公开(公告)号：US20250125522A1

公开(公告)日：2025-04-17

申请号：US18991311

申请日：2024-12-20

Applicant: ZHEJIANG UNIVERSITY ,  DONGHAI LABORATORY

Inventor： Chunyi SONG ,  Haotian CHEN ,  Nayu LI ,  Zhiwei XU ,  Xinhong XIE ,  Zixian MA ,  Bing LAN

IPC: H01Q3/26 ,  G06T5/20 ,  G06V10/44

Abstract: Disclosed is a method for fast automatic calibration of a phased array based on a residual neural network. A phase setting matrix is set and an amplitude and a phase of a array far-field complex signal are measured with a network analyzer to obtain an amplitude and phase vector of the array far-field complex signal. A real part, an imaginary part, and a magnitude of the far-field measured complex signal value are separated and normalized, and mapped to RGB three-channel image data. Datasets are automatically generated according to a preset amplitude-phase error range by a simulation software, the datasets are proportionally divided into a training set and a test set to be input into the residual neural network for training to obtain a calibration model. Measured data is input into the calibration model for automatic estimation of the amplitude-phase error of the phased array.

公开(公告)号：US20250102623A1

公开(公告)日：2025-03-27

申请号：US18976291

申请日：2024-12-10

Applicant: DONGHAI LABORATORY

Inventor： Chunyi SONG ,  Xinhong XIE ,  Zixian MA ,  Haotian CHEN ,  Nayu LI ,  Haohong XU ,  Bing LAN ,  Zhiwei XU

IPC: G01S7/40 ,  G01S13/02 ,  G06N3/0442 ,  G06N3/0464 ,  G06N3/09 ,  H01Q1/28

Abstract: Embodiments of the present disclosure provide a method for phased array calibration based on CNN-LSTM using power measurement, comprising: establishing a phased array calibration signal model, and utilizing a program to conveniently obtain a large amount of data for training a neural network without the need for actual measurements; converting and preprocessing the generated data, and saving as a training dataset in the form of feature data and labels; establishing a CNN-LSTM network, and inputting the training data with labels into the CNN-LSTM network for training until the CNN-LSTM network converges to obtain the final calibration model; measuring the phased array to be measured to obtain feature data, obtaining a calibration result of the phased array by inputting the feature data into the calibration model obtained from the training. The method is designed to solve problems of low calibration accuracy, low measurement efficiency, and high instrumentation requirements of the existing phased array calibration processes, and the proposed calibration method has a very high calibration efficiency, and the number of measurements required is much lower than that of all current power measurement-based calibration methods.