317 results about "Residual neural network" patented technology

The embodiment of the invention discloses an outer wall thermal insulation defect diagnosis method and system based on artificial intelligence, and the method comprises the steps: firstly obtaining an infrared thermal imaging and visible light image sequence of a target building outer wall, the former comprising continuous temperature distribution data, and the latter comprising textural feature data in time-space alignment with the latter; performing dynamic temperature gradient analysis on the infrared thermal imaging image sequence to generate a three-dimensional heat conduction abnormal map, extracting surface deformation characteristics from the visible light image sequence to generate a structure deformation distribution map, and performing multi-modal characteristic fusion on the two to obtain a joint defect characteristic matrix; performing defect type classification and region positioning on the matrix based on a pre-trained deep residual neural network model, outputting a defect type identifier and a corresponding region boundary coordinate, and finally generating a diagnosis report containing a repair priority score and a material matching suggestion according to the defect type identifier and the corresponding region boundary coordinate, and sending the diagnosis report to a user terminal for visual display. And efficient and accurate external wall thermal insulation defect diagnosis is realized.

The invention discloses an operating room intelligent monitoring method and system based on monitoring video recognition, and relates to the technical field of medical safety supervision, and the method comprises the steps: collecting a video through an operating room camera array, and constructing an operation region panoramic sequence through a residual neural network and an optical flow field; a double-branch target detection network is adopted to extract the position of a medical worker, the body position of a patient and the characteristics of surgical instruments, and a surgical scene model is constructed; performing trajectory tracking based on skeleton key point extraction and Kalman filtering, and constructing a dynamic graph of the operation process; generating an operation process state report by using the time sequence diagram convolutional network and a multi-head attention mechanism; and comparing the operation specification library through a knowledge distillation algorithm, and carrying out grading recording on abnormal events. According to the invention, efficient abnormal event tracking and recording functions are realized, technical support is provided for operation quality control and safety management, and the overall performance of operating room intelligent monitoring is improved.

The invention relates to an electromechanical fault prediction and diagnosis method and system based on big data, and the method comprises the steps: collecting the operation state data of electromechanical equipment in real time, and synchronously obtaining historical associated data; performing dynamic feature extraction on the operation state data and the historical associated data, constructing a sliding mean value feature matrix, and calculating dynamic weights of feature parameters; generating a fusion weight coefficient according to the dynamic weight and a preset fault threshold interval; extracting a distribution density curve of a historical fault occurrence probability, and calculating a dynamic threshold value; performing weighted reconstruction on the sliding mean feature matrix based on the fusion weight coefficient, and outputting a fault type and an occurrence probability through a pre-trained lightweight residual neural network model; and when the fault occurrence probability exceeds a dynamic threshold value adjusted based on a historical fault occurrence probability distribution density curve, generating an electromechanical fault diagnosis result so as to realize the purposes of real-time monitoring of the operation state of the electromechanical equipment and accurate fault prediction and diagnosis.

The present invention relates to the technical field of railway inspection, and relates in particular to a railway foreign-object intrusion detection method and system based on deep learning. The method comprises: S10, acquiring image data to undergo detection; and S20, inputting the image data into a trained attention semantic segmentation network to obtain a foreign-object detection result. The attention semantic segmentation network is obtained by first training a preset attention semantic segmentation network architecture using a preconfigured data set, and then re-training the attention semantic segmentation network on specified image data using an adaptive correction algorithm. A backbone network architecture is obtained by inserting a specified attention mechanism at a specified position within a pre-selected residual neural network, and using three parallel dilated convolutions as an initial convolutional layer in the residual neural network. A dual-branch decoder combines an edge recognition branch and a semantic segmentation branch. The method is applicable to various scenarios, achieves improved detection accuracy and maintains a lightweight design.

