Product
Patsnap Eureka
For R&D, Patsnap Eureka makes reading and utilizing patents & technical documents easy.
Patsnap Eureka AIR
Designed for self-driven R&D workflows. Generate viable solutions, solve complex R&D challenges, empower your innovation with AI.
Patsnap Eureka Materials
Designed for material experts only. Revolutionize your material R&D, from search, analyze, to developing new materials.
Feature
TechResearch
Generate reliable direction feasibility study reports for your R&D in just a few steps.
TechSeek
Discover and master advanced knowledge NOW. Basics, ideas, possibilities, all at once.
TechMind
As an expert in R&D Theories, TechMind can generates customized viable solutions instantly.
TechRisk
Analyze your overall solution with one click, know your potential R&D risks in advance.
TechMonitor
Get weekly tech updates, stay abreast of the latest tech innovations and key insights.
Patents
Literature
Hiro is an intelligent assistant for R&D personnel, combined with Patent DNA, to facilitate innovative research.
34 results about "Adaptive integration" patented technology
Efficacy Topic
Property
Owner
Technical Advancement
Application Domain
Technology Topic
Technology Field Word
Patent Country/Region
Patent Type
Patent Status
Application Year
Inventor
Method and multi-scale attention system for spatiotemporal change determination and object detection
A method and multi-scale attention system for the detection of objects and temporal change regions by a spatiotemporal attention operator of an image sequence, which linearly aggregates temporal change filter with spatial saliency filter and includes an extractor of salient maxima, which selects consecutive salient maxima of the spatiotemporal operator to produce the locations of the objects of interest and the centers of temporal change regions. The concept of spatial local scale introduced into the system and method for its determination allows for a scale-adaptive integration of the temporal change with spatial saliency and effective detection of different in size and location objects of interest. Can be used for object and spatiotemporal change detection in monitoring pollution, natural disasters, weather conditions and environmental changes based on satellite remote sensing imagery from various sensors.
Owner:PALENYCHKA ROMAN +1
Target tracking method and device based on video
InactiveCN101404086AThe description is validEffectively deal with "multi-peak" phenomenonImage analysisRadiologyNuclear medicine
The invention discloses a video target tracking method which is based on multi-cue integration and particle filtration and a device thereof. The method carries out the self-adaptive integration according to three cues of color, edge and feature points to obtain target observation information, then the particle filtration technology is used for updating the target state, and the specific steps comprise: A. a target template is extracted and target parameters are initialized; B. dynamic prediction is carried out on a particle set according to a motion model; C. the particle weight is updated according to multi-cue integration information; D. the motion state of a target is updated. The video target tracking method and the device can improve the tracking effect and the tracking stability of the moving target under the complex environment and the tracked target can comprise human heads, pedestrians, cars, etc.
Owner:ZHEJIANG UNIV
Method and apparatus of adaptive integration activity management for business application integration
InactiveUS20050120353A1High costHigh labor-intensive one-to-one application integrationResourcesInput/output processes for data processingSoftware engineeringWorkload
An adaptive integration activity management framework for on demand business process integration provides a mechanism to enable easy integration of legacy and new applications. The framework minimizes the effort need to integrate a new application into an existing business process environment such that the new activity is a “plug-in” into an action manager by implementing a standard adaptation layer. Activity integration is implemented in the principle of “on-demand” because it is invoked as required, so the communication and collaboration between partners become much more flexible.
Owner:IBM CORP
Systems and Methods for Adaptive Integration of Hardware and Software Lock Elision Techniques
ActiveUS20150026688A1Improve scalabilityImprove performanceSpecific access rightsProgram initiation/switchingSoftware lockoutParallel computing
Particular techniques for improving the scalability of concurrent programs (e.g., lock-based applications) may be effective in some environments and for some workloads, but not others. The systems described herein may automatically choose appropriate ones of these techniques to apply when executing lock-based applications at runtime, based on observations of the application in the current environment and with the current workload. In one example, two techniques for improving lock scalability (e.g., transactional lock elision using hardware transactional memory, and optimistic software techniques) may be integrated together. A lightweight runtime library built for this purpose may adapt its approach to managing concurrency by dynamically selecting one or more of these techniques (at different times) during execution of a given application. In this Adaptive Lock Elision approach, the techniques may be selected (based on pluggable policies) at runtime to achieve good performance on different platforms and for different workloads.
Owner:ORACLE INT CORP
SVC sliding mode control method based on integration adaptive backstepping
InactiveCN107240921AImprove transient stabilityImprove robustnessFlexible AC transmissionReactive power adjustment/elimination/compensationSystem of imprimitivityBackstepping
The invention discloses a SVC sliding mode control method based on integration adaptive backstepping; the control method comprises the following steps: building a SVC equipment single-machine infinite bus system dynamic mathematics model, designing a controller according to an integration adaptive backstepping method, firstly designing a state variable tracking error, adding an integration item into the error item, simultaneously considering system parameter nondeterminacy, building a Liapunov function, online adaptively processing the uncertain parameters, finally adding a Terminal slide mode surface, obtaining a SVC integration adaptive backstepping stable controller, and finishing SVC sliding mode control based on integration adaptive backstepping. The method uses the adaptive integration method to eliminate errors, adds the Terminal slide mode control, so the system has stronger robustness on interference and system perturbation; the method can fast damp power concussions, can keep the machine end voltage, and can improve the power system transient stability.
Owner:李昊昊 +2
Knowledge graph completion method and device, storage medium and electronic equipment
ActiveCN112836064AImprove accuracyReliable Confidence ScoreNatural language data processingSpecial data processing applicationsAlgorithmTheoretical computer science
The invention discloses a knowledge graph completion method and device, a storage medium and electronic equipment, and belongs to the technical field of computers. The knowledge graph completion method comprises the steps of obtaining a to-be-verified target knowledge text, generating a plurality of triples according to the target knowledge text and a preset knowledge graph, calculating each triple to obtain a corresponding confidence coefficient, verifying a target triple based on the corresponding confidence coefficients, and complementing the knowledge graph according to the verification result. Therefore, according to the method, the mixed model combining the text coding technology and the graph embedding technology is provided to learn the context and the structured knowledge at the same time, the reliable triple confidence score is obtained, advantage complementation of the two methods is achieved, the calculation overhead is remarkably reduced, and the complementation accuracy is improved. The invention further provides an adaptive integration scheme, scores of the coding method and the graph embedding method are fused in an adaptive mode, and the knowledge graph completion accuracy is further improved.
Owner:JILIN UNIV
Adaptive channel estimation using continuous pilot signal based on doppler period
InactiveUS7274728B1Error preventionLine-faulsts/interference reductionSelf adaptiveAdaptive integration
A method and apparatus to estimate the channel fade (both the amplitude gain / loss and the phase rotation) to assist the receiver to detect and recover the transmitted signal employs a continuous pilot signal such as the pilot code channel or pilot symbols. The channel estimator uses the same scrambling pattern of pilot channel and coherently integrates the continuous pilot signal to yield a channel estimate. The present invention employs adaptive integration duration to yield a channel estimate. The integration duration of the pilot signal for channel estimation is adaptive and proportional to the Doppler period. The Doppler period is proportional to the inverse of Doppler frequency and is an indicator of how fast the channel changes.
