1721results about How to "Improve recognition efficiency" patented technology

According to the goaf detection method based on transient electromagnetic and seismic wave field joint inversion, data acquisition and joint inversion are carried out on the goaf through the combination of the transient electromagnetic detection system and the reflection seismic detection system, the complementary advantages of the two detection methods are played, the bottlenecks of a single method in the aspects of resolution and signal-to-noise ratio are broken through, and the goaf detection method based on transient electromagnetic and seismic wave field joint inversion is realized. Fine characterization of the structure, the physical property and the stability of the goaf is realized; a machine learning classification algorithm is introduced to analyze a goaf multi-attribute feature data set, and intelligent discrimination of the type, scale and stability of the goaf under complex geological conditions is realized; establishing a quantitative response relationship between goaf physical property parameters and goaf electrical and elastic difference characteristic parameters, constructing a goaf transient electromagnetic and seismic wave field joint forward modeling numerical model, and constructing an electromagnetic-seismic joint inversion objective function; and calculating and solving to obtain goaf resistivity, seismic wave velocity three-dimensional distribution and uncertainty quantitative evaluation results, and reducing blind areas of goaf judgment.

The invention relates to the technical field of data desensitization, in particular to an electronic commerce platform information security desensitization scheme analysis system based on artificial intelligence, which comprises a data classification module, an access evaluation module, a dynamic desensitization module and a security audit module. According to the method, the data of the e-commerce platform is intelligently classified and evaluated by adopting an artificial intelligence technology, dynamic desensitization and finer access control of the data are realized, various data access requirements can be dynamically met by evaluating the sensitivity level of the file and the security level of the access request, data processing is performed according to requirements, and the data processing efficiency is improved. The security and privacy of user data are effectively protected, through automation of security audit, the recognition efficiency of abnormal behaviors is improved, the transparency and traceability of overall data management are enhanced, through real-time analysis and response, the risk of data leakage is reduced, and the practical value of data and the fluency of service operation are kept.

The invention discloses a traffic accident identification method based on unsupervised pre-training and a multi-modal large model, and the method comprises the following steps: S1, collecting and sorting video data in a traffic monitoring scene, selecting a video clip without a traffic accident as a data sample, extracting a video key frame, carrying out the unsupervised pre-training of a mask auto-encoder, and carrying out the unsupervised pre-training of the mask auto-encoder; reconstructing a video clip which is shielded randomly; s2, calculating a reconstruction error between the original video and the reconstructed video to evaluate the reconstruction quality, and screening out key frame video clips with poor reconstruction quality; according to the invention, through unsupervised training of the mask auto-encoder, even under the condition of limited annotation data, more traffic accident-free segments can be filtered, video segments in which traffic anomalies possibly exist can be rapidly screened out, and by constructing fine-tuning training of multi-modal traffic data on a multi-modal large model, the real-time performance of the model is improved. The method can improve the recognition accuracy and efficiency of a traffic accident in a complex scene, provides real-time alarm and detailed analysis, and takes countermeasures in time.

The invention relates to the technical field of fire hazard monitoring, and discloses a fire hazard remote monitoring and multistage early warning mechanism integration system which integrates a data acquisition module, a heat gathering map generation module, an image fusion module, a data calculation module, a risk prediction module, an early warning notification module and the like. Through an infrared temperature measurement unit, a smoke concentration acquisition unit and an image acquisition unit, the system can acquire temperature, smoke and image information of a key area in real time. A heat gathering map generation and image fusion technology is utilized, a fusion image is systematically generated, a fire scene and temperature distribution thereof are visually displayed, and the fire source positioning efficiency is improved. Meanwhile, the system analyzes the gradient change of the temperature, the heat accumulation area and the smoke concentration through a data calculation module, constructs a risk prediction model in combination with a machine learning algorithm, and achieves the refined prediction of the fire risk. And according to a prediction result, the early warning notification module automatically sends a corresponding early warning message to ensure rapid transmission and timely response of the early warning message. According to the invention, the intelligent, precise and efficient level of fire monitoring is improved.

