DocumentCode :
2717659
Title :
Fault Diagnosis System for a Multilevel Inverter Using a Principal Component Neural Network
Author :
Khomfoi, Surin ; Tolbert, Leon M.
Author_Institution :
The University of Tennessee, Electrical and Computer Engineering, 414 Ferris Hall, Knoxville, TN 37996-2100, USA, Email: surin@utk.edu
fYear :
2006
fDate :
18-22 June 2006
Firstpage :
1
Lastpage :
7
Abstract :
A fault diagnosis system in a multilevel-inverter using a compact neural network is proposed in this paper. It is difficult to diagnose a multilevel-inverter drive (MLID) system using a mathematical model because MLID systems consist of many switching devices and their system complexity has a nonlinear factor. Therefore, a neural network classification is applied to the fault diagnosis of a MLID system. Multilayer perceptron (MLP) networks are used to identify the type and location of occurring faults from inverter output voltage measurement. The neural network design process is clearly described. The principal component analysis (PCA) is utilized to reduce the neural network input size. A lower dimensional input space will also usually reduce the time necessary to train a neural network, and the reduced noise may improve the mapping performance. The comparison between MLP neural network (NN) and PC neural network (PC-NN) are performed. Both proposed networks are evaluated with simulation test set and experimental test set. The PC-NN has improved overall classification performance from NN by about 5% points. The overall classification performance of the proposed networks is more than 90%. Thus, by utilizing the proposed neural network fault diagnosis system, a better understanding about fault behaviors, diagnostics, and detections of a multilevel inverter drive system can be accomplished. The results of this analysis are identified in percentage tabular form of faults and switch locations.
Keywords :
Fault diagnosis; multilevel inverter; neural network; principal component; Fault diagnosis; Inverters; Mathematical model; Multilayer perceptrons; Neural networks; Principal component analysis; Process design; Switches; Testing; Voltage measurement; Fault diagnosis; multilevel inverter; neural network; principal component;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Power Electronics Specialists Conference, 2006. PESC '06. 37th IEEE
ISSN :
0275-9306
Print_ISBN :
0-7803-9716-9
Type :
conf
DOI :
10.1109/PESC.2006.1712246
Filename :
1712246
Link To Document :
بازگشت