Fault Classification Method for Inverter Based on Hybrid Support Vector Machines and Wavelet Analysis

다국어 초록 (Multilingual Abstract)

A new classification method for fault waveform is proposed based on discrete orthogonal wavelet transform (DOWT) and hybrid support vector machine (hybrid SVM) for fault type of a three-phase voltage inverter. The waveforms of output voltage obtained from the faulty inverter are decomposed by DOWT into wavelet coefficient matrices, through which we can obtain singular value vectors acted as features of time-series periodic waveforms. And then a multi-classes classification method based on a new Huffman Tree structure is presented to realize 1-v-r SVM strategy. The extracted features are applied to hybrid SVM for determining fault type. Compared to employing the structure based on ordinary binary tree, the superiority of the proposed SVM method is shown in the success of fault diagnosis because the average Loo-correctness of the SVM based on Huffman tree structure exceed the general SVM 3.65%, and the correctness reaches 99.6%.

참고문헌 (Reference)

1 V. Vapnik, "The Nature of Statistical Learning Theory" Springer 128-136, 1995

2 S. F. Yuan, "Support vector machines- based fault diagnosis for turbo-pump rotor" 20 (20): 939-952, 2006

3 V. Vapnik, "Statistical Learning Theory" Wiley 1998

4 Zhi-kun Hu, "Sequences Feature Vectors Extracting Method for Similarity Measurement Based on Wavelet and Matrix Transforming" 제어·로봇·시스템학회 8 (8): 250-256, 2010

5 C. Goutte, "Note on free lunches and crossvalidation" 9 (9): 1245-1249, 1997

6 S. X. Ding, "Model-based Fault Diagnosis Techniques: Design Schemes, Algorithms, and Tools" Springer 2008

7 F. Zhang, "Matrix Theory: Basic Result and Techniques" Springer 1998

8 P. Lingras, "Interval set representations of 1-v-r support vector machine multi-classifiers" 1 : 193-198, 2005

9 Atthapol Ngaopitakkul, "Internal Fault Classification in Transformer Windings using Combination of Discrete Wavelet Transforms and Back-propagation Neural Networks" 제어·로봇·시스템학회 4 (4): 365-371, 2006

10 W. Li, "Integrated design of an observer- based fault detection system over unreliable digital channels" 2710-2715, 2008

11 G. Gao, "Hybrid support vector machines-based multi-fault classification" 17 (17): 246-250, 2007

12 K. C. Franky, "Haar wavelets for efficient similarity search of timeseries: with and without time warping" 15 (15): 686-705, 2003

13 D. Groutage, "Feature sets for nonstationary signals derived form moments of singular value decomposition of Cohen-Posch distributions" 48 (48): 1498-1503, 2006

14 S. Lina, "Extraction of Shell Texture Feature of Coscinodiscus for Classification Based on Wavelet and PCA" IEEE 2009

15 R. Agrawall, "Efficient similarity search in sequence databases" 69-84, 1993

16 D. Rafiei, "Efficient retrieval of similar time sequences using DFT" 249-257, 1998

17 S. R. Samantaray, "Distance relaying for transmission line using support vector machine and radial basis function neural network" 29 (29): 551-556, 2007

18 김대진, "Constructing support vector machine ensemble" 36 (36): 2757-2767, 200301

19 C. Lin, "A complex texture classification algorithm based on gabor-type filtering cellular neural networks and self-organized fuzzy inference neural networks" 3942-3945, 2005