The invention provides a welding equipment state monitoring method and device based on artificial intelligence, relates to the technical field of artificial intelligence and data processing, and obtains a vibration data flow corresponding to target welding equipment by collecting vibration signals generated in the operation process of the target welding equipment in real time. And time-frequency energy distribution corresponding to the vibration data flow is determined, and energy changes of the signals in two dimensions of time and frequency are revealed, so that the signal-to-noise ratio of the signals is enhanced, non-correlation frequency band interference is reduced, early fault signals are enhanced, and the sensitivity of the model to abnormal events is improved. Rapid change features and stable structure features in the to-be-identified data are extracted by adopting a preset dynamic gating attention mechanism through a deep residual neural network, so that the rapid change features and the stable structure features can be distinguished and weighted, and the sensitivity of the model to abnormal events (such as early fault impact) is improved; therefore, accurate equipment state analysis is carried out on the welding equipment.

The invention discloses a radar lifting control method and system based on meteorological monitoring, and relates to the technical field of radar lifting control, and the method comprises the steps: completing the switching of a power supply and communication after a radar is powered on, initializing a controller, collecting the data of a meteorological station, and generating a future fusion wind speed in real time through a Kalman filtering physical model and a residual neural network; future fused wind speed is converted into wind pressure for evaluation, the risk degree is judged according to the evaluation result, early warning is given out, and the controller is preheated to enter a lifting preparation state. The input stability is improved through meteorological data sliding window smoothing and feature extraction, wind speed dynamic prediction and uncertainty quantification are achieved through XGBoost prediction and residual variance estimation, the time sequence consistency and robustness are enhanced through remote API interpolation correction and adaptive extended Kalman filtering, residual correction is conducted through a neural network, the prediction precision is improved, and the prediction accuracy is improved. And a reliable decision basis is provided for radar lifting control.

The invention discloses a circulating fluidized bed temperature intelligent prediction method based on a physical information neural network, and mainly relates to the technical field of industrial process intelligent control and energy power engineering crossing. Comprising the following steps: S1, acquiring operation data of the circulating fluidized bed, and preprocessing the operation data to obtain a data set; s2, constructing a physical information residual neural network; s3, constructing a loss function of adaptive weight adjustment; s4, training the physical information residual neural network by using the data set, and performing iterative optimization in combination with the constructed physical information residual neural network and the loss function to obtain a bed temperature prediction model; s5, inputting operation data of the circulating fluidized bed into the bed temperature prediction model to obtain a bed temperature prediction value; the method can solve the problem of complexity and nonlinearity of dynamic prediction of the bed temperature of the circulating fluidized bed, can optimize the operation efficiency of the boiler, improves the combustion stability, and reduces the emission of pollutants.

The invention discloses a super-resolution image reconstruction method based on a multi-scale large-kernel convolution double-residual neural network, which is suitable for the field of image processing, and comprises the following steps: cutting a data set, inputting a cut original low-resolution image into a preprocessing module, carrying out image normalization and data enhancement operation, and carrying out image reconstruction; generating a preprocessed low-resolution image; the preprocessed low-resolution images form a distorted image block data set, and a training set, a verification set and a test set are formed; according to an existing distorted image block data set, a super-resolution image reconstruction method based on a multi-scale large-kernel convolution double-residual neural network is constructed; and inputting the data set into the constructed multi-scale large-kernel convolution double-residual neural network to extract semantic features, and amplifying a feature map by using an up-sampling module of the model to generate a super-resolution image. According to the method, a multi-scale large-kernel convolution and double-residual structure is introduced, a visual attention mechanism is used in the neural network, the extracted features better conform to human visual perception features, and super-resolution image reconstruction is more accurate.

The invention provides an insulator defect detection method based on mixed attention and multi-scale features. By constructing a multi-scale feature extraction module and combining a bottom-up residual neural network and a top-down reverse residual neural network, the ability of the model to extract different scale features is improved. An introduced multi-head mixed attention mechanism enhances the attention of the model to details and overall information through the combination of local attention and global attention. An improved Transform framework is combined with a multi-head mixed attention and Hungary bisection matching algorithm, so that the target distribution and detection precision is optimized, and the small defect recognition capability of the model under a complex background is improved. According to the method, high-precision detection is realized at low calculation cost, and particularly, the method has a remarkable detection effect and practical application value when being used for coping with multiple targets, complex backgrounds and small defects.

