臺灣博碩士論文加值系統

本研究論文中主要是提出一種利用離散小波轉換以及適應性類神經模糊推論系統所建構而成之智慧型車用發電機故障診斷系統。當車輛充電系統失效，一般傳統發電機的故障警示器通常利用一組警示燈來提醒駕駛者，然而，該警示器只能粗略的告知發電機故障狀況與否。在本研究中，將提出利用發電機不同的故障輸出電壓波形來進行發電機之故障診斷，該系統將以離散小波轉換為基礎之能量頻譜特徵擷取方法以及統計學手法來減少龐大且複雜的特徵向量資料，並且為了能夠準確的辨識各故障訊號，我們將提出適應性類神經模糊推論系統來進行數據的分類，並輔以倒傳遞類神經、廣義回歸類神經系統進行測試比對。最後由實驗平台的結果證實離散小波轉換技術與適應神經模糊推論系統對於發電機故障診斷具有相當的潛在發展的可能性。

This paper describes a fault diagnosis system for automotive generators using discrete wavelet transform (DWT) and an artificial neural network. Conventional fault indications of automotive generators generally use an indicator to inform the driver when the charging system is malfunction. But this charge indicator tells only if the generator is normal or in a fault condition. In the present study, an automotive generator fault diagnosis system is developed and proposed for fault classification of different fault conditions. The proposed system consists of feature extraction using discrete wavelet analysis to reduce complexity of the feature vectors together with classification using the artificial neural network technique. In the output signal classification, the back-propagation neural network (BPNN), generalized regression neural network (GRNN) and adaptive neuro-fuzzy inference system (ANFIS) are used to classify and compare the synthetic fault types in an experimental engine platform. The experimental results indicate that the proposed fault diagnosis is effective and can be used for automotive generators of various engine operating conditions.

ABSTRACT (CHINESES) i
ABSTRACT (ENGLISH) ii
ACKNOWLEDGEMENT iii
CONTENTS iv
LIST OF FIGURES vi
LIST OF TABLES viii
LIST OF SYMBOLS ix

CHAPTER 1
INTRODUCTION
1-1 Introduction of the Thesis 1
1-2 Literature Review 4
1-3 Overview of this Thesis 6

CHAPTER 2
PRINCIPLE OF WAVELET ANALYSIS AND FEATURE EXTRACTION
2-1 Background of Wavelet Transform 7
2-2 Principle of Discrete Wavelet Transform 10
2-3 Principle of Parseval's Theorem 14

CHAPTER 3
PRINCIPLE OF NEURAL NETWORK CLASSIFIERS
3-1 Principle of Back-Propagation Neural Network 16
3-2 Principle of Generalized Regression Neural Network 20
3-3 Principle of Adaptive Neuro-Fuzzy Inference System 23

CHAPTER 4
EXPERIMENTAL INVESTIGATION AND ANALYSIS
4-1 Experimental Arrangement 28
4-2 Recognition of Extraction Features 32
4-3 Experimental Result and Classification 45

