6727 results about "Feature set" patented technology

The invention discloses an equipment anomaly detection method and system based on multi-source heterogeneous data, and the method comprises the steps: obtaining a real-time multi-source monitoring data flow of production equipment in a smart park, carrying out the cross-modal data alignment processing of the real-time multi-source monitoring data flow, and generating a target monitoring data set, and executing a dynamic feature extraction operation in each edge computing node, generating a multi-dimensional equipment state feature set based on the target monitoring data set, inputting the multi-dimensional equipment state feature set into the trained anomaly detection integrated model, generating equipment anomaly probability distribution through a multi-level feature fusion strategy, and outputting the equipment anomaly probability distribution. Determining the abnormity type and abnormity confidence of the target equipment according to the equipment abnormity probability distribution, generating an equipment maintenance instruction set based on the abnormity type and the abnormity confidence, and sending the equipment maintenance instruction set to an equipment management terminal of the smart park to trigger abnormity processing operation; therefore, the automation degree and decision reliability of the equipment maintenance response of the smart park are improved.

The invention provides an AI-based factory abnormal behavior identification monitoring method and system. The method comprises the steps of obtaining continuous video stream data collected by a plurality of monitoring devices in a target factory in real time; performing time dimension segmentation and space dimension preprocessing on the continuous video stream data to obtain a multi-frame behavior feature set corresponding to the dynamic behavior sequence, and inputting the multi-frame behavior feature set into a pre-trained abnormal behavior recognition model, performing cross-modal association fusion on the skeleton key point features, the environment associated object contour features and the action trajectory features to generate a target behavior feature vector, performing similarity matching with a preset abnormal behavior feature library, determining an abnormal behavior category, and triggering a corresponding early warning signal according to the behavior type when it is determined that the target behavior feature vector belongs to the abnormal behavior category. And real-time alarm display is carried out. According to the invention, the problem that the existing monitoring system is insufficient in accuracy and real-time performance can be solved.

The invention relates to the technical field of online calibration, in particular to a multi-parameter fusion intelligent electric energy meter online calibration method and system, and the method comprises the following steps: collecting voltage waveforms, current harmonics and active power data, dividing windows, calculating a covariance matrix, and generating a feature set; a power factor curvature extreme value and a temperature inflection point offset are analyzed to generate an interference identifier, current density distribution and a voltage distortion spectrum are jointly analyzed to extract a harmonic energy ratio to generate a feature vector, and phase compensation is performed on a pulse sequence to generate a calibration instruction set. According to the method, the covariance matrix is constructed by synchronously collecting voltage and current power parameters, the abnormal mark section is generated by combining the temperature change and the covariance difference value, the environment disturbance and the real deviation are effectively distinguished, and the temperature hysteresis effect is identified through the power factor curvature extreme value and the temperature inflection point offset. And combining current density and voltage distortion spectrum analysis to extract a fundamental wave and harmonic wave energy ratio, establishing a composite calibration reference, and dynamically adjusting a pulse duty ratio to realize harmonic wave energy compensation.

The invention discloses a cross-modal information fusion and retrieval method and system driven by semantic comprehension, and the method comprises the steps: obtaining text, image and audio original data, and extracting an initial feature set of each modal through a deep neural network; dynamically distributing each modal weight coefficient based on an attention mechanism, and performing weighted fusion on the initial feature set to obtain cross-modal fusion feature representation; through a cross-modal semantic association analysis model, high-dimensional semantic association features are extracted from the fusion feature representation, and semantic enhancement feature vectors are generated; constructing a cross-modal semantic graph network based on the vector, complementing missing modal features, and generating an optimized multi-modal feature set; and inputting the optimized feature set and the query sample into a contrast learning model, calculating a semantic similarity score, and generating a cross-modal retrieval result sorting list according to the score.

