Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

171results about How to "Enhanced description ability" patented technology

Advanced nasopharynx cancer treatment effect prediction system based on deep learning

The invention relates to the technical field of medical data processing, in particular to an advanced nasopharynx cancer treatment effect prediction system based on deep learning. According to the invention, a data acquisition module acquires multi-modal medical images and clinical data of a patient from a hospital information system; the data preprocessing module is used for cleaning, registering, normalizing and standardizing the data; the feature extraction module extracts image features by using a convolutional neural network and fuses the image features with clinical features to form a comprehensive feature vector; the model construction and training module constructs a deep learning model, and is adjusted and optimized through training; the treatment prediction module inputs the comprehensive feature vector to obtain a treatment effect prediction result; and the result evaluation and feedback module compares prediction and actual results, calculates indexes and collects and feeds back the improved model. The system comprehensively integrates data, accurately mines features, constructs an effective model, provides personalized prediction to assist clinical decision, continuously improves the model performance, and has important significance in improving the prediction accuracy of the treatment effect of advanced nasopharynx cancer, promoting personalized medical treatment and the like.
Owner:THE FIRST AFFILIATED HOSPITAL OF FUJIAN MEDICAL UNIV

Large container crane intelligent early warning system based on personnel behavior analysis

The invention discloses a large container crane intelligent early warning system based on personnel behavior analysis, and the system comprises the following steps: collecting operator behaviors, equipment operation states and environment parameters in real time through a multi-mode sensor network, constructing a dynamic data set, extracting behavior characteristics through a time difference embedding algorithm, and carrying out the early warning of the operator behaviors, the equipment operation states and the environment parameters; a multi-level spatial-temporal characteristic matrix is generated in combination with dynamic scene influence factors, regional risk factors are dynamically calculated by using a Bayesian inference model, comprehensive risk values are generated through an adaptive multi-objective optimization algorithm, risk levels are divided into low, medium and high classes, and a system triggers graded early warning responses according to the risk levels. And an optimized behavior adjustment suggestion is generated in combination with a quantum probability behavior prediction algorithm, and a feature extraction rule and risk assessment logic are dynamically optimized through a progressive learning algorithm to form a closed-loop optimization process. According to the invention, intelligent analysis and real-time early warning of personnel behaviors are realized, and the safety and adaptability of the crane in an operation environment are improved.
Owner:BEIJING GUOXINZHIKE TECH DEV CO LTD

Multi-scale fluid dynamics digital twin model based on coupling algorithm

The invention discloses a multi-scale hydrodynamic digital twin model based on a coupling algorithm, which ensures the accuracy and consistency of the model on the overall and local levels through effective information exchange and integration among different scales. The consistency of macroscopic and microscopic variables is ensured on a boundary layer through bridging coupling of different scale models and a Lagrangian multiplier method, and physical behaviors of a complex system are simulated more accurately. Besides, through parameter estimation and data fusion, the model can integrate and utilize real-time data, so that dynamic optimization and prediction are realized, and the practicability and flexibility of the model are greatly enhanced. Therefore, the construction of the multi-scale digital twinborn model not only enhances the description capability of the model to a complex system, but also improves the adaptability and prediction precision of the model in practical application, and provides a more efficient and dynamic method for accurately simulating and predicting behaviors of the complex system.
Owner:ZHENGZHOU INST OF TECH

Wind wave flow prediction method and system based on meteorological simulation

The invention relates to the technical field of data processing, and discloses a wind wave flow prediction method and system based on meteorological simulation. The method comprises the following steps: performing atmospheric mode simulation on initial condition data and boundary condition data to obtain sea surface wind field data and atmospheric parameter data; performing post-processing and interpolation on the sea surface wind field data and the atmospheric parameter data to obtain wind wave model driving force field data; carrying out wind wave model coupling and simulation on the wind wave model driving force field data to obtain wind wave prediction result data; performing ocean current model coupling and simulation on the wind wave prediction result data and the wind wave model driving force field data to obtain ocean environment prediction result data; and performing data fusion and data assimilation processing on the marine environment prediction result data, the storm prediction result data and the storm model driving force field data to obtain storm flow prediction data, thereby improving timeliness and accuracy of storm flow prediction based on meteorological simulation.
Owner:SHENGDONG RUDONG OFFSHORE WIND POWER CO LTD +3