The invention provides a high-density RFID tag group scanning system based on a multi-antenna array and beam forming, and relates to the technical field of the Internet of Things. The system comprises a multi-antenna array, an RFID reader-writer, a beam forming unit, a signal processing unit, a feedback unit and a data management unit. Through a digital beam forming technology, the system dynamically adjusts the direction and width of a beam, and achieves the precise scanning of a target area. And in combination with real-time signal feedback, a density peak clustering algorithm and a gradient descent algorithm are adopted to optimize beam parameters, so that the recognition efficiency is improved. The system further utilizes an anti-collision algorithm to dynamically adjust frame parameters, and performs logic grouping based on spatial positions and type characteristics of tags, so that signal collision and missed reading rates are remarkably reduced. Meanwhile, the data management unit stores and outputs the label data in a classified mode, and intelligent management capacity is provided for multi-scene application.

The invention discloses an e-commerce platform high-risk user identification method based on time series data analysis. The method comprises the following steps: S1, constructing a user behavior data set; s2, organizing the collected original user behavior data into a behavior sequence according to a time sequence based on the collected original user behavior data set; s3, performing data cleaning on the generated user behavior sequence; s4, carrying out clustering analysis on the preprocessed behavior sequence by adopting a time sequence clustering algorithm in Scikit-learning, and identifying a user group with similar behavior characteristics; s5, dividing the user behavior modes into different risk categories based on a clustering analysis result; s6, automatically labeling new potential high-risk users on the basis of labeled high-risk user data by utilizing a semi-supervised clustering algorithm, and expanding a risk identification range; s7, generating a corresponding risk score; and S8, performing collective management and prevention for high-risk user groups. According to the method, the user groups with similar high-risk characteristics can be identified, and the flexibility and effectiveness of the system in coping with different risk scenes are improved.

The invention relates to the technical field of pattern recognition, in particular to an AI-based breathing anomaly recognition method and system, which comprises the following steps of: extracting a time sequence analysis trend value, a local amplitude change value and a periodic change value in each group of data based on breathing frequency monitoring data and breathing depth analysis data; and comparing the time sequence trend value with the local amplitude change value to obtain a respiratory rhythm characteristic parameter set, and carrying out classification and partition statistics on the periodic change value to generate a respiratory rhythm preliminary partition result. According to the method, by carefully analyzing the respiratory frequency and depth, extracting the trend value, the local amplitude and the periodic change, deeply analyzing the respiratory rhythm, and accurately capturing the respiratory dynamic state, the cross matching fluctuation amplitude and the trend rate by utilizing a partitioning and classifying method, the comprehensiveness and the recognition precision in respiratory monitoring are improved; the abnormal interval deviation value is associated with the respiratory frequency and depth difference, abnormal points are scientifically marked, and the detection efficiency and accuracy of the respiratory anomaly are effectively improved.

The invention discloses an online public opinion research, judgment, analysis, classification and grading early warning method and system, and the method comprises the steps: constructing a malicious public opinion data detection and judgment model, and carrying out the iterative training of a pre-training neural network through large-scale online public opinion historical data, so as to achieve the fine adjustment and optimization of the model; after malicious public opinion data are detected, fine-grained classification of malicious public opinions is realized through deep semantic comprehension and multi-dimensional text structure analysis by adopting BERT and ERNIE deep learning models and combining semantic role labeling and dependency syntactic analysis technologies; a malicious public opinion data grading and distinguishing model is constructed, deep correlation between public opinion events is captured through multi-layer convolution operation, and the recognition capacity for public opinion sensitivity and urgency degree is improved. According to the invention, malicious public opinion data related to a specific industry field can be efficiently and accurately identified and classified, and the malicious public opinion data is subjected to severity grading, so that the accuracy and the real-time performance of network public opinion management are improved.

