Patents by Inventor Xinhong Xie

Xinhong Xie has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Patent number: 12320921
    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.
    Type: Grant
    Filed: December 10, 2024
    Date of Patent: June 3, 2025
    Assignee: DONGHAI LABORATORY
    Inventors: Chunyi Song, Xinhong Xie, Zixian Ma, Haotian Chen, Nayu Li, Haohong Xu, Bing Lan, Zhiwei Xu
  • Patent number: 12288936
    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.
    Type: Grant
    Filed: December 20, 2024
    Date of Patent: April 29, 2025
    Assignees: ZHEJIANG UNIVERSITY, DONGHAI LABORATORY
    Inventors: Chunyi Song, Haotian Chen, Nayu Li, Zhiwei Xu, Xinhong Xie, Zixian Ma, Bing Lan
  • Publication number: 20250125522
    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.
    Type: Application
    Filed: December 20, 2024
    Publication date: April 17, 2025
    Applicants: ZHEJIANG UNIVERSITY, DONGHAI LABORATORY
    Inventors: Chunyi SONG, Haotian CHEN, Nayu LI, Zhiwei XU, Xinhong XIE, Zixian MA, Bing LAN
  • Publication number: 20250102623
    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.
    Type: Application
    Filed: December 10, 2024
    Publication date: March 27, 2025
    Applicant: DONGHAI LABORATORY
    Inventors: Chunyi SONG, Xinhong XIE, Zixian MA, Haotian CHEN, Nayu LI, Haohong XU, Bing LAN, Zhiwei XU
  • Patent number: 11897049
    Abstract: The invention provides a retractable friction stir welding spindle, aims at the deficiencies and defects of the existing friction stir welding spindle technology, that is, when the welding is finished, the stirring needle leaves a keyhole at the end of the weld seam, which affects the forming performance of the workpiece, the overall structure design of the spindle is complicated with many transmission chains and low reliability which is difficult to realize modularization. The retractable friction stir welding spindle includes an electric spindle system and a retracting mechanism. The electric spindle system includes stirring shaft shoulder, hilt, front end cover, hollow spindle, motorized spindle shell, motor rotor, motor stator, tail end cover, etc. The retracting mechanism includes stirring needle, connecting ball head and electric cylinder. The invention has the advantages of simple structure and can be mainly divided into two modules to improve reliability and integrity.
    Type: Grant
    Filed: April 10, 2023
    Date of Patent: February 13, 2024
    Assignee: BEIJING UNIVERSITY OF TECHNOLOGY
    Inventors: Shujun Chen, Bo Cheng, Xinhong Xie, Zirui Cao
  • Publication number: 20230241707
    Abstract: The invention provides a retractable friction stir welding spindle, aims at the deficiencies and defects of the existing friction stir welding spindle technology, that is, when the welding is finished, the stirring needle leaves a keyhole at the end of the weld seam, which affects the forming performance of the workpiece, the overall structure design of the spindle is complicated with many transmission chains and low reliability which is difficult to realize modularization. The retractable friction stir welding spindle includes an electric spindle system and a retracting mechanism. The electric spindle system includes stirring shaft shoulder, hilt, front end cover, hollow spindle, motorized spindle shell, motor rotor, motor stator, tail end cover, etc. The retracting mechanism includes stirring needle, connecting ball head and electric cylinder. The invention has the advantages of simple structure and can be mainly divided into two modules to improve reliability and integrity.
    Type: Application
    Filed: April 10, 2023
    Publication date: August 3, 2023
    Inventors: Shujun Chen, Bo Cheng, Xinhong Xie, Zirui Cao