現今高科技產業中所面臨的工作環境相當嚴苛，尤其在面板的附屬製程中，機台會利用轉軸以及毛刷將面板進行運送並清洗。由於產品的高精密性，機台的運作環境限制嚴格，在產線上往往無法承受無預警的停機。因此本研究將提出一個數據驅動模型來預測機台是否在異常狀態下，並結合物理模型研究轉軸在正常狀態下以及異常狀態下的振動方式。為了工廠端的數據預測，將蒐集到的時域資料進行統計分析的預處理，並應用處理後的資料來偵測旋轉軸系統中的故障。分析後的數據依照損壞程度進行分類，建置一個設備健康指標以便能夠達到高效率的分類與預測，本研究則是採用多層感知器做為模型並確定了此模型中的最佳化的參數。在分析資料時為了找出數據中異常狀態的原因，本研究將工廠機台進行簡化過後的機構作為一個整體的轉軸系統。由於零件(例如:軸承)難以磨損至損壞狀態，因此本研究利用不同剛性之聯軸器作為轉軸不同的狀態。使用雷射位移計定點以及多點量測轉軸系統之擺幅，並利用加速規量測轉軸系統的振動頻率以及振動模態的頻譜分析。

In today's high-tech industry, the working environment is particularly demanding, especially in the ancillary processes of panel manufacturing. Machines utilize shafts and brushes to transport and clean panels. Due to the products' high precision, the machines' operational environment is strictly regulated, and unexpected downtime is often intolerable on the production line. Therefore, this study proposes a data-driven model to predict whether the machine is in an abnormal state. It also combines a physical model to investigate the vibration patterns of the rotating shaft in both normal and abnormal conditions. For the data prediction on the factory side, the collected time-domain data undergoes statistical analysis preprocessing. The processed data is then applied to detect faults in the rotating shaft system. The analyzed data is classified based on the degree of damage, establishing an equipment health index for efficient classification and prediction. This study uses a multilayer perceptron as the model and determines the optimal parameters for this model. In analyzing the data to find the causes of abnormal states, the research simplifies the factory machine's mechanism as an integrated rotating shaft system. Since components (e.g., bearings) are challenging to wear to a damaged state, this study uses couplings with different rigidities to represent different states of the rotating shaft. Laser displacement sensors and accelerometers measure the system's swing amplitude, vibration frequency, vibration modes, and spectrum analysis at different speeds.

摘要 II
Abstract III
致謝 IV
圖目錄 VII
表目錄 XII
符號說明 XIII
第一章 緒論 1
1.1 前言 1
1.2 研究動機 2
1.3 文獻回顧 3
1.3.1 分析方法 3
1.3.2 感測器選用 8
1.4 研究問題 21
1.5 研究目標與方法 22
1.6 本章總結 24
第二章 人工智慧 26
2.1 本章綜述 26
2.2 人工智慧技術之介紹 26
2.3 Artificial Neural Network架構與參數介紹 28
2.4 本章總結 32
第三章 伺服訊號數據分析 33
3.1 本章綜述 33
3.2 伺服訊號擷取 33
3.3 伺服訊號分析 35
3.4 設備健康指標 (EHI) 建立 43
3.4.1 人工神經網路 45
3.4.2 資料前處理 45
3.4.3 模型建立 46
3.4.4 模型訓練與驗證 48
3.5 本章總結 53
第四章 振動物理模型 54
4.1 實驗平台與理論推導 54
4.2 實驗平台雷射量測 58
4.3 振動量測 64
4.4 結果比較 80
4.5 本章總結 80
第五章 結論與未來展望 82
5.1 結論 82
5.2 研究貢獻 83
5.3 未來展望 83
參考文獻 85
附錄A 89
附錄B 92

[1] "Report of Large Motor Reliability Survey of Industrial and Commercial Installations, Part I," IEEE Transactions on Industry Applications, vol. IA-21, no. 4, pp. 853-864, 1985, doi: 10.1109/TIA.1985.349532.
[2] L. Swanson, "Linking maintenance strategies to performance," International Journal of Production Economics, vol. 70, no. 3, pp. 237-244, Apr. 2001.
[3] N. L. Clement and R. C. Lasky, "Weibull Distribution and Analysis: 2019," in 2020 Pan Pacific Microelectronics Symposium (Pan Pacific), 2020.
[4] H. O. Charles and A. L. Kenneth, "Physically based diagnosis and prognosis of cracked rotor shafts," in Proc.SPIE, 2002, vol. 4733, pp. 122-132.