The invention relates to the technical field of multi-modal data processing, and discloses a multi-modal sensor fusion inspection method and system, and the method comprises the steps: collecting the multi-modal original data of power equipment through a multi-modal sensor in an inspection robot, and constructing a feature vector set; performing adaptive weight calculation on the multi-modal sensor according to the feature vector set to obtain a sensor weight set; carrying out conflict identification and resolution on the multi-modal original data to obtain a fusion data set; performing abnormal feature extraction on the power equipment based on the fused data set to obtain an abnormal feature set; and carrying out routing inspection trajectory optimization based on the abnormal feature set to obtain a target routing inspection path sequence, and carrying out equipment state joint prediction in combination with historical equipment routing inspection data to obtain an equipment fault prediction result. And thus, more accurate equipment state joint prediction is realized.

The invention discloses a stainless steel surface defect detection method based on machine vision, and relates to the field of material defect detection.The stainless steel surface defect detection method comprises the steps that stainless steel surface images are collected, the collected multispectral surface images are subjected to image fusion, and a multispectral composite image is generated; performing detail enhancement on the low-resolution image through a super-resolution reconstruction algorithm to obtain a high-resolution image set; positioning a defect area position from the high-resolution image set through a defect detection algorithm, and obtaining a defect position data set; extracting a historical image defect feature set and a real-time image defect feature set from the defect position data set, and constructing a defect classification model according to the historical image defect feature set; inputting the real-time image defect feature set into a defect classification model, and performing defect classification and evaluation to obtain a defect classification data set; and generating and distributing a defect detection report. By combining the multispectral imaging algorithm, the super-resolution reconstruction algorithm and the defect classification model, the automation, precision and efficiency of stainless steel surface defect detection are improved.

The invention provides a BIM-based fabricated building component management method and system, and the method comprises the steps: firstly obtaining a building information model data set of a target fabricated building project, a component attribute parameter set covering a prefabricated component unit, and a component geometric feature set, and then carrying out the multi-level component feature analysis of the building information model data set, obtaining a standardized geometric feature sequence and a dynamic construction state feature set containing a transportation positioning offset, a hoisting stress distribution gradient and an installation collision risk coefficient, and then performing cross-stage collaborative analysis on the features based on a preset construction stage matching strategy to generate a component matching strategy set; and the component dynamic optimization module is used for indicating component installation sequence adjustment and connection node precision compensation, finally generating a component dynamic optimization instruction set according to the component matching strategy set, and synchronizing the component dynamic optimization instruction set to the building information model data set to update component attributes, so that efficient management of the fabricated building components is realized.

The invention discloses a turbofan engine operation monitoring method and system based on digital twinning, belongs to the technical field of turbofan engine monitoring, and aims to solve the problems that weak fault signals such as early cracks and abrasion are difficult to extract and the prediction precision of a multi-source fault propagation path is low under a strong noise background. An original operation signal is collected through a sensing array, and is processed by an adaptive resonance demodulation chain to generate a demodulation signal. The method comprises the following steps: carrying out time-frequency transformation on a demodulation signal, constructing an initial candidate feature set by combining feature frequency prior matching actual measurement and theoretical feature frequency, and generating an independent feature set by fusing multi-scale decoupling network separation features of digital twin constraints; for independent features, effective causal pairs are screened by adopting a physical coupling relationship combining Granger causal analysis and digital twinborn simulation, a dynamic Bayesian network is constructed to simulate fault propagation, a posterior probability is calculated through digital twinborn verification and Monte Carlo simulation, early warning is triggered, and a maintenance decision is generated. And weak signal extraction and accurate fault prediction under strong noise are realized.

The invention provides a power plant system equipment fault diagnosis method and system based on artificial intelligence, and the method comprises the steps: firstly obtaining a continuous operation state data flow of key equipment of a power plant, then carrying out the feature extraction of the continuous operation state data flow, and generating a fusion feature set reflecting the equipment operation state coupling relation; calling a pre-trained fault dynamic diagnosis model to perform state evolution analysis processing on the fusion feature set to generate a diagnosis intermediate result which comprises a fault potential node and a fault evolution path, and performing fault attribute analysis processing based on the diagnosis intermediate result to obtain a fault attribute analysis result; according to the method, fault diagnosis information including fault trigger conditions, fault development trends and fault influence ranges is generated, and finally, an equipment diagnosis report including early warning strategies and maintenance priorities is generated according to the fault diagnosis information and is transmitted to a power plant intelligent operation and maintenance terminal, so that the accuracy and timeliness of power plant equipment fault diagnosis can be improved, and the power plant equipment fault diagnosis efficiency is improved. Safe and stable operation of a power plant is ensured.

