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

44results about How to "Fix implementation issues" patented technology

Method for actually measuring wing torque loads of high-manoeuvrability aircraft

The invention belongs to the field of aircraft flight load actual measurement and relates to a method for actually measuring wing torque loads of a high-manoeuvrability aircraft. The method comprises the following steps: 1, determining a structure or a part sensitive to influences of wing aerodynamic loads on wing torque loads by virtue of wing finite element computation and analysis; 2, realizing a torque load test system for each section of wings by virtue of adopting a sensitive torque bridge piece distribution scheme and a torque bridge combination technology; 3, performing a ground calibration test on the torque loads according to the structure or part sensitive to the influences of the aerodynamic loads on the wing torque loads, thereby obtaining conversion relation between external loads and bridge strain gauge signals by virtue of the ground calibration test; 4, performing a flight load actual measurement flight test, thereby obtaining the torque loads of each section of the wings according to the bridge strain gauge signals during flight. The method has the advantages that by virtue of aiming at the implementation difficulty in aircraft wing torque load actual measurement, the implementation problem of a torque load flight actual measurement test is solved, and the accuracy and high precision of the wing torque load test are ensured.
Owner:SHENYANG AIRCRAFT DESIGN INST AVIATION IND CORP OF CHINA

A dual-mode deep learning descriptor construction method based on graphic primitives

The method is suitable for the technical field of image registration. The invention provides a dual-mode deep learning descriptor construction method based on graphic primitives. According to the method, attribute categories of patch images are learned by labeling samples, geometric features of the patch images are learned by utilizing graphic primitives, and the attribute categories and the geometric features are fused to obtain feature vectors of local patch images, namely descriptors based on the graphic primitives. Registration between the patches is completed by describing similarity of the sub-vectors. According to the dual-mode deep learning descriptor construction method based on the graphic primitives, which is provided by the invention, a descriptor classification method calculated by a GPU (Graphics Processing Unit) is explored aiming at the defect that a classic image registration method is relatively large in CPU (Central Processing Unit) calculation amount. A descriptor training set is mainly established, a multi-mode convolutional network is constructed, categories and geometric modes are trained on a GPU, and classification and registration of local patch images areachieved. The classification description method of the descriptors and the implementation problem on the GPU are solved.
Owner:ANHUI NORMAL UNIV

Tray type axle box body strength test device and method

The invention discloses a tray type axle box body strength test device and method, and the method comprises the steps: a tie spring is set between a framework and an axle box body, and the X-directionposition of an axle between two pairs of axle box bodies is restrained; the Y-direction position of the axle between the two pairs of axle boxes isrestrained; the Z-direction position of the axle between the two pairs of axle boxes on the same framework is restrained, specifically, Z-direction restraining is conducted on the first axle from the position where the wheel pair is installed on the first axle, and Z-direction restraining is conducted on the second axle from the position where the wheel pair is installed on the second axle; X-direction force or displacement is applied to the axle box body from a traction rod of the framework; Y-direction force or displacement is applied to the axle box body from the transverse stop position of the framework; Z-direction force or displacement isapplied to the axle box body from the secondary spring position of the framework. The method can effectively solve the problems that in the static strength and fatigue strength test verification working process of the tray type axle box body, a test object is difficult to place, restrain and fix, and force loading is difficult.
Owner:CRRC QINGDAO SIFANG CO LTD

High-order mapping spectral imaging system and method

InactiveCN106248207AAchieve consistent detectionHigh transform dimensionRadiation pyrometrySpectrum investigationSignal-to-noise ratio (imaging)High dimensional
The invention belongs to the optical field, and particularly relates to a high-order mapping spectral imaging system and a method. Based on high-order mapping, a novel high-order mapping spectral imaging method is provided. Unlike general transformation, high-order mapping has the features corresponding to different sets and features of high-dimensional transformation, and thus, the transformation domain is wider, and the transformation dimension is higher. Meanwhile, as slit dispersion and filter light splitting are cancelled, the high resolution is ensured, and the multichannel advantages brought by high-order mapping can ensure a high signal-to-noise ratio. Particularly, high-order mapping can realize consistent detection on multi-dimensional information, and in comparison with a multi-dimensional information detection mode of single-dimensional information detection firstly and then combination, hardware requirements are reduced. The system and the method of the invention have the beneficial effects that the high-resolution spectral imaging system realization problem is solved; the problem that the high-signal-to-noise ratio spectral imaging energy is not enough is solved; and the high-dimensional spectral imaging technical means problem can be solved.
Owner:XI'AN INST OF OPTICS & FINE MECHANICS - CHINESE ACAD OF SCI

A two-mode deep learning descriptor construction method based on graph primitives

The present invention is applicable to the technical field of image registration, and provides a method for constructing a dual-mode deep learning descriptor based on graphics primitives. In this method, the attribute category of the patch image is learned by labeling samples, and the geometry of the patch image is learned by using the graphics primitive. Features, the attribute category and geometric features are fused to obtain the feature vector of the local patch image, that is, the descriptor based on the graphics primitive. The registration between patches is completed through the similarity of descriptor vectors, and the classification and description based on machine learning descriptors are realized. The dual-mode deep learning descriptor construction method based on graphics primitives proposed by the present invention is aimed at the classic image registration method CPU. Disadvantages of a large amount of calculation, explore the descriptor classification method of GPU (image processor) calculation. It mainly establishes a descriptor training set, builds a multi-mode convolutional network, trains categories and geometric modes on the GPU, and realizes classification and registration of local patch images. Solve the classification description method of the descriptor and the implementation problem on the GPU.
Owner:ANHUI NORMAL UNIV
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