臺灣博碩士論文加值系統

馬達在現今的科技發展中扮演著不可或缺的角色。若因馬達損壞造成機器故障或是產線停擺，其損失將無法估計。所以馬達的故障檢測與預防診斷技術將越受重視。現今馬達檢測方式主要又分為振動檢測(Vibration analysis)與馬達電流特徵分析MCSA(Motor Current Signature Analysis)。振動檢測技術雖然能立即察覺機器異常，但主要為局部性的損壞觀察。其檢測方式為侵入式之檢測，且在低轉速時較難觀察出異常。MCSA方面則可全面性觀察馬達故障，其檢測方式為非侵入式，且價格較振動檢測低廉許多，所以現今MCSA技術越來越受到業界歡迎。
本研究使用振動分析及電流特徵分析觀察轉動設備軸承隨時間的磨耗情形，並從電流訊號中挑選符合振動趨勢的特徵，以建立回歸方程式模型，並從中推估馬達軸承的狀況，在機器壞損前達到提前預防之動作。

The motor has played an indispensable role in the technological development since the Industrial Revolution. The motor damage or motor failure would cause the shutdown of the entire production line and result in huge loss. Therefore, the motor fault detection and preventive maintenance will attract more and more attentions. Nowadays, the motor detection methods are mainly divided into vibration analysis and MCSA (Motor Current Signature Analysis). Although the vibration analysis can detect the abnormality of the machine immediately, it is an intrusive detection method mainly for local damage observation. It is difficult to detect the abnormality at low rotation speed. On the other hand, the MCSA is non-intrusive and is more comprehensive in observing motor faults. Its price is much lower than the vibration detection. Therefore, MCSA technology has become more and more popular in the industry.
In this paper, the vibration and current analysis are used to observe the bearing wear condition of the rotating equipment over time. Moreover, the characteristics of the vibration trend not only are selected from the current signal to establish the regression model, but are also used to estimate the condition of the motor bearing to achieve pre-emptive action before the machine is damaged.

摘要 1
abstract 2
目錄 4
表目錄 8
圖目錄 9
壹、 緒論 1
1.1 研究動機 1
1.2 論文架構 1
貳、 文獻回顧 3
2.1 軸承特徵頻率與現實案例探討 3
2.2 研究現況 4
2.3 訊號分析 5
2.3.1. 振動訊號分析 5
2.3.2. 電流訊號分析 6
2.4 特徵提取與軸承損傷種類 7
2.5 人工類神經網絡(artificial neural network, ANN) 9
參、 實驗方法 10
3.1 傅立葉轉換分析 10
3.2 小波分析 10
3.2.1. 離散小波轉換(DWT) 11
3.2.2. 小波包分解(wavelet packet decomposition, WPD) 12
3.3 斜波失真率(total harmonic distortion, THD) 13
3.4 帶拒濾波器(notch filter) 14
3.5 特徵指標運算 15
3.6 馬達負載計算 19
3.6.1. 輸入功率法(input power measurements) 19
3.6.2. 線電流檢測法(line current measurements) 19
3.6.3. 轉速檢測法(the slip method) 20
3.7 P VALUE與共線性診斷 21
3.7.1. 機率密度值(probability density value, P value) 21
3.7.2. 共線性診斷 22
3.8 迴歸參數選取法(method of selection of predictors) 23
3.8.1. 向前選取法(forward selection) 23
3.8.2. 向後選取法(backward elimination) 24
3.8.3. 逐步迴歸選取法(stepwise regression) 24
3.8.4. 全部進入法(all enter) 25
3.9 人工神經網路（artificial neural network, ANN） 25
3.9.1. 非監督式學習網絡(unsupervised learning network) 25
3.9.2. 監督式學習網絡(supervised learning network) 25
肆、 實驗設置 29
4.1 實驗機台 29
4.2 實驗流程與步驟 33
伍、 實驗分析與討論 35
5.1 分析流程 35
5.2 數據量測與資料擷取 37
5.3 資料前處理 38
5.4 特徵指標運算 40
5.4.1. 時域 40
5.4.2. 頻域 42
5.4.3. 時頻域 43
5.5 特徵指標篩選與其建立迴歸方程式之比較 43
陸、 結論與未來展望 62
6.1 結論 62
6.2 未來展望 64
參考文獻 65
附錄一 70
附錄二 76

[1] W. T.Thomson andM.Fenger, “Current signature analysis to detect induction motor faults,” IEEE Ind. Appl. Mag., vol. 7, no. 4, pp. 26–34, 2001.
[2] M.Reliability, W.Group, P.Systems, R.Subcommittee, andE.Committee, “Report of Large Motor Reliability Survey of Industrial and Commercial Installations Parts I , II , and III,” vol. I, no. February 1987, pp. 853–872, 2007.