Ocean current simulation method and system based on three-dimensional temperature-salinity value

The invention relates to the technical field of data processing, and discloses an ocean current simulation method and system based on a three-dimensional temperature-salinity value. The method comprises the following steps: carrying out line calculation and adaptive mesh refinement processing on a three-dimensional temperature and salt field simulation model to obtain a model operation scheme; performing three-dimensional visualization processing on the three-dimensional temperature and salt field initial data set and the model operation scheme to obtain dynamic three-dimensional temperature and salt field visualization data, and analyzing the dynamic three-dimensional temperature and salt field visualization data to obtain three-dimensional structure data and evolution process data of the key ocean phenomenon; performing data assimilation processing on the multi-source real-time observation data, the three-dimensional structure data and the evolution process data to obtain a fusion data set; and performing ocean current prediction calculation on the fused data set to obtain a three-dimensional ocean current prediction field, and performing uncertainty quantitative analysis on the three-dimensional ocean current prediction field to obtain ocean current simulation probability distribution data. According to the invention, the accuracy and timeliness of ocean current simulation based on the three-dimensional temperature-salinity value are improved.
Owner:SHENGDONG RUDONG OFFSHORE WIND POWER CO LTD +3

High-rise building settlement prediction method and system, storage medium and program product

ActiveCN119089282AImprove forecast accuracyAchieve early settlement predictionBiological modelsData miningDistribution diagram
The invention discloses a high-rise building settlement prediction method and system, a storage medium and a program product, and the method comprises the steps: separating a trend term, a periodic term and a random term for multi-source monitoring data, and constructing a nonlinear time sequence prediction model; inputting historical multi-source monitoring data into the nonlinear time sequence prediction model to obtain a preliminary settlement prediction result; a continuous settlement distribution diagram of the high-rise building is generated, and spatial distribution characteristics are obtained; determining a plurality of key influence factors and corresponding influence factor weights based on the multi-source monitoring data; constructing a settlement prediction model; inputting the multi-source monitoring data into the settlement prediction model to obtain a final settlement prediction result; and sending the settlement trend curve graph and the prediction and early warning time point to a management terminal. The early settlement prediction of the high-rise building is realized, the timeliness of detecting the settlement risk of the high-rise building is improved, and the probability of potential safety hazards caused by settlement of the high-rise building is reduced.
Owner:BEIJING XINXING HUANYU INFORMATION TECH CO LTD

Remote acquisition system for operation data of gas equipment

The invention provides a remote acquisition system for operation data of gas equipment, and relates to the technical field of data processing, and the remote acquisition system comprises the steps: capturing the time-varying rule of the state of the gas equipment through learning the long-term dependency relationship in a sequence, and generating key features containing time sequence information; fusing the time sequence characteristic representation output by the long short-term memory network with the equipment attributes and relationships in the knowledge graph to form a characteristic vector reflecting the comprehensive state of the gas equipment; comprehensively analyzing the feature vector to obtain a hidden mode related to the risk of the gas equipment; and based on the hidden mode related to the gas equipment risk, adopting a multi-classification support vector machine to predict the risk level so as to obtain a final risk level prediction result. According to the invention, risk assessment of the operation state of the gas equipment can be realized, so that the safety and the operation efficiency of the equipment are improved.
Owner:SHANDONG ORDER GAS CO LTD

Motor stator vibration suppression method and system based on electromagnetic pad and deep learning