CHAPTER 5
CONCLUSIONS 60

REFERENCES 62

LIST OF FIGURES
Figure. 1.1 Distorted signal of generator in five generator conditions, Fig (a) to (e) are the experimental signals; Fig (f) to (j) are the theoretical signals. 3
Figure. 2.1 Principle of wavelet transform technique. 9
Figure. 2.2 Discrete wavelet in time-scale space on a dyadic grid. 12
Figure. 2.3 Principle of multi-resolution analysis. 13
Figure. 3.1 Architecture of the BPNN. 19
Figure. 3.2 Structure of GRNN. 22
Figure. 3.3 Architecture of ANFIS. 27
Figure. 4.1 Experimental procedure of generator fault diagnosis system 30
Figure. 4.2 Block diagnosis of automotive generator fault diagnosis system. 31
Figure. 4.3 DWT of voltage signal in normal condition. 33
Figure. 4.4 DWT of voltage signal in voltage regulator disconnect condition. 34
Figure. 4.5 DWT of voltage signal in one phase stator coil fault condition. 35
Figure. 4.6 DWT of voltage signal in one diode fault condition. 36
Figure. 4.7 DWT of voltage signal in two diodes fault condition. 37
Figure. 4.8 Energy distribution pattern in normal condition. 38
Figure. 4.9 Energy distribution pattern in voltage regular disconnected condition. 39
Figure. 4.10 Energy distribution pattern in one phase stator coil fault condition. 40
Figure. 4.11 Energy distribution pattern in one diode fault condition. 41
Figure. 4.12 Energy distribution pattern in two diodes fault condition. 42
Figure. 4.13 Energy distribution of different faults using db4 wavelet coefficient at various engine operation conditions: (A) idle, (B) 1500rpm, (C) 2000rpm, (D) 2500rpm. 43
Figure. 4.14 Energy distribution of different faults using db4 wavelet coefficients at various engine operation conditions: (A) idle, (B) 1500 rpm, (C) 2000 rpm, (D) 2500 rpm. 44
Figure. 4.15 Average result of different wavelet coefficients using BPNN and GRNN. 49
Figure. 4.16 Triangular-shaped built-in membership function. 51
Figure. 4.17 Gaussian curve built-in membership function.52
Figure. 4.18 Generalized bell-shaped built-in membership function. 53
Figure. 4.19 Initial and final generalized bell membership function of input D3, D4, D5 and A9. 54
Figure. 4.20 Initial and final generalized bell membership function of input A9. 55
Figure. 4.21 Adaptation of parameter steps of ANFIS. 56
Figure. 4.22 Curve of network error convergence of ANFIS. 57

LIST OF TABLES
Table 4.1
Total record data for each distorted signals. 47
Table 4.2
Performance of test results in various engine speeds. 48
Table 4.3
Comparison of recognition time. 50
Table 4.4
Performance of the final convergence value. 58
Table 4.5
Performance of identification rate. 59

[1] Hollembeak, B. (1997). Automotive Electricity & Electronics. New York: Delmar Publisher.
[2] Corinthios, M. J. (1971). A fast Fourier transform for high-speed signal processing. IEEE Transaction on Computer C-20, 843-846.
[3] Portnoff, M. (1980). Time-frequency representation of digital signals and system based on short-time Fourier analysis. IEEE Transactions on Acoustic, Speech, and Signal Processing ASSP-28, 55-69.
[4] Staszewski, W. J., Worden, K., & Tomlinson, G.R. (1997). Time-frequency analysis in gearbox fault detection using the wiger-ville distribution and pattern recognition. Mechanical Systems and Signal Processing, 11(5), 673-692.
[5] Wu, J. D., & Chiang, P. H. (2008). Application of Wigner-Ville distribution and probability neural network for scooter engine fault diagnosis. Expert Systems with Applications, 36, 2187-2199.
[6] Poisson, O., Rioual, P., & Meunier, M. (1999). New signal processing tools applied to power quality analysis. IEEE Transactions on Power Delivery 14(2), 561-566.
[7] Shi, Z., Wei, G. W., Kouri, D. J., Hoffman, D. K., & Bao, Z. (2001). Lagrange wavelets for signal processing. IEEE Transactions. Image Processing 10, 1488-1508.
[8] Mohamed, E. A., Abdelaziz, A. Y., & Mostafa, A. S. (2005). A neural network-based scheme for fault diagnosis of power transforms. Electric Power System Research, 75, 29-39.
[9] Kim, Y. J., Kim, J. M., Lee, S. H., & Jung, T. U. (2006). Detection of shorted-turns in the rotor winding of cylindrical synchronous using discrete wavelet transform. Proceedings of Applied Power Electronics Conference and Exposition. 1582-1586. Dallas.