The invention relates to the field of digital twinborn modeling, and discloses a digital twinborn visual modeling method and system based on a neural network, and the method comprises the steps: collecting the multi-dimensional perception data of a target physical system, carrying out the format unification and normalization processing of the original data of a sensor through a heterogeneous data fusion module, and obtaining a data fusion module; constructing a high-dimensional input feature set for neural network modeling by combining a structured embedding algorithm; carrying out stability pre-evaluation on the constructed input feature set, and screening core features by adopting a disturbance sensitivity analysis mechanism; a dynamic residual feedback mechanism is introduced to carry out enhanced training on the preliminary twin model, and modeling is carried out on the space-time dependency relationship of different components through a graph neural network; tracking a stability index of visual representation in real time in a model training process; and according to a multi-dimensional visualization result output by the final twin model, performing interpretation in combination with an industrial scene semantic rule base. The method has the advantage of improving the practicability of the twin model in the industrial scene.

The invention provides an urban functional area gridding identification and classification method based on multi-source spatio-temporal data, and relates to the technical field of area identification, and the method comprises the steps: carrying out the dynamic grid division of an urban area through employing a self-adaptive grid division algorithm, obtaining the multi-source spatio-temporal data of a gridding area, carrying out the space-time alignment, and generating a multi-dimensional time sequence feature set; extracting multi-dimensional feature vectors of the grid units through a multi-modal feature fusion algorithm, acquiring long-range time sequence features by using a bidirectional gating recursion unit, calculating spatial correlation features based on a multi-head attention mechanism, and inputting the two types of features into a feature fusion network with jump connection to generate enhanced spatial-temporal features; and an optimization strategy is adopted, a functional area clustering center point is determined through density peak value clustering in sequence to obtain an initial division result, the initial result is optimized by combining spectral clustering of spatial adjacency constraints, and the boundary of the functional area is optimized by using a simulated annealing algorithm, so that accurate identification and classification of the urban functional area are realized.

The invention belongs to the technical field of equipment health monitoring and anomaly detection, and discloses an industrial time series data learning fusion and anomaly detection method, which comprises the steps of constructing an IP-PLC mapping relation table, collecting multi-modal data, constructing a physical constraint parameter list, and generating structured data and a storage index. Time domain features and frequency domain features are extracted, a spatial topological graph is constructed, node spatial feature vectors and edge association strength are extracted, spatial association feature vectors are generated, a constraint rule base is constructed, and an enhanced feature set is formed; aggregating the enhanced feature set and the constraint rule base, generating a multi-dimensional feature matrix and a global reference parameter table, further constructing a global reference system, obtaining an equipment-level anomaly probability matrix, and generating a working condition-level anomaly probability matrix; hierarchical optimization is carried out through hierarchical modeling, and an optimization parameter set is generated; constructing an alarm response mechanism, and performing reverse updating to form closed-loop iteration; and an interpretable and extensible solution is provided for equipment health management in a complex industrial scene.

The invention provides an intelligent robot inspection system in a power distribution and transformation intelligent auxiliary system, and relates to the technical field of intelligent sensing and control, and the system comprises a real-time operation collection module which is used for planning a global path of an intelligent inspection robot, generating an initial inspection path, carrying out real-time operation collection, and obtaining a multi-modal detection data set; the fault feature recognition module is used for performing fault feature recognition, generating an abnormal feature set and constructing a dynamic risk map; the simulation maintenance feedback module is used for carrying out simulation maintenance feedback according to the inspection correction path in combination with the equipment maintenance suggestion and generating a maintenance feedback result; and the inspection control module is used for generating an optimized inspection path to perform inspection control on the intelligent inspection robot. According to the invention, the technical problem that the routing inspection efficiency and the fault diagnosis accuracy are influenced because routing inspection path planning often depends on a preset environment map and the intelligent routing inspection robot cannot automatically adjust the routing inspection path according to the change of the equipment state in the prior art is solved.