The invention provides a motor stator vibration suppression method and system based on an electromagnetic pad and deep learning, and relates to the field of electrical technology, and the method comprises the steps: collecting a vibration signal of a motor stator, and carrying out the preprocessing of the vibration signal; inputting the preprocessed signal into a deep learning model, and training and optimizing the deep learning model; fusing the features through a full connection layer to obtain a comprehensive feature vector; predicting the future vibration state of the motor stator by using the comprehensive feature vector; establishing an electromagnetic force model, and designing an adaptive control law based on the predicted future vibration state and the electromagnetic force model; electromagnetic force required by vibration suppression is calculated by using a self-adaptive control law and is converted into a control signal to adjust the electromagnetic pad; a multi-objective optimization algorithm is used to consider the vibration suppression effect and energy consumption at the same time, an adaptive control law is adjusted, and closed-loop feedback control is formed to continuously optimize the vibration suppression effect.
Owner:NINGBO KEDA DRIVING TECH CO LTD

Graph neural network power grid cascade fault prediction method based on physical information guidance

The invention belongs to the field of power system cascade fault prediction, and relates to a graph neural network power grid cascade fault prediction method based on physical information guidance, and the method comprises the steps: obtaining the operation data of a cascade fault, inputting the operation data of the cascade fault into a trained power grid cascade fault prediction model, and obtaining a prediction result; the power grid cascade fault prediction model comprises a common embedded graph neural network and a structure coding module; according to the invention, data enhancement is carried out by using a multi-step random walk matrix considering power grid line attributes and structure coding represented by node degrees, so that the capability of capturing topological information is improved; according to the invention, the interaction between the power grid nodes and the power grid lines is promoted by using the co-embedded graph neural network, and the accuracy of power grid cascade fault prediction is improved; according to the method, the node-edge interaction aggregation function of the co-embedded graph neural network is changed through the power transmission distribution factor of the power grid, the description capability of the actual complex interaction relation of the power grid is improved, and the accuracy of power grid cascade fault prediction is improved.
Owner:CHONGQING UNIV OF POSTS & TELECOMM

Water supply network pipe burst alarm positioning system based on real-time pressure monitoring data

The invention relates to the technical field of pipe network monitoring, in particular to a water supply pipe network pipe burst alarm positioning system based on real-time pressure monitoring data, and the system comprises a pressure data collection module which collects pressure data from a plurality of pressure monitoring points of a water supply pipe network; the pressure drop threshold calculation module is used for determining an alarm pressure drop threshold of each pressure monitoring point based on historical pressure data; the voltage drop alarm module is used for calculating a current time window voltage drop value and comparing the current time window voltage drop value with a voltage drop threshold value; the association alarm module is used for clustering alarm information of adjacent pressure monitoring points and combining a plurality of alarm points which are close in space into a single alarm event; the alarm positioning module is used for matching a pipe explosion node corresponding to the current alarm information by utilizing a mode recognition algorithm and quickly positioning the pipe explosion node; according to the method, the system calculates the aggregation characteristics, the description capability and the credibility of the alarm event are enhanced, and the identification and positioning efficiency of the system on the pipe explosion event in the complex pipe network environment is improved.
Owner:SHENZHEN WATER GRP CO LTD

Real-time multi-person motion analysis system based on motion perception and semantic understanding

The invention relates to the field of computer vision and artificial intelligence, in particular to a real-time multi-person motion analysis system based on motion perception and semantic understanding, which comprises a motion perception module, a motion tracking module, a motion semantic understanding module and a motion performance analysis module. The motion area segmentation unit adopts a background modeling or inter-frame difference method to identify a motion area and generate a motion mask; the target detection unit is connected with the central processing unit through a data bus and used for processing video frame data and detecting the position and the bounding box of a moving target. The motion area segmentation unit is connected with the target detection unit and is used for generating a motion mask. By integrating a plurality of modules, the motion data can be comprehensively captured and analyzed, and the accuracy and real-time performance of motion analysis are improved. Through combination of the target detection unit and the motion area segmentation unit, the system can accurately identify a motion target and a motion area, and a solid foundation is laid for subsequent tracking and analysis.
Owner:RONGMENGYUESHI (SHANGHAI) SPORTS TECHNOLOGY CO LTD

