臺灣博碩士論文加值系統

中文摘要
本研究提出一種利用適應性階次分析與類神經網路於車輛故障診斷的專家系統。論文中所提出的系統架構主要可分為兩個主要階段。在第一階段，首先錄下引擎的聲音訊號並追蹤其訊號的頻率變化。藉由高解析度的適應性濾波器演算法，我們可求得聲音訊號中每一階次的能量。從階次圖中，我們可以看到代表各種不同故障點的訊號特徵。接著我們使用能量圖來正規化這些訊號的特徵並減少它們的資料量來提升運算效率。在第二階段中，利用類神經網路來訓練先前正規化後的特徵能量圖並加以辨別每個故障點。為了證明所提出的機率類神經對故障診斷的判別效果，我們將利用三種較傳統的類神經網路一起做比較，其中包括Hopfield，倒傳遞類神經與徑向基底方程類神經網路。由實驗結果得知，所提出的機率類神經網路在故障診斷系統中可達到最佳的效率與判別效果。

ABSTRACT
An expert system for fault diagnosis in vehicle using adaptive order tracking technique and artificial neural networks is presented in this paper. The proposed system can be divided into two parts. In the first stage, the engine sound emission signals are recorded and treated as the tracking of frequency-varying bandpass signals. Ordered amplitudes can be calculated with a high-resolution adaptive filter algorithm. The vital features of signals with various fault conditions are obtained and displayed clearly by order figures. Then the sound energy diagram is utilized to normalize the features and reduce computation quantity. In the second stage, the artificial neural network is used to train the signal features and engine fault conditions. In order to verify the effect of the proposed probability neural network (PNN) in fault diagnosis, three conventional neural networks that included the Hopfield neural network (HNN), back-propagation (BP) network and radial-basic function (RBF) network are compared with the proposed PNN network. The experimental results indicated that the proposed PNN network achieved the best performance in the present fault diagnosis system.

CONTENTS
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
FEATURE EXTRACTION USING ADAPTIVE ORDER TRACKING
2-1 Principle of Order Tracking 7
2-2 Energy Amplitude Diagram 11
CHAPTER 3
PRINCIPLE OF ARTIFICIAL NEURAL NETWORK 14
3-1 Back-Propagation Neural Network 18
3-2 Radial Basis Function Neural Network 27
3-3 Hopfield Neural Network 33
3-4 Probability Neural Network 40
CHAPTER 4
EXPERIMENTAL INVESTIGATION OF FAULT DIAGNOSIS SYSTEM
4-1 Experimental Procedure and Signal Processing 46
4-2 Result of Fault Diagnosis and Discussion 53
CHAPTER 5
CONCLUSIONS 62
REFERENCES 64

