38results about How to "Improve anomaly detection accuracy" patented technology

The invention provides a satellite measurement and control data anomaly detection and intelligent diagnosis early warning method and system, and relates to the technical field of satellite measurement and control, and the method comprises the steps: obtaining multi-source heterogeneous data in a satellite measurement and control system, and carrying out the preprocessing of the multi-source heterogeneous data; constructing a multi-level space-time fusion network model, inputting the preprocessed multi-source heterogeneous data into the multi-level space-time fusion network model, and extracting high-dimensional space-time features; based on the extracted high-dimensional spatial-temporal features, designing a dynamic adaptive anomaly detection algorithm, and performing anomaly detection on the satellite measurement and control data; according to an anomaly detection result, performing intelligent diagnosis by using a pre-constructed multi-level satellite system knowledge graph; based on the intelligent diagnosis result, multi-level early warning information is generated; a distributed edge computing architecture is designed, and partial data processing and anomaly detection tasks are deployed to a ground station and a satellite end; and presenting the generated multi-level early warning information through a visual interface, and automatically triggering a corresponding emergency plan according to the early warning level.

The invention relates to the technical field of intelligent management, and discloses a digital twinning-based production line abnormal data processing method and system, and the method comprises the steps: collecting digital twinning model data of a production line, obtaining the number of equipment of the production line, and determining a data analysis period; acquiring operation data of each device in the data analysis period, arranging the operation data into a data matrix according to a time sequence, and judging whether the device is abnormal or not; when it is judged that the equipment is abnormal, abnormal features are extracted and compared with historical operation data, and the fault type of the equipment is determined; determining equipment risk values according to the fault types and the abnormal characteristics, and sorting abnormal equipment; and correspondingly traversing the historical operation data of each abnormal device, obtaining a historical influence value, judging whether the sequence is adjusted or not, and obtaining a final abnormal device sequence. The anomaly detection precision of the production line is improved, and the maintenance cost of the production line is reduced.

The invention discloses a time-frequency domain cooperative industrial Internet of Things anomaly detection method under a full MLP lightweight architecture, and the method only employs four parallel two-layer MLP networks to construct a lightweight full MLP architecture with high timeliness and low resource consumption, and guarantees that the lightweight full MLP architecture can be flexibly applied in an industrial scene with limited resources. According to the architecture, a double-branch reconstruction learning process is constructed from two angles of'local to global 'and'global to local'; in order to further improve the accuracy, the reconstruction learning process of each branch utilizes two two-layer MLP networks to carry out reconstruction learning in a time domain and a frequency domain respectively, and the time domain and the frequency domain are aligned by utilizing reconstruction consistency, so that the feature capture capability of the full MLP architecture is improved; and finally, designing an anomaly scoring scheme based on a time-frequency reconstruction error, fusing the time-frequency domain reconstruction error obtained in double-branch reconstruction learning by using different weights, thereby generating a final anomaly score for each timestamp, and further judging whether the timestamp is abnormal or not.

The invention discloses a big data anomaly detection processing method based on machine learning, and relates to the technical field of data processing.The method comprises the steps that task running logs of K big data tasks in a preset historical window are obtained, and K historical running log sequences are obtained; obtaining K concentrated abnormal feature set sequences; performing abnormal feature correlation iteration identification, determining K task abnormal coefficient sets of the K big data tasks, and configuring K abnormal detection paths according to the K task abnormal coefficient sets; according to the method and the device, the technical problem of low detection processing reliability caused by lack of deep analysis of implicit association conditions existing in historical operation of the big data tasks during big data anomaly detection in the prior art is solved; the technical effect of improving the anomaly detection precision is achieved.

The invention discloses an anomaly detection method and device, a product, equipment and a medium. The anomaly detection method comprises the steps of obtaining historical time sequence data corresponding to a monitoring index of a target platform in a preset historical time period; inputting the historical time sequence data into a data prediction model for data prediction to obtain prediction data of the monitoring index in a target time period; determining a data normal threshold range corresponding to the monitoring index in the target time period based on the prediction data; and if any item of data in the actual data of the monitoring index in the target time period exceeds the data normal threshold range, determining that the any item of data is abnormal data. In this way, the accuracy and flexibility of anomaly detection can be improved.