Stay wire connector machining method based on automation

The invention discloses a stay wire connector processing method based on automation, and relates to the field of automation control, and the method comprises the steps: obtaining the point cloud data of a wedge-shaped connector physical model; real-time data in the machining process of the wedge-shaped connector is collected through a sensor; preprocessing the point cloud data; reconstructing a three-dimensional model of the wedge-shaped joint by using the processed point cloud data, and extracting geometric parameters of the wedge-shaped joint from the three-dimensional model; according to the collected real-time data, a physical model of the wedge-shaped connector machining process is established; according to the three-dimensional model, a tool machining motion path is generated through computer aided manufacturing software; a self-adaptive particle swarm optimization algorithm is adopted to optimize a tool machining motion path; and the optimized tool machining motion path is converted into a G code recognized by a numerical control machine tool, and the numerical control machine is controlled to machine the wedge-shaped connector. The machining precision of the wedge-shaped connector is improved by aiming at the low machining precision of the wedge-shaped connector in the prior art.
Owner:CHINA RAILWAY ELECTRIFICATION ENGINEERING GROUP CO LTD +2

Concentrating holographic induced polarization advanced water detection method and system for construction of full-face tunnel boring machine

The invention belongs to the technical field of geophysical advanced forecasting. According to the method and the system, by acquiring holographic parameters, accurate parameterized description can be performed on related information in an induced polarization phenomenon, and physical characteristics of a rock-soil body can be described more comprehensively; according to the method, rich information in induced polarization parameters is fully excavated and utilized, holographic data and actual rock mass sampling data are combined, an innovative method is provided for spatial distribution prediction of permeability, and finally water inflow prediction is conducted according to a permeability prediction result; optimization design is carried out aiming at specific environment conditions of the full-face tunnel boring machine, and a power supply electrode and a detection electrode are reasonably carried on the tunneling machine equipment; more reliable geological information support is provided for the construction process of the full-face tunnel boring machine, and safety accidents caused by sudden water burst in the construction process can be effectively avoided.
Owner:SHANDONG UNIV

Dry method dense medium coal preparation intelligent process prediction control method

The invention discloses a dry method dense medium coal dressing intelligent process prediction control method which comprises the following steps: firstly, collecting data of raw coal to be washed, and counting prior selectability information of the collected data; establishing a bed density dynamic model based on evolution time, and forming stable bed density; then a sorting density model is obtained through calculation, an empirical distribution function model based on the sorting density model, possible deviation of a sorting system and boundary control parameters is established, and the product distribution rate corresponding to each density level interval is calculated; and finally, predicting and calculating the product yield and ash content of the coal dressing system according to the priori selectability information and the product distribution rate corresponding to each density level interval, and correcting the product yield and ash content. According to the method, different dry-method dense medium separation mathematical models are fused, the description capacity of the models for the steady-state and dynamic characteristics of the separation process is enhanced, the prediction precision of the clean coal ash content and the yield is improved, and the problem that dynamic control is difficult to implement due to lack of theoretical models in the dry-method dense medium field is solved.
Owner:CHINA UNIV OF MINING & TECH

Knowledge graph generation method and device based on word document and electronic equipment

The invention discloses a word document-based knowledge graph generation method and apparatus, and an electronic device, and relates to the field of data processing. The method comprises the following steps of: analyzing a target document to obtain a corresponding xml (Extensible Markup Language) file; the xml file is analyzed to obtain a first data structure, and the first data structure comprises a plurality of elements; in the first data structure, sorting the plurality of elements according to a preset sorting rule to obtain a second data structure; segmenting the second data structure by adopting a preset recursive function to obtain a plurality of entities and a relationship among the plurality of entities; and taking the plurality of entities as nodes of a preset knowledge graph, and taking the relationship among the plurality of entities as edges of the preset knowledge graph to obtain a target knowledge graph. According to the technical scheme provided by the invention, the document content is converted into the XML format for recognition and extraction, so that the accuracy of converting the document into the knowledge graph is improved.
Owner:BEIJING HUARONG XINNING TECH CO LTD

