在現今工業裡，高壓馬達為不可或缺之動力來源，高壓馬達具壽
命長、高能效、低振動噪音與高穩定等特性，而高壓馬達常需長期運
轉以保持經濟效能，因此如何維護高壓馬 達便是一重要課題。現今
工廠或電廠大多採定期性保養之維護策略，雖可降低故障發生機率，
但無法即時顯示高壓馬達潛在的運轉狀態。如能及早預測高壓馬達運
轉狀態，事先預防，即能大大降低維修成本，與避免重大危害發生。
本論文致力於建置一基於電氣訊號之主動式高壓馬達運轉狀態
監測方法。首先利用測量平台擷取在一電廠中運轉之高壓馬達三線電
壓與三線電流，再從資料庫中抓取一天之資料做為正常狀態。因未有
高壓馬達危險運轉狀態資料，本研究將正常狀態資料加入加成性白高
斯雜訊與線性放大，合成警戒與危險狀態資料，以此做案例分析。接
下來計算國際規範中相關電氣指標，透過主成份分析萃取出數量最
少，資訊量最多之特徵指標；以萃取完之特徵指標資料集做為輸入，
運用模糊C 均值分群法將資料分群，即區分資料所屬狀態，最後解模
糊化，將各資料點以百分比顯示運轉狀態，供使用者參考高壓馬達運
轉狀態，以做出最適合之維護決策。

In today's industry, high-voltage motors are indispensable sources of power. There are some characteristics about high-voltage motors, like long life cycle, high energy efficiency, low vibration noise and high stability. High-voltage motors usually need long-term operation to maintain economic efficiency. Therefore, how to maintain high-voltage motors is an important issue. Most of today's factories or electric power plants adopt a maintenance strategy for predetermined maintenance, also known as time-based maintenance (TBM). Although the probability of failure can be reduced, the potential operation status of the high-voltage motor cannot be displayed immediately. If the operation status of the high-voltage motor can be predicted early and prevented in advance, the maintenance cost can be greatly reduced, and major accidents can be avoided.
This thesis is dedicated to the establishment of a proactive high-voltage motor operation condition monitoring method based on electric signals. Firstly, the three-line voltage and current signal of the high-voltage motor running in an electric power plant are captured by the measuring platform, and the one-day data of normal operation is taken from the database. Because there is no dangerous operation data of the high-voltage motor, this study adds additive white Gaussian noise (AWGN) and linear amplification on normal state data, synthesizing warning and dangerous state data, and makes a case study. Next, calculate the relevant electrical indexes in the international standard, and then extract the least number of characteristic indexes with the most structure information through the principal component analysis (PCA). Further, we use the extracted characteristic indexes dataset as the inputs, and employ the fuzzy C-means (FCM) clustering method to cluster the data, that is, distinguish the various operation states of the motor. Finally, the data is defuzzified, and the data points are displayed in percentage for the user to refer to the high-voltage motor operating state to make the most suitable maintenance decision.

Deutsches Institut fu ̈r Normung, DIN EN 13306: Maintenance. Maintenance terminology, 2010.

Diego Coronado and Katharina Fischer, "Condition Monitoring of Wind Turbines: State of the Art, User Experience and Recommendation," Fraunhofer Institute for Wind Energy and Energy System Technology IWES, January 2015.

F. Filippetti, G. Franceschini, C. Tassoni and P. Vas, "Recent developments of induction motor drives fault diagnosis using AI techniques," IEEE Transactions on Industrial Electronics, vol. 47, no. 5, pp. 994-1004, Oct. 2000.

Z. Geng, J. Chen and Y. Han, "Energy Efficiency Prediction Based on PCA-FRBF Model: A Case Study of Ethylene Industries," IEEE Transactions on Systems, Man, and Cybernetics: Systems, vol. 47, no. 8, pp. 1763-1773, Aug. 2017.

Zhou Yang, Xiqiao Lin, Wenqian Jiang and Gang Li, "An electricity data cluster analysis method based on SAGA-FCM algorithm," 2017 IEEE 14th International Conference on Networking, Sensing and Control (ICNSC), Calabria, Italy, May 2017, pp. 389-393.