The invention discloses an anomaly detection method for a satellite remote sensing application system. The anomaly detection method comprises the following steps: acquiring spectral remote sensing data in real time by using a multispectral sensor and carrying out data preprocessing on the spectral remote sensing data; establishing a processing model based on a convolutional neural network, and performing feature extraction and fusion on the preprocessed spectral remote sensing data to generate spectral remote sensing feature representation; establishing a spectrum anomaly detection model based on a deep learning algorithm, performing learning training on the spectrum anomaly detection model, and deploying the detection model in a satellite remote sensing system after the training is finished; and taking the spectral remote sensing feature representation as input of a detection model, performing anomaly detection on the spectral remote sensing feature representation by the detection model, and outputting a detection result. According to the method, the processing processes of multispectral data acquisition, convolutional neural network feature extraction and deep learning anomaly detection are combined, many defects in anomaly detection in the prior art are effectively overcome, and the anomaly detection precision, efficiency and real-time performance in a satellite remote sensing application system are comprehensively improved.

The invention belongs to the technical field of mine transportation, and discloses a belt conveyor roller anomaly detection system based on optical fiber auscultation, which comprises a data acquisition unit, a preprocessing unit and a prediction model which are connected in sequence, and an anomaly detection unit and a linear layer which are connected with the prediction model. The data acquisition unit acquires audio data in the running process of the carrier roller, converts the audio data into vibration data and outputs the vibration data to the preprocessing unit, the preprocessing unit segments the input vibration data, the segmented vibration data are input into the trained prediction model, and the prediction model is used for predicting the carrier roller. And the prediction model outputs the characteristics of the potential space corresponding to the current vibration data to an anomaly detection unit, the distance between the characteristics of the current potential space and the characteristic center of the potential space when the carrier roller normally operates is calculated, and if the distance is larger than a set distance threshold value, the current operation of the corresponding section of carrier roller is abnormal. According to the method, automatic detection of the abnormity of the carrier roller is realized, the information contained in the potential spatial features output by the prediction model is richer, and the abnormity detection precision of the carrier roller is improved.

The invention belongs to the technical field of network security, and discloses an industrial control network unsupervised anomaly detection method and system based on a space-time codec, and the method comprises the following steps: 1, carrying out the data processing and sample construction of an industrial control network sensor; performing sampling and data processing on the historical sensor original data and the time sequence to obtain a sample sequence; step 2, constructing an unsupervised deep learning model based on a space-time codec and training the unsupervised deep learning model; step 3, sensor data spatio-temporal characteristic analysis, and outputting sensor data in a future predetermined time period as a predicted value; and 4, abnormal alarm: determining a confidence space by combining the predicted value output in the step 3 and the confidence coefficient, and triggering network abnormal alarm when the current actual sensor data exceeds a normal range. According to the invention, the identification rate and generalization of industrial control network anomaly detection are improved.

The invention provides an internet portal website abnormity monitoring method and system, and the method comprises the steps: carrying out the sensitive text recognition and matching of page behavior information, so as to obtain a sensitive text proportion, and determining a first recognition result based on the sensitive text proportion; performing feature extraction and malicious link identification on the website link information to output a second identification result; performing feature description and malicious image recognition on the page picture information to output a third recognition result; and outputting a final identification result and an abnormal type of influence based on the first identification result, the second identification result and the third identification result. The method can effectively manage the access condition, the page content, the internal and external links and the link content of the target portal website, and carries out monitoring and system warning on the three abnormal conditions; the link security and the content security of the website are improved, and the anomaly detection precision is high.

The invention discloses a network link security management method based on artificial intelligence, which relates to the technical field of network security management, and comprises the following steps: when a network receiving link receives a data file of a sending end, obtaining first parameter data of the sending end to generate a sending feature and a fingerprint mark, and performing security verification on the fingerprint mark; and after verification, the data file and the fingerprint mark are packaged to generate a to-be-transmitted file. And when the to-be-transmitted file passes through an intermediate node of the network transmission link, recording second parameter data of the intermediate node, gradually generating a dynamic path mark and inputting the dynamic path mark. And when the file is transmitted to a receiving end, obtaining a complete dynamic path mark, carrying out anomaly analysis on the path mark according to a preset anomaly analysis algorithm, and if an anomaly is detected, generating an anomaly signal and giving an alarm. By sending the fingerprint mark in combination with the dynamic path mark and real-time monitoring, the adaptability of the network environment is improved, and the abnormality in the transmission path is accurately detected.