Substation site selection planning method based on II-type fuzzy credibility constraint planning

The invention discloses a transformer substation site selection planning method based on II-type fuzzy credibility constraint planning, and the method comprises the steps: firstly employing an interval II-type fuzzy membership function to represent the output of renewable energy sources, and building an uncertainty model of the output of the renewable energy sources; and determining the number of transformer substations according to hardware conditions in the planning area. And then, taking the minimum load moment as an optimization target, and establishing a transformer substation site selection planning model based on II-type fuzzy credibility constraint planning. And finally, solving the substation site selection planning model by using an optimization algorithm, and outputting coordinates of the substation. According to the method, uncertainty brought by photovoltaic energy is processed by introducing II-type fuzziness, fuzzy credibility constraint programming is fused into a mixed integer linear programming framework, planning schemes under different confidence levels can be obtained, system stability and economic benefits can be balanced conveniently, and the method is suitable for large-scale popularization and application. Unnecessary economic cost caused by excessive refinement is avoided to a certain extent, and actual requirements of different power distribution networks are better met.
Owner:STATE GRID ZHEJIANG ELECTRIC POWER CO LTD

In-transit supervision method and system for large piece transportation on highway

The invention relates to the technical field of logistics management, in particular to an in-transit supervision method for large-size transportation on an expressway. The method comprises the following steps: acquiring transportation speed data and transportation vibration data; carrying out transportation speed feature extraction on the transportation speed data to obtain transportation speed feature data, and carrying out transportation vibration feature extraction on the transportation vibration data to obtain transportation vibration feature data; performing feature map construction on the transportation speed feature data and the transportation vibration feature data to obtain transportation speed vibration feature map data; abrupt change feature collection and change degree extraction are carried out according to the transportation speed vibration feature map data, and transportation abrupt change feature data and transportation change degree data are obtained so as to carry out large piece transportation anomaly detection operation. According to the invention, the safety and the management level of the large-piece transportation process are effectively improved.
Owner:HUNAN COMM RES INST CO LTD

Vibration analysis method and system for intermediate bearing in double-rotor system

The invention provides a vibration analysis method and system for an intermediate bearing in a double-rotor system. The method comprises the following steps: determining a rolling body entering a defect area at the current moment and a rolling body with the maximum contact deformation based on bearing parameters, an operation state, defect information, contact rigidity and damping parameters; respectively calculating the time-varying displacement and impact force of the rolling body entering the defect area and the rolling body with the maximum contact deformation, and the angle difference between the time-varying displacement and the impact force; the impact force is corrected through the angle difference between the rolling body entering the defect area and the rolling body with the largest contact deformation and serves as external force input of a nonlinear kinetic equation of an intermediate bearing system of the double-rotor system; and calculating a nonlinear bearing force in the nonlinear kinetic equation based on the time-varying displacement of the rolling body entering the defect area and the rolling body with the maximum contact deformation. And solving the nonlinear kinetic equation. According to the method, the vibration analysis precision under the condition of the defect of the intermediate bearing in the double-rotor system is improved.
Owner:NAVAL UNIV OF ENG PLA

Building information model IFC format analysis method

The invention provides a method for analyzing an IFC format of a building information model, which can reduce the complexity of the model, improve the processing efficiency and expand the application field. The method comprises the following steps: converting building information model BIM data in an IFC format into a neutral data file, and then converting the neutral data file into a building information model data structure aemoate-data to realize analysis. The process comprises analysis preparation, IFC format file processing and data conversion; the analysis preparation comprises construction of an SPF analyzer module and construction of an IFC version configuration module; the SPF parser module is used for parsing ISO data according to an ISO-10303-21 standard, and the IFC version configuration module is used for redefining all objects and classes of an IFC data architecture according to an IFC version; the IFC format file processing comprises the steps of traversing all information of an IFC file, and analyzing the IFC file by using an SPF analyzer to form a neutral data file.
Owner:CHINA STATE CONSTRUCTION ACADEMY CORPERATION LTD