[3] N.Mehala, “Condition Monitoring and Fault Diagnosis of Induction Motor Using Motor Current Signature Analysis,” Electr. Eng., no. 2, p. 12, 2010.
[4] F.Immovilli, C.Bianchini, M.Cocconcelli, A.Bellini, andR.Rubini, “Bearing fault model for induction motor with externally induced vibration,” IEEE Trans. Ind. Electron., vol. 60, no. 8, pp. 3408–3418, 2013.
[5] L.Weili, X.Ying, S.Jiafeng, andL.Yingli, “Finite-Element Analysis of Field Distribution and Characteristic Performance of Squirrel-Cage Induction Motor With Broken Bars,” IEEE Trans. Magn., vol. 43, no. 4, pp. 1537–1540, 2007.
[6] G.Didier, E.Ternisien, O.Caspary, andH.Razik, “Fault detection of broken rotor bars in induction motor using a global fault index,” IEEE Trans. Ind. Appl., vol. 42, no. 1, pp. 79–88, 2006.
[7] A.Bellini, F.Immovilli, R.Rubini, andC.Tassoni, “Diagnosis of Bearing Faults of Induction Machines by Vibration or Current Signals: A Critical Comparison,” Ind. Appl. Soc. Annu. Meet. 2008. IAS ’08. IEEE, vol. 46, no. 4, pp. 1–8, 2008.
[8] L.Eren andM. J.Devaney, “Bearing Damage Detection via Wavelet Packet Decomposition of the Stator Current,” IEEE Trans. Instrum. Meas., vol. 53, no. 2, pp. 431–436, 2004.
[9] M.Blodt, P.Granjon, B.Raison, andG.Rostaing, “Models for bearing damage detection in induction motors using stator current monitoring,” IEEE Trans. Ind. Electron., vol. 55, no. 4, pp. 1813–1822, 2008.
[10] S.Singh, A.Kumar, andN.Kumar, “Motor Current Signature Analysis for Bearing Fault Detection in Mechanical Systems,” Procedia Mater. Sci., vol. 6, no. Icmpc, pp. 171–177, 2014.
[11] B. S.Yang andK. J.Kim, “Application of Dempster-Shafer theory in fault diagnosis of induction motors using vibration and current signals,” Mech. Syst. Signal Process., vol. 20, no. 2, pp. 403–420, 2006.
[12] J. L. H.Silva andA. J. M.Cardoso, “Bearing failures diagnosis in three-phase induction motors by extended Park’s Vector approach,” IECON Proc. (Industrial Electron. Conf., vol. 2005, pp. 2591–2596, 2005.
[13] K.Teotrakool, “Adjustable speed drive bearing fault detection via support vector machine incorporating feature selection using genetic algorithm,” no. December, 2007.
[14] Y.Cheng, “Vibration-based Bearing Failure Monitoring based on the Time-Frequency Transform Method,” 2014.
[15] I.Standard, “International Standard Time,” Science (80-. )., vol. ns-1, no. 6, pp. 159–160, 2006.
[16] M. D.Prieto, G.Cirrincione, A. G.Espinosa, J. A.Ortega, andH.Henao, “Bearing fault detection by a novel condition-monitoring scheme based on statistical-time features and neural networks,” IEEE Trans. Ind. Electron., vol. 60, no. 8, pp. 3398–3407, 2013.
[17] S. J.Lacey, “An Overview of Bearing Vibration Analysis,” Maint. Asset Manag., vol. 23, no. 6, pp. 32–42, 2008.
[18] E.Analysis, F.Diagnosis, andB.Bearings, “Application of Envelope Analysis for the Faults Diagnosis in Ball Bearings.,” 2005.
[19] F.Immovilli, M.Cocconcelli, A.Bellini, andR.Rubini, “Detection of generalized-roughness bearing fault by spectral-kurtosis energy of vibration or current signals,” IEEE Trans. Ind. Electron., vol. 56, no. 11, pp. 4710–4717, 2009.
[20] T.Surveillance, “INTERNATIONAL STANDARD Condition monitoring and diagnostics qualification and assessment of,” vol. 2014, 2014.
[21] H. A.Toliyat, S.Nandi, S.Choi, H.Meshgin-Kelk, andS.Nandi, “Fault Diagnosis of Electric Machines Using Techniques Based on Frequency Domain,” Electr. Mach., pp. 99–154, 2012.
[22] W.Hsu, C.Lan, M.Liu, andS.Chang, “Fault Signature Analysis of Industrial Machines,” vol. 2, pp. 1–6.
[23] W. T.Thomson andR. J.Gilmore, “MOTOR CURRENT SIGNATURE ANALYSIS TO DETECT FAULTS IN INDUCTION MOTOR DRIVES — FUNDAMENTALS , DATA INTERPRETATION , AND INDUSTRIAL CASE HISTORIES by and,” no. 1987, pp. 145–156, 2001.
