臺灣博碩士論文加值系統

本文將模糊類神經網路應用於齒輪轉子系統的故障診斷，根據既有的文獻與實驗數據建立齒輪故障類型與頻譜特徵關係，作為貼近度診斷與類神經網路學習的依據。文中將具有四項典型故障的齒輪進行振動量測：(1)齒輪偏心(2)軸不平行(3)斷齒(4)磨損。用細化頻譜分析技術提取特徵信號，經過三級隸屬度函數分級，再以模糊類神經網路進行診斷，診斷後的結果與貼近度診斷、類神經網路診斷進行比較。探討在齒輪囓合的複雜頻譜中，模糊類神經網路能作出合理與準確的診斷。

This paper applies fuzzy neural network (FNN) in the fault diagnosis of the gear-rotor system. According to the document and experiment data, the relationship between fault and frequency spectrum is built up as the rule of approximate reasoning diagnosis and the training data of NN. In this paper, gears which have the four typical faults will be taking into vibrating examining : (1)Gear skew (2)Shaft not parallel (3) Tooth breakage (4)wear. Picking up the characteristic signals by using the technique of analysing spectrums . After classifing by membership function, and detect this classified data in NN. Comparing with the detect result of FNN, NN, and approximate reasoning. Verifying that FNN could make rational and accurate diagnosis from the complicated spectrum.

中文摘要......................................................I
英文摘要.....................................................II
致謝........................................................III
目錄.........................................................IV
表目錄.......................................................VI
圖目錄......................................................VII
第一章 導論
1.1 故障診斷簡介....................................1
1.2 文獻回顧........................................1
1.3 研究目的與方法..................................3
第二章 齒輪故障類型與特徵關係之建立
2.1 齒輪的振動頻率..................................4
2.2 常見齒輪故障類型................................6
2.3 信號提取........................................9
2.4 齒輪故障類型與特徵關係.........................11
2.5 振動分析方法...................................12
2.5.1 時域分析............................12
2.5.2 頻域分析............................13
2.5.3 倒頻譜分析..........................13
第三章 診斷原理與應用方法
3.1 貼近度診斷.....................................15
3.2 類神經網路診斷.................................15
3.3 模糊類神經網路診斷.............................17
3.3.1 模糊隸屬度函數......................17
3.3.2 模糊類神經網路架構..................18
3.3.3 訓練與診斷..........................19
第四章 實例測試
4.1 診斷實例一.....................................22
4.1.1 貼近度診斷..........................24
4.1.2 類神經網路診斷......................24
4.1.3 模糊類神經網路診斷..................25
4.1.4 討論................................26
4.2 診斷實例二.....................................30
4.2.1 貼近度診斷..........................32
4.2.2 類神經網路診斷......................33
4.2.2 模糊類神經網路診斷..................33
4.2.4 討論................................33
4.3 診斷實例三.....................................37
4.3.1 貼近度診斷..........................39
4.3.2 類神經網路診斷......................40
4.3.3 模糊類神經網路診斷..................41
4.3.4 討論................................41
4.4 診斷實例四.....................................44
4.4.1 貼近度診斷..........................46
4.4.2 類神經網路診斷......................46
4.4.3 模糊類神經網路診斷..................46
4.4.4 討論................................47
第五章 結論..................................................51
參考文獻......................................................52
附錄一、正常齒輪狀態下振動量測頻譜............................53
附錄二、機台共振頻率響應......................................56
個人簡歷......................................................60
表2.1 故障特徵矩陣.........................................12
表3.1 頻譜特徵與故障類型關係之模糊矩陣表...................20
表4.1 試驗齒輪的主要參數(mm)...............................22
表4.2 軸承型號.............................................22
表4.3 工作轉速.............................................22
表4.4 頻譜特徵參數值.......................................23
表4.5 診斷結果.............................................27
表4.6 診斷結果.............................................28
表4.7 診斷結果.............................................29
表4.8 工作轉速.............................................30
表4.9 頻譜特徵參數值.......................................31
表4.10 診斷結果.............................................34
表4.11 診斷結果.............................................35
表4.12 診斷結果.............................................36
表4.13 工作轉速.............................................37
表4.14 頻譜特徵參數值.......................................38
表4.15 診斷結果.............................................41
表4.16 診斷結果.............................................42
表4.17 診斷結果.............................................43
表4.18 工作轉速.............................................44
表4.19 頻譜特徵參數值.......................................45
表4.20 診斷結果.............................................48
表4.21 診斷結果.............................................49
表4.22 診斷結果.............................................50
圖2.1 齒輪偏心特徵頻譜......................................7
圖2.2 軸不平行特徵頻譜......................................7
圖2.3 斷齒特徵頻譜..........................................7
圖2.4 磨損特徵頻譜..........................................7
圖2.5 內環損傷特徵頻譜......................................8
圖2.6 外環損傷特徵頻譜......................................8
圖2.7 滾珠損傷特徵頻譜......................................8
圖2.8 實驗架設..............................................9
圖2.9 齒輪轉子系統..........................................9
圖2.10 信號提取流程圖.......................................11
圖3.1 類神經網路架構.......................................16
圖3.2 三級模糊隸屬度函數...................................18
圖3.3 模糊類神經網路架構...................................19
圖4.1 實驗裝置圖...........................................21
圖4.2 齒輪偏心示意圖.......................................23
圖4.3 頻譜圖...............................................24
圖4.4 診斷結果.............................................27
圖4.5 診斷結果.............................................28
圖4.6 診斷結果.............................................29
圖4.7 軸不平行示意圖.......................................30
圖4.8 頻譜圖...............................................31
圖4.9 診斷結果.............................................34
圖4.10 診斷結果.............................................35
圖4.11 診斷結果.............................................36
圖4.12 齒輪斷齒示意圖.......................................37
圖4.13 頻譜圖...............................................38
圖4.14 診斷結果.............................................41
圖4.15 診斷結果.............................................42
圖4.16 診斷結果.............................................43
圖4.17 磨損示意圖...........................................44
圖4.18 頻譜圖...............................................44
圖4.19 診斷結果.............................................48
圖4.20 診斷結果.............................................49
圖4.21 診斷結果.............................................50