The invention discloses a ground resistance detection method and system for an electrostatic management tester, and relates to the field of ground resistance detection, and the key points of the technical scheme are that Op collection nodes are arranged in parallel on a circuit, voltage data on each node are obtained through a data collection device, and preliminary processing is carried out to obtain an initial data set; an optimization detection algorithm is used for the initial data set, and voltage data are converted into comprehensive direct-current voltage and comprehensive alternating-current voltage; setting an advanced detection threshold value, judging the obtained comprehensive direct current voltage and the comprehensive alternating current voltage with the advanced detection threshold value, performing mode selection according to a judgment result, giving an alarm if the mode is abnormal, and switching to a resistance detection mode and performing voltage measurement if the mode is normal. The device is suitable for detecting grounding resistance by an electrostatic management tester, and high-quality detection is realized.

The invention belongs to the technical field of intelligent equipment fault detection, and discloses a multi-robot-based large-scale equipment abnormal component cooperative detection method. According to the large complex intelligent equipment abnormal component detection method based on the multi-robot and cloud edge collaborative architecture, clustering, an A * algorithm, shortest route distribution and a Kalman filtering fusion algorithm are utilized, and multi-robot rapid inspection and accurate abnormal component detection are achieved. Through multi-robot uniform distributed inspection, global three-dimensional coordinate system establishment, abnormal point secondary inspection, abnormal point clustering analysis and screening, task list distribution, observable path division and fitting and optimal detection scheme construction, multi-angle and multi-mode abnormal data are finally fused, and an accurate detection result is obtained. The multiple robots are evenly distributed around the large complex intelligent equipment at equal intervals for inspection, the detection efficiency is improved, the coverage range is wider, and abnormal information can be fed back in time.

The invention discloses a method for detecting a motor based on a hybrid auto-encoder integrated learning model, and relates to the technical field of motor testing. The method comprises the steps that S1, a hybrid auto-encoder integrated learning model is constructed and obtained, the model comprises m * n base models, and each base model comprises an audio feature extraction method and an auto-encoder AU; s2, training an auto-encoder AU of each base model to obtain a trained base model, and inputting normal audio data of the motor in the training set into each trained base model to obtain an optimal base model; s3, inputting normal and abnormal audio data of a motor in the test set into each optimal base model, obtaining a test set abnormal score of each optimal base model, and averaging all abnormal scores to obtain an abnormal score of the test set; the larger the difference between the base models is, the higher the precision of the base models is, and the higher the precision of the hybrid auto-encoder integrated learning model is, so that the motor anomaly detection precision is higher.

This invention discloses a method and electronic device for anomaly identification in a distribution network. It relates to the field of distribution network state estimation technology. The method includes: acquiring monitoring data of the distribution network at the current moment; determining the target state value of the distribution network at the current moment using a target state estimation model based on the monitoring data, wherein the target state estimation model is obtained by optimizing and training a state estimation network based on historical monitoring data of the distribution network at multiple historical moments and the corresponding historical state values; determining whether there is an anomaly in the distribution network at the current moment based on the target state value; and, if there is an anomaly in the distribution network at the current moment, determining the anomaly area of ​​the distribution network at the current moment. This invention solves the technical problems of low accuracy in anomaly detection and low accuracy in identifying anomaly areas in distribution network anomaly identification due to insufficient measurement coverage and poor generalization ability of the anomaly identification method.

