Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
DECISION TREE SUPPORT VECTOR MACHINE (SVM) FAULT DIAGNOSIS METHOD FOR PHOTOVOLTAIC DIODE CLAMPED THREE-LEVEL INVERTER
Document Type and Number:
WIPO Patent Application WO/2018/045689
Kind Code:
A1
Abstract:
A decision tree SVM fault diagnosis method for a photovoltaic diode clamped three-level inverter, for use in fault diagnosis of a three-level inverter in a photovoltaic microgrid. Using an inversion state as an example, an operation state of an inverter main circuit is first analyzed and fault classification is performed, and then with middle, upper, and lower bridge arm voltages as measurement signals, feature signals are extracted using a wavelet multi-scale decomposition method, so as to generate decision tree SVM classification models using a particle swarm clustering algorithm and thus finally achieve multi-mode fault diagnosis for the photovoltaic diode clamped three-level inverter. The method is advantageous in that: the algorithm can clearly distinguish different fault states of a photovoltaic diode clamped three-level inverter, fewer classification models to complete a fault diagnosis task, and is high in diagnosis precision and strong in anti-interference capability.

Inventors:
TAO HONGFENG (CN)
ZHOU CHAOCHAO (CN)
LIU YAN (CN)
TONG YAJUN (CN)
Application Number:
PCT/CN2016/113645
Publication Date:
March 15, 2018
Filing Date:
December 30, 2016
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
UNIV JIANGNAN (CN)
International Classes:
G01R31/02; G06K9/62
Foreign References:
CN104698397A2015-06-10
KR20150130594A2015-11-24
CN102937688A2013-02-20
CN102704054A2012-10-03
Attorney, Agent or Firm:
WUXI HUAYUAN PATENT AND TRADEMARK AGENCY (GENERAL PARTNERSHIP) (CN)
Download PDF: