Patents
Literature
Hiro is an intelligent assistant for R&D personnel, combined with Patent DNA, to facilitate innovative research.
Hiro

32results about How to "The method is simple and intuitive" patented technology

Method for customizing digitalized shoe trees according to a plurality of images of foot shapes

The invention relates to a method for directly generating digitalized shoe trees by using foot shapes, solving the difficult problem of customizing shoe trees by measuring feet. The method comprises the following steps: (1) selecting shoe tree samples to form a shoe tree sample set; (2) designing gauge points, determining gauge points on each shoe tree sample and then acquiring the positions of the gauge points by using a scanner to obtain gauge point distribution models of the shoe tree samples; (3) aligning the gauge point distribution models of the samples; (4) generating statistic deformation models of the shoe trees; (5) calibrating the parameter of each camera and then acquiring a plurality of images of target foot shapes; (6) calculating the center of gravity of the foot shapes; (7) estimating the sizes of the foot shapes; (8) estimating the direction of the foot shapes; (9) changing individual vectors in the statistic deformation models of the shoe trees according to the plurality of images of the foot shapes until the projection of the models in each image is most identical with the true images of the foot shapes; and (10) outputting digitalized three-dimensional shoe tree models. The invention has the advantages of full automation, high speed and efficiency, simple use, low cost and the like.
Owner:WENZHOU UNIVERSITY +1

Power battery pack series connection fault diagnosis method

ActiveCN107843853ADistinguishing faults with increased internal resistanceReduce operating burdenElectrical testingElectrical resistance and conductancePower battery
The invention puts forward a power battery pack series connection fault diagnosis method. A battery pack is formed via series connection of n battery single cells, and a crossover voltage test method.A battery management system is used for recording battery single cell voltage and battery single cell surface temperature. An MATLAB/simuink is used for simulating adopted power batteries and recording simulation voltage. A mean squared error between experimental and simulation output voltages is calculated to preliminarily determine if voltage exception occurs. If yes, a Z-score is calculated asa voltage detection exception coefficient based on the mean squared error. According to the voltage detection exception coefficient, whether a fault is connection failure or increased internal resistance of single cells; if yes, the fault is determined as a secondary fault, and the rise rate of battery surface temperature is calculated to determine whether the rise rate is greater than a preset threshold value; if yes, the fault is determined as a primary fault. Via the method disclosed in the invention, reliable diagnosis of connection failure of the power battery pack can be realized, increase of contact resistance and increase of internal resistance can be differentiated from each other, only a simple algorithm is needed, and an operating burden of a battery management system can be effectively lowered.
Owner:UNIV OF SCI & TECH OF CHINA +1

Device and method for measuring aperture of foamed aluminum based on machine vision

The invention relates to a device and method for measuring the aperture of foamed aluminum, in particular to a device and method for measuring the aperture of foamed aluminum based on machine vision. The device comprises an image capture working machine, an optical fiber signal transmitter and a computer, wherein the upper surface of the image capture working machine is provided with an X-axis working table; a Y-axis working table is arranged below the X-axis working table; an upright post is arranged at one side of the image capture working machine; and photographing equipment is arranged at one side of the upright post opposite to the working table. The invention aims to disclose a method for measuring the aperture of the foamed aluminum or foamed aluminum alloy by using the machine vision, namely an image of a sectional aperture condition of the measured foamed aluminum is directly acquired through a camera and then is transmitted to the computer; and the image is accurately analyzed and calculated by using computer software to obtain the size of the aperture. The method is intuitive, simple and convenient; and errors brought by visual observation can be avoided, so that the data are more accurate and great help is provided for the research of the aperture and the porosity of the foamed aluminum or foamed aluminum alloy.
Owner:DONGGUAN UNIV OF TECH +3