The invention relates to the technical field of artificial intelligence and the field of financial science and technology, and discloses a risk event identification method and device, computer equipment and a storage medium, and the method comprises the steps: collecting service call records of all clients in a target time period, carrying out the preprocessing, obtaining recording data, and converting the recording data into text data; extracting voiceprint features of each piece of recording data through a voiceprint model, and performing PLDA scoring on any two voiceprint features to obtain a scoring result; recognizing a plurality of feature clusters based on the scoring results, calculating an average value of all the scoring results in each feature cluster, and generating a voice risk value; selecting a target feature cluster based on each voice risk value and a cluster screening strategy, and taking the voice risk value of the target feature cluster as a voice risk factor; generating a text risk factor of each piece of text data through a large language model; based on the voice risk factor and the text risk factor, identifying whether the target service call recording is a risk event through a risk event identification model; and the risk event identification efficiency and accuracy can be effectively improved.

The invention discloses a power distribution network visual management and control method and device, a storage medium and a product, and the method comprises the steps: obtaining the multi-dimensional information of a power distribution network in a target region, carrying out the preprocessing of the multi-dimensional information, obtaining a standardized power distribution network data set, carrying out the recognition of a power distribution network problem according to the power distribution network data set, and obtaining a power distribution network fault. The method comprises the following steps: obtaining a structured problem list of a power distribution network, carrying out spatial positioning and attribute mapping processing on the structured problem list in a preset geographic information system to obtain a power distribution network problem spatial distribution representation, and carrying out multi-dimensional analysis and prediction on the operation condition of the power distribution network according to the power distribution network problem spatial distribution representation. And obtaining a management and control strategy of the power distribution network, carrying out resource allocation according to the management and control strategy to obtain a cooperative work flow, and visualizing the problem space distribution representation of the power distribution network and the cooperative work flow in a geographic information system to provide a visual management and control mode. And the management efficiency and safety of the power distribution network are improved.

The invention relates to the technical field of financial data processing, in particular to a data processing method and system based on financial information bills. The data processing method comprises the following steps: acquiring multi-modal financial information bill data; and performing bill modal decomposition on the multi-modal financial information bill data to generate financial information bill modal decomposition data. Bond information price income prediction needs a large amount of financial data, such as market interest rate, bond expiration date, face interest rate and the like, the data are similar to the data form of bill modal decomposition, and a more accurate model can be obtained through standardization and feature extraction of multi-modal data. Therefore, valuable input is provided for bond price and income prediction. According to the invention, through multi-modal data fusion, counterfeited feature comparison modeling, abnormal bill clustering analysis and dynamic risk assessment, the security and accuracy of financial bill identification are improved.

The invention discloses a ship classification method based on multi-source information feature level fusion, and the method comprises the steps: firstly obtaining the HRRP and SAR original radar data of a ship target, carrying out the preprocessing of the HRRP original radar data, and generating two formats of HRRP samples; secondly, performing feature extraction on the HRRP sample in the first format to form traditional features; secondly, constructing a sequential network model branch, taking an HRRP sample in a second format as input, embedding a traditional feature, and outputting a mixed feature; a two-dimensional convolution model branch is constructed, SAR original radar data passes through a lightweight CNN network, and ship target structure features are extracted. And finally, designing a feature fusion module of an attention weighting mechanism, carrying out weighted fusion on the mixed features and ship target structure features, and outputting a ship classification result. According to the method, the problem that automatic target radar recognition is limited in recognition precision and performance based on single-modal data is solved, and the classification accuracy is improved.

The invention provides a converter valve fault identification method based on voiceprint small sample learning, and belongs to the technical field of artificial intelligence, and the method comprises the steps: obtaining a to-be-identified target audio comprising converter valve environment noise, and carrying out the noise reduction processing based on FRCRN, and obtaining a noise-reduced audio signal; carrying out feature extraction based on the Mel frequency cepstrum coefficient and the Gammatone filter bank cepstrum coefficient, and carrying out dimension reduction on features based on a principal component analysis method to obtain feature vectors; inputting the feature vector into a voiceprint recognition model which is completely trained based on a voiceprint small sample for recognition, and obtaining a recognition result; according to the method, the to-be-recognized audio is denoised based on the FRCRN, most noise in the converter valve environment can be filtered out, and the technical effect of accurately recognizing the to-be-recognized audio is achieved; by adjusting the structure of the voiceprint recognition network, useful information of the features can be highlighted, redundancy of repeated information is reduced, and therefore the recognition accuracy of the voiceprint recognition model in the converter valve noisy environment is improved.