The invention relates to the technical field of magnesium-based alloy manufacturing data processing, and provides an anomaly detection method for a magnesium-based alloy production raw material conveying system, which comprises the following steps: collecting basic data of the magnesium-based alloy production raw material conveying system, including equipment operation parameters, raw material state parameters, conveying environment parameters and the like, and carrying out preprocessing and feature extraction; and constructing a data feature library. Then, abnormal points and trend change information thereof in the data are identified by using a statistical analysis model, and a potential abnormal mode is formed. And based on the potential abnormal mode and the historical operation data, training a neural network model to realize abnormal prediction and classification of the real-time data. And finally, by comparing a model prediction result with actual data, the model is optimized by using a genetic algorithm, and the detection accuracy is improved. According to the method, the anomaly detection accuracy of the magnesium-based alloy production raw material conveying system is effectively improved, and a powerful guarantee is provided for stable operation of the magnesium-based alloy manufacturing and producing process.

The present invention belongs to the technical field of mine transportation, and discloses a belt conveyor roller abnormality detection system based on optical fiber auscultation, comprising: a data acquisition unit, a preprocessing unit and a prediction model connected in sequence, and an abnormality detection unit and a linear layer connected to the prediction model. The data acquisition unit collects audio data during the operation of the roller, converts it into vibration data, and outputs it to the preprocessing unit. The preprocessing unit segments the input vibration data, and inputs the segmented vibration data into a trained prediction model. The prediction model outputs the features of the latent space corresponding to the current vibration data to the abnormality detection unit, and calculates the distance between the features of the current latent space and the feature center of the latent space when the roller is operating normally. If the distance is greater than the set distance threshold, the corresponding segment of the roller is currently operating abnormally. Not only is the automatic detection of roller abnormalities realized, but the latent space features output by the prediction model contain richer information, thereby improving the accuracy of roller abnormality detection.

The application provides a video anomaly detection model training method, a video anomaly detection method and equipment, which can be applied to the technical field of computer vision and machine learning. The training method comprises the following steps: obtaining a video source domain and a video target domain; using normal video slices to train an initial video anomaly detection model to obtain a prediction network; inputting randomly selected samples from a frame-level labeled source domain into an adversarial generation network to output first intermediate domain samples; using the first intermediate domain samples and the frame-level labeled source domain to train the initial video anomaly detection model to obtain a teacher network, and constructing a student network based on the teacher network; inputting second intermediate domain samples corresponding to the video target domain and the video target domain into the student network, inputting the first intermediate domain samples and the frame-level labeled source domain into the teacher network, adjusting network parameters of the student network based on output results of the teacher network and the student network, and obtaining a video anomaly detection model.

The present disclosure provides a user abnormal behavior detection method and system that fuses data enhancement and dynamic graphs, relates to the technical field of deep learning anomaly detection, and includes: obtaining original behavior data of a user; inputting preprocessed original behavior data into a conditional variational autoencoder model, using the conditional variational autoencoder to extract latent space variables in a time series of the original behavior data, using a decoder to convert the latent space variables back to reconstructed values of the original time series, generating new time series data, and fusing the new time series data with the original behavior data to obtain enhanced data; inputting the enhanced data into a dynamic graph model after converting the enhanced data into graph structure data, using a space-time separation attention mechanism in the dynamic graph model to perform attention calculation on decoupled time and space dimensions, obtaining a feature graph representation, determining abnormal behavior by calculating the cosine similarity of the feature graph representation through a KNN algorithm, and obtaining an abnormal behavior determination result.

A wind turbine gearbox anomaly detection method considering the similarity of multi-unit operating states, based on the piecewise linear time series similarity evaluation method, evaluates a single state variable; considering the similarity of multiple state variables, the wind turbine operating state spatiotemporal similarity quantification method evaluates the similarity of each wind turbine and the operating state of the unit to be detected; a state estimation LSTM model is constructed, different LSTM models are trained; the accuracy and adaptability of different LSTM model performances are verified; select several LSTM models that perform well in performance verification, construct a combined state estimation model CPEM through weighted combination; estimate the target variable of the unit to be detected, calculate the residual error between the estimated value and the true value, and based on the residual effective value comparison and residual information entropy comparison, identify the anomaly. This method detects the operating state of the gearbox based on the historical operating data of the wind turbine, without the need for maintenance personnel to conduct on-site detection, reducing the operating and maintenance costs of the wind turbine.