[1] R.B.Randall,“A new method of modeling gear faults,”Journal of Mechanical Design, Vol.104, pp.259-267, 1982.
[2] Randall, R B, Hee, J“Cepstrum analysis,”Wireless World, Vol.88, pp.77-80, 1982.
[3] Ming Xie, Kang Ding,“Correction for the frequency, amplitude and phase in FFT of harmonic signal,”Mechanical System and Signal Processing, Vol.10, pp.211-221, 1996.
[4] F. Filippetti, G. Franceschini, C. Tassoni, P. Vas,“Recent Developments of Induction Motor Drives Fault Diagnosis Using AI Technique,”IEEE Transactions on Industrial Electronics, Vol.47, pp. 994 – 1004, 2000.
[5] L.A. Zadeh, “Fuzzy Sets,”Information Contr., Vol.8, pp. 338-353, 1965
[6] H.J. Cho, J.K. Park,“An Expert System for Fault Section Diagnosis of Power Systems Using Fuzzy Relations,”IEEE Transactions on Power Systems, Vol. 12, pp. 342 – 348, 1997.
[7] G. Goddu, B. Li, M.Y. Chow, J.C. Hung,“Motor Bearing Fault Diagnosis by a Fundamental Frequency Amplitude Based Fuzzy Decision System,”Proceedings of the 24th Annual Conference of the IEEE, Vol. 4, pp. 1961 - 1965, 1998.
[8] D.M. Xie, X. Song, H.L. Zhou, M.W. Guo,“Fuzzy Vibration Fault Diagnosis System of Steam Turbo-Generator Rotor,”Proceedings of International Conference on Machine Learning and Cybernetics, Vol.1, pp. 411 – 415, 2002.
[9] W.S. McCulloch, W. Pitt,“A Logical Calculus of the Ideas Immanent in Nervous Activity,”Bulletin of Mathematical Biophysics, Vol.5, pp.115-133, 1943.
[10] D.E. Rumelhart, G.E. Hinton, R.J. Williams,“Learning Representations by Back- Propagating Errors, ” Nature, Vol. 323, pp. 533-536, 1986.
[11] A. Fanni, A. Giua, E. Sandoli,“Neural Networks for Multiple Fault Diagnosis in Analog Circuits,”The IEEE International Workshop on Defect and Fault Tolerance in VLSI Systems, pp.303 – 310, 1993
[12] Z.E. Aygen, S. Seker, M. Bagnyanik, F.G. Bagnyanik, E. Ayaz,“Fault Section Estimation in Electrical Power Systems Using Artificial Neural Network Approach,”Transmission and Distribution Conference of IEEE, Vol. 2, pp.466 - 469, 1999.