Arc screen multi-view 3D image generation method and device

The invention relates to the technical field of image generation, and discloses an arc-shaped screen multi-view 3D image generation method and device, and the method comprises the steps: collecting a view parameter set of an arc-shaped screen, and carrying out the residual feature processing of an original image sequence, and obtaining a multi-dimensional space feature map; performing tensor product operation on the multi-dimensional spatial feature map and the view angle parameter set to obtain view angle conversion delay data; performing graph convolution operation to obtain space-time dependence features; performing multi-head self-attention calculation on the space-time dependency features to obtain delay compensation features, and performing comparative learning on the view angle features based on the delay compensation features to obtain view angle mapping parameters; the view angle mapping parameters, the delay compensation features and the original image sequence are input into a U-Net network for 3D image reconstruction, and a 3D image sequence with continuous view angles is output, the feature consistency in the view angle conversion process is improved, image distortion during view angle switching is reduced, and therefore the visual quality of 3D images is improved.
Owner:SHENZHEN MEIYAD OPTOELECTRONICS CO LTD

Ionized layer TEC determination method based on satellite-ground active measurement and SAR image joint inversion

The invention relates to an ionized layer TEC determination method and system based on satellite-ground active measurement and SAR image joint inversion. The method comprises the steps that S1, a mapping relation database of ionized layer scattering characteristics measured by a dual-frequency SAR satellite, ionized layer penetration characteristics measured by satellite-ground active measurement and ionized layer TEC measured by a GPS receiving station is established; s2, establishing and training a TEC inversion deep learning model by using a multi-source amplitude-phase parameter neural network according to the mapping relation database, and outputting a corresponding TEC value by the TEC inversion deep learning model by taking an ionized layer amplitude-phase parameter as an input; the ionosphere amplitude-phase parameters are ionosphere scattering signal amplitude-phase parameters and / or ionosphere transmission signal amplitude-phase parameters; and S3, performing on-orbit intelligent rapid inversion on the ionized layer TEC over the globe according to the TEC inversion deep learning model. According to the method, the TEC inversion model based on SAR satellite measurement data is established, the method has the advantages of high precision and high timeliness, and high-precision inversion of any space-time TEC can be realized.
Owner:CHINA ACADEMY OF SPACE TECHNOLOGY +1

Phishing webpage detection method fusing URL characters and HTML content semantics

The invention discloses a phishing webpage detection method fusing URL (Uniform Resource Locator) characters and HTML (Hypertext Markup Language) content semantics, which comprises the following steps of: finely extracting URL character-level local features based on a multi-scale convolution strategy, processing URL character strings in parallel by using CNNs (Convolutional Neural Neural Neural Neural Neural Neural Neural Neural Neural Neural Neural Neural Neural Neural Neural Neural Neural Neural Neural Neural And carrying out HTML text word-level feature extraction based on a cascade dense connection CNN architecture. A plurality of convolution layers are stacked, dense connection is established between convolution blocks, and deeper and fine-grained semantic features are extracted; the URL feature characters and the HTML features are fused through a full connection layer, and the corresponding probability is calculated to judge whether the webpage is a phishing webpage or not. According to the method, the advantages of the deep learning algorithm are fully utilized, the characteristics of the URL characters and the HTML content of the phishing webpage are integrated, more comprehensive semantic representation is formed, and the recognition rate of phishing webpage detection is greatly improved.
Owner:ANHUI UNIV

Index sequence generation method and device, electronic equipment and storage medium

The invention discloses an index sequence generation method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring first gene expression data and at least one codebook entry, encoding the first gene expression data, extracting local information in the first gene expression data, and mapping the local information into a potential space to obtain potential representation of the local information; performing quantization processing on the potential representation based on the at least one codebook entry to generate a first codebook index matrix and at least one quantization vector; decoding and reconstructing the first codebook index matrix, outputting second gene expression data, performing adversarial training on a decoder and at least one quantization vector, and outputting optimization parameters; and performing autoregression modeling processing on at least one new codebook entry to obtain a second codebook index matrix, and processing the second codebook index matrix by using the optimized decoder to obtain a data sample. According to the method, the calculation burden of high-dimensional data modeling is reduced, and the data capturing capability of the model is improved.
Owner:INSPUR SUZHOU INTELLIGENT TECH CO LTD

