Patents
Literature
Hiro is an intelligent assistant for R&D personnel, combined with Patent DNA, to facilitate innovative research.
53results about How to "Strong analytical skills" 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
Hybrid nuclear power plant fault diagnosis method
ActiveCN107301884AFast diagnosisPoor readabilityPower plant safety arrangementNuclear energy generationQuantitative assessmentDiagnosis methods
The invention discloses a hybrid nuclear power plant fault diagnosis method, belonging to the technical field of fault diagnosis. The method comprises a step of collecting operation parameters in a diagnosed system and transmitting the parameters to an established mechanism simulation model, a step of calculating a residual error on real-time data and a corresponding parameter obtained by simulation model calculation, a step of judging a result or result set of a fault type when the calculated residual error exceeds a limit value, a step of adding a diagnosis result into the simulation model to carry out fault verification, a step of selecting a part of operation parameters obtained by measurement as evaluation parameters, and determining a data analysis model of a Mahalanobis distance function for fault degree evaluation, a step of calculating a Mahalanobis distance value, and establishing evaluation curves of different fault modes, and a step of calculating the Mahalanobis distance function distance value of actual fault data by using the operation data of the diagnosed system after failure, and establishing evaluation curves under different fault degrees to carry out match analysis to complete the quantitative assessment of a fault degree.
Owner:HARBIN ENG UNIV
Quantum chip, quantum processor and quantum computer
ActiveCN111967603AImprove adaptabilityImprove coherenceQuantum computersNanoinformaticsQuantum technologyBit array
Owner:TENCENT TECH (SHENZHEN) CO LTD
Urban inland inundation early warning system and method
InactiveCN110992653AWaterlogging early warning is convenientWaterlogging early warning is accurateHuman health protectionMeasurement devicesEarly warning systemRainfall runoff
An embodiment of the invention discloses an urban inland inundation early warning system and an urban inland inundation early warning method. The urban inland inundation early warning system comprisesa data acquisition device and a cloud server, wherein the data acquisition device is configured to acquire and store urban basic data and urban monitoring data of a to-be-early-warned region; the cloud server is configured to determine rainfall runoff production and rainfall confluence of the to-be-early-warned region according to the urban basic data and the urban monitoring data, perform urbaninland inundation simulation on the to-be-early-warned region according to the rainfall runoff production and rainfall confluence to obtain an inland inundation simulation result for performing inlandinundation early warning. By adopting the urban inland inundation early warning system and the urban inland inundation early warning method, urban inland inundation early-warning analysis is achievedby means of the cloud server, urban inland inundation early-warning is more convenient by utilizing the advantages that the cloud server is easy to deploy rapidly, change flexibly, low in cost, easyto manage in a centralized mode and the like, and due to the processing capacity of the cloud server, the urban inland inundation early-warning analysis capacity is higher, and the early-warning result is more precise.
Owner:软通智慧信息技术有限公司
Detection method of five types of compounds in Xuebijing injection
ActiveCN106950307AComprehensive reflection of quality uniformityReflect uniformity of qualityComponent separationChemical compositionAdenosine
The invention provides a detection method of five types of compounds in Xuebijing injection. The detection method comprises the following steps: 1) preparing a solution to be detected; 2) preparing a standard solution; 3) simultaneously determining the content of any one or more components in a first type compound, a second type compound and a fifth type compound excepting adenine and adenosine by adopting an ultrahigh performance liquid chromatography-mass spectrometry system; 4) simultaneously determining the content of any one or more components of a third type compound by adopting an ultrahigh performance liquid chromatography-high resolution mass spectrometry system; 5) simultaneously determining the content of any one or more components in a fourth type compound and adenine and adenosine components in the fifth type compound by adopting the ultrahigh performance liquid chromatography-mass spectrometry system. The detection method of five types of the compounds in the Xuebijing injection, provided by the invention, can be used for accurately and comprehensively detecting chemical components in the Xuebijing injection in a high throughput manner; and the detection method has positive significance on improvement of quality control levels in an agent processing and production process and reasonable drug selection in clinical researches.
