Patents by Inventor Yajun TONG

Yajun TONG 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).

  • Decision tree SVM fault diagnosis method of photovoltaic diode-clamped three-level inverter
    Patent number: 10234495
    Abstract: The present invention discloses a decision tree SVM fault diagnosis method of a photovoltaic diode-clamped three-level inverter in view of fault diagnosis problems of the photovoltaic three-level inverter in a photovoltaic microgrid. Taking an inverting state for example, firstly, analyzing running conditions of an inverter main circuit and performing fault classification, then taking the middle, upper and lower bridge leg voltages as measurement signals, extracting feature signals with a wavelet multiscale decomposition method, and thereby generating a decision tree SVM fault classification model with a particle swarm clustering algorithm, to finally achieve multi-mode fault diagnosis of the photovoltaic diode-clamped three-level inverter. Advantages of the present invention are that, this algorithm can obviously distinguish various fault states of the photovoltaic diode-clamped three-level inverter, complete the failure diagnostic task with fewer classification models And the diagnosis precision is high.
    Type: Grant
    Filed: December 30, 2016
    Date of Patent: March 19, 2019
    Assignee: JIANGNAN UNIVERSITY
    Inventors: Hongfeng Tao, Chaochao Zhou, Yan Liu, Yajun Tong
  • Decision Tree SVM Fault Diagnosis Method of Photovoltaic Diode-Clamped Three-Level Inverter
    Publication number: 20180238951
    Abstract: The present invention discloses a decision tree SVM fault diagnosis method of a photovoltaic diode-clamped three-level inverter in view of fault diagnosis problems of the photovoltaic three-level inverter in a photovoltaic microgrid. Taking an inverting state for example, firstly, analyzing running conditions of an inverter main circuit and performing fault classification, then taking the middle, upper and lower bridge leg voltages as measurement signals, extracting feature signals with a wavelet multiscale decomposition method, and thereby generating a decision tree SVM fault classification model with a particle swarm clustering algorithm, to finally achieve multi-mode fault diagnosis of the photovoltaic diode-clamped three-level inverter. Advantages of the present invention are that, this algorithm can obviously distinguish various fault states of the photovoltaic diode-clamped three-level inverter, complete the failure diagnostic task with fewer classification models And the diagnosis precision is high.
    Type: Application
    Filed: December 30, 2016
    Publication date: August 23, 2018
    Applicant: Jiangnan University
    Inventors: Hongfeng TAO, Chaochao ZHOU, Yan LIU, Yajun TONG