Owner:INTEL CORP
Objective evaluation method for full reference image quality based on neural network learning integration
ActiveCN108615231AIntuitively comparableSmall range of variationImage enhancementImage analysisImaging qualityNeural network learning
The invention discloses an objective evaluation method for the full reference image quality, which comprises the steps of applying a BP neural network to image quality evaluation, designing a visual multi-channel multi-algorithm adaptive integration BP neural network image quality prediction model, inputting a distorted image into the BP neural network based on visual multi-channel evaluation results of various objective evaluation algorithms, performing supervised learning and training on the BP neural network by taking the score of a human eye subjective test result as a training objective,then predicting and outputting objective evaluation results of the various objective evaluation algorithms, and performing adaptive integration on the objective evaluation results of the various algorithms to obtain final objective evaluation for the quality of the distorted image. The method disclosed by the invention comprehensively improves the level of various indexes of the evaluation methodsuch as PSNR, SSIM and SVD, exceeds the latest evaluation methods such as visual feature perception processing and visual psychological derivation integration, and has better evaluation stability.
Owner:ZHEJIANG UNIVERSITY OF SCIENCE AND TECHNOLOGY
Method and apparatus of adaptive integration activity management for business application integration
InactiveUS7404185B2Easy to integrateMinimize effortResourcesSpecific program execution arrangementsSoftware engineeringApplication software
An adaptive integration activity management framework for on demand business process integration provides a mechanism to enable easy integration of legacy and new applications. The framework minimizes the effort need to integrate a new application into an existing business process environment such that the new activity is a “plug-in” into an action manager by implementing a standard adaptation layer. Activity integration is implemented in the principle of “on-demand” because it is invoked as required, so the communication and collaboration between partners become much more flexible.
Owner:INT BUSINESS MASCH CORP
Industrial rubber compound Mooney viscosity soft measurement method based on integrated immediate learning
ActiveCN110263488AImprove forecast accuracyEnsemble learningDesign optimisation/simulationLearning basedMooney viscosity
The invention relates to an industrial rubber compound Mooney viscosity soft measurement method based on integrated immediate learning. The method is used for online prediction of Mooney viscosity in the industrial rubber compound process. According to the method, Gaussian process regression (GPR) is used as a local modeling technology; in combination with similarity disturbance and a multi-modal disturbance strategy of an input sample, the diversity of instant learning is excited; secondly, an instant learning base model meeting diversity and accuracy is constructed on the basis of evolutionary multi-objective optimization, and finally, fusion of the instant learning base model is realized and a final Mooney viscosity predicted value is obtained by introducing an adaptive integration strategy of a limited mixing mechanism. According to the method, the problems that the cost is increased and the product quality is difficult to improve due to acquisition lag of the Mooney viscosity value in the rubber mixing process are solved, and high-precision online real-time acquisition of the Mooney viscosity is realized.
Owner:KUNMING UNIV OF SCI & TECH
Self-adaptive integrated unbalanced data classification method based on Euclidean distance
InactiveCN110533116AGood choiceQuick selectionCharacter and pattern recognitionIntegration ruleClassification methods
The invention discloses an self-adaptive integrated unbalanced data classification method based on Euclidean distance, which comprises the following steps of: firstly, obtaining a plurality of diversified balance subsets by using a random balance method, then establishing and obtaining a plurality of basic classifiers on each balance subset; and adding a classifier pre-selection algorithm before the dynamic selection algorithm. After a screened basic classifier is obtained, a new dynamic selection algorithm is provided, and by evaluating the condition of the sample classifier in the surrounding area of a to-be-classified sample, the capability is stronger when more minority class samples belong to the correct classification range. And finally, a prediction result obtained by the selected basic classifier by adopting a distance-based adaptive integration rule is output. According to the method, basic classifiers can be established on the generated diversified subsets, meanwhile, a dynamic selection algorithm is provided, the sub-classifier with the highest classification capacity can be selected out, finally, the proposed integration rule can provide a better output result, and finally, the unbalanced data classification precision is effectively improved.