[24] M.Riera-Guasp, J. A.Antonino-Daviu, andG. A.Capolino, “Advances in electrical machine, power electronic, and drive condition monitoring and fault detection: State of the art,” IEEE Trans. Ind. Electron., vol. 62, no. 3, pp. 1746–1759, 2015.
[25] M.Fenger, B. A.Lloyd, andW. T.Thomson, “Development of a tool to detect faults in induction motors via current signature analysis,” pp. 37–46, 2003.
[26] W. T.Thomson andM.Fenger, “Case histories of current signature analysis to detect faults in induction motor drives,” IEMDC 2003 - IEEE Int. Electr. Mach. Drives Conf., vol. 3, no. August, pp. 1459–1465, 2003.
[27] H.Henao et al., “Trends in Fault Diagnosis for Electrical Machines: A Review of Diagnostic Techniques,” IEEE Ind. Electron. Mag., vol. 8, no. 2, pp. 31–42, 2014.
[28] 曹文昌, “Fault diagnosis of ball bearings using ML methods.pdf.”
[29] A.Phinyomark, S.Hirunviriya, C.Limsakul, andP.Phukpattaranont, “Evaluation of EMG feature extraction for hand movement recognition based on Euclidean distance and standard deviation,” Electr. Eng. Comput. Telecommun. Inf. Technol. (ECTI-CON), 2010, pp. 856–860, 2010.
[30] SKF軸承公司, “SKF 軸承尺寸的選擇,” p. 32 ، ص 117, 1386.
[31] W.Zhou, T. G.Habetler, andR. G.Harley, “Bearing condition monitoring methods for electric machines: A general review,” 2007 IEEE Int. Symp. Diagnostics Electr. Mach. Power Electron. Drives, SDEMPED, pp. 3–6, 2007.
[32] A.Vencl andA.Rac, “Diesel engine crankshaft journal bearings failures: Case study,” Eng. Fail. Anal., vol. 44, pp. 217–228, 2014.
[33] M. R.Hoeprich, “Rolling Element Bearing Fatigue Damage Propagation,” J. Tribol., vol. 114, no. 2, p. 328, 2008.
[34] B.Li, S.Member, M.Chow, S.Member, Y.Tipsuwan, andJ. C.Hung, “Neural-Network-Based Motor Rolling,” vol. 47, no. 5, pp. 1060–1069, 2000.
[35] 曾顗恆, “國立臺灣科技大學 機械工程系 碩士學位論文 基於音頻分析之刀具磨耗監控與預測 Tool Wear Monitoring and Prediction based on Acoustic Analysis,” 2018.
[36] C.Dr John Cheng, CEng, CEM, CEA, “IEEE_STD_519-2014,” 2014.
[37] 陳明周, “1. 濾波器的基本分類.” [Online]. Available: http://designer.mech.yzu.edu.tw/articlesystem/article/compressedfile/(2002-09-24) 主動式濾波器簡介.pdf.
[38] J.Li et al., “Research on rolling bearing fault diagnosis based on multi-dimensional feature extraction and evidence fusion theory,” R. Soc. Open Sci., vol. 6, no. 2, 2019.
[39] E. T.Esfahani, S.Wang, andV.Sundararajan, “Multisensor wireless system for eccentricity and bearing fault detection in induction motors,” IEEE/ASME Trans. Mechatronics, vol. 19, no. 3, pp. 818–826, 2014.
[40] I.Of, D.Presented, T. A.Faculty, X. H.Fulfillment, andD.Doctor, “DIAGNOSTICS OF AIR GAP ECCENTRICITY IN CLOSEDLOOP DRIVE-CONNECTED INDUCTION MOTORS,” Comput. Eng., no. May, 2005.
[41] M. A.Alsaedi, “Fault Diagnosis of Three-Phase Induction Motor: A Review,” Optics, vol. 4, no. 1, p. 1, 2017.
[42] US Department of Energy, “Determining Electric Motor Load Ranges,” 1997.
[43] T.Huang, “統計學:大家都喜歡問的系列-p值是什麼.” [Online]. Available: https://medium.com/@chih.sheng.huang821/統計學-大家都喜歡問的系列-p值是什麼-2c03dbe8fddf.
[44] “Multiple Regression Analysis,” 複迴歸分析簡介 (Multiple Regres. Anal.
[45] B. M.Wilamowski andHao Yu, “Improved Computation for Levenberg–Marquardt Training,” IEEE Trans. Neural Networks, vol. 21, no. 6, pp. 930–937, 2010.
[46] M.TECH, MAC TECH 振動感測器(Vibration Sensor MS-VS & MD)型錄, no. c. pp. 2–6.