[10] Huang, S. J., & Hsieh, C. T. (2000). Application of continuous wavelet transform for study of voltage flicker-generated signals. IEEE Transactions. Acrosp. Electron. Syst., 36, 925-932.
[11] Kandaswamy, A., Sathish Kumar, C., Ramanathan, Rm. Pl., Jayaraman, S., & Malmurugan, N. (2004). Computers in Biology and Medicine, 34, 523-537.
[12] Wu, J. D., & Lin, B. F. (2008). Speaker identification using discrete wavelet packet transform technique with irregular decomposition. Expert Systems with Applications, 36, 3136-3143.
[13] Angrisani, L., Apuzzo, M. D., & Testa, A. (1998). A measurement method based on the wavelet transform for power quality analysis. IEEE Transaction on Power Delivery 13(4), 990-998.
[14] Butler-Purry, K. L., & Bagriyanik, M. (2003). Characterization of transients in transformers using discrete wavelet transforms. IEEE Transaction on Power Delivery 18(2), 648-656.
[15] Kandaswamy, N., Kumar, C S., Ramanathan, R. P., Jayaraman, S., & Malmurugan, N. (2004). Neural classification of lung sounds using wavelet coefficients. Computers in Biology and Medicine, 34(6), 523-537.
[16] Varshney, K. and Panigrahi, P. K. (2005). Artificial neural network control of a heat exchanger in a closed flow air circuit. Applied Soft Computing, 5, 441–465.
[17] Lei, Y., He, Z., Zi, Y. and Hu, Q. (2007). Fault diagnosis of rotating machinery based on multiple ANFIS combination with Gas. Mechanical Systems and Signal Processing, 21, 2280–2294.
[18] Jang, J.-S.R. (1993). ANFIS: adaptive network based fuzzy inference system. IEEE Transaction on Systems, Man, and Cybernetics, 23(3), 665-685
[19] Lo, S. P. (2003). An adaptive-network based fuzzy inference system for prediction of workpiece surface roughness in end milling. Journal of Materials Processing Technology, 142, 665-675.
[20] Chang, F. J., & Chang, Y. T. (2006). Adaptive neuro-fuzzy system for prediction of water level in reservoir. Advances in Water Resources, 29, 1-10.
[21] Guler, I., & Ubeyli, E. D. (2005). Adaptive neuro-fuzzy system for classification of EEG signals using wavelet coefficients. Journal of Neuroscience Methods, 148, 113-121.
[22] Subasi, A., (2007). Application of adaptive neuro-fuzzy inference system for epoliptic seizure detection using wavelet feature extraction. Computers in Biology and Medicine, 37, 227-244.
[23] Yazc, B. and Kliman, G. B. (1999). An adaptive statistical time-frequency method for detection of broken bars and bearing faults in motors using stator current. IEEE Transactions on Industry Applications, 35, 442-452.
[24] Mallat, S. G. (1989). A theory for multiresolution signal decomposition: The wavelet representation. IEEE Transactions on Pattern Analysis and Machine Intelligence 11(7), 674-693.
[25] Gaing, Z. L. (2004). Wavelet-based neural network for power disturbance recognition and classification. IEEE Transactions on Power Delivery 19, 1560-1568.
[26] Wu, J. D., & Liu, C. H. (2007). Investigation of fault diagnosis using discrete wavelet transform and neural network. Expert Systems with Applications, article in press.
[27] Rumelhart, D. E., Hinton, G. E. and Williams, R. J. (1986). Learning Internal Representations by Error Propagation. Paralled Distributed Processing. Explorations in the Microstructure of Cognition, 1, 318–362.
[28] Cigizoglu, H. K., & Alp, M. (2006). Generalized regression neural network in modeling river sediment yield. Advances in Engineering Software 37, 63-68.
[29] Specht, D. F. (1991). A general regression neural network. IEEE Transactions on Neural Network, 2(6), 568-576.
[30] Yibin, S., & Ying, R. (2005). A predictive model of nonlinear system based on Generalized Regression Neural Network. ICNN&B ’05. International conference on neural networks and brain 3, 2009-2012.
[31] Zadeh, L. A. (1965). Fuzzy sets. Information and Control, 8, 338-353
[32] Wu, J. D., & Hsu, C. C. (2009). Fault gear identification using vibration signal with discrete wavelet transform technique and fuzzy-logic inference. Expert System with Applications, 36, 3785-3794.