Owner:DALIAN UNIV
Hyperspectral image super-resolution method based on mixed attention network fusion
ActiveCN113222823AImprove performanceImprove reliabilityImage enhancementGeometric image transformationPattern recognitionImage resolution
The invention discloses a hyperspectral image super-resolution method based on mixed attention network fusion. The method comprises the following steps: acquiring a hyperspectral low-resolution image and a corresponding hyperspectral high-resolution image, and forming training data; constructing a hyperspectral image super-resolution basic model; training the hyperspectral image super-resolution basic model by adopting the training data to obtain a final hyperspectral image super-resolution model; obtaining a to-be-processed hyperspectral image; and processing the to-be-processed hyperspectral image by using the hyperspectral image super-resolution model to complete the super-resolution process of the hyperspectral image. According to the invention, the hybrid attention network is adopted to improve the network performance, mutual learning loss is adopted to ensure that each network has mutual supervision and learning capabilities, and finally, an adaptive integration module is adopted to fuse output images of the hybrid attention network. Therefore, the invention is better in effect, higher in reliability and more excellent in performance.
Owner:STATE GRID HUNAN ELECTRIC POWER +2
Fast transient stability analysis method based on adaptive integration steps
InactiveCN108269017AMeet the precision requirements of rapid analysisImprove analysis accuracyResourcesTransient stateGuideline
The invention discloses a fast transient stability analysis method based on adaptive integration steps, and belongs to the field of power systems and automation technologies thereof. The method of theinvention is based on an extended equal-area criterion, deeply explores different margin information contained in each fast transient stability analysis algorithm with different integration steps anda comparison result thereof to reflect the time-varying degree of a research example, and further determines whether to increase a small number of integration steps according to the strong or weak time-varying degree to improve the analysis accuracy. The method of the invention can automatically match the appropriate integration steps for each example according to the strong or weak time-varyingdegree thereof; and improves, as compared with the original fast transient stability analysis method based on fixed few integration steps, the analysis accuracy of the example of a strong time-varyingdegree at the cost of a small calculation increment under the premise of maintaining the analysis accuracy of the example of a weak time-varying degree, further coordinates the accuracy and rate of the online transient stability analysis, solves the transient stability analysis problem considering uncertainties, and has significant theoretical and engineering significance.
Owner:NARI TECH CO LTD
MIMO-SCFDE (Multiple Input Multiple Output-Synchronized Frequency Division Multiplexing Element) self-adaptive transmission method based on model-driven deep learning
ActiveCN112235023AAddress reliabilityModulation type identificationCharacter and pattern recognitionEngineeringNetwork model
The invention relates to an MIMO-SCFDE self-adaptive transmission scheme based on model-driven deep learning. According to the method, a self-adaptive transmission model is established based on an MIMO SCFDE system. AMNet and ADNet are adopted to replace a signal modulation part and a modulation identification part in a traditional system respectively. The AMNet adopts a combined network taking a2D CNN, an LSTM and an FCDNN as sub-networks to form an integrated neural network model, a modulation mode of a sending end is adjusted according to a channel condition of a receiving end, feature information extracted from a received signal is input into the plurality of sub-networks, and conversion between features and an optimal modulation scheme are achieved according to network parameters obtained by training. Meanwhile, the receiving power under different path delays is selected as an adaptive factor to achieve adaptive integration of each sub-network result. The ADNet completes adaptiveselection of a modulation identification scheme based on the complexity of a cyclic spectrum according to the advantage that the cyclic spectrum has accurate detection on the signal type under a lowsignal-to-noise ratio. The system is more suitable for performance requirements of a 5G communication system.
Owner:QILU UNIV OF TECH
Performance evaluation and prediction method and system for life cycle of water quality sensor
PendingCN111751508AImplement Systematic Lifecycle ManagementSolve complexityTesting waterRegression analysisWater quality
The invention discloses a performance evaluation and prediction method and system for the life cycle of a water quality sensor. The method comprises the steps: S100, collecting and storing state parameters used for reflecting the performance of the water quality sensor; and S200, based on the state parameters of the water quality sensor and a self-adaptive integration model, performing regressionanalysis on the performance, the aging rule and the residual service life of the water quality sensor, evaluating the performance of the water quality sensor, and predicting the residual service life,the next calibration time and the next maintenance time of the water quality sensor. The method provided by the invention is used for systematically and comprehensively evaluating and predicting theperformance of the sensor. Self-adaptive regression solves the problems of complex life distribution and easy sudden change of the state; the integrated model solves the problems of low prediction precision and poor stability.