The invention provides a data quality monitoring and repairing system, and belongs to the technical field of data repairing, and the system comprises an identification module which obtains data of a plurality of data sources, and automatically identifies a plurality of data quality problems existing in the data; the first determination module is used for determining a root cause and an influence path of a data quality problem based on a causal relationship reasoning technology; the evaluation module is used for evaluating the severity and the influence range of each data quality problem; the selection module is used for distributing priority for each data quality problem on the basis of a predefined rule according to the severity and the influence range, determining a processing sequence and selecting an optimal repair strategy for automatic repair; and the automatic repairing module is used for continuously monitoring the repaired data in real time, detecting a new data quality problem by utilizing a stream processing technology and a real-time analysis algorithm, and automatically repairing the data. The problems that data is inaccurate due to low identification efficiency and automatic and real-time processing of the data quality problem cannot be guaranteed are solved.

The invention relates to the technical field of data identification, in particular to a spectroscopy-based Chinese herbal medicine component identification method and system. The method comprises the following steps: carrying out difference wavelength characteristic analysis and wavelength calibration treatment on a quantitative Chinese herbal medicine sample to be detected to obtain spectrum calibration data of the Chinese herbal medicine sample to be detected; performing spectral feature recognition analysis and feature vector conversion processing on the spectral calibration data of the to-be-detected Chinese herbal medicine sample to obtain a spectral feature vector of the to-be-detected Chinese herbal medicine sample; performing vector classification processing and feature point set sampling processing on the spectral feature vectors of the Chinese herbal medicine sample to be detected to obtain spectral feature point sets of different components to be detected in the Chinese herbal medicine to be detected; and obtaining a spectral feature point set of known components of the Chinese herbal medicine, and carrying out incidence matrix mapping analysis and component extreme value identification analysis on the spectral feature point set of different to-be-detected components in the to-be-detected Chinese herbal medicine to obtain a component identification result of the to-be-detected Chinese herbal medicine sample. According to the invention, specific components in the Chinese herbal medicine can be identified more accurately and efficiently.

The invention discloses an intelligent identification method for high-position collapse geological disasters. The method comprises the steps that INSAR monitoring data, a radar topographic map and a remote sensing image map of a to-be-identified area are acquired; obtaining surface deformation information according to the INSAR monitoring data, and determining a hidden danger area according to the surface deformation information and a radar topographic map; registering the remote sensing image map of the hidden danger area based on the radar topographic map; and inputting the registered remote sensing image into a high-position collapse and slip identification model constructed based on CNN and RNN networks, and carrying out accurate identification on the high-position collapse and slip geological disaster point. According to the method, information of different data sources is fully utilized, the comprehensive capability and accuracy of geological disaster monitoring are improved, geological disaster monitoring is carried out on high-altitude collapse through multi-level and multi-angle analysis in combination with a deep learning network, the geological disaster occurrence place in a high-altitude area can be accurately recognized with high precision, and the geological disaster monitoring efficiency is improved. And scientific support is provided for geological disaster prevention and control work in high-altitude areas.

The invention discloses a multistage safety response control method of an industrial and commercial liquid cooling energy storage system, and relates to the technical field of electric energy storage systems, a sensor network collects an operation state data time sequence matrix, and abnormal data cleaning is carried out on the time sequence matrix; the method comprises the following steps: preprocessing a vibration signal of a cooling system, extracting characteristic data of abnormal vibration through Fourier transform and energy distribution analysis, and positioning a time-frequency distribution abnormal region; generating a time sequence multivariable data set according to the characteristic data of the abnormal vibration, determining a cause label according to the fused time sequence multivariable data set, obtaining the inherent frequency and the resonant frequency of the cooling system in combination with simulation analysis, and matching and determining the cause of the abnormal vibration; an LSTW neural network is used for predicting the abnormal resonance risk, and corresponding countermeasures are taken for the cooling network according to the prediction result; unnecessary vibration caused by error adjustment is avoided, the relation between cooling efficiency and safety is balanced, and unnecessary power loss is reduced.