The embodiment of the invention provides a power distribution network disaster risk assessment method and system based on multi-source big data, and the method comprises the steps: obtaining a multi-source dynamic data set associated with a power distribution network, carrying out the multi-source feature deep coupling of the multi-source dynamic data set, and generating a power distribution network risk coupling feature set; the power distribution network risk coupling feature set comprises an equipment state coupling feature, an environment interference coupling feature and a topological correlation coupling feature; inputting the power distribution network risk coupling feature set into a preset risk situation coupling deduction model to perform multi-dimensional risk situation coupling deduction, and outputting a power distribution network disaster risk situation map; key node risk traceability coupling analysis is carried out based on the power distribution network disaster risk situation map, and a power distribution network weak link set and a risk evolution dynamic parameter set are determined. According to the method, the weak link in the power distribution network can be accurately positioned, the change rule of the risk along with time can be captured, and the improvement from static recognition to dynamic traceability and evolution prediction is realized.

The invention provides an intelligent factory production scheduling method and system based on digital twinning, and the method comprises the steps: firstly obtaining a real-time monitoring data set, including equipment operation states, material flow tracks and environment sensing data, of a physical workshop; generating a three-dimensional digital twinborn model containing an equipment dynamic operation topology, a material real-time distribution thermodynamic diagram and an environment state simulation layer, then performing operation state correlation analysis on the three-dimensional digital twinborn model, and generating a feature set of equipment operation efficiency, material flow bottleneck, environment interference and the like; generating a dynamic scheduling parameter set containing equipment load balancing, material priority distribution and environment adaptation compensation parameters, and finally calling a preset scheduling strategy optimization algorithm to perform multi-objective optimization processing on the dynamic scheduling parameter set to generate an equipment scheduling, material distribution and environment regulation and control instruction set. And synchronizing to a physical workshop to execute real-time scheduling operation, thereby realizing intelligent and efficient production scheduling.

The invention relates to a multi-modal AI data fusion processing method, device and equipment and a medium, and the method comprises the steps: firstly extracting visual, auditory and text modal features through a pre-training encoder, executing dimension alignment, and generating a standard data feature set with unified dimensions; a cross-modal semantic graph is constructed based on a cosine similarity algorithm, and the problem of semantic mismatch of heterogeneous data is solved; residual enhancement is carried out on the map nodes, and noise interference is eliminated; fusing the optimized features and the semantic topology in combination with a graph convolutional network to generate aggregation graph representation; the fusion features are mapped to a low-dimensional semantic space through a variational auto-encoder, and cross-modal correlation essence is captured; the key dimension contribution degree is quantified, a visual report is generated, and semantic association rules among modals are disclosed, so that the dimension isomerism limitation of a traditional fusion technology is broken through, quantifiable cross-modal semantic mapping is established, the whole process traceability from feature fusion to decision interpretation is realized, and the method is suitable for popularization and application. And the multi-modal decision black box problem in the fields of medical diagnosis, automatic driving and the like is effectively solved.

The invention provides an advertisement recommendation method and system fused with user dynamic behavior modeling. The method comprises the following steps: acquiring a cross-device operation record of a user on multiple terminal devices, and synchronously acquiring a device unique identification code, high-frequency click area data and an operation timestamp; and constructing a space-time relation graph based on combined analysis of the equipment switching time interval and the click behavior, and generating a feature set reflecting the behavior correlation degree. The trajectory similarity is calculated at the edge calculation node through hardware acceleration, and migration correlation parameters are generated. And inputting the space-time relation graph into a behavior analysis model to extract coherent behavior characteristics, and forming a multi-dimensional scene portrait in combination with geographic position change and interface element distribution. And finally, through identifying a user cross-device interest migration mode, dynamically screening advertisement contents matched with the current scene, and realizing accurate pushing strategy optimization based on behavior continuity. According to the technical scheme provided by the invention, the accuracy of cross-terminal advertisement recommendation and the scene response speed are remarkably improved.