The invention discloses a charging gun abnormity identification and judgment method based on data driving, and relates to the technical field of charging piles. The charging gun abnormity identification and determination method based on data driving comprises the following steps: obtaining a query order; performing user statistics; screening data features; and making a data perspective table. The charging order is obtained by querying the date, user statistics is performed on the charging order, then the obtained user data table is analyzed to obtain the abnormal number and the abnormal rate, data feature screening is performed in combination with the user data table to generate the fault information, and the fault file table of the charging gun to be detected is obtained in combination with the charging gun file information. And finally, a data perspective table is made according to the fault file table, and fault gun information is summarized, so that the effect of improving the abnormality detection accuracy of the charging gun is achieved, and the problem of inaccurate abnormality detection of the charging gun in the prior art is solved.

The present invention relates to the field of data processing, and more specifically, to an intelligent hot dry noodle production line monitoring method, the method comprising: obtaining a data set; calculating the degree of isolation of each dimension data; calculating the abnormal possibility according to the degree of isolation, and removing the dimension whose abnormal possibility is less than a preset possibility threshold; taking the dimension whose abnormal possibility is not less than the preset possibility threshold as the dimension to be analyzed; obtaining possible abnormal data points corresponding to the dimension to be analyzed; performing dimension retention control according to the intersection ratio of possible abnormal data points of two dimensions; and performing abnormal detection on quality monitoring data points based on the retained dimension using an isolation forest algorithm to realize production monitoring of the hot dry noodle production line. The accuracy of abnormal detection is improved by accurately screening out appropriate dimensions.

This invention relates to a method and related equipment for detecting abnormal object behavior. The method includes: acquiring a behavior log stream and mapping the logs to feature vectors including object identifiers; for any object, generating a behavior state sequence based on the feature vectors, constructing reachable links between state points based on the distance relationships between state points in the behavior state sequence, thereby constructing a topological structure of the object's behavior state space, calculating the topological closure of the object's historical state vector set under the topological structure, and using the topological closure as the normal behavior baseline region of the object; wherein, the behavior state space consists of multiple state points obtained by mapping state vectors from the behavior state sequence; acquiring the target state vector corresponding to the behavior of the object to be detected, determining whether the target state vector belongs to the normal behavior baseline region of the corresponding object, and if not, determining it as abnormal behavior. This method at least partially solves the problems of high storage overhead and poor anomaly detection effect in related technologies.

The invention provides a GANopen tire anomaly detection method based on double auto-encoders and GAM (Gamma Amplitude Modulation), which reconstructs a tire image, captures local and global information in a network through auto-encoder feature extraction and attention of a GAM channel, and effectively solves the quality problem of the reconstructed image. According to the method, an unsupervised learning method is adopted for training, and optimal parameters are determined through experiments, so that the performance of the method is improved. Experiments show that the anomaly detection algorithm provided by the invention shows a relatively high AUC value and accuracy on a self-made tire data set, the effectiveness and superiority of the model are proved, and the method has important significance on development and progress of tire defect detection.

The application provides a kind of satellite telemetry multidimensional time series data-oriented anomaly detection method, device, medium and product, it is related to satellite telemetry multidimensional time series data anomaly detection field, method includes: the satellite telemetry multidimensional time series data to be detected is input into anomaly detection model, and the fusion error of each time is output;Anomaly detection model includes denoising sparse auto-encoder and graph attention network;Denoising sparse auto-encoder learns the low-dimensional feature of input satellite telemetry multidimensional time series data, reconstructs satellite telemetry multidimensional time series data, generates reconstruction error;Graph attention network extracts the correlation between different reconstructed satellite telemetry multidimensional time series data from two levels of causality and similarity, generates prediction error;Generate the fusion error of each time, judge whether the satellite telemetry multidimensional time series data to be detected exists anomaly;If yes, record abnormal time point.The application can be suitable for satellite telemetry multidimensional time series data of different dimensions, improve anomaly detection precision.