The invention belongs to the field of tunnel engineering construction, and provides an anomaly detection method and system before shutdown of a shield tunneling machine, and the method comprises the steps: collecting and preprocessing multi-system sensor data of the shield tunneling machine; performing grouping, feature extraction and dimension reduction processing on the data by adopting a hierarchical hybrid dimension reduction strategy; a multi-scale space-time attention residual error neural network model is constructed and trained; and real-time monitoring and shutdown early warning are carried out on the operation state of the shield tunneling machine. Experiments prove that the accuracy rates of the method on four test sets all exceed 95%, the F1 score is 0.90 or above, and the abnormal state of the shield tunneling machine before shutdown can be accurately predicted. According to the method, engineers can take measures in advance, construction period delay and economic loss caused by sudden shutdown are avoided, the safety and efficiency of shield construction are improved, and the method has important significance in promoting shield tunneling machine construction intelligentization.

The invention discloses an RIS-assisted indoor fingerprint positioning method based on a residual neural network, which is suitable for an RIS-assisted downlink multipath transmission SISO millimeter wave positioning system, and the system comprises a base station, an RIS and a user. The method is realized through the following steps: defining a received signal matrix of a user, including three-dimensional positions of a base station, an RIS, the user and a scatterer; normalizing the received signal matrix of the user to obtain a real value matrix as a sample; adjusting a three-dimensional position of a user in an indoor environment, recording a real three-dimensional position as a label, constructing a data set, and dividing the data set into a training set and a verification set; performing off-line training on the residual neural network by using the training set, optimizing network parameters and storing an optimal weight; in an actual positioning scene, processing a real-time received signal matrix, inputting the processed real-time received signal matrix into the trained model, and outputting a predicted three-dimensional position of a user; according to the invention, the RIS and the residual neural network are combined, the precision and robustness of indoor positioning are improved, and rapid positioning is realized.

The present disclosure belongs to the technical field of health status assessment of secondary circuits in power systems, and specifically relates to an image recognition method for a secondary circuit terminal based on contrastive learning and an improved CRNN. The method includes: step 1: pre-training sample data of a secondary circuit terminal block of a power system through the contrastive learning; step 2: improving a feature extraction layer of a CRNN by using a residual neural network; and step 3: introducing an ECA-Net on the basis of the step 2 to construct a recognition model for the secondary circuit terminal based on the contrastive learning and the improved CRNN. In the method of the present disclosure, an image of the secondary circuit terminal block can be accurately recognized, and the accuracy of image recognition, detection accuracy and detection efficiency can be greatly improved.

The invention provides an electricity meter running state online calibration method, which relates to the technical field of electric power metering, and comprises the following steps: acquiring voltage signals and current signals of an electricity meter to be calibrated under different load conditions, and extracting instantaneous phase characteristics and instantaneous amplitude characteristics of the voltage signals and the current signals; a voltage feature sequence and a current feature sequence are obtained, and a deep residual neural network model is constructed based on a load feature vector to output a dynamic compensation parameter matrix, so that online calibration is performed on a measured value of the electric meter. Therefore, the accuracy and the real-time performance of ammeter calibration under the complex load condition can be remarkably improved, the influence of environment change and nonlinear load characteristics on the calibration result is effectively avoided, and the long-term metering reliability of the ammeter and the operation efficiency of a smart power grid can be improved.