The invention relates to the field of frequency converter fault detection, and discloses a frequency converter fault prediction method and system based on machine learning, and the method comprises the steps: obtaining multi-dimensional real-time data in the operation process of a frequency converter; constructing a dynamic mapping relation to obtain a basic feature set; generating a time sequence feature vector capable of reflecting the state change of the equipment based on the basic feature set; comparing, analyzing and judging whether the equipment state deviates from a normal operation interval or not based on the historical operation data and the time sequence feature vector, and outputting a state deviation index; performing abnormal fluctuation judgment on the time sequence feature vector; extracting fluctuation amplitude and frequency characteristics of the key indexes to obtain quantitative description data of abnormal fluctuation; inputting the quantitative description data of the abnormal fluctuation into an abnormal prediction model; and generating a coping strategy and a triggering condition of the coping strategy based on the risk prediction result. The method has the advantages that the abnormal state of the frequency converter is recognized in time, and potential risks are predicted.

A reactor partial discharge diagnosis method based on multi-source feature fusion and a deep network relates to the technical field of partial discharge detection, and comprises the following steps: S1, data preprocessing and feature extraction; s2, extracting multi-dimensional feature information; s3, processing the high-dimensional feature set through an SWFK-DPC clustering algorithm; s4, constructing a deep multi-source adaptive convolutional neural network (EDMSACNN); s5, introducing cross-domain feature compression and a double-path attention mechanism; s6, introducing a confrontation enhancement and classification module; and S7, model optimization and iterative training. According to the method, non-linear interaction of multi-source features is realized through tensor shrinkage and an attention mechanism, the limitation of traditional linear fusion is broken through, data distribution differences under different working conditions are effectively relieved based on an optimal transmission feature alignment technology, and the adaptive cross-domain capability is remarkably improved.

The embodiment of the invention provides an unmanned aerial vehicle data anomaly detection method based on multi-modal time sequence modeling, and the method comprises the steps: carrying out the multi-stage data preprocessing of original data obtained in the working process of an unmanned aerial vehicle, and generating a standardized input data flow; extracting time sequence features of the standardized input data stream through continuous LSTM blocks in the multi-level feature extraction network, and generating a shallow time sequence feature set; performing depth time sequence modeling on the shallow time sequence feature set to generate a deep time sequence feature set; performing multi-stage information fusion and mask screening on the shallow time sequence feature set and the deep time sequence feature set to generate a fusion time-space correlation feature set; and generating an attitude parameter prediction result of the unmanned aerial vehicle according to the fusion time-space correlation feature set, and obtaining an anomaly detection decision result of the unmanned aerial vehicle by using a deviation comparison and multi-level anomaly judgment mechanism based on an adaptive threshold obtained based on the attitude parameter prediction result and prediction error statistical distribution. Therefore, the anomaly detection accuracy of the unmanned aerial vehicle data is improved.

The invention relates to an AI real-time intelligent guidance and self-adaptive obstacle avoidance method for multi-source sensing fusion of an unmanned aerial vehicle, and the method comprises the steps: collecting flight data through a visual sensor and an infrared sensor, obtaining a timestamp and space coordinate information, calculating a sampling frequency difference, and generating a fusion data set of time-space alignment through a self-adaptive interpolation algorithm; image and heat source features in the fusion data set are extracted, and a multi-dimensional feature set is generated, so that whether an obstacle exists or not is judged, and related information is extracted; and analyzing environment data, calculating an environment complexity index, generating a risk level in combination with obstacle information, predicting a dynamic weight of the sensor, and adjusting a working mode of the sensor. And then based on the obstacle condition, calculating a comprehensive risk value and predicting a motion trend through a path risk model, and finally generating an optimal obstacle avoidance path and a flight instruction, thereby realizing high-efficiency processing of sensor data, accurate risk assessment and real-time obstacle avoidance planning, and ensuring stable and safe flight of the unmanned aerial vehicle in a complex environment.