[5] C. J. Li and H. Lee, "Gear fatigue crack prognosis using embedded model, gear dynamic model and fracture mechanics," Mechanical Systems and Signal Processing, vol. 19, no. 4, pp. 836-846, 07/01/ 2005.
[6] G. Vachtsevanos and P. Wang, "Fault prognosis using dynamic wavelet neural networks," in 2001 IEEE Autotestcon Proceedings. IEEE Systems Readiness Technology Conference. (Cat. No.01CH37237), 20-23 Aug. 2001, pp. 857-870.
[7] W. Q. Wang, M. F. Golnaraghi, and F. Ismail, "Prognosis of machine health condition using neuro-fuzzy systems," Mechanical Systems and Signal Processing, vol. 18, no. 4, pp. 813-831, 07/01/ 2004.
[8] K. Goode, J. Moore, and B. Roylance, "Plant machinery working life prediction method utilizing reliability and condition-monitoring data," Proceedings of The Institution of Mechanical Engineers Part E-journal of Process Mechanical Engineering - PROC INST MECH ENG E-J P M E, vol. 214, pp. 109-122, 05/01 2000.
[9] S. A. McInerny and Y. Dai, "Basic vibration signal processing for bearing fault detection," IEEE Transactions on Education, vol. 46, no. 1, pp. 149-156, 2003.
[10] M. Amar, I. Gondal, and C. Wilson, "Vibration Spectrum Imaging: A Novel Bearing Fault Classification Approach," IEEE Transactions on Industrial Electronics, vol. 62, no. 1, pp. 494-502, 2015.
[11] M. F. Yaqub, I. Gondal, and J. Kamruzzaman, "Inchoate Fault Detection Framework: Adaptive Selection of Wavelet Nodes and Cumulant Orders," IEEE Transactions on Instrumentation and Measurement, vol. 61, no. 3, pp. 685-695, 2012.
[12] A. Rai and S. H. Upadhyay, "A review on signal processing techniques utilized in the fault diagnosis of rolling element bearings," Tribology International, vol. 96, pp. 289-306, 04/01 2016.
[13] J. H. Zhou and X. Yang, "Reinforced Morlet wavelet transform for bearing fault diagnosis," in IECON 2010 - 36th Annual Conference on IEEE Industrial Electronics Society, 7-10 Nov. 2010 2010, pp. 1179-1184.
[14] K. W. Wilson, "Probabilistic inter-disturbance interval estimation for bearing fault diagnosis," in 2009 IEEE International Symposium on Diagnostics for Electric Machines, Power Electronics and Drives, 31 Aug.-3 Sept. 2009 2009, pp. 1-6.
[15] A. Garcia-Perez, R. d. J. Romero-Troncoso, E. Cabal-Yepez, and R. A. Osornio-Rios, "The Application of High-Resolution Spectral Analysis for Identifying Multiple Combined Faults in Induction Motors," IEEE Transactions on Industrial Electronics, vol. 58, no. 5, pp. 2002-2010, 2011.
[16] I. E. Alguindigue, A. Loskiewicz-Buczak, and R. E. Uhrig, "Monitoring and diagnosis of rolling element bearings using artificial neural networks," IEEE Transactions on Industrial Electronics, vol. 40, no. 2, pp. 209-217, 1993.
[17] C.-G. Huang, H.-Z. Huang, Y.-F. Li, and W. Peng, "A novel deep convolutional neural network-bootstrap integrated method for RUL prediction of rolling bearing," Journal of Manufacturing Systems, vol. 61, pp. 757-772, 10/01/ 2021.
[18] N. Gebraeel, M. Lawley, R. Liu, and V. Parmeshwaran, "Residual life predictions from vibration-based degradation signals: a neural network approach," IEEE Transactions on Industrial Electronics, vol. 51, no. 3, pp. 694-700, 2004.
[19] U. Benko, J. Petrovc̆ic̆, Đ. Juričić, J. Tavčar, and J. Rejec, "An approach to fault diagnosis of vacuum cleaner motors based on sound analysis," Mechanical Systems and Signal Processing, vol. 19, no. 2, pp. 427-445, 03/01/ 2005.
[20] G. Yan and B. Ma, "Research on Fault Diagnosis Method of Bogie Bearing Based on Microphone Arrays," in 2018 Prognostics and System Health Management Conference (PHM-Chongqing), 26-28 Oct. 2018 2018, pp. 157-161.