Owner:SHANGHAI INST OF MATERIA MEDICA CHINESE ACAD OF SCI +1
Method for determining content of pigments in mixed pigment solutions by adopting three-dimensional fluorescence spectroscopy combined with PARAFAC (parallel factor analysis) algorithm
InactiveCN104792752ARapid determinationEasy to superviseFluorescence/phosphorescenceFood industrySpectroscopy
The invention discloses a method for determining the content of pigments in mixed pigment solutions by adopting three-dimensional fluorescence spectroscopy combined with the PARAFAC (parallel factor analysis) algorithm. According to the method, firstly, a correction sample set is formed by preparing multiple mixed pigment solutions according to different concentrations, then three-dimensional fluorescence spectra of the correction sample set and the background are measured, measured signals are pre-processed, a three-dimensional data matrix after pre-processing is analyzed with the PARAFAC algorithm, a correction model is established according to an analysis result, and the content of the pigments in unknown samples is predicted with the correction model. The method overcomes the defects of tedious process, time consumption of detection, higher detection cost and the like of a traditional chemical detection method, the concentration of each pigment in the to-be-detected samples can be determined rapidly, the method has the advantages of rapidness, safety, reliability, simple operation, lower cost and the like, technical support is provided for determination of synthetic edible pigments in food, and supervision of the food industry and protection of consumer interests are facilitated.
Owner:JIANGNAN UNIV
Signal assessment and improvement system of remote monitoring device and control method
The invention discloses a signal assessment and improvement system of a remote monitoring device and a control method. The system comprises an elevator control system used for controlling elevator running, the remote monitoring device used for receiving and transmitting elevator running information, a signal base station for transferring data and a cloud server; and the remote monitoring device comprises a data processing module and an antenna module, and the antenna module comprises an antenna and a signal strength detection device. During installation or debugging of the remote monitoring device, the remote monitoring device continuously transmits testing data packages to the cloud server through the signal base station, the cloud server responds the remote monitoring device and feeds back testing data, the remote monitoring device receives the fed-back data and conducts statistics on signal reliability at the position, and the best antenna placing position at the current environment is comprehensively operated in cooperation with signal strength data fed back by the signal strength detection device. Meanwhile, when an elevator runs, telecommunication abnormal failures are fed back when it is detected that the current signal reliability is too poor.
Owner:GUANGZHOU GUANGRI ELEVATOR IND
Electric energy quality mixed disturbance analysis method based on deep learning
PendingCN110222953AIncrease the strength of distinctionImprove classification performanceResourcesNeural architecturesPower qualityClassification methods
The invention discloses an electric energy quality mixed disturbance analysis method based on deep learning. The power quality mixed disturbance classification method can effectively classify the power quality mixed disturbance, and has higher robustness. The method comprises the steps of firstly adjusting the attenuation rate of a Gaussian window function to change the time resolution and the frequency resolution of S transformation so as to embody the characteristics of different types of electric quality signals better and improve the distinguishing strength of the different types of electric quality signals; then constructing a deep learning model based on the LSTM, and classifying the the electric quality signals, in a constructed deep learning model, preprocessing the data by adopting a multi-layer perceptron, carrying out preliminary analysis and feature extraction on the data, and then, carrying out semantic segmentation on the electric quality signal by utilizing an LSTM artificial neural network with stronger analysis capability on sequence data, and finally, performing supervised classification on the semantic segmentation of the LSTM by adopting a pooling layer and a multi-layer perceptron, thereby facilitating the improvement of the classification capability of the model.
Owner:BEIJING INSTITUTE OF TECHNOLOGYGY
Transient temperature field test method and system based on high-speed imaging technology
InactiveCN109506782AShort response timeHigh upper limit of temperature measurementRadiation pyrometryCMOS sensorField tests
The invention discloses a transient temperature field test method and system based on a high-speed imaging technology. The transient temperature field test system comprises a color high-speed camera,a medium-density optical filter, an optical lens and a computer. The transient temperature field test method comprises the steps that the optical lens focuses lightness information generated by a transient temperature field on a CMOS image sensor of the high-speed camera; the medium-density optical filter is used for controlling the light amount so that it can be guaranteed that the camera works in an unsaturated area and the upper temperature measurement limit can be expanded at the same time; the high-speed camera converts the light information which is imaged on the CMOS sensor into digitalimage RGB information; the computer analyzes the transient temperature field image information collected by the high-speed camera, and according to a temperature conversion model which is obtained through calibration of the camera and is arranged in software, the transient temperature field and related characteristic parameters can be obtained. The transient temperature field test method and system can achieve remote distance measurement of the transient temperature field, have the advantages of high time resolution and high temperature measurement upper limit, and can visually acquire a temperature distribution render graph of every moment and the related temperature characteristic parameters.