Intelligent power transformer operation monitoring system

The invention belongs to the technical field of the detection system, and discloses an intelligent power transformer operation monitoring system comprising a circuit board, a display screen, groundingbolts, a power panel, an inductor, an antenna device, an SIM card, an intelligent chip, an RS communication board, a bellows connector, a display screen button and manholes. The manholes are inlaid in the upper and lower parts of the monitoring device. The circuit board is arranged exactly below the monitoring device. The display screen is embedded in the middle part of the circuit board. The display screen button is arranged on the lower part of the display screen. The antenna device is welded on the left side of the circuit board. The grounding bolts are arranged on the lower part of the circuit board and distributed on the four feet. The power panel is arranged below the right side grounding bolt. The inductor is arranged on the lower left part of the power panel. The RS communicationboard is arranged on the left side of the inductor. Electrical appliance part cooperative work monitoring can be realized, the operation state of the transformer can be effectively and comprehensivelymonitored and assessed, real-time comprehensive assessment can be performed and the requirements of early warning can be met.
Owner:杨彦青 +1

Image registration method and system and image shooting alignment method and system

The invention relates to an image registration method and system and an image shooting alignment method and system. The image registration method comprises steps that the feature area in a first imageis projected multiple times to the search area in a second image, the feature area projected in the second image each time defines a matching area, the feature area of the first image comprises multiple first target points, the first target points projected to the matching areas are defined as first target centers, and the search area of the second image comprises multiple second target points; the second target point closest to each of the first target centers in the matching areas is sequentially searched, the distance between each of the first target centers and the closest second target point is defined as a target offset value, the sum of all the target center offset values in the matching areas is defined as a registration value of the matching areas; the matching area with the smallest registration value in the search area is acquired as the feature registration area, a displacement difference between the feature area of the first image and the feature registration area of thesecond image is calculated as the registration offset for registration of the first image and the second image. The method is advantaged in that calculation is relatively fast.
Owner:GUANGZHOU KANGXINRUI GENE HEALTH TECH CO LTD

Facial expression synthesis method based on generative adversarial network

PendingCN111192343AThe method is convenient and intuitiveThe intensity of expression is vivid and realAcquiring/recognising facial featuresFilling planer surface with attributesGenerative adversarial networkMachine learning
The invention discloses a facial expression synthesis method based on a generative adversarial network. The method comprises the following steps: firstly, acquiring data of facial expressions, preprocessing the facial expression data, cutting facial images into training data and test data, and manually classifying the training data into different categories according to different facial expressionintensities; then constructing a generative adversarial network, and adding judgment information of expression intensity and associated information between different expression intensities into the network; training and testing the generative adversarial network by using the preprocessed expression data, and adjusting network parameters to optimize the generative adversarial network model; and finally, selecting test data of neutral expressions and inputting the test data into the trained generative adversarial network model to obtain expression images with different intensities. According tothe method, the facial expression images with different intensities can be synthesized through the neutral expression-free facial images, the method is convenient and visual, and the synthesized expression intensity is more vivid and realistic.
Owner:NANJING UNIV OF SCI & TECH

Method for customizing digitalized shoe trees according to a plurality of images of foot shapes

The invention relates to a method for directly generating digitalized shoe trees by using foot shapes, solving the difficult problem of customizing shoe trees by measuring feet. The method comprises the following steps: (1) selecting shoe tree samples to form a shoe tree sample set; (2) designing gauge points, determining gauge points on each shoe tree sample and then acquiring the positions of the gauge points by using a scanner to obtain gauge point distribution models of the shoe tree samples; (3) aligning the gauge point distribution models of the samples; (4) generating statistic deformation models of the shoe trees; (5) calibrating the parameter of each camera and then acquiring a plurality of images of target foot shapes; (6) calculating the center of gravity of the foot shapes; (7) estimating the sizes of the foot shapes; (8) estimating the direction of the foot shapes; (9) changing individual vectors in the statistic deformation models of the shoe trees according to the plurality of images of the foot shapes until the projection of the models in each image is most identical with the true images of the foot shapes; and (10) outputting digitalized three-dimensional shoe tree models. The invention has the advantages of full automation, high speed and efficiency, simple use, low cost and the like.
Owner:WENZHOU UNIV +1

Multi-satellite positioning and orbit determination precision rapid analysis method for space-based space target monitoring