Owner:HKY TECH
Systems and methods for adaptive integration of hardware and software lock elision techniques
ActiveUS9183043B2Improve scalabilityImprove performanceSpecific access rightsProgram initiation/switchingSoftware lockoutParallel computing
Owner:ORACLE INT CORP
Wind power probability prediction method based on hierarchical integration
The invention discloses a wind power probability prediction method based on hierarchical integration. According to the method, a subspace set is constructed through resampling and a partial least square method, a plurality of local areas are obtained on each subspace through GMM clustering, a corresponding local GPR model is established, and a Bayesian reasoning strategy and a finite mixing mechanism are used for fusing the local models to establish a first-layer integrated model. And a genetic algorithm is adopted to select a suitable first-layer integration model for selective adaptive integration, so that a selective hierarchical integration Gaussian process regression probability prediction model can be obtained. In order to solve the problem of performance deterioration caused by change of wind power data characteristics, an adaptive updating strategy is introduced, so that the prediction model has adaptive updating capability. According to the method, the selective hierarchical ensemble learning framework is used for ultra-short-term wind power prediction, compared with a traditional ensemble learning prediction method, the method has higher prediction precision and stability, and the generated prediction interval can provide effective reference for power dispatching.
Owner:KUNMING UNIV OF SCI & TECH
Target tracking method based on deep convolution feature adaptive integration
ActiveCN112053386AFully expressAccurate acquisitionImage enhancementImage analysisPattern recognitionCorrelation filter
The invention discloses a target tracking method based on deep convolution feature adaptive integration. The method comprises the steps of extracting deep convolution features; calculating a kernel correlation filter; updating the integrated vector of the current frame by using an integrated vector updating formula; predicting a target position of the current frame image by using a self-adaptive integrated calculation formula; updating the deep convolution feature of the current frame by using a deep convolution feature updating formula; and taking the target center position of the current frame as the center position of the to-be-tracked target when the iteration of the video image sequence containing the to-be-tracked target is ended. By integrating the features, the defect that a tracker in the prior art cannot fully utilize information contained in different channel target features is overcome, so that the position of the target to be tracked is more accurately acquired in the target tracking process, and the accuracy and reliability of target tracking are enhanced.
Owner:XIDIAN UNIV
Oil drive quadrotor unmanned aerial vehicle attitude control method
InactiveCN108646772AImprove flight anti-jammingSmall steady state errorAttitude controlAdaptive controlBacksteppingAttitude control
The present invention discloses an oil drive quadrotor unmanned aerial vehicle attitude control method. A height controller, a horizontal position controller, an attitude controller and a filter are provided. The filter and an arithmetic mean filtering are combined to obtain an accurate height vector z at this time, an accurate horizontal vector y at this time and an accurate horizontal vector x at this time, an adaptive backstepping control algorithm is employed to obtain a height controlled quantity U1, a pitch channel controlled quantity U2, a roll channel controlled quantity U3 and a yaw channel controlled quantity U4. The control algorithm through combination of the adaptive integration backstepping method and the hybrid filtering algorithm is applied to the oil drive quadrotor unmanned aerial vehicle having large interference from the external environment to reduce the steady state errors and improve the flight anti-interference performance of the oil drive quadrotor unmanned aerial vehicle itself. The oil drive quadrotor unmanned aerial vehicle attitude control method perform comparison and experiment with a conventional integration backstepping algorithm to fully proof thegood convergence and stability of the system, the good control effect, the high track tracking feature and good robustness and resistance to gust interference.
