科技發展日新月異，伴隨著工業4.0智慧製造的浪潮，電動機於各產業扮演不可或缺的角色，因此能否持續運轉將直接影響工廠正常運作。長期運作的電動機其內部或許已有潛在的故障發生，但尚未立即危及到運轉安全，若持續運轉而未將故障排除，損壞程度可能持續加重，甚而導致發生無預期的停機迫使工廠運作停擺，造成嚴重的經濟損失，甚至對現場操作人員造成危害。傳統的電動機修護方式是採取定期保養，雖能減少無預警故障發生，但卻消耗大量的人力及時間，且無法即時發現潛在的故障。因此，若能即時得知電動機故障診斷及狀態監測相關資訊，將能提早預警將故障排除，提升整體動力系統運轉可靠度。
本研究旨在研製一套低成本之簡易型感應馬達狀態監測及故障診斷嵌入式系統。首先，基於先進Cortex-M4核心之微控制器，利用電壓、電流感測器及三軸加速規，量測馬達三相電壓、三相電流及振動訊號，由高速類比數位轉換器傳送至微控制器。其次，本研究提出快篩型故障診斷與狀態監測判斷法則，透過振動訊號檢測法及電氣訊號檢測法，將故障診斷及狀態監測分析結果即時顯示於螢幕。此外，也能將量測之原始資料透過乙太網路傳遞至遠端伺服器，以利使用者於電腦進行更精確的資料處理及運算分析，並回傳至嵌入式系統顯示完整故障診斷與狀態監測訊息。本研究已成功研製馬達監測嵌入式系統，經現場實地量測，將運算分析結果與構建於工業級電腦之狀態系統作比對，其誤差率皆屬合理範圍，初步驗證本系統之可行性。

The technology changes quickly, with the tide of Industry 4.0 intelligent manufacturing, the motor plays an indispensable role in various industries. Therefore, if the motor can run continuously or not will influence the normal operation of factories directly. In a long running motor, there may be potential faults, but the operational safety is not endangered yet. If the operation continues without clearing the faults, the extent of damage may be aggravated, even causing unexpected shutdown compelling the factory to suspend operation, that will cause serious economic loss, even hazard the site operation personnel. The traditional motor repair and maintenance mode is constant maintenance, the unwarned malfunctions can be reduced, but a great deal of manpower and time is consumed, and potential faults cannot be found instantly. Therefore, if the information about the motor fault diagnosis and condition monitoring can be obtained instantly, the faults will be early warned and cleared, so as to enhance the overall power system operating reliability.
This study aims to develop a low-cost simple embedded system for induction motor condition monitoring and fault diagnosis. First, based on the advanced Cortex-M4 core micro control unit, the motor three-phase voltage, three-phase current and vibration signal are measured by using voltage and current sensors and triaxial accelerometer, and sent by high speed analog-digital converter to the micro control unit. Secondly, this study proposes fast screening fault diagnosis and condition monitoring judgment rules, the analysis results of fault diagnosis and condition monitoring are displayed on the screen instantly by using vibration signal detection method and electrical signal detection method. In addition, the measured raw data can be transferred via Ethernet to the remote server, so that the user can implement more accurate data processing and operation analysis on computer, and the data are fed back to the embedded system to display complete fault diagnosis and condition monitoring information. This study has developed an embedded motor monitoring system successfully. After field measurement, the operational analysis result is compared with the condition system built on industrial computer, the error rates are within reasonable range, the feasibility of this system is validated preliminarily.

[1] 經濟部能源局，「產業節能總動員，政府全面推動馬達革新計畫」，2008年。
[2] ISO Std. 10816-1, “Mechanical vibration--Evaluation of machine vibration by measurements on non-rotating parts--Part 1: General guidelines,” 1995.
[3] NEMA Std. MG 1, “Motors and Generators,” 2009.
[4] M. Tsypkin, “Induction motor condition monitoring: vibration analysis technique-A twice line frequency component as a diagnostic tool,” IEEE International Electric Machines & Drives Conference (IEMDC), 2013, pp. 117-124.
[5] 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, 2001.
[6] 徐子權，「電氣與振動檢測法於馬達狀態評估之研究」，碩士論文，台灣科技大學電機工程學系，2014年。
[7] 廖家祺，「電氣指標於感應電動機運轉狀態之適切性評估」，碩士論文，台灣科技大學電機工程學系，2015年。
[8] R. Puche-Panadero, J. Roger-Folch, M. Riera-Guasp, J. Roger-Folch, E. Hurtado-Perez, and J. Perez- Cruz, “Improved resolution of the MCSA method via Hilbert transform, enabling the diagnosis of rotor asymmetries at very low slip,” IEEE Transactions on Energy Conversion, Vol. 24, No. 1, pp. 52-59, 2009.