Owner:NANJING UNIV OF SCI & TECH
Method for detecting a plurality of small molecular chemical components in Xuebijing injection
ActiveCN110632230ASimple preparation processImprove consistencyComponent separationChemical compositionHigh flux
The invention provides a method for detecting a plurality of small molecular chemical components in a Xuebijing injection. The method comprises the following steps: step one, preparing a sample solution; step two, preparing a first standard solution; step three, preparing a second standard solution; and step four, carrying out measurement on the sample solution, the first standard solution and thesecond standard solution by using a high performance liquid chromatography-mass spectrometry method, quantifying 57 kinds of small molecule chemical components in the sample solution by using a standard curve method and then determining contents of other 66 kinds of small molecule chemical components with structures similar to those of the 57 small molecule chemical components that are determinedin a quantified mode in a semi-quantitative manner. According to the method provided by the invention, 123 traditional Chinese medicine small molecule compounds can be quantitatively or semi-quantitatively detected with high flux and high sensitivity and a key technical way is provided for optimizing the preparation process of Xuebijing and improving the product quality uniformity.
Owner:SHANGHAI INST OF MATERIA MEDICA CHINESE ACAD OF SCI +1
Image splicing fusion system
InactiveCN106303296ASave resourcesReduce computationTelevision system detailsColor television detailsFault toleranceGeneral Packet Radio Service
The invention discloses an image splicing fusion system in the technical field of video image processing. The image splicing fusion system comprises an image collection module which is in electrical output connection with an image processing module, the image processing module is electrical output connection with a video flow server, a GPRS (general packet radio service) network unit is in electrical output connection with an image splicing fusion unit, and a wireless communication module is in electrical output connection with an equipment terminal. Detection and tracking of a moving target in a splicing image are implemented through the image splicing fusion unit, display through multiple video windows is avoided, an observer is enabled to concentrate on observing an image, and receiving multiple video flows is changed into receiving one video flow, so that resources of a computer are saved, and operand of the image processing module is reduced; splicing imaging is performed after processing through a fusion algorithm. The image splicing fusion system is high in fault tolerance and openness, short in processing time, low in data requirement and high in analysis capability.
Owner:XUCHANG UNIV
Fluorescent alga in-situ analysis device based on beam splitting and combining of broadband spectrum
InactiveCN105628664ADetectiveHigh precisionFluorescence/phosphorescenceBeam splittingDisplacement control
The invention relates to a fluorescent alga in-situ analysis device based on beam splitting and combining of a broadband spectrum. A beam shaping element, a broadband spectrum beam splitting element, a collimation shaping element and a movable light passing hole are sequentially arranged on a broadband spectrum light source emergent light path; a beam converging element, a broadband spectrum beam combining element, an excitation beam shaping element and a fluorescent excitation focusing element are sequentially arranged on a fluorescent excitation beam transmitted through the movable light passing hole; a detection converging element, a light filtering element and a fluorescent photoelectric detector are sequentially arranged on a fluorescent light beam path; the fluorescent photoelectric detector detects an alga fluorescent signal converged by the detection converging element and filtered by the light filtering element; a microscope objective, an imaging element and a two-dimension imaging photoelectric detector are arranged in a water body detection area to form an in-situ alga microscope imaging module; and a control analysis part is connected with a displacement control part, the fluorescent photoelectric detector and the two-dimension imaging photoelectric detector to obtain fluorescent information and image information and realize a passing-through function of movable selective-wavelength beams through the movable light passing hole, thereby realizing in-situ alga analysis.