Owner:YUTONG BOHUI AEROSPACE SCI & TECH DEV CO LTD
Gas adaptive integration valve with double air sources
InactiveCN102494164BSimple structureEliminates manual selector switchEqualizing valvesSafety valvesEngineeringHigh pressure
Owner:PROCOM ELECTRIC APPLIANCES SHANGHAI
A MIMO-SCFDE adaptive transfer method based on model-driven deep learning
The invention relates to a MIMO-SCFDE adaptive transmission scheme based on model-driven deep learning. The invention establishes an adaptive transmission model based on the MIMO‑SCFDE system. AMNet and ADNet are used to replace the signal modulation and modulation identification parts in the traditional system respectively. AMNet adopts a combined network with 2D CNN, LSTM and FC-DNN as sub-networks to form an integrated neural network model, and adjusts the modulation mode of the sending end according to the channel conditions of the receiving end, and inputs the feature information extracted from the received signal into multiple sub-networks , and realize the conversion of features and optimal modulation schemes according to the network parameters obtained through training. At the same time, the received power under different path delays is selected as the adaptive factor to realize the adaptive integration of the results of each sub-network. According to the cyclic spectrum, ADNet has the advantage of accurately detecting the signal type under low signal-to-noise ratio, and based on the complexity of the cyclic spectrogram, it completes the adaptive selection of the modulation recognition scheme. This system is more suitable for the performance requirements of the 5G communication system.
Owner:QILU UNIV OF TECH
An Embedded Infrared Image Superframe Processing Method Based on Adaptive Integration Time
ActiveCN104618664BSolve the problem of non-uniformityImprove SNRTelevision system detailsColor television detailsImaging processingRadiation temperature
The invention provides an embedded infrared image super-frame processing method based on adaptive integration time, the purpose of which is to utilize the advantages of the infrared image super-frame processing method to improve the detection sensitivity and dynamic range of the infrared imaging system, and effectively solve the problem of traditional super-frame processing In the method, the integration time of acquiring subframes cannot be adaptively adjusted according to the radiation temperature of the target scene, so as to better guide the detector to work in the middle area of the entire response range. The invention includes two stages of off-line calibration and on-line processing. The invention also provides correction measures for the image non-uniformity problem caused by the adjusted integration time of the detector. The invention is an infrared image super-frame processing method based on an embedded platform, does not need any special device in the realization process, and can realize the real-time engineering application of the method.
Owner:KUNMING INST OF PHYSICS
CCD adaptive integration time and frequency spectrum visualization system
ActiveCN110213509ASolve slow loadingSolve the phenomenon of CatonTelevision system detailsColor television detailsFrequency spectrumData acquisition
A CCD adaptive integration time and frequency spectrum visualization system comprises a frequency spectrum distribution data acquisition part, a parameter estimation part, a file management part and afrequency spectrum drawing part, and by using WIFI and a TCP protocol, the system interacts with a frequency spectrum distribution data acquisition device, to acquire, process, store and display frequency spectrum distribution data. Under the condition that the light source intensity is unknown, a self-adaptive integral time algorithm for controlling CCD exposure time is given, so that a CCD hassufficient exposure time and is not in a saturated state. The APP adopts a double-buffer mechanism to solve the phenomena of slow loading and jamming of the spectrogram in the visualization process.According to the adaptive integral time and the double-buffer mechanism provided by the invention, the detected frequency spectrum data is more reasonable, and the user experience is remarkably improved.