The invention discloses a sonar image classification method based on high and low frequency combined features, and the method comprises the steps: obtaining a to-be-recognized sonar image, inputting the to-be-recognized sonar image into a trained image classification network, and outputting a target classification result in the sonar image; the image classification network comprises a wavelet transformation module, a residual neural network, a bidirectional cross attention mechanism module, an adaptive fusion module and an output module, wherein the wavelet transformation module is used for transforming an input sonar image into a high-frequency sonar image and a low-frequency sonar image; the residual neural network has a high-frequency branch and a low-frequency branch which are parallel and is used for extracting high-frequency features and low-frequency features; the bidirectional cross attention mechanism module is used for performing interaction and complementation on the high-frequency features and the low-frequency features; the self-adaptive fusion module is used for performing deep fusion on high-frequency feature maps and low-frequency feature maps output by the high-frequency branch and the low-frequency branch; and the output module is used for classifying the fused image features and outputting a classification result of the target.

The invention provides a mineralogical substance composition testing method and system based on multispectral data fusion. The method comprises the following steps: separating out a first characteristic interference signal caused by the oxidation state of an iron element and a second characteristic interference signal caused by the oxidation state of a manganese element by adopting wavelet transform in a superposition region of a Raman spectrum signal and a visible light absorption spectrum; performing spatial weighting on the intensity of the first feature interference signal and the intensity of the second feature interference signal to construct a multi-dimensional feature vector, inputting the multi-dimensional feature vector to a pre-trained residual neural network, and combining a radioactivity attenuation parameter measured by a gamma spectrometer to determine the radioactivity attenuation of the first feature interference signal and the second feature interference signal. And generating a mineralogical substance composition test result containing a mineral phase, an isomorphic substitution ratio, color cause analysis data and a radiation safety level. According to the method, the collaborative interpretation of the multispectral data and the radiation parameters can be realized, the mineral component analysis precision is improved, the color formation mechanism is synchronously analyzed, and the radioactive risk level is quantitatively evaluated.

The invention discloses a visual detection test method for damage cracks of a solidified soil test piece, and particularly relates to the technical field of geotechnical engineering material detection. The method comprises the following steps: doping fluorescence labeling particles in a solidified soil test piece, and applying periodic load to induce crack formation after curing and forming; synchronously exciting fluorescent particles through an ultraviolet excitation light source, and collecting a short-wave fluorescence response image sequence; inputting the image sequence into a deep residual neural network model, identifying a nonlinear enhancement region of a fluorescence signal, and deducing a crack initiation position and a propagation path; constructing a three-dimensional dynamic model of crack evolution in combination with an image space reconstruction algorithm and time sequence comparison, extracting indexes such as a crack propagation rate, a bending angle and crack density, performing comparative analysis on the indexes and initial parameters of a material, evaluating a microstructure damage development mechanism, and outputting a visual damage evolution result; the method provided by the invention can realize high-precision, non-destructive and dynamic detection of the fine cracks in the solidified soil, and has the advantages of high identification sensitivity, strong modeling precision and good engineering adaptability.

The invention provides a monocular vision and sparse IMU rehabilitation action whole body posture estimation method and system, and the method comprises the steps: synchronously collecting video data and inertial data of human body rehabilitation actions through a monocular RGB camera and a plurality of IMUs, and cutting and zooming an image to a preset resolution; extracting a key point thermodynamic diagram from continuous N frames of images by using a sliding window and a residual neural network, and calculating 2D key point pixel coordinates of each frame; splicing the N frames of 2D key point pixel coordinates, the rotation matrix of the IMU and the acceleration signal into an input sequence; cross-modal time sequence modeling is carried out on an input sequence through time Transform, and after high-dimensional features are extracted, weighted average is carried out through a convolutional layer, and 3D relative key point coordinates of the last frame are output through a regression head. According to the method, by fusing monocular vision and sparse IMU cross-modal data, the problem of visual information loss caused by limb self-shielding is effectively solved, and the defect that a traditional pure vision method is insufficient in precision in rehabilitation actions is overcome.