[9] W. S. Gongora, H. V. D Silva, A. Goedtel, W. F. Godoy, and S. A. O. da Silva, “Neural approach for bearing fault detection in three phase induction motors,” IEEE International Symposium on Diagnostics for Electric Machines, Power Electronics and Drives (SDEMPED), 2013, pp. 566-572.
[10] Santanu Das, P. Purkait, and S. Chakravorti, “Characterization of short circuit faults and incipient insulation degradation between stator winding turns of induction motor,” IEEE International Conference on Condition Assessment Techniques in Electrical Systems (CATCON), 2013, pp. 54-59.
[11] W. T. Thomson, “On-line MCSA to diagnose shorted turns in low voltage stator windings of 3-phase induction motors prior to failure,” IEEE International Electric Machines and Drives Conference, 2001, pp. 891-898.
[12] T. Ishikawa, R. Ishigame, M. Matsunami, and N. Kurita, “Analysis and failure diagnosis of squirrel-cage induction motor with broken rotor,” International Conference Electrical Machines and Systems (ICEMS), 2012, pp. 1-5.
[13] S. Sridhar and K. UmaRao, “Detection of simultaneous unbalanced under-voltage and broken rotor fault in induction motor,” IEEE International Conference on Condition Assessment Techniques in Electrical Systems (CATCON), 2013, pp. 48-53.
[14] B. Li and J. C. Hung, “Neural- network-based motor rolling bearing fault diagnosis,” IEEE Transactions on Industrial Electronics, Vol. 47, No. 5, pp. 1060-1069, 2000.
[15] 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, 1995.
[16] B. Akin, Seungdeog 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, 2011.
[17] S. Sridhar and K. U. Rao, “Detection of simultaneous unbalanced under-voltage and broken rotor fault in induction motor,” IEEE International Conference on Condition Assessment Techniques in Electrical Systems (CATCON), 2013, pp. 48- 53.
[18] 北京森社電子股份有限公司，SENSOR Module CHV-50P/*，2011年7月，
http://www.bjsse.com.cn/en/uploadpic/products/201172914563123.pdf
[19] LEM, “Current Transducer HTR 50 to 500-SB,” July 2011,
http://www.lem.com/docs/products/htr%2050%20to%20500-sb%20e.pdf
[20] IMI SENSORS A PCB PIEZOTRONICS DIV., “Precision Triaxial Industrial ICP® Accelerometer Installation and Operating Manual,” June 2013,
https://www.imi-sensors.com/ContentStore/mktg/IMI_Downloads/Triaxial%20Accelerometer%20Data%20Sheet.pdf
[21] TEXAS INSTRUMENTS, “ADS855x 16-, 14-, 12-Bit, Six-Channel, Simultaneous Sampling Analog-to-Digital Converters,” Feb 2016,
http://www.ti.com/lit/ds/symlink/ads8556.pdf
[22] NXP Semiconductors,“LPC408X_7X-Datasheet,“ April 2016,
http://cache.nxp.com/documents/data_sheet/LPC408X_7X.pdf?pspll=1
[23] Rob Toulson，ARM快速嵌入式系統原型設計：基於開源硬件mbed，大陸：機械工業出版社，2014年3月。
[24] 蕭文龍、蔡佳翰，TCP/IP最佳入門實用書：Wireshark封包解析x流量統計，七版，台灣：碁峰出版社，2013年2月。
[25] 張慧珠，圖書館電子資源組織：從書架到網路，初版，台灣：Airiti Press Inc.，2011年6月。
[26] 張宏展、林上智、郭政謙、程于真，「基於振動檢測方法於鼠籠式感應電動機運轉狀態風險評估」，第三十六屆電力工程研討會，台灣桃園，2015年12月。
[27] 林家民，「感應電動機狀態監測平台之研製」，碩士論文，台灣科技大學電機工程學系，2015年。
[28] 黃維澤，「電壓、電流不平衡率定義之探討與分析」，碩士論文，台灣科技大學電機工程學系，1999年。
[29] 楊承翰，「電壓不平衡率之定義及電壓不平衡對系統與設備影響之研究」，碩士論文，國立台灣科技大學，2008年。
[30] IEC 60034-1, “Rotating electrical machines,” 2004.
[31] 福祿克數字資料庫，http://www.fluke.com/library
[32] 黃建裕，「諧波對小能量過電流電驛的影響」，碩士論文，中原大學電機工程學系，2003年。
[33] 杜耿邦，「應用人工智慧於電力系統諧波源與位置偵測」，碩士論文，中山大學電機工程學系，2003年。
[34] IEEE Std. 519, “IEEE Recommended Practices and Requirements for Harmonic Control in Electrical Power Systems,” New York, April 1993.
[35] 張宏展、林上智、郭政謙、謝政甫、廖家祺，「應用電氣指標評估感應電動機之運轉狀態」，台灣風能協會學術研討會暨NEP-II離岸風力及海洋能源主軸中心成果發表會，台灣台北，2015年12月。