The invention relates to a part surface defect detection and process optimization method and system, and solves the problems that defect detection has defects, missing detection and erroneous judgment are easy to occur, and subsequent process improvement faces huge challenges even if defects are detected, and the method comprises the following steps: inputting a feature set into a double-branch fusion deep learning model, the first branch identifies defect types and quantization parameters by fusing three-dimensional features and two-dimensional features, and the second branch calculates the correlation degree between the defect features and each process through association rule mining and a random forest algorithm; when the three-dimensional features and the two-dimensional features both meet a preset defect threshold value and the association degree of a certain process exceeds a preset value, determining that the process is a root process; and analyzing a deviation value between the key parameter of the source process and the defect quantization parameter, and correcting the parameter through a dynamic adjustment mechanism according to the deviation degree. The method has the advantages that the defects of the part are accurately detected, the procedure is traced, parameters are dynamically adjusted, closed-loop optimization is formed, and the quality of the part is improved.

The invention provides a tunnel construction monitoring analysis method and system based on AI video monitoring, and relates to the technical field of artificial intelligence. A tunnel construction original video stream data set is acquired through a multi-view video acquisition device, and a spatio-temporal feature sequence is generated through spatio-temporal feature fusion processing; the spatiotemporal feature unit comprises a pixel region movement track, a personnel wearing identifier and a construction equipment contour feature, then extracting dynamic features of the spatiotemporal feature sequence to obtain a dynamic spatiotemporal feature set, and executing construction personnel statistical processing based on the dynamic spatiotemporal feature set; generating a hole entering personnel quantity statistical result, a personnel distribution statistical result of each construction part and a personnel identity matching result, performing work efficiency comparative analysis according to the personnel statistical result and a preset construction progress plan, and generating a construction progress deviation index and resource allocation optimization strategy; and when the progress deviation index exceeds the first threshold value, early warning is triggered, and a strategy is output to the management terminal, so that effective monitoring and management of tunnel construction are realized.

The invention discloses a medical image enhancement method and system based on multi-modal fusion, and the method comprises the steps: obtaining medical image data which comprises a CT image, an MRI image, a PET image and an ultrasonic image; calculating a mutual information value of each semantic tag in the cross-modal feature vocabulary, and generating an inter-modal feature correlation matrix; performing non-rigid space registration on the unified dimension image set to generate a geometrically consistent multi-modal image set; extracting skeleton region features, soft tissue region features and high metabolism region features from the multi-modal image set, and generating a core feature set; a deep learning algorithm is adopted to train the core feature set, and a segmented image set containing a segmentation mask is generated; and dynamically adjusting the fusion weight according to the regional features of the segmented image set, and generating a fusion enhanced image. According to the invention, through feature extraction, spatial registration and deep learning fusion of the multi-modal medical image, effective integration of different-modal medical image information is realized.

The invention provides a human body posture detection method and equipment based on machine vision, which are applied to posture recognition in physical fitness detection, and are used for generating a dynamic human body region set of a target user by acquiring a multi-frame continuous image sequence of a physical fitness training scene and performing human body region positioning processing on the multi-frame continuous image sequence. Performing posture feature extraction processing on the dynamic human body region set to obtain a space-time posture feature set of the target user, performing posture state recognition processing on the space-time posture feature set based on a preset physical fitness evaluation model to generate a posture state recognition result of the target user, and generating physical fitness evaluation parameters according to the posture state recognition result, and the physical fitness evaluation parameters are fed back to the physical fitness training guidance system. According to the method, the identification capability of fine posture change in the fitness action of the complex body can be improved, the synchronous evaluation of the action specification degree and the physiological load state is realized, and the limitation of the traditional single-dimensional action evaluation is broken through.

The invention relates to the technical field of multi-target tracking, in particular to a dynamic multi-target tracking and trajectory prediction method. Comprising the following steps: acquiring a color image and a depth image, and preprocessing; constructing a dynamic threshold double-flow neural network, extracting features from the preprocessed color image and depth image to obtain a visual feature set and a depth feature set, fusing the visual feature set and the depth feature set through an adaptive attention mechanism to obtain a fused feature set, and combining a dynamic threshold to obtain an observation information list of a target; updating the observation information list through a self-motion decoupling mechanism to obtain a real information list; establishing space association and time association between the target and the track based on the real information list to obtain a newest track set; and analyzing target characteristics, environmental constraints, social behaviors and historical trajectories, generating a prediction trajectory of each target and a corresponding multi-factor score, generating a time-varying influence graph, and performing planning and decision making by adopting a double-layer decision-making mechanism.