One or more aspects of the techniques and models described herein provide for bidirectional recurrent neural network (BiRNN)-based digital pre-distortion techniques for radio frequency (RF) power amplifiers (PAs). As an example, a digital pre-distorter (DPD) system may implement residual learning and long short-term memory (LSTM) projection layer features to reduce computational complexity and memory requirements. Implementing the described unconventional techniques of applying residual learning in RNN (e.g., in BiLSTM), using LSTM projection to develop a DPD structure, or both, may provide several advantages over preexisting techniques. For instance, the complexity in training and pre-distortion may be reduced and significantly less memory may be required to store the DPD neural network coefficients (e.g., while achieving similar or better linearization performance compared to other LSTM models). Further, faster training convergence speed may be achieved (e.g., compared to other LSTM models).

The invention discloses a grinding state on-line monitoring method based on multilayer data fusion and a mathematical combined driving model, and the method comprises the steps: carrying out the signal collection through a multi-source sensor, carrying out the fusion according to a corresponding weight, and carrying out the noise reduction through stacking self-coding. When signals are extracted, frequency domain multi-dimensional features are fed into the residual neural network and the bidirectional double-layer LSTM fusion model after being subjected to Pearson correlation screening, and single-working-condition grinding state recognition is achieved. 10 types of discrete grinding states are defined, and a physical driving type empirical formula for working condition and monitoring signals and working condition and state characterization is established based on working condition parameters such as grinding depth and main shaft rotating speed. And generating a training data set by using an empirical formula, and training a cross-working-condition monitoring model through a transfer learning mechanism to realize cross-working-condition identification. According to the method, online accurate recognition of the grinding state is achieved, the limitation of traditional single-working-condition monitoring is broken through, and the problem of repeated data collection training is solved through the physical law of an empirical formula.

The invention relates to a Raspberry Pi-based fault arc positioning detection and electrical fire early warning method, and belongs to the field of fault arc fire. According to the method, Raspberry Pi is used as a core processing unit, multiple types of sensors are integrated, and multiple kinds of alternating current and direct current load data are collected to establish a typical multi-dimensional data waveform library; deep processing is carried out on multi-time-frequency features and wavelet transform features of the signals in combination with a residual neural network, multi-dimensional features of a fault arc are comprehensively captured, and alternating-current and direct-current universal fault arc detection is achieved; multi-dimensional data are analyzed, and the arc danger level is evaluated through the time difference of fault arcs detected by different sensors, so that graded alarm is realized. Meanwhile, the Bayesian network is used for reasoning and judgment, and accurate positioning of the fault arc is achieved. Through cooperative work with the cloud host, a remote monitoring and management platform is established. The invention provides an electrical fire early warning solution which is intelligent, real-time and high in reliability.

The invention discloses a porous asphalt concrete gap blockage identification method based on pavement noise signals, and belongs to the technical field of asphalt concrete blockage identification, and the method comprises the following steps: S1, collecting tire-pavement contact original noise signal audio data, and carrying out the preprocessing; s2, carrying out pavement gap blockage degree sensitive correlation analysis, and extracting multi-dimensional acoustic features; s3, dividing a single-layer drainage asphalt pavement data set and a double-layer drainage asphalt pavement data set, and giving a blockage level label to obtain a marked data set; s4, constructing a deep residual neural network model, and performing training and verification to obtain a gap blockage degree identification model; and S5, identifying porous asphalt concrete gap blockage. According to the method, the accurate classification of the gap blockage degree is realized through the blockage recognition model based on the acoustic characteristics, the optimal cleaning and maintenance opportunity can be determined, a scientific decision basis is provided for the maintenance of the porous asphalt concrete pavement, and the pertinence and economy of the maintenance are improved.