REFERENCES
[1]J. D. Wu, Y. H. Wang, 2007, ‘‘Development of an expert system for fault diagnosis in scooter engine platform using fuzzy-logic inference,’’ Expert Systems with Applications, Vol. 33(4), pp. 1063-1075.
[2]G. C. Luh, W. C. Cheng, 2005, “Immune model-based fault diagnosis,” Mathematics and Computers in Simulation, Vol. 67, pp. 515-539.
[3]F. Wen, C. S. Chang, 1998, “A new approach to fault diagnosis in electrical distribution networks using a genetic algorithm,” Artificial Intelligence in Engineering, Vol. 12, pp. 69-80.
[4]F. Kong, R. Chen, 2004, “A combined method for triplexpump fault diagnosis based on wavelet transform, fuzzy logic and neuro-networks,” Mechanical Systems and Signal Processing, Vol. 18, pp. 161-168.
[5]B. S. Yang, T. Han, J. L. An, 2004, “ART–KOHONEN neural network for fault diagnosis of rotating machinery,” Mechanical Systems and Signal Processing, Vol. 18, pp. 645-657.
[6]J. D. Wu, C. W. Huang, J. C. Chen, 2005, “An order-tracking technique for the diagnosis of faults in rotating machineries using a variable step-size affine projection algorithm,” NDT & E International, Vol. 38, pp. 119-127.
[7]M. Bai, J. Jeng, C. Chen, 2002, “Adaptive order tracking technique using recursive least-square algorithm,” ASME, Journal of Vibrations and Acoustics, Vol. 124(4), pp. 502-511.
[8]J. D. Wu, C. W. Huang, J. C. Chen, 2004, “An application of a recursive Kalman filtering algorithm in rotating machinery fault diagnosis,” NDT&E International, Vol. 37, pp. 411-419.
[9]M. Bai, J. Huang, M. Hong, F. Su, 2005, “Fault diagnosis of rotating machinery using an intelligent order tracking system,” Journal of Sound and Vibration, Vol. 280, pp. 699-718.
[10]D. Chen, W. J. Wang, 2002, “Classification of wavelet map patterns using multi-layer neural networks for gear fault detection,” Mechanical System and Signal Processing, Vol. 16(4), pp. 695-704.
[11]C. K. Sung, H. M. Tai, C. W. Chen, 2000, “Locating defects of a gear system by the technique of wavelet transform,” Mechanism and Machine Theory, Vol. 35, pp. 1169-1182.
[12]N. Baydar, A. Ball, 2001, “A comparative study of acoustic and vibration signals in detection of gear faults using Wigner-Ville distribution,” Mechanical System and Signal Processing, Vol. 15(6), pp. 1091-1107.
[13]J. Zou, J. Chen, 2004, “A comparative study on time-frequency feature of cracked rotor by Wigner-Ville distribution and wavelet transform.” Journal of Sound and Vibration, Vol.276, pp. 1-11.
[14]W. J. Staszewski, K. Worden, G. R. Tomlinson, 1997, “Time-frequency analysis in gear fault detection using the Wigner-Ville distribution and pattern recognition,” Mechanical System and Signal Processing, Vol. 11(5), pp.673-692.
[15]F. Y. Partovi, M. Anandaraian, 2002, “Classifying inventory using an artificial neural network approach,” Computer & Industrial Engineering, Vol. 41, pp. 389-404.
[16]M. N. S. Hadi, 2003, “Neural networks applications in concrete structure,” Computers and Structures, Vol. 81, pp. 373-381.
[17]B. Walczak, 1996, “Neural networks with robust backpropagation learning algorithm,” Analytica Chimica Acta, Vol. 322, pp. 21-29.
[18]T. Stubbings, H. Hutter, 1999, “Classification of analytical images with radial basis function networks and forward selection,” Chemometrics and Intelligent Laboratory Systems, Vol. 49, pp. 163-172.
[19]C. G. Looney, 2002, “Radial basis function link nets and fuzzy reasoning,” Neurocomputing, Vol. 48, pp. 489-509.
[20]W. Lai, P. W. Tse, G. Zhang, T. Shi, 2004, “Classification of gear faults using cumulants and the radial basis function network,” Mechanical System and Signal Processing, Vol. 18, pp. 381-389.
[21]S. Wang, 2005, “Classification with incomplete survey data: a Hopfield neural network approach,” Computers & Operations Research, Vol. 32, pp. 2583-2594.
[22]X. S. Yang, Q. Yuan, 2005, “Chaos and transient chaos in simple Hopfield neural networks,” Neurocomputing, Vol. 69, pp. 232-241.
[23]R. K. Brouwer, 1997, “Automatic growing of a Hopfield style network during training for classification,” Neural Networks, Vol. 10(3), pp. 529-537.
[24]M. Hajmeer, I. Basheer, 2002, “A probabilistic neural network approach for modeling and classification of bacterial growth/no-growth data,” Journal of Microbiological Methods, Vol. 51, pp. 217- 226.
[25]L. Rutkowski, 2004, “Adaptive probabilistic neural networks for pattern classification in time-varying environment,” IEEE Transactions on Neural Networks, Vol. 15(4), pp. 811-827.
[26]B. Karthikeyana, S. Gopalb, M. Vimala, 2005, “Conception of complex probabilistic neural network system for classification of partial discharge patterns using multifarious inputs,” Expert Systems with Applications, Vol. 29, pp. 953-963.
[27]L. Simon, M. N. Karim, 2001, “Probabilistic neural networks using Bayesian decision strategies and a modified Gompertz model for growth phase classification in the batch culture of Bacillus subtilis,” Biochemical Engineering Journal, Vol. 7, pp. 41-48.