[21] J. Grebenik, Y. Zhang, C. Bingham, and S. Srivastava, "Roller element bearing acoustic fault detection using smartphone and consumer microphones comparing with vibration techniques," in 2016 17th International Conference on Mechatronics - Mechatronika (ME), 7-9 Dec. 2016 2016, pp. 1-7.
[22] M. Amarnath, V. Sugumaran, and H. Kumar, "Exploiting sound signals for fault diagnosis of bearings using decision tree," Measurement, vol. 46, no. 3, pp. 1250-1256, 04/01/ 2013.
[23] A. Widodo et al., "Fault diagnosis of low speed bearing based on relevance vector machine and support vector machine," Expert Systems with Applications, vol. 36, no. 3, Part 2, pp. 7252-7261, 04/01/ 2009.
[24] H. Shao, M. Xia, G. Han, Y. Zhang, and J. Wan, "Intelligent Fault Diagnosis of Rotor-Bearing System Under Varying Working Conditions With Modified Transfer Convolutional Neural Network and Thermal Images," IEEE Transactions on Industrial Informatics, vol. 17, no. 5, pp. 3488-3496, 2021.
[25] D. Lopez-Perez and J. Antonino-Daviu, "Application of infrared thermography to fault detection in industrial induction motors: Case stories," in 2016 XXII International Conference on Electrical Machines (ICEM), 4-7 Sept. 2016 2016, pp. 2172-2177.
[26] C. Peng, C. Zeng, and Y. Wang, "Camera-Based Micro-Vibration Measurement for Lightweight Structure Using an Improved Phase-Based Motion Extraction," IEEE Sensors Journal, vol. 20, no. 5, pp. 2590-2599, 2020.
[27] S. Lu, J. Guo, Q. He, F. Liu, Y. Liu, and J. Zhao, "A Novel Contactless Angular Resampling Method for Motor Bearing Fault Diagnosis Under Variable Speed," IEEE Transactions on Instrumentation and Measurement, vol. 65, no. 11, pp. 2538-2550, 2016.
[28] X. Wang, J. Guo, S. Lu, C. Shen, and Q. He, "A computer-vision-based rotating speed estimation method for motor bearing fault diagnosis," Measurement Science and Technology, vol. 28, no. 6, p. 065012, 04/27 2017.
[29] M. J. Devaney and L. Eren, "Detecting motor bearing faults," IEEE Instrumentation & Measurement Magazine, vol. 7, no. 4, pp. 30-50, 2004.
[30] J. Ma and J. Jiang, "Applications of fault detection and diagnosis methods in nuclear power plants: A review," Progress in Nuclear Energy, vol. 53, no. 3, pp. 255-266, 2011/04/01/ 2011.
[31] M. E. H. Benbouzid, "A review of induction motors signature analysis as a medium for faults detection," IEEE Transactions on Industrial Electronics, vol. 47, no. 5, pp. 984-993, 2000.
[32] E. C. C. Lau and H. W. Ngan, "Detection of Motor Bearing Outer Raceway Defect by Wavelet Packet Transformed Motor Current Signature Analysis," IEEE Transactions on Instrumentation and Measurement, vol. 59, no. 10, pp. 2683-2690, 2010.
[33] S. T. Wu, J. Y. Chen, and S. H. Wu, "A Rotary Encoder With an Eccentrically Mounted Ring Magnet," IEEE Transactions on Instrumentation and Measurement, vol. 63, no. 8, pp. 1907-1915, 2014.
[34] S. Komatsuzaki, A. Takeyama, K. Sado, Y. Nagatsu, and H. Hashimoto, "Absolute Angle Calculation for Magnetic Encoder Based On Magnetic Flux Density Difference," in IECON 2021 – 47th Annual Conference of the IEEE Industrial Electronics Society, 13-16 Oct. 2021, pp. 1-6.
[35] A. Simm, Q. Wang, S. Huang, and W. Zhao, "Laser based measurement for the monitoring of shaft misalignment," Measurement, vol. 87, pp. 104-116, 06/01 2016.
[36] P. Avitabile, "Experimental modal analysis," Sound and vibration, vol. 35, no. 1, pp. 20-31, 2001.
[37] K.-Y. Huang, K.-Y. Peng, H.-H. Tsai, and J.-Y. Chang, "A Data-Driven and Physical Feature Analysis Method for Diagnosing Bearing Faults in Rotating Shaft," Springer Nature Switzerland, 2023, pp. 926-933.