陳俊毅，「具狀態監測與故障診斷功能之馬達雲系統之研發」，碩士論文，國立臺灣科技大學電機工程系，2018年。

S. Nandi, H. A. Toliyat and X. Li, "Condition Monitoring and Fault Diagnosis of Electrical Motors- A Review," IEEE Transactions on Energy Conversion, vol. 20, no. 4, pp. 719-729, Dec. 2005.

W. T. Thomson and M. Fenger, "Current signature analysis to detect induction motor faults," IEEE Industry Applications Magazine, vol. 7, no. 4, pp. 26-34, July-Aug. 2001.

NEMA Std. MG1, "Motors and Generators," 2009.

IEEE Std. 141, "IEEE Recommended Practice for Electric Power Distribution for Industrial Plants," 1993.

IEEE Std. 112, "IEEE Standard Test Procedure for Polyphase Induction Motors and Generators," 2004.

IEC 60034-1, "Rotating electrical machines, " 2004.

IEC 60034-26, "Effects of unbalanced voltages on the performance of three-phase cage induction motors," 2006.

Gianfranco Chicco, Petru Postolache, Cornel Toader, "Triplen harmonics: Myths and reality," Electric Power Systems Research, vol. 81, no. 7, pp. 1541-1549, 2011.

Emadi, Ali. Energy-Efficient Electric Motors, Revised and Expanded. CRC Press, 2018.

IEEE Std. 519, "IEEE Recommended Practices and Requirements for Harmonic Control in Electrical Power Systems," 2014.

The U.S. Department of Energy Motor. (2007, May). Determining Electric Motor Load and Efficiency. Retrieved July 2, 2019, from Motor Challenge Website via GPO Access: https://www.energy.gov/sites/prod/files/2014/04/f15/10097517.pdf.

Rao, Kamisetty Ramamohan, Do Nyeon Kim, and Jae Jeong Hwang. Fast Fourier transform-algorithms and applications. Springer Science & Business Media, 2011.

S. B. Lee et al., "Identification of false rotor fault indications produced by on-line MCSA for medium voltage induction machines," 2015 61st IEEE Pulp and Paper Industry Conference (PPIC), Milwaukee, WI, USA, June 2015, pp. 1-9.

T. Yang, H. Pen, Z. Wang and C. S. Chang, "Feature Knowledge Based Fault Detection of Induction Motors Through the Analysis of Stator Current Data," IEEE Transactions on Instrumentation and Measurement, vol. 65, no. 3, pp. 549-558, March 2016.

林芝以，「運用電氣訊號於感應馬達狀態監測與故障診斷之研究」，碩士論文，國立臺灣科技大學電機工程系，2018年。

S. Das, P. Purkait and S. Chakravorti, "Characterization of short circuit faults and incipient insulation degradation between stator winding turns of induction motor," 2013 IEEE 1st International Conference on Condition Assessment Techniques in Electrical Systems (CATCON), Kolkata, INDIA, Dec. 2013, pp. 54-59.

W. T. Thomson, "On-line MCSA to diagnose shorted turns in low voltage stator windings of 3-phase induction motors prior to failure," IEMDC 2001. IEEE International Electric Machines and Drives Conference (Cat. No.01EX485), Cambridge, MA, USA, June 2001, pp. 891-898.

B. Li, M. -Y. Chow, Y. Tipsuwan and J. C. Hung, "Neural-network-based motor rolling bearing fault diagnosis," IEEE Transactions on Industrial Electronics, vol. 47, no. 5, pp. 1060-1069, Oct. 2000.

R. R. Schoen, T. G. Habetler, F. Kamran and R. G. Bartfield, "Motor bearing damage detection using stator current monitoring," IEEE Transactions on Industry Applications, vol. 31, no. 6, pp. 1274-1279, Dec. 1995.

J. R. Stack, T. G. Habetler and R. G. Harley, "Fault classification and fault signature production for rolling element bearings in electric machines," 4th IEEE International Symposium on Diagnostics for Electric Machines, Power Electronics and Drives, 2003. SDEMPED 2003., Atlanta, GA, USA, Aug. 2003, pp. 172-176.