The invention discloses an underground pipe network construction segment supervision system based on deep learning. The method comprises the following steps: establishing a segment coordinate framework by using construction segment boundary information and mileage pile number information; constructing a super voxel graph; obtaining super voxel maps with consistent time sequences; generating a cross-modal feature vector; outputting a first abnormity identification result; updating the first dense residual neural network model to obtain a second dense residual neural network model; obtaining a third dense residual neural network model, and outputting a second uncertainty score and a third anomaly recognition result; and generating a structured anomaly report according to the third anomaly recognition result, the second uncertainty score and laws and regulations in the building information model and the geographic information model. According to the method, abnormal features of different spatial scales can be captured at the same time, meanwhile, multi-type abnormal structures are subjected to accurate grading identification, the generalization ability and the robustness adaptability to multi-scale anomalies are higher, and the probability of false alarm and missing alarm is remarkably reduced.

The invention discloses a three-dimensional vision measurement system error compensation method based on a spatial adaptive weighted RBF residual neural network, and particularly provides a spatial adaptive residual learning framework SAW-RFramework, in the first stage, global rigid body errors are eliminated based on a Kabsch algorithm, and point cloud rigid alignment is realized; in the second stage, a thin-plate spline kernel RBF interpolator is used for modeling a spatial smoothing error field, and position-related systematic deviation is captured; and in the third stage, a partition weighted residual neural network is adopted, and an improved residual compensation network is proposed for residual high-fluctuation nonlinear residual after RBF modeling: a regional importance coefficient is calculated based on a mean value and a variance of the residual in a self-adaptive three-dimensional grid, so that network training focuses on a high-error and high-fluctuation region. According to the method, the problems of insufficient global spatial modeling capability, low boundary region compensation precision, poor generalization capability and the like of an existing method can be solved; high-precision error compensation of the three-dimensional vision measurement system is realized, the measurement result reaches submillimeter precision, and the application reliability in robot control, man-machine interaction and precision manufacturing is improved.

The invention discloses a multi-sensor track management method based on spatio-temporal feature comparison, belongs to the field of multi-sensor information fusion and target tracking, and provides a track association algorithm based on spatio-temporal feature comparison by combining a bidirectional LSTM network and a residual neural network for the track association problem of multiple sensors and multiple targets. Through time feature extraction, space feature extraction, track feature comparison and a classifier module, conversion from a track association problem to a dichotomy problem is realized. And finally, through an analog simulation experiment, the convergence and generalization of the proposed network are verified. In a Monte Carlo experiment, the algorithm provided by the invention can reach the correlation accuracy of 95% or more, the trained network can quickly realize track correlation, and the track correlation effect is not sensitive to the influence of scene change.

The invention discloses a livestock and poultry behavior pattern abnormity identification method based on a distribution estimation algorithm and a residual network. The method comprises the following steps: S1, obtaining a livestock and poultry behavior uniform structure data set with a consistent structure; s2, constructing a livestock and poultry behavior probability distribution model and storing model parameters; s3, generating a behavior probability difference scoring matrix; s4, constructing a residual neural network model, completing model parameter initialization, and executing multi-layer residual operation to obtain a depth anomaly feature vector; and S5, marking a normal behavior mark or an abnormal behavior mark for each piece of livestock and poultry behavior data, generating a behavior track aggregation result in combination with the behavior abnormality judgment result and the corresponding timestamp information, and completing abnormal grade division on the behavior abnormality judgment result and the behavior track aggregation result according to a preset rule. According to the method, the collaborative change rule among the multi-modal data can be captured, so that the model can detect the significant probability deviation at the initial stage of stress or the early stage of sudden abnormality, and the method has higher prospective abnormality early warning capability.

The invention relates to the technical field of electroencephalogram signal processing, and discloses a focal epileptic seizure feature level identification method and system. The method specifically comprises the steps that electroencephalogram data are obtained, time sequence electroencephalogram data are generated, the electroencephalogram data comprise electroencephalogram signals, focal epileptic seizure feature tags and seizure interval tags, and in the subsequent feature extraction process, the type of seizure which each seizure specifically belongs to can be judged; and focal epileptic seizure characteristic wavebands with short duration and small range can be accurately captured. And on the basis, performing feature extraction on the time sequence electroencephalogram data by using a feature extraction model integrated with a strategy network, a residual neural network and a recurrent neural network. Wherein the policy network can optimize the data processing flow and improve the real-time response speed of the system. The residual neural network can deeply mine the dynamic characteristic relation in the complex electroencephalogram signals, and it is ensured that focal epilepsy characteristics can still be efficiently recognized under the complex background.