New energy power generation scene generation method and system considering uncertainty

The invention discloses a new energy power generation scene generation method and system considering uncertainty, and relates to the technical field of new energy power scene generation, and the method comprises the steps: carrying out the modeling through combining the error fluctuation of Bayesian optimization and kernel density estimation; modeling is carried out based on the error time sequence of the Markov chain; and based on a new energy prediction error modeling process, generating a new energy power sequence scene, and analyzing prediction error characteristics. According to the new energy power generation scene generation method considering uncertainty provided by the invention, the output interval of each prediction box is determined through the Bayesian optimization method, the utilization efficiency of data in the prediction boxes is improved, the prediction error in each prediction box is fitted through the kernel density estimation method, the adaptability of the model is enhanced, and the generation efficiency of the new energy power generation scene is improved. The time sequence correlation of the prediction error is modeled through the Markov chain, the time sequence consistency of the generated scene is enhanced, and the method achieves better effects in the aspects of utilization efficiency, adaptability and time sequence consistency.
Owner:GUIZHOU POWER GRID CO LTD +1

A knowledge and data fusion-driven time series forecasting method and system

PendingCN122310007AEnhance accurate captureImprove the vanishing gradient problemFeature extractionParallel encoding
This invention discloses a knowledge- and data-driven time series forecasting method and system, belonging to the field of industrial time series forecasting technology. To address the technical problems of existing technologies when processing strongly non-stationary data, such as key signal attention dilution, systematic underestimation of peak amplitude, incomplete capture of multi-scale dynamic patterns, and difficulty in embedding physical domain knowledge, this invention constructs standardized multi-dimensional time series data, performs heterogeneous feature grouping and parallel encoding to obtain multiple sets of feature representations, then extracts and integrates features from multiple sources to obtain intermediate state features, and finally performs multi-branch prediction and adaptive weighted fusion based on the intermediate state features to obtain the final time series forecast result. This invention can achieve active focusing on abrupt events in industrial sequences and accurate characterization of extreme value amplitudes, significantly improving prediction accuracy, physical consistency, and robustness to extreme conditions.
Owner:PEKING UNIV +1

A data analysis system and method for vehicle electrical system fault diagnosis

The application provides a data analysis system and method for vehicle electrical system fault diagnosis, which extracts multi-dimensional feature indexes representing the running state of the electrical system from the running data of the electrical system under different working conditions; performs credibility evaluation on the corresponding multi-dimensional feature indexes under each working condition, and determines the credible evidence thereof, and then determines the credibility difference of the multi-dimensional feature indexes under different working conditions from all the credible evidence; performs difference analysis on the data collected under different working conditions according to the distribution correlation of the multi-dimensional feature indexes in each running data, and obtains the consistency difference of the multi-dimensional feature indexes under different working conditions; and performs feature fusion on all the collected running data according to the credibility difference and the consistency difference, and generates a fusion feature parameter capable of reflecting the running state of the vehicle electrical system. The application scheme can realize the fusion of the electrical system state features through the credibility difference and the consistency difference of the features under multiple working conditions, thereby improving the robustness of the electrical system fault diagnosis.
Owner:AUTOPHIX TECH CO LTD