Owner:UNIV OF SHANGHAI FOR SCI & TECH
Soil testing and formulated fertilization method based on deep learning and weighting type multi-factor evaluation
PendingCN113435707AImprove generalization abilityStrong analytical skillsResourcesNeural architecturesAlgorithmEdaphic
The invention provides a soil testing and formulated fertilization method based on deep learning and weighting type multi-factor evaluation, which comprises the following steps: sorting and archiving soil data and plot yield data, and carrying out normalization processing and label adding operation to obtain sample data; setting corresponding weights according to differences of sensitivities of different crops to different chemical elements, and grading fertility conditions and heavy metal pollution conditions of soil by utilizing a fertility coefficient standard formula and an improved Nemero index method to obtain a comprehensive fertility index; improving a fitness function in a classical genetic algorithm through weighting type multi-factor evaluation, selecting proper filial generation data through the fitness function to perform data enhancement, and expanding a data sample; and training the neural network model by using the expanded data sample to obtain a crop yield prediction and fertilizer preparation and supplement strategy. According to the method, the problem that a neural network requires a large number of training samples is solved, and abundance and deficiency degree evaluation and pollution index evaluation of soil are given.
Owner:大连钜智信息科技有限公司
High-pressure gas conveying pipe leakage monitoring system and method
PendingCN108799847AImprove performanceStrong analytical skillsPipeline systemsData acquisitionMonitoring system
The invention discloses a high-pressure gas conveying pipe leakage monitoring system and method. The high-pressure gas conveying pipe leakage monitoring system comprises a first data acquiring and processing device, a first flow sensor, a first vibration signal sensor, a first pressure sensor and a first temperature sensor arranged on a first section of a high-pressure gas conveying pipe, and a second data acquiring and processing device, a second vibration signal sensor, a second pressure sensor and a second temperature sensor arranged on a second section of the high-pressure gas conveying pipe; the first section is positioned at the upstream of the second section; the first flow sensor, the first vibration signal sensor, the first pressure sensor and the first temperature sensor are connected with the first data acquiring and processing device; and the first data acquiring and processing device is used for processing data acquired by the first flow sensor, the first vibration signalsensor, the first pressure sensor and the first temperature sensor to obtain first data to be analyzed.
Owner:北京科力达宏业科贸有限责任公司
Method for detecting alkylphenol compounds in ginkgo leaf raw material and preparation
The invention provides a method for detecting alkylphenol compounds in a ginkgo leaf raw material and a preparation. The method comprises the following steps: using HPLC (High Performance Liquid Chromatography) separation and ESI-Q-TOF-MS (Electric Spray Ion Source-High Resolution Quadrupole Time of Flight- Mass Spectrometry) to simultaneously determine content of alkylphenol compounds in the ginkgo leaves. The method for detecting the alkylphenol compounds in the ginkgo leaf raw material and the preparation disclosed by the invention can simultaneously detect 31 sensitized alkylphenol compounds in the ginkgo leaves, the ginkgo leaf extract and the ginkgo preparation, which comprise 22 ginkgo acid compounds, 3 resorcylic acid compounds and 6 urushiol compounds; compared with the existing alkylphenol compound analytic method at present, the method is higher in analytical ability, and capable of effectively increasing the quality control level of the processed semi-finished products and finished products of the ginkgo leaf raw material and the preparation, so as to achieve positive meaning for ensuring the clinical medication safety.
Owner:SHANGHAI INST OF MATERIA MEDICA CHINESE ACAD OF SCI +1
Skin detector with artificial intelligence
InactiveCN109008970AStrong analytical skillsHigh accuracy of analysisDiagnostics using spectroscopySensorsLight sourceSignal lines
The invention discloses a skin detector with artificial intelligence. The skin detector with artificial intelligence includes a detection module and an artificial intelligence analysis module, whereinthe detection module comprises a base, a housing, a light source device, a picture collecting device, a microprocessor, a first wireless signal transmitter-receiver set and a display device, whereinthe light source device and the picture collecting device are fixedly arranged on the housing; the microprocessor, the first wireless signal transmitter-receiver set and the display device are fixedlymounted on the base; the housing is arranged on the upper surface of the base; the light source device comprises a cross-polarized light source, a standard LED white light source and a multi-spectralLED light source; the picture collecting device comprises a main collecting device and a plurality of auxiliary collecting devices; and the plurality of the auxiliary collecting devices are symmetrically distributed on both sides of the main collecting device, and the picture collecting device is electrically connected to the microprocessor through a signal line. The skin detector with artificialintelligence can obtain the basic situation of the face skin so as to be convenient for people to select skin care products targetedly.