The invention discloses a multi-source ship target identification method based on two-stage collaborative fusion, and relates to the technical field of signal processing, and the method comprises the steps: firstly collecting target sea area data, including original optical image and radar image data, by means of an optical camera and a radar sensor on an aircraft, and then carrying out the preprocessing of the collected data through Gaussian filtering; performing sea-land segmentation by using a deep learning algorithm, constructing a loss function optimization network parameter to obtain a segmentation mask, and removing a land background area according to a mask result to obtain processed optical and radar images; an improved SURF feature and graph cut algorithm combined registration method is adopted, optimal transformation parameters are obtained by screening feature point pairs and solving the minimum value of an energy function, and image registration is achieved; for the registered images, fusing the images based on an adaptive fusion rule; and finally, extracting corresponding features through manual feature extraction and feature extraction based on deep learning, and fusing the features to obtain a final target recognition result.

The invention discloses a modulation signal identification method based on continuous wavelet transform and deep learning, and the method comprises the steps: firstly modulating a to-be-transmitted sequence at a transmitting end, obtaining a wireless continuous time signal at a receiving end, sampling the continuous time signal, carrying out the wavelet decomposition of the sampled data, and filtering out the high-frequency noise; carrying out reconstruction by using wavelet inverse transformation, and carrying out median filtering on the reconstructed signal to obtain a new data set; performing continuous wavelet transform on the new data set to obtain a time-frequency graph, and extracting feature information of a time domain and a frequency domain of the time-frequency graph to obtain a two-dimensional feature graph; constructing a convolutional neural network prediction algorithm model, and training the convolutional neural network prediction algorithm model by using the two-dimensional feature map extracted by continuous wavelet transform; and finally, classifying the modulation modes of the signals by using the trained convolutional neural network prediction algorithm model. According to the method, the modulation signal identification accuracy in a complex environment in reality is improved, the network parameter quantity is reduced, and the modulation signal identification efficiency is improved.

The invention discloses a deep learning method for desertification grassland mouse hole recognition based on a neural network model, and belongs to the field of image recognition. The method solves the problems of low efficiency and poor accuracy of an existing mouse hole recognition method, constructs a mouse hole distribution image set through a high-resolution image obtained by an unmanned aerial vehicle, identifies a desertification grassland mouse hole sample according to the mouse hole distribution image set, can obtain a mouse hole feature data set, and achieves the recognition of a mouse hole based on a neural network model. The mouse hole feature data set is used for training the neural network model, mouse holes can be trained and recognized, then the test set is used for testing the trained neural network model, the performance of the neural network model can be evaluated, the steps are repeated, machine deep learning is carried out, and the accuracy of machine learning is improved. The neural network model parameters can be configured, the accuracy of the neural network model can be verified, the grassland mouse hole recognition deep learning method based on the neural network model is finally obtained, and the recognition efficiency and precision of mouse hole recognition can be improved based on the method.

The invention relates to the technical field of RFID chip manufacturing, in particular to an RFID chip image anomaly detection method and system based on intelligent learning. The method comprises the following steps: acquiring a real-time RFID chip sampling image set, performing feature alignment based on a registration template, generating an average grey-scale map by using an alignment image set, and obtaining a chip edge mask image set by using an edge search algorithm; segmenting the edge mask image set of the RFID chip to obtain an effective edge mask variance image set of the RFID chip; integrating the variance image set to obtain a pre-generated variance image; acquiring field environment data of the RFID chip and performing sensitivity coefficient estimation to obtain an edge sensitivity coefficient; and performing convolution filtering smoothing processing on the pre-generated variance image to obtain a chip edge variance image, and constructing an RFID chip image anomaly detection model based on the edge variance image and the average grey-scale image. According to the invention, the detection accuracy and stability are improved.