Owner:ZHEJIANG UNIV OF TECH
An Adaptive Integral Backstepping Control Method for Anti-Load Disturbance of Elevator pmsm
ActiveCN108306568BImprove tracking accuracyHelps decouple controlElectronic commutation motor controlAC motor controlMotor speedLoad torque
The invention proposes an adaptive integral backstepping control method for anti-load disturbance of PMSM used in elevators. Compare the motor speed w with the given motor speed w * By comparison, the speed error e is obtained; according to the feedback motor speed w and electromagnetic torque T e Estimated load torque τ L ;The estimated load torque τ L and the rotational speed error e are input into the adaptive integral backstepping controller for adjustment to eliminate the steady-state error of the speed so as to obtain the virtual control quantity of the q-axis of the stator current in the rotating coordinate system d-q and use the excitation current component as a reference value to input the current In the ring, and the stator current i after the coordinate transformation d Make a difference to get the d-axis stator current error e d ;According to the q-axis stator current error e q and d-axis stator current error e d Calculate the control voltage u d and u q ; will u d and u q After inverting through the park, it is input to the SVPWM pulse width modulation module to generate the pulse signal required to drive the inverter, thereby driving the motor to run. The invention improves the robustness of the electric system of the elevator, and enhances the comfort and speed of the elevator.
Owner:NANJING UNIV OF SCI & TECH
A Method for Acquiring Electromagnetic Scattering Characteristics Based on Subregion Adaptive Integration
ActiveCN105930567BIncrease flexibilityIncrease condition numberSpecial data processing applicationsScattering cross-sectionElectrical conductor
The invention discloses a method for obtaining electromagnetic scattering properties based on subregion adaptive integration. First, geometric modeling is performed on a radar conductor object by means of CAD software for cutting the whole object into multiple subregions and virtual surfaces among subregions are kept; secondly, all subregion surfaces are scattered with triangles and subregion grid information after dissection is output; Descartes grids are established in subregions respectively again, induced current of subregion surfaces is obtained by means of adaptive integration method and coupling among subregions; finally, far region scattered field is calculated by means of the induced current of subregion surfaces and further radar scattering cross section of the conductor object is obtained. Auxiliary point current amount is reduced on the premise that accurate calculation results are guaranteed, and memory requirement is reduced and convergence rate and simulation efficiency are increased.
Owner:XIDIAN UNIV
A NMR Gyro Adaptive Dynamic and Static Closed-loop Control Method
ActiveCN110542412BPrecise closed-loop controlConfidenceTurn-sensitive devicesNMR - Nuclear magnetic resonanceLoop control
A nuclear magnetic resonance gyro self-adaptive dynamic and static closed-loop control method, including gyro dynamic work and static work adaptive discrimination strategy, dynamic work closed-loop parameter adaptive adjustment method, static work closed-loop parameter adaptive adjustment method and self-adaptive integral method. The invention performs mean square statistics on the long-term input closed-loop error, and then divides the dynamic working state and the static working state of the gyroscope through the setting of the soft threshold, which has a high degree of confidence and is beneficial to the gyroscope closed-loop output in different situations. More precise closed-loop control. In addition, through the dynamic adjustment of the closed-loop coefficient, the static and dynamic response ability is improved. Finally, the present invention performs selective input control on the integral quantity of the closed-loop control, which can play the role of the integral term in the closed-loop control, and can effectively avoid the influence of long-term noise accumulation on the drift of the gyro output.
Owner:BEIJING INST OF AEROSPACE CONTROL DEVICES
A Neural Network-Based Method for Infrared Focal Plane Array Nonuniformity Correction Adapting to Dynamic Adjustment of Integration Time
ActiveCN108663122BAdjust fine and flexibleImprove uniformityRadiation pyrometryComputational physicsComputer vision
The invention discloses an infrared focal plane array non-uniformity correction method adapted to the dynamic adjustment of integration time based on a neural network, which belongs to the field of non-uniformity correction of an infrared system. The method includes: calibrating at multiple working points of the system, calculating Average gray-scale response; use mathematical regression to calculate the interpolation curve of average gray-scale response and pixel gray-scale response under different integration times; build and train a forward neural network for non-uniformity correction; use the trained neural network to perform Non-uniformity correction, the integration time can be adjusted dynamically during the correction process. The present invention overcomes the disadvantages of the previous infrared system, such as few steps of integration time, large adjustment span, and troublesome switching, makes the adjustment of integration time more delicate and flexible, expands the adaptability of the infrared system to scenes with a large dynamic temperature range, and is beneficial to infrared systems. The system performs intelligent imaging on the target.
