obtained network public opinion data; after feature extraction, a deep learning model is used for performing sentiment tendency and theme analysis on public opinions; performing public opinion trend prediction by adopting a method of combining an improved particle swarm algorithm and a BP neural network or a deep belief network; and the operation process is integrated into a network public opinion monitoring system to realize monitoring. The deep learning-based network public opinion monitoring method is implemented in a network public opinion monitoring system. According to the method, the problem of limitation of a traditional public opinion analysis method in the aspects of feature extraction, research and judgment accuracy and tracking real-time performance is effectively solved, and intelligent and automatic development of a network public opinion analysis technology is promoted.

The invention discloses an operation state and characterization state parameter method of a GIS isolation switch, and relates to the field of GIS isolation switch operation. Multi-source heterogeneous sensors including vibration, temperature, strain gauges, fiber bragg gratings, acoustic cameras and the like are deployed at key parts, and data are collected in a self-adaptive mode according to working conditions; processing data by using a deep learning noise reduction auto-encoder, adaptive weighted fusion and DBSCAN; deeply mining features by using empirical wavelet transform, a heat conduction model and the like; constructing a composite state parameter by means of a deep belief network and principal component analysis in combination with particle swarm optimization; the state is evaluated through a convolutional neural network of transfer learning, LSTM prediction and early warning are carried out, and a fault tree and a Bayesian network are combined to locate a fault. According to the invention, data is comprehensively collected, intelligent processing and deep mining are carried out, scientific state parameters are constructed, and accurate state evaluation and early warning are realized in combination with transfer learning; the adaptability is improved through self-learning and multi-modal fusion, the operation and maintenance efficiency is improved through a VR / AR visual platform, the risk of the power system is reduced, and benefits are remarkable.