The invention provides a hilly and mountainous area tracked vehicle intelligent chassis system and algorithm based on environmental perception and road surface recognition, and belongs to the technical field of agricultural mechanical equipment. The system comprises a mechanical structure part and a control system part. According to the algorithm, multi-modal sensing and fusion decision making of the mobile terminal are achieved, the FPN + ResNet50 algorithm, the IPM image inverse perspective algorithm, the 3D sparse convolutional graph neural network, the TSDF truncation signature distance algorithm, the MDU algorithm, the gating modal sensing convolutional network and the Pi-Sigma fuzzy neural network learning algorithm are innovatively combined, the recognition precision and the decision making reliability are guaranteed, and meanwhile, the fusion decision making efficiency of the mobile terminal is improved. And the calculation amount and the calculation cost are reduced, and the recognition efficiency is improved, so that more accurate, timely and reliable recognition perception and feedback control are realized. The algorithm comprises the steps of image acquisition, image feature extraction, feature fusion, feature comparison and the like, and the method is not only suitable for field operation of tracked vehicles in complex hilly and mountainous areas, but also suitable for transfer driving of the tracked vehicles in a working environment.

The invention discloses an image recognition method and system for contact corrosion, and the method comprises the following operation steps: obtaining a to-be-detected contact image, and carrying out the preprocessing of the to-be-detected contact image, and obtaining a contact gray image; acquiring a defect area of the contact gray level image to obtain a plurality of suspected areas; clustering is carried out according to the brightness values of the pixel points in the suspected areas, and a rusted area is obtained; calculating a surface fading index according to the brightness value of each pixel point in the suspected area, and calculating a corrosion comprehensive characteristic index of the corrosion area according to the surface fading index; and judging whether corrosion exists in the corrosion area or not through the corrosion comprehensive characteristic index, and obtaining a final recognition result of the to-be-detected contact image.

The invention relates to an intelligent automatic parking control device and method based on multi-sensor information fusion, and belongs to the field of vehicle intelligent control. The control device comprises an information acquisition module, a microcontroller and a vehicle control unit; the method comprises the following steps: acquiring parking environment information through the point cloud information acquisition sensor, and acquiring parking space image information through the image information acquisition sensor; acquiring the current speed of the vehicle through a vehicle speed signal acquisition sensor; the deflection amplitude of a front wheel rotation angle is collected through a front wheel rotation angle signal collection sensor; the preprocessed image information and the point cloud information are fused through an unscented Kalman filter, the front wheel turning angle is calculated according to the position coordinates of the current driving state of the vehicle and the vehicle course angle, and the vehicle speed and the front wheel turning angle are controlled through a vehicle control unit so that the vehicle can be parked along a planned path. According to the invention, the coverage scene of the automatic parking method is expanded, and the accuracy of parking space detection and the comfort and stability in the parking process are improved.

The invention discloses a training-free action recognition method and system for skeleton point features based on AI recognition, and the method comprises the steps: obtaining an action video which needs to be recognized, and the action video comprises a standard action video and a to-be-detected action video; recognizing the action video and the action video to be detected by using an AI model for human skeleton point recognition, obtaining three-dimensional coordinate data of each skeleton point, and obtaining posture and track data of the standard action and posture and track data of the action video to be detected according to three-dimensional coordinates; and comparing the posture and track data of the standard action with the posture and track data of the action video to be detected, and if a comparison result is within a set error range, identifying a response action. According to the method, one-by-one action AI training is not needed, only a standard video is recorded, actions are recognized through digital comparison, software generalization is high, and the method is suitable for multiple scenes; cost and time are saved, and industrial application is efficient; customized parameters are supported, different requirements are flexibly met, and the recognition precision and efficiency are improved.

The invention provides a coal rock recognition method and system based on image and XRF spectral information fusion, and relates to the technical field of geological rock recognition and classification, and the method comprises the steps: obtaining a to-be-detected coal rock image; inputting the coal rock image into an image detection model to obtain suspicious coal gangue and position information thereof; the method comprises the following steps: performing element testing on suspicious coal gangue, acquiring element information, inputting the element information and a suspicious coal gangue image into a fusion classification model, extracting element features through an element feature extraction module, extracting image features through an image feature extraction module, performing matrix multiplication on the image features and the element features in an initial fusion module, and performing fusion classification on the suspicious coal gangue; and performing deep fusion on the similarity matrix and the image features to obtain initial fusion features, and obtaining a classification result of the coal / coal gangue by using the initial fusion features.