The invention provides an AI-based intelligent inspection method and system, and the method comprises the steps: collecting environment data, poultry behavior data and equipment operation data, forming a multi-dimensional fusion data set containing time-space coordinates, and constructing a digital twinborn model of a farm; updating the digital twinborn model and establishing a virtual-real mapping relation; inputting real-time data output by the digital twin model into a pre-trained multi-task learning AI model to obtain a comprehensive risk assessment report containing confidence and a time window; according to the comprehensive risk assessment report, an ant colony algorithm is combined with a real-time risk thermodynamic diagram to dynamically generate an optimal inspection path, and the inspection frequency and key areas are adjusted in real time; new data and processing results obtained in the inspection process are fed back to update parameters of the digital twinborn model and the multi-task learning AI model, and an inspection strategy is continuously optimized through a reinforcement learning algorithm. According to the method, the anomaly detection accuracy can be improved, the loss is greatly reduced, and the labor cost and poultry stress response are reduced.

The application discloses an agricultural process big data statistical analysis and alarm method, collects meteorological, soil, insect, irrigation state and equipment working condition data in agricultural production, carries out cleaning, time alignment and unified modeling on multi-source data, forms a monitoring sequence, carries out standardization and rank statistical processing on the monitoring sequence, identifies candidate abnormal points, further combines local significance test and interval distribution change test, confirms abnormal intervals, and then comprehensively scores mutation strength, significance strength and distribution change strength, generates early warning grades, early warning time and related index information, and outputs alarm results. The application realizes statistical analysis and graded early warning of abnormal changes in agricultural processes.

The present invention discloses an unsupervised energy consumption anomaly detection method PLAD. The present invention uses pseudo labels to guide the classification of energy consumption data reconstruction errors, overcoming the dependence of supervised anomaly detection methods on label data. In particular, the key features of energy consumption data are extracted, and a density clustering algorithm with adaptive parameters is used to generate pseudo labels for energy consumption data to avoid the problem of difficult parameter selection in different scenarios. The energy consumption data is reconstructed using an automatic encoder to obtain the reconstruction error of the energy consumption data, and finally the pseudo labels are used to guide the classification of the reconstruction error to obtain the result of energy consumption data anomaly detection, thereby achieving higher anomaly detection accuracy.

The invention relates to the technical field of computer vision, and discloses a video anomaly detection method and system, a medium and equipment, and the method comprises the steps: obtaining a continuous video frame sequence; based on the continuous video frame sequence, detecting an abnormal event through a video anomaly detection model; wherein the video anomaly detection model executes a time shift operation between two continuous feature maps, and replaces a part of channels of each feature map with the same channel part from the previous feature map to extract time features; and after the time shift operation is executed, the spatial features are accumulated through a recursive aggregation method so as to capture multi-scale context information. The sensitivity to time information and space information is improved, and the video anomaly detection precision is improved.

The present invention discloses a road anomaly detection method and system, which belongs to the technical field of road detection. The method includes: obtaining gyroscope data and accelerometer data, and performing Kalman filtering on the gyroscope data and accelerometer data; obtaining road bump anomaly detection results based on the sampling frequency of the accelerometer data and the accelerometer data or the gyroscope data after Kalman filtering; obtaining mobile video, inputting the mobile video into a trained road anomaly detection model for processing, and obtaining road anomaly detection results; wherein, the mobile video is stored through a spatiotemporal query algorithm based on trajectory segmentation to improve the query efficiency of road anomaly detection. The method can improve the accuracy and efficiency of road anomaly detection and solve the problems of low robustness and accuracy of existing road detection.

The present application relates to the field of panoramic image technology, and discloses a full-link intelligent monitoring system, method, vehicle and medium for panoramic image, the system comprises: a video stream monitoring module is used for state monitoring and quality detection to the video acquisition equipment of panoramic image system, and outputs the first abnormal result when monitoring the exception;Video stream tracing module is used for full-process monitoring and tracing to the algorithm processing link and rendering output link of panoramic image system, and outputs the second abnormal result when monitoring the exception;System resource monitoring module is used for monitoring the system resource occupation state and the resource competition behavior of third party application in the running process of panoramic image system, and outputs the third abnormal result when monitoring the exception;The abnormal diagnosis module is respectively connected with each module, is used for receiving the abnormal result of each module, and carries out comprehensive diagnosis through the abnormal correlation analysis model, determines the root cause of the exception and outputs the diagnosis result, can realize full-link intelligent monitoring.