Owner:上海爱肌悦智能科技有限公司
Method for measuring contents of active substances and chemical components of traditional Chinese medicines
InactiveCN108627486ARapid identificationSensitive identificationFluorescence/phosphorescenceWavelet noiseChemical composition
The invention discloses a method for measuring contents of active substances and chemical components of traditional Chinese medicines. The method comprises the following steps: step a, preparing a correcting sample set and a prediction sample set; step b, carrying out three-dimensional fluorescence spectrum measurement on the correcting sample set and the prediction sample set to obtain three-dimensional fluorescence spectrum charts of the correcting sample set and the prediction sample set; step C, preprocessing of data: carrying out wavelet noise reduction processing on spectroscopic data bywavelet transform; and then deducting three-dimensional spectral signals of background from three-dimensional spectral signals of traditional Chinese medicinal materials; and step d, establishment ofa correcting model: analyzing the correcting sample set by using a parallel factor algorithm at first; and then establishing a quantitative regression model, and predicting the concentration of the prediction sample set. The active substances and the chemical components of traditional Chinese medicinal materials and the contents of the active substances and the chemical components can be identified rapidly, sensitively and accurately, and the method is applied to monitoring and evaluating of quality of the traditional Chinese medicinal materials.
Owner:JIANGNAN UNIV
Global human mtDNA development tree classified query method based on integrated learning
ActiveCN108052796AImprove accuracyStrong abstract expression abilityRelational databasesCharacter and pattern recognitionEnsemble learningNeural network classifier
The invention discloses a global human mtDNA development tree classified query method based on integrated learning. Artificially-measured mtDNA data is adopted to train a neural network classifier, mtDNA development tree data is adopted to calculate parameters of a naive Bayes classifier, mutation loci of mtDNA to be classified and queried are input into the neural network classifier to obtain thefirst Q possible classifications, merging the mutation loci of mtDNA to be classified and queried and mutation locus sequences corresponding to the first Q possible classifications to obtain input mutation locus sequences of the naive Bayes classifier, calculating to obtain the weights of various mutation loci of the input mutation locus sequences, obtaining first Q possible classification through the naive Bayes classifier, and weighting probabilities of the two groups of mutation locus sequences to obtain the first Q possible classifications as the final classification result. By means of the global human mtDNA development tree classified query method based on integrated learning, the advantages of the neural network classifier and the naive Bayes classifier are comprehensively utilized, and the accuracy of global human mtDNA development tree classified query is improved.
Owner:YUNNAN UNIV
A method and system for determining state of power system transformer device
ActiveCN110927478ASolve the lack of seriousSolve balance problemsElectrical testingInformation technology support systemPositive sampleTransformer
The invention provides a method and a system for determining the state of transformer equipment of a power system. The method comprises the following steps: processing acquired characteristic value data of N gases for determining the state of the transformer equipment of the power system to generate an effective sample set, and distributing the effective sample set according to a preset proportionto generate a training set and a test set; and determining an optimal logistic classifier according to the established logistic regression model, the training set and the test set, and outputting thestate of the transformer of the power system by using the optimal logistic classifier according to the characteristic value data of the N gases in the actual operation of the transformer equipment. According to the method, a positive sample synthesis algorithm is utilized, the accuracy of the model is improved to a certain extent, the requirement of the model for data is low, the analysis capacity for massive transformer gas characteristic values is high, classification can be well achieved, and then the running state of the transformer is judged.