The invention belongs to the technical field of building construction safety management, and provides a construction safety early warning method and system based on mixed reality, and the method comprises the steps: converting the longitude and latitude of geographic coordinate system data into plane coordinates, and converting the plane coordinates into a local coordinate system of a spatial mapping grid formed by simultaneous positioning and a map construction technology; through coordinate transformation, geographic coordinate system data can be accurately mapped into a model space coordinate system of the mixed reality equipment, the limitation that external high-precision positioning data are difficult to integrate in a traditional mixed reality technology is broken through, and high-precision equipment positioning is realized; meanwhile, an initial weight value is distributed to each grid unit in the space mapping grid, the weight is dynamically adjusted to change the size of the grid, dynamic management of space mapping grid data is achieved, detailed real space mapping grid data can be reserved after initial alignment is carried out through the space mapping capacity of mixed reality equipment, and the space mapping capacity of the mixed reality equipment is improved. And a data basis is provided for subsequent dynamic collision detection.

The invention relates to the technical field of power supply monitoring, in particular to a power supply monitoring system with a hierarchical authority encryption function, which comprises an edge calculation processing module for reading voltage, current and load data based on a power supply monitoring node, calculating voltage fluctuation in sections, monitoring current change in real time, comparing amplitude and screening a sudden change value; load balance and abnormity are judged, and power node fluctuation characteristics are generated. According to the method, the current and voltage signal characteristics are analyzed step by step by adopting the mode matching algorithm, the power abnormal event is accurately captured, the identification efficiency of the fault event is effectively improved, the false alarm and missing report conditions are reduced, and the accuracy and timeliness of power monitoring are ensured; the fault source node is positioned by using the Bayesian network in combination with the power grid topological relation, so that the fault point is quickly and accurately judged, the positioning time is shortened, the monitoring and management level of the power system is improved, and the stability and safety of the system are enhanced.

The invention discloses a pre-accepted work order closed-loop management system, which comprises a sensitive first-aid repair work order automatic research and judgment module, a non-sensitive work order handling module, a pre-accepted work order accurate closed-loop grading management and control module, a closed-loop process management module, a comprehensive auditing module and a visualization module, an intelligent grading management and control rule, a responsibility investigation mechanism, a timestamp technology and the like are embedded into the corresponding module to enhance the disposal effect of the pre-accepted work order; according to the invention, by establishing an online pre-acceptance work order closed-loop management system, sensitive emergency pre-acceptance work orders can be found in time, and the core problems of untimely work order reporting, information blocking, large workload, difficult supervision, difficult management and control, difficult statistical analysis, difficult employee assessment and the like in the existing pre-acceptance work order processing process are solved; and workers are assisted to realize whole-process closed-loop management of processing time node management and control of each link of a pre-accepted work order, accurate order making of sensitive problems, time-limited grading, automatic circulation and the like, and the quality and efficiency of power supply service are improved.

The invention discloses a tunnel lining steel frame recognition method based on GAR-Net and related equipment, spatial domain enhancement is performed on geological radar data to improve the robustness of a neural network structure, a GAR-Net network model is constructed, the network model comprises a mileage recognition model, a lining thickness recognition model and a steel arch recognition model, and the mileage recognition model, the lining thickness recognition model and the steel arch recognition model are used for recognizing a tunnel lining steel frame. The lining thickness recognition model and the steel arch recognition model perform lining thickness recognition and steel arch recognition on the basis of the mileage recognition model respectively, whether a tunnel lining steel frame has defects or not can be judged according to the lining thickness and positioning information of the tunnel steel arch, and the defects of traditional radar image interpretation are overcome. The method can achieve the automatic recognition of the tunnel steel arch and lining thickness, and remarkably improves the precision and recognition efficiency of the automatic recognition of a geological radar image.