S. Sridhar and K. U. Rao, "Detection of simultaneous unbalanced under-voltage and broken rotor fault in induction motor," 2013 IEEE 1st International Conference on Condition Assessment Techniques in Electrical Systems (CATCON), Kolkata, INDIA, Dec. 2013, pp. 48-53.

J. Vico, I. Voloh, D. Stankovic and Z. Zhang, "Enhanced algorithm for motor rotor broken bar detection," 2010 IEEE Industrial and Commercial Power Systems Technical Conference - Conference Record, Tallahassee, FL, USA, May 2010, pp. 1-8.

X. Li, Q. Wu and S. Nandi, "Performance Analysis of a Three-Phase Induction Machine with Inclined Static Eccentricity," IEEE Transactions on Industry Applications, vol. 43, no. 2, pp. 531-541, April 2007.

沈緯璋，「簡易型感應馬達故障診斷及狀態監測嵌入式系統之研製」，碩士論文，國立臺灣科技大學電機工程系，2016年。

B. Akin, S. Choi, U. Orguner and H. A. Toliyat, "A Simple Real-Time Fault Signature Monitoring Tool for Motor-Drive-Embedded Fault Diagnosis Systems," IEEE Transactions on Industrial Electronics, vol. 58, no. 5, pp. 1990-2001, May 2011.

J. Faiz, B. M. Ebrahimi and H. A. Toliyat, "Effect of Magnetic Saturation on Static and Mixed Eccentricity Fault Diagnosis in Induction Motor," IEEE Transactions on Magnetics, vol. 45, no. 8, pp. 3137-3144, Aug. 2009.

Kevin McClaning. (2005 Jan. 8). Zero Crossing of A noisy Cosine. In Additive white Gaussian noise. Retrieved from https://en.wikipedia.org/wiki/Additive_white_Gaussian_noise

Alam, ATM Shafiul, "Introduction to Data Communications," Dec. 2008.
Jolliffe, Ian. Principal component analysis. Springer Berlin Heidelberg, 2011.

Guo, Q., et al, "Feature selection in principal component analysis of analytical data," Chemometrics and Intelligent Laboratory Systems, vol. 61, no.1, pp. 123-132, 2002.

Shlens, Jonathon, "A tutorial on principal component analysis," arXiv preprint arXiv:1404.1100 (2014).

許邦輝，「以主成分分析法為基礎之文件自動分類模式」，碩士論文，國立清華大學工業工程與工程管理學系，2006年。

Bezdek, James C., Robert Ehrlich, and William Full, "FCM: The fuzzy c-means clustering algorithm," Computers & Geosciences, vol. 10, no. 2, pp. 191-203, 1984.

Chitra, R., and V. Seenivasagam, "Heart attack prediction system using Fuzzy C Means classifier," IOSR Journal of Computer Engineering, vol. 14, pp. 23-31, 2013.

Matsunaga, Masaki, "How to Factor-Analyze Your Data Right: Do's, Don'ts, and How-To's," International journal of psychological research, vol. 3, no. 1, pp. 97-110, 2010.

Braeken, Johan, and Marcel ALM Van Assen, "An empirical Kaiser criterion," Psychological Methods, vol. 22, no. 3, pp. 450, 2017.

Cattell, Raymond B., "The scree test for the number of factors," Multivariate behavioral research, vol. 1, no. 2, pp. 245-276, 1966.

Radziwill, N. (2012, March). Pareto Charts in R. In R-bloggers. Retrieved from https://www.r-bloggers.com/pareto-charts-in-r/

Beleites, Claudia, Reiner Salzer, and Valter Sergo, "Validation of soft classification models using partial class memberships: An extended concept of sensitivity & co. applied to grading of astrocytoma tissues." Chemometrics and Intelligent Laboratory Systems, vol. 122, pp. 12-22, 2013.

Ellison, S. L. R., and T. Fearn, "Characterising the performance of qualitative analytical methods: statistics and terminology," TrAC Trends in Analytical Chemistry vol. 24, no. 6, pp. 468-476, 2005.