Owner:CHINA ELECTRIC POWER RES INST +1
Analysis method for topology relation between tri-dimensional composite body objects
InactiveCN101504777AStrong analytical skillsSuitable for a wide range of objects3D modellingAnalysis methodComputer science
Owner:NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
Whale optimized damaged terracotta figure fragment registration method based on chaos reverse learning
PendingCN113034554AHigh precisionIncrease diversityImage analysisCharacter and pattern recognitionShardImaging processing
The invention belongs to the technical field of image processing, and discloses a whale optimized damaged terracotta figure fragment registration method based on chaos reverse learning. The method comprises the steps: carrying out the data preprocessing, and generating source point cloud data P and to-be-registered data Q; establishing a mapping relation between population individuals and a model according to a target function, and obtaining an optimal transformation matrix by using a rotation R parameter and a translation T parameter; initializing parameters; saving the elite data in an elite database by using an elite retention mechanism; designing a weight factor and a convergence factor, updating the position of the whale individual, and calculating the fitness of the whale individual; updating the partship degree, the non-membership degree and the hesitation degree; updating the distance between the whale individuals; calculating a shared function value of the niche technology, and updating a fitness value; judging whether an iteration condition is met or not; and applying the searched optimal solution to the R and T parameters to obtain a final registration model. The whale optimization algorithm is optimized, and the improved whale optimization algorithm is more suitable for fragment registration.
Owner:NORTHWEST UNIV(CN)
Optical fiber testing system based on cloud computing
PendingCN111010226AFast deployment cycleImprove reliabilitySatellite radio beaconingElectromagnetic transmissionComputer hardwareVirtualization
The invention relates to an optical fiber testing system based on cloud computing, and the system comprises a test subsystem which is used for collecting optical fiber testing data; a resource subsystem which is connected with the test subsystem and is used for carrying out parameter calculation on the optical fiber test data. The test subsystem comprises a plurality of optical fiber test devices,wherein each optical fiber test device is connected with a resource subsystem through a network; and the resource subsystem operates on a cloud computing platform. Compared with the prior art, the system has the advantages of being short in deployment period, high in reliability, scalability, dynamics, virtualization and expandability, low in price, flexible and good in stability.
Owner:浙江光维通信技术有限公司
A plane wave discontinuity finite element method for simulating a radar scattering cross-sectional area
PendingCN109711044AVersatilityReduce complexitySpecial data processing applicationsScattering cross-sectionComputation complexity
The invention belongs to the technical field of radar cross sections, and discloses a plane wave discontinuous finite element method for simulating a radar cross section area, which comprises the following steps of: supplying power to a simulated radar system through a power supply module; performing control operation on the radar by using the operation keys through a key operation module; a maincontrol module transmitting wireless electromagnetic waves through an electric wave transmitting module by using a transmitter; receiving returned electromagnetic waves by using a receiving antenna through a radio wave receiving module; Calculating the radar cross section area by using a data calculation program through a cross section calculation module; and carrying out simulation operation on radar electromagnetic waves by using a simulation program through an electromagnetic simulation module. According to the invention, the complexity of modeling is greatly reduced; A method for judging whether the product of the surface element normal vector and the electromagnetic wave incident direction vector is smaller than zero or not is adopted, calculation is simplified, and calculation time is saved; the discrete fitting accuracy is high through an electromagnetic simulation module model; the calculation complexity and the memory consumption are low; the calculation precision is controllable; High stability.
Owner:SHANDONG UNIV OF SCI & TECH
Visual analysis platform for vehicle track-guided geographic spatial-temporal characteristics
PendingCN114265833AMake up for the disadvantage in storing and analyzing the initial trajectory dataDisadvantages in storing and analyzing initial trajectory data in line withVisual data miningStructured data browsingTrajectory databaseEngineering
On the basis of an Oracle network data model and a Stop / Run model, a database table structure for realizing a geographic space-time associated feature trajectory database is designed, including association of stay and motion behaviors in geographic space data and trajectory data, an Oracle NDM road network model is constructed according to OSM open source data, map matching is carried out on vehicle trajectory data, and a geographic space-time associated feature trajectory database is obtained. According to a matching result, acquiring stop and motion information in a vehicle driving process, associating the stop and motion information with point / line space elements by means of a space connection method, and constructing and filling a geographically associated track database; by taking a typicality retrieval request as an example, position-time, position-sequence and position-relationship trajectory spatial-temporal characteristic mode query and hot interest point analysis are performed, a new thought is provided for solving urban traffic and planning problems, the motion entities are effectively stored and managed, and the urban traffic planning method has the advantages of being high in practicability and easy to popularize. And powerful support is provided for traffic flow analysis, urban planning and hot scenic spot analysis.
Owner:刘心亮
Unsupervised domain adaptation system and method based on generative adversarial network
PendingCN111754478AStrong analytical skillsSolve difficult to convergeImage enhancementImage analysisImage analysisGenerative adversarial network
The invention discloses an unsupervised domain adaptation system and method based on a generative adversarial network, and a storage medium. The system comprises a feature extraction module used for extracting high-dimensional feature maps of a first sample and a second sample that are slice images with different dyeing styles, a dimension reduction module used for performing dimension reduction on the high-dimensional feature maps of the first sample and the second sample to convert the high-dimensional feature maps into low-dimensional feature maps, a discriminator used for receiving the low-dimensional feature maps of the first sample and the second sample, and enabling the low-dimensional feature maps output by the dimension reduction module to have consistency through adversarial training, a dimension raising module used for raising the dimensions of the low-dimensional feature maps of the first sample and the second sample to regenerate high-dimensional feature maps of the firstsample and the second sample, and a classification module used for receiving the regenerated high-dimensional feature maps of the first sample and the second sample and outputting an image analysis result. The system has good analysis capability for slice images with different dyeing styles.
Owner:怀光智能科技(武汉)有限公司
Landslide displacement prediction method based on intuitionistic fuzzy memetic PSO-LSTM
ActiveCN113033879AImprove forecast accuracyQuality improvementForecastingArtificial lifeAlgorithmLandslide
The invention discloses a landslide displacement prediction method based on an intuitionistic fuzzy memetic PSO-LSTM model. The method comprises the following steps: 1, establishing an initial LSTM model; 2, initializing a sub-population; 3, executing a collision rebound operator when the aggregation degree of the exploring sub-populations reaches a threshold value, otherwise, executing the step 4; 4, updating the exploration sub-population, calculating the fitness and updating the optimal solution; 5, calculating the Lamarch factors of the particles in the development sub-population; 6, updating the speed and position of the particles, calculating the fitness of the particles, and updating the optimal solution; 7, judging whether the development sub-populations converge or not, and if yes, selecting an optimal target area; 8, if the end condition is not met, returning to the step 3; 9, explaining the optimal solution as LSTM; and training the LSTM model by using the training sample. According to the invention, the heuristic optimization algorithm is combined with the intuitionistic fuzzy set, the LSTM prediction model is optimized and is more suitable for the landslide prediction problem, and the prediction precision of the prediction model on the lively problem is improved.
Owner:NORTHWEST UNIV(CN)
Method for detecting chromium element in jelly
InactiveCN106442691AProtect your healthLow detection limitMaterial analysis by electric/magnetic meansTrace elementInternal standard
The invention provides a method for detecting the chromium element in jelly. Cr (III) is an essential trace element in human bodies, but hexavalent chromium Cr (VI) has obvious toxicity to human bodies, has a stimulating and corroding effect on skin mucosa, interferes important enzyme systems, and has carcinogenesis and gene mutation induction effects. The method for detecting the chromium element in jelly comprises the following steps: drawing a standard curve; preparing and preprocessing a sample; preparing an internal standard solution, and selecting a tuned liquid; producing an ion exchange column, and regenerating and filling resin; and detecting the practical sample. The method has the advantages of low lower detection limit, high precision and high sample analysis ability.