An emotion recognition method based on online cross-modal knowledge distillation

ActiveCN121960702BAchieve real-timeAchieve collaborative learningPsychotechnic devicesSensorsData segmentBi modal
The application discloses an emotion recognition method based on online cross-modal knowledge distillation, comprising the following steps: acquiring electroencephalogram and electrocardiogram original signals and windowing and cutting; constructing electroencephalogram and electrocardiogram student models, extracting intermediate features from each modal data segment through an encoder, and obtaining non-normalized prediction output through a classifier; constructing a teacher probability distribution through a joint encoder fusion; introducing adaptive contrast loss to align the cross-modal intermediate features, introducing distillation loss to constrain the prediction probability distribution of each modal to align with the teacher probability distribution; synchronously optimizing new student model parameters through online collaborative training; and performing actual inference prediction based on the student model after training. The application combines double modal signals to make up for the defects of single modal information, excavates the complementarity of modes, realizes dynamic generation of teacher supervision signals and real-time collaborative learning of modes through online distillation, does not increase test calculation overhead, effectively improves the recognition accuracy, model robustness and generalization ability, and has good application prospect.
Owner:ANHUI UNIV

A method and system for analyzing drought propagation considering multi-dimensional characteristics of drought events

PendingCN122656050AImprove adaptabilityGood transferabilitySoil scienceBiology
The application provides a drought propagation analysis method and system considering multi-dimensional characteristics of drought events. The method comprises the following steps: calculating a drought duration propagation index based on a meteorological drought total duration and an agricultural drought total duration; calculating a drought intensity propagation index based on meteorological drought intensities of previous meteorological drought events and agricultural drought intensities of previous agricultural drought events; calculating a drought intensity trend propagation index based on meteorological drought intensity trends of previous meteorological drought events and agricultural drought intensity trends of previous agricultural drought events; calculating a drought fluctuation propagation index based on meteorological drought index fluctuation rates of previous meteorological drought events and agricultural drought index fluctuation rates of previous agricultural drought events; calculating a drought probability propagation index based on a meteorological drought occurrence probability and an agricultural drought occurrence probability of a target region within a given time period; and constructing a comprehensive drought propagation index by using a CRITIC objective weighting method. The application can accurately describe the propagation process between meteorological drought and agricultural drought.
Owner:河南省水文水资源中心

Adaptive grid division method based on 4D imaging millimeter wave radar point cloud

The invention relates to the technical field of radar data processing, and particularly discloses a self-adaptive grid division method based on 4D imaging millimeter wave radar point clouds, which comprises the following steps: step S11, acquiring multiple pieces of dimension information of target point clouds around a vehicle; s12, establishing a grid map according to the current dimension information of the target point cloud around the vehicle; s13, distributing the target point clouds around the vehicle to the corresponding minimum grids on the grid map according to the current dimension information of the target point clouds, and calculating the density of the target point clouds in each minimum grid; step S14, according to the target point cloud density in each minimum grid, merging the plurality of minimum grids in the grid map to form a plurality of merged grids; and the step S12 to the step S14 are repeated until all the grid maps established by all the dimension information of the target point cloud around the vehicle are subjected to grid combination. According to the invention, through adaptive grid division, redundant grids are reduced, and a basis is provided for a subsequent rasterization clustering algorithm.
Owner:WEIFU INTELLIGENT SENSE (WUXI) TECH CO LTD

Virtual power plant-oriented multi-data source fusion multi-energy load prediction method

The invention relates to the technical field of virtual power plant operation and optimization control, in particular to a virtual power plant-oriented multi-data-source fusion multi-energy load prediction method, which comprises the following steps of: constructing aggregated multi-source heterogeneous data of a virtual power plant; the data comprises historical multi-energy load data, calendar and market information and external environment auxiliary data in the jurisdiction of a virtual power plant, preprocessing the multi-source heterogeneous data, performing feature screening on the time sequence feature matrix based on correlation analysis, constructing a model input set, constructing a load prediction model, and predicting the load of the power plant. The model comprises an input layer, a plurality of stacked space-time fusion layers and an output layer which are connected in sequence; the space-time fusion layer comprises a multi-scale time convolution module and a graph convolution module which are parallel, and is used for model training and parameter optimization, load prediction and result output; and combined prediction of the electric load, the thermal load and the cold load is realized under a unified multi-scale space-time diagram neural network framework.
Owner:ANSHAN POWER SUPPLY COMPANY OF STATE GRID LIAONING ELECTRIC POWER COMPANY +1