Please use this identifier to cite or link to this item:
Title: A data-driven method for IGBT open-circuit fault diagnosis in three phase inverters for induction motor drive system
Authors: Yin, Rui
Keywords: DRNTU::Engineering
Issue Date: 2018
Abstract: As one of the important components of induction motor driven system, the working condition of the three-phase inverter will have a direct impact on the stability of electrical power system. According to the traditional approach of fault diagnosis, the output signals of electrical power system or the electrical power system models are analyzed before confirming system operation situations. However, the data-driven approach of fault diagnosis only needs historical data for constructing diagnostic models, accompanied by the appropriate algorithm for judgment. This report presents a data-driven method for IGBT open-circuit fault diagnosis in three-phase inverters. As things stand, random learning algorithm has been a focal point of research on artificial neural networks. Based on the algorithm’s random initial weight, this report can design a fault diagnosis model that relies on ensemble learning to quickly and accurately pinpoint faults. In order to further improve the performances of diagnosis model, a credibility evaluation criterion is introduced, in which the results rated as credible will become the final outcome. However, the incredible results will be abandoned to reduce the probability of erroneous judgment of diagnostic system. The data for training and testing can be obtained through the emulation functions of Matlab. Regarding the given testing examples, the system demonstrates excellent performances, premium efficiency and ultra-high classification accuracy.
Schools: School of Electrical and Electronic Engineering 
Rights: Nanyang Technological University
Fulltext Permission: restricted
Fulltext Availability: With Fulltext
Appears in Collections:EEE Student Reports (FYP/IA/PA/PI)

Files in This Item:
File Description SizeFormat 
  Restricted Access
Main article2.1 MBAdobe PDFView/Open

Page view(s)

Updated on Jun 17, 2024


Updated on Jun 17, 2024

Google ScholarTM


Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.