Owner:中华人民共和国嘉兴出入境检验检疫局
Dynamic stream ciphering system and method based on broad sense information field
InactiveCN101394274AImprove securityHas chaotic propertiesSecuring communicationKey sizeComputer hardware
The invention provides a system for encrypting a dynamical flow based on a generalized information field, which comprises a PRG (Pseudorandom Code Generator) connected with the system and based on the generalized information field, and an encryption and decryption subsystem; the encryption and decryption subsystem comprises a size control module of a dynamic buffering area, a locus ring conversion and matrix generation module, a flow encryption module and a flow decryption module; the PRG (Pseudorandom Code Generator) comprises an IV generation module, an IV normalization module, an m module, a constrained processing module, a key length judgment module, a physical reconfiguration module and a logical reconfiguration module; the PRG (Pseudorandom Code Generator) is respectively connected with the size control module of the dynamic buffering area, the flow encryption module and the flow decryption module; and the flow encryption module and the flow decryption module are connected with the m module through a transfer entrance. The system realizes locus ring conversion and flow encryption in a conventional activity background space between both sides of encryption and decryption, overcomes the problem of the periodic property of a normal key flow generator, achieves 'one word one cipher', and has strong resistance to conventional cipher analysis.
Owner:SOUTH CHINA UNIV OF TECH
A fault diagnosis method for a hybrid nuclear power plant
ActiveCN107301884BGuaranteed real-timeGuaranteed demandPower plant safety arrangementNuclear energy generationReal-time dataDiagnosis methods
The invention discloses a hybrid nuclear power plant fault diagnosis method, belonging to the technical field of fault diagnosis. The method comprises a step of collecting operation parameters in a diagnosed system and transmitting the parameters to an established mechanism simulation model, a step of calculating a residual error on real-time data and a corresponding parameter obtained by simulation model calculation, a step of judging a result or result set of a fault type when the calculated residual error exceeds a limit value, a step of adding a diagnosis result into the simulation model to carry out fault verification, a step of selecting a part of operation parameters obtained by measurement as evaluation parameters, and determining a data analysis model of a Mahalanobis distance function for fault degree evaluation, a step of calculating a Mahalanobis distance value, and establishing evaluation curves of different fault modes, and a step of calculating the Mahalanobis distance function distance value of actual fault data by using the operation data of the diagnosed system after failure, and establishing evaluation curves under different fault degrees to carry out match analysis to complete the quantitative assessment of a fault degree.
Owner:HARBIN ENG UNIV
Broadband burst signal spectrum analyzer and wideband burst signal analysis method
ActiveCN110988473BStrong analytical skillsExcellent detection and interception abilityFrequency analysisTransmission monitoringFrequency spectrumSpectrum analyzer
The invention discloses a broadband burst signal spectrum analyzer and a broadband burst signal analysis method, belonging to the technical field of electronic measurement. The execution bandwidth of the technical solution of the present invention is greater than the signal analysis capability of the acquisition and analysis bandwidth of the instrument; the measurement efficiency of the technical solution of the present invention is high, and the technical solution of the present invention is suitable for burst signals whose occurrence time, frequency and duration of the signal are unknown. The ability to detect and intercept signals is superior to traditional technical solutions; in the patented solution of the present invention, the tuned local oscillator can be tuned according to the changing characteristics of the input signal, and the frequency spectrum of the signal of interest can be quickly obtained.
Owner:CHINA ELECTRONIS TECH INSTR CO LTD
General packet radio service (GPRS) end-to-end performance analysis method and system
InactiveCN101754253BImprove complaint handling methodsImprove relevanceTransmissionWireless communicationGPRS core networkData acquisition
The invention relates to the technical field of wireless and data services, in particular to a general packet radio service (GPRS) end-to-end performance analysis method. The method comprises the steps of data acquisition, protocol analysis and correlation analysis. A GPRS end-to-end performance analysis system comprises a Gb data acquisition front-end computer, a Gn and Gi data acquisition front-end computer, a G-miniature data acquisition system (MDAS) client, a G-MDAS system server and a multi-interface correlation analysis module. The invention provides the whole course of end-to-end correlation analysis, has high data correlation and strong analysis capacity, provides a reference for whole-course optimization, makes a compromise on individual difficult problem processing and a large number of common user data, perfects a user complain processing means, can accomplish the performance analysis from a cell level to a GPRS core network and provides a reference for the system optimization.
Owner:中国移动通信集团甘肃有限公司
Features
- R&D
- Intellectual Property
- Life Sciences
- Materials
- Tech Scout
Why Patsnap Eureka
- Unparalleled Data Quality
- Higher Quality Content
- 60% Fewer Hallucinations
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.
© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com