The invention provides a deep learning-based avalanche early warning model construction method and system, and the method comprises the steps: firstly obtaining multi-source environment monitoring data, including meteorological time sequence, topographic space and accumulated snow layer physical data, of a target region, carrying out the time dimension alignment of the meteorological time sequence data to generate a feature sequence, carrying out the meshing of the topographic space data to generate a feature set, and carrying out the construction of an avalanche early warning model; the method comprises the following steps: extracting parameters from accumulated snow layer physical data to generate a state vector, inputting a deep learning network model containing time sequence attention, spatial convolution and cross-modal interaction units, generating a fusion feature vector, constructing a training set based on historical avalanche event annotation data, performing dynamic weight optimization on the fusion feature vector, and generating an avalanche risk prediction model. And finally, receiving current monitoring data in real time, outputting a risk level and an early warning trigger threshold value by the avalanche risk prediction model, and generating a multi-level early warning signal when a real-time risk value exceeds the threshold value, thereby realizing accurate avalanche early warning.

The invention provides an edge computing traffic light intelligent decision-making method integrated with AI video analysis, and the method comprises the steps: collecting a real-time traffic video stream of a target intersection through an edge computing device, and extracting a dynamic traffic feature set in the real-time traffic video stream, calling a pre-trained space-time analysis model to carry out multi-modal fusion processing on the dynamic traffic characteristic set, generating a traffic state vector of the target intersection, matching a candidate control strategy in a preset decision rule base based on the traffic state vector, and carrying out parameter adjustment on the candidate control strategy through a strategy optimization model to obtain a target traffic state vector; generating a target signal lamp control parameter; and issuing the target signal lamp control parameters to a traffic signal control terminal of the target intersection, and monitoring traffic state change data of the target intersection in real time to update weight parameters of the space-time analysis model. According to the invention, the traffic efficiency, pedestrian safety and traffic management intelligence degree of urban intersections can be improved.

The invention discloses a compressed air energy storage system operation state evaluation method based on principal component clustering analysis. The method comprises the steps that system operation data are collected and preprocessed; performing multi-time scale decomposition and feature extraction on the preprocessed data set; performing nonlinear time-varying adaptive principal component analysis on the multi-time scale feature set, and extracting main features of a system operation state; carrying out clustering analysis on the dimension reduction feature space by adopting a PCA-clustering iterative optimization mechanism; establishing an evaluation model of each functional area of the system based on thermodynamic constraints, and calculating performance index values of the functional areas in combination with the principal component transformation matrix and an operation mode clustering result; dynamically adjusting the weight of each evaluation index; and generating a CAES comprehensive operation state evaluation result. According to the method, the problems of poor PCA adaptability, difficulty in multi-time scale data fusion, low abnormal mode detection sensitivity and the like under the nonlinear time-varying characteristic of the CAES system are solved.

The invention provides an AI-based marketing video auditing method, and relates to the technical field of AI marketing video auditing, and the method comprises the steps: obtaining a multi-modal data original structure set, and extracting image semantic features, voice expression features, text semantic features and scene label information, and obtaining an image semantic feature set, a visual rhythm feature set, a voice expression feature set, a voice and picture synchronous association vector structure, a text semantic feature set and a subtitle semantic and image main body linkage relation graph. By constructing an image semantic feature set, a voice expression feature set, a text semantic feature set and a visual rhythm feature set and fusing the image semantic feature set, the voice expression feature set, the text semantic feature set and the visual rhythm feature set into a multi-modal content fusion feature tensor, unified modeling of an AI marketing video at visual, auditory and semantic levels can be realized; and subsequent microscopic consistency detection, compliance knowledge graph and emotion semantic conflict identification are effectively performed, so that full-link risk perception and accurate auditing of video contents are realized.