Owner:INST OF OPTICS & ELECTRONICS - CHINESE ACAD OF SCI
Environment Adaptive Import Method for Intelligent Driving Vehicles in Urban Environment
ActiveCN109143852BLow applicabilityImport success rate increasedAdaptive controlSimulationArtificial intelligence
The invention discloses an intelligent driving vehicle environment adaptive merging method under an urban environment. The method comprises steps: an initial state vector is extracted; an action variable is calculated according to a greedy strategy, a merging scene is updated while a merging action is executed, if the action variable adopts a random action, a merging gap and a merging action are selected with a uniform probability, if an intelligent method is adopted, candidate gaps comprise a front vehicle, a following vehicle and a merging vehicle, the maximum action value functions of all candidate gaps are compared, the maximum value function is selected, the gap and the action corresponding to the maximum value are picked out, and a target merging gap and an intelligent merging actionare returned; the state vector at a next moment is sensed; a reward value is calculated according to the environmental feedback information; the initial state vector, the action variable, the state vector at the next moment and the reward value are saved to a sample set, and after enough samples are obtained, evaluation and improvement are carried out according to an LSQ method; and the above steps are repeated until merging succeeds. The sample set and the learning time are lower than a Q learning algorithm, and the success rate is high.
Owner:BEIJING INSTITUTE OF TECHNOLOGYGY
A Reduced Matrix Construction Method for Accelerating Iterative Solution of Eigenbasis Function Method
ActiveCN110069863BIterative solution speed upMatrix condition number optimizationDesign optimisation/simulationComplex mathematical operationsSingular value decompositionMain diagonal
The invention discloses a reduced matrix construction method for accelerating the iterative solution of the characteristic basis function method, which can effectively accelerate the iterative solution speed of the characteristic basis function method. Firstly, the excitation source is compressed using the singular value decomposition technique, and the compressed new excitation source is obtained, which is defined as voltage basis functions (VBFs); secondly, under the new excitation source, the characteristic basis function of each subdomain ( CBFs); Finally, VCBFs and CBFs are used as test functions and basis functions to construct a reduced matrix, and the main diagonal sub-matrixes of the obtained reduced matrix are unit matrices, and the condition number of the reduced matrix is optimized, which can speed up the iterative solution of the reduced matrix equation. The invention provides a new method for the iterative solution of the eigenbasis function method. At the same time, the invention can be combined with algorithms such as multi-layer fast multipole method, adaptive integration method, pre-correction-fast Fourier transform method, etc. Efficiency of function method in analyzing electromagnetic scattering characteristics of electrically large targets.
Owner:ANHUI UNIV OF SCI & TECH
Device security threat prediction method and device through adaptive integration
The invention discloses a device security threat prediction method and device through adaptive integration, and the method comprises the steps: collecting abnormal data sets during the operation of a plurality of devices, inputting the abnormal data sets into n preset neural networks, and obtaining n prediction results, n being a positive integer greater than 1; performing weight distribution and integration on the n prediction results to obtain an initial integration result; repeatedly carrying out weight iteration updating by utilizing the initial integration result to obtain a target integration result; and predicting potential security threats of the equipment based on the target integration result. According to the method, the multiple neural networks are iteratively updated and predicted, so that manual feature extraction and a complex mathematical modeling process can be avoided, high-precision end-to-end potential security threat prediction of equipment is realized, the weight is adaptively adjusted according to an individual model prediction result, and the prediction accuracy of the potential security threat of the equipment is improved. The method has better data adaptability for different data, and the prediction accuracy is further improved.
Owner:GUANGDONG POWER GRID CO LTD +1
Who we serve
- R&D Engineer
- R&D Manager
- IP Professional
Why Patsnap Eureka
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com