The invention discloses a multi-satellite positioning and orbit determination precision rapid analysis method for space-based space target monitoring, and relates to the technical field of space target monitoring. According to the method, firstly, the multi-satellite positioning error is rapidly analyzed according to the single-station data type, the measurement error and the multi-satellite geometric configuration, then the relationship between the semi-major axis error and the positioning error of short-arc-segment orbit determination is given by utilizing the characteristics of propagation along the track of the orbit, the method is simple, convenient and visual, and quantitative support is provided for the overall design of a space-based space target monitoring system. The method can be suitable for the design of a multi-satellite positioning and orbit determination system for space-based space target monitoring, can also be popularized and applied to the design of a space-ground multi-satellite multi-station combined positioning and orbit determination system, can rapidly and quantitatively evaluate the space target positioning and orbit determination result under different constellation designs, is clear in principle, is simple in calculation, is accurate in evaluation, and can be widely applied to a space-based space target monitoring system.
Owner:NO 63921 UNIT OF PLA

A fault diagnosis method for series connection of power battery packs

ActiveCN107843853BDistinguishing faults with increased internal resistanceReduce operating burdenElectrical testingPower batteryInternal resistance
The invention puts forward a power battery pack series connection fault diagnosis method. A battery pack is formed via series connection of n battery single cells, and a crossover voltage test method.A battery management system is used for recording battery single cell voltage and battery single cell surface temperature. An MATLAB / simuink is used for simulating adopted power batteries and recording simulation voltage. A mean squared error between experimental and simulation output voltages is calculated to preliminarily determine if voltage exception occurs. If yes, a Z-score is calculated asa voltage detection exception coefficient based on the mean squared error. According to the voltage detection exception coefficient, whether a fault is connection failure or increased internal resistance of single cells; if yes, the fault is determined as a secondary fault, and the rise rate of battery surface temperature is calculated to determine whether the rise rate is greater than a preset threshold value; if yes, the fault is determined as a primary fault. Via the method disclosed in the invention, reliable diagnosis of connection failure of the power battery pack can be realized, increase of contact resistance and increase of internal resistance can be differentiated from each other, only a simple algorithm is needed, and an operating burden of a battery management system can be effectively lowered.
Owner:UNIV OF SCI & TECH OF CHINA +1

Industrial monitoring control system based on industrial internet platform

The invention discloses a system and method based on an industrial internet platform. The system comprises a data acquisition module and an information issuing terminal which are in signal connection with a data processing module. The data acquisition module is used for acquiring condition information, related to blockage, of at least one branch bin in branch bins of a rotary air preheater; the data processing module is used for determining the blockage level of the rotary air preheater according to the blockage-related condition information and determining whether ash removal measures need to be taken or not according to the blockage level; and the information issuing terminal is used for issuing the processing information of the data processing module, so that a user can obtain specific monitoring information, early warning information and processing suggestions. According to the system and method based on the industrial internet platform, the state information, related to blockage, of the rotary air preheater can be monitored in real time, whether blockage occurs or not and the blockage degree can be obtained according to the monitoring information, corresponding measures can be provided in a targeted mode according to the actual situation, the intelligent level is improved, and safe and stable operation of the rotary air preheater is guaranteed.
Owner:黄剑敏

Optimal dispatching of cascade hydropower station group by stage-by-stage reverse learning and dimensionality reduction optimization method

The present invention relates to the technical field of high-efficiency utilization of water resources and optimal scheduling of hydropower, and discloses a step-by-stage reverse learning dimension reduction optimization method for optimal scheduling of cascade hydropower station groups. First, the initial scheduling state process and discrete step length of each hydropower station are calculated; In each stage of the calculation, on the upper and lower sides of the initial state combination, the number of discrete states on the upper and lower sides is randomly generated and combined to form a corridor. Based on the upper and lower boundaries of the corridor, the reverse state combination of the initial state is calculated Perform iterative optimization to obtain an improved scheduling process; repeat the above process until all stages are calculated; finally shrink the discrete step length, iterate repeatedly until convergence, thereby approaching the global optimal solution, and output the optimal scheduling process. The method for optimal dispatching of cascade hydropower station groups of the present invention reversely learns dimensionality reduction optimization method step by step, effectively reduces computational complexity, greatly improves computational efficiency, and is suitable for optimal dispatching of large-scale cascade hydropower station groups.
Owner:CHANGJIANG SURVEY PLANNING DESIGN & RES
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products