中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

1129 records (took 0.026 seconds)

    Prediction method for stall and surge of axial compressor based on deep learning
    14.
    发明授权
    Prediction method for stall and surge of axial compressor based on deep learning 有权

    公开(公告)号：US12288164B2

    公开(公告)日：2025-04-29

    申请号：US17312278

    申请日：2020-09-28

    Applicant: DALIAN UNIVERSITY OF TECHNOLOGY

    Inventor： Ximing Sun ,  Fuxiang Quan ,  Hongyang Zhao ,  Yanhua Ma ,  Pan Qin

    IPC: G06N3/084 ,  G06N3/045

    Abstract: The present invention relates to a prediction method for stall and surge of an axial compressor based on deep learning. The method comprises the following steps: firstly, preprocessing data with stall and surge of an aeroengine, and partitioning a test data set and a training data set from experimental data. Secondly, constructing an LR branch network module, a WaveNet branch network module and a LR-WaveNet prediction model in sequence. Finally, conducting real-time prediction on the test data: preprocessing test set data in the same manner, and adjusting data dimension according to input requirements of the LR-WaveNet prediction model; giving surge prediction probabilities of all samples by means of the LR-WaveNet prediction model according to time sequence; and giving the probability of surge that data with noise points changes over time by means of the LR-WaveNet prediction model, to test the anti-interference performance of the model.

    METHOD FOR MEASURING THICKNESS, ROUGHNESS AND INTERFACE STIFFNESS OF COATING LAYER USING ULTRASONIC PHASE DERIVATIVE SPECTRUM
    17.
    发明申请
    METHOD FOR MEASURING THICKNESS, ROUGHNESS AND INTERFACE STIFFNESS OF COATING LAYER USING ULTRASONIC PHASE DERIVATIVE SPECTRUM 有权

    公开(公告)号：US20250076260A1

    公开(公告)日：2025-03-06

    申请号：US18800210

    申请日：2024-08-12

    Applicant: DALIAN UNIVERSITY OF TECHNOLOGY

    Inventor： Zhiyuan MA ,  Li LIN

    IPC: G01N29/46 ,  G01B17/02 ,  G01B17/08 ,  G01N29/04 ,  G01N29/28

    Abstract: The method for measuring thickness, roughness and interface stiffness of coating layer by using ultrasonic phase derivative spectrum which relates to technical field of the ultrasonic non-destructive testing. The method adopts an ultrasonic detection system which includes a sample of the coating layer, an ultrasonic flat probe, an ultrasonic flaw detector, a XYZ three-dimensional stepping device and a computer. The method derives UPDS (Ultrasonic phase derivative spectrum) when the ultrasonic wave is vertically incident on structure with three-medium and two-interface including coupled medium/coating layer/substrate, to conduct sensitivity analysis to identify the high sensitivity range of ultrasonic phase derivative spectrum to thickness, roughness and interface stiffness of coating layer, and to conduct correlation analysis to eliminate deviation introduced by initial phase of the reference signal and the detection signal, so as to achieve simultaneous quantitative characterization of thickness, roughness as well as interface stiffness of coating layer.

    A self-learning method of generative adversarial multi-headed attention neural network for aero-engine data reconstruction
    18.
    发明申请
    A self-learning method of generative adversarial multi-headed attention neural network for aero-engine data reconstruction 有权

    公开(公告)号：US20250036924A1

    公开(公告)日：2025-01-30

    申请号：US18548204

    申请日：2022-10-28

    Applicant: DALIAN UNIVERSITY OF TECHNOLOGY

    Inventor： Song MA ,  Tao SUN ,  Zengsong XU ,  Ximing SUN ,  Zhi LI

    IPC: G06N3/0475 ,  G06N3/094

    Abstract: A generative adversarial multi-headed attention neural network self-learning method for aero-engine data reconstruction belongs to the field of end-to-end self-learning of aero-engine missing data. First, the samples are pre-processed, and the machine learning algorithm is used to pre-fill the normalized data first, and the pre-filled information is involved in the network training as part of the training information. Second, a generative adversarial multi-headed attention network model is constructed and the trained sample set is used to train the generative adversarial multi-headed attention network model. Finally, the samples are generated using the trained sample generator G. The method uses the generative adversarial network to better learn the distribution information of the data, and uses parallel convolution and multi-headed attention mechanism to fully exploit the spatial and temporal information among the aero-engine data.

    METHOD, SYSTEM AND DEVICE FOR ALLOCATING TOTAL EMISSION REDUCTION OF WATER ENVIRONMENTAL POLLUTION LOAD
    19.
    发明申请
    METHOD, SYSTEM AND DEVICE FOR ALLOCATING TOTAL EMISSION REDUCTION OF WATER ENVIRONMENTAL POLLUTION LOAD 有权

    公开(公告)号：US20240403514A1

    公开(公告)日：2024-12-05

    申请号：US18487559

    申请日：2023-10-16

    Applicant: Dalian University of Technology

    Inventor： Zhuohang XIN ,  Ming CONG ,  Zhihong LIU ,  Chi ZHANG

    IPC: G06F30/20

    Abstract: A method, system and device for allocating total emission reduction of a water environmental pollution load are provided. The method includes: dividing a watershed based on terrain elevation information in watershed-related data to generate a plurality of watershed control units; with a watershed control unit as a basic unit, estimating a pollution load output in each watershed control unit by using an output coefficient method; acquiring GDP of each watershed control unit, and combined with the pollution load output, calculating relative environmental efficiency of each watershed control unit by using a data envelopment method; quantifying a contribution rate of a pollution load produced by each watershed control unit to a pollution load of a section of river entering the sea one by one based on a constructed watershed water environmental model; and formulating a pollutant emission reduction scheme according to the relative environmental efficiency and the contribution rate.

    Semi-automatic corrosion box of copper clad laminate
    20.
    发明授权
    Semi-automatic corrosion box of copper clad laminate 有权

    公开(公告)号：US12101892B2

    公开(公告)日：2024-09-24

    申请号：US16962729

    申请日：2019-11-13

    Applicant: DALIAN UNIVERSITY OF TECHNOLOGY

    Inventor： Shengming Li ,  Sen Qiu ,  Fangyuan Hu ,  Huihui Wang

    IPC: H05K7/20 ,  B32B15/20 ,  H05K3/06

    CPC classification number: H05K3/068 ,  B32B15/20 ,  H05K7/20272 ,  H05K2203/0165 ,  H05K2203/075 ,  H05K2203/1105

    Abstract: A semi-automatic corrosion box of a copper clad laminate is disclosed. The corrosion device comprises a box body which has no cover; a baffle plate which divides the corrosion box into an upper part and a lower part, wherein a copper clad laminate circuit board is placed on the baffle plate, and a temperature detection module, water pumps and a heating rod are placed on a lower part; and a thermal imaging camera which is placed on a pressing plate through a bracket. Modules in corrosive liquid are connected with an external single chip microcomputer control module through corrosion-resistant wires. The working mode of the present invention is that time and temperature are set with a key matrix at first, and the control module can automatically stop working and enter a low power consumption mode.

Patent Agency Ranking