The invention provides a self-adaptive pulse width modulation method, medium and system for a charging pile, and belongs to the technical field of charging piles. The self-adaptive pulse width modulation method comprises the following steps: acquiring voltage and current values of a battery, calculating a charge state parameter and a tilt change rate of the battery, and calculating a load coefficient and a third-order precision index by combining a load sensing algorithm; and analyzing the current waveform by using Fourier transform to obtain a harmonic distortion index, and calculating a delay compensation function value. The core technology is to call a deep residual neural network model of a double-path parallel architecture, input multi-dimensional characteristic parameters, output optimal pulse width modulation parameters and generate pulse width modulation signals to adjust charging characteristics. Meanwhile, the temperature and the internal resistance value of the battery are monitored in real time, parameter updating is triggered when the preset threshold value is exceeded, a complete closed-loop control cycle is formed, and the technical problem that the pulse width modulation parameter accurately adapts to the change of the charging state of the battery under the complex dynamic load condition is effectively solved.

The invention relates to the technical field of ship navigation behavior prediction, and discloses a ship navigation behavior prediction method and system based on interpretable artificial intelligence. Comprising the following steps: acquiring ship AIS historical data and historical marine environment data in a target sea area; based on a time scale and a space scale, fusing the ship AIS historical data and the historical marine environment data, and constructing a spatio-temporal data set; performing feature decoupling on a static variable and a time-varying variable of the spatio-temporal data set, and determining historical input data, known future input data and static input data; an interpretable space-time fusion neural network model is constructed based on a dynamic gating residual neural network, a space-time characteristic variable selection network, a Fourier analysis gating neural unit and an interpretable multi-head attention mechanism so as to accurately predict ship navigation behaviors such as a ship trajectory, an over-the-ground navigational speed and an over-the-ground course. And a navigation behavior influence factor weight visualization result is output, and the method has interpretability.

The present invention discloses a defense method for collaborative false data attacks on power grid state topology, which is based on spatio-temporal multi-modal neural network for collaborative false data attack defense on power grid, and includes the following steps: 1. Use the residual detection method to filter out bad data, and then use a detection model composed of a graph autoencoder and a residual neural network to detect and locate data attacks; 2. Construct a prediction model based on spatio-temporal features to predict corresponding telemetry data based on a possible set of tele-signals; 3. Use the N-k search method to input the telemetry and tele-signal combinations into the above detection model, and use the detected data as the true value. The present invention improves the defect that traditional methods are not suitable for collaborative FDIA scenarios. The defense strategy has stronger robustness against the situation where the topological structure is tampered with, enhances the power grid's ability to defend against collaborative FDIA, and meets the practical requirements of the industry for collaborative FDIA defense.

The invention relates to the technical field of power quality identification, and discloses a power quality disturbance identification method and device, equipment and a storage medium, and the method comprises the steps: obtaining a power quality disturbance signal; performing feature extraction on the power quality disturbance signal by using a preset one-dimensional convolutional neural network and a one-dimensional residual neural network to obtain a target time feature vector of the power quality disturbance signal; performing feature fusion processing on the target time feature vector by using a preset multi-head attention mechanism to obtain a fused signal feature; and classifying the fused signal features by using a preset classifier to obtain a final classification result used for indicating the disturbance type of the power quality disturbance signal. According to the method, various feature information can be integrated, the influence of noise on a classification result is effectively reduced, the classification performance and generalization ability of a classifier are improved, better performance is achieved in the aspects of classification accuracy and noise immunity, disturbance recognition accuracy is improved, and effective support is provided for electric energy fault diagnosis in an electric power system.