隨著科技的發展，許多新技術被應用於製造業中以提高生產效率與降低成本。為了兼顧成本的考量，以及使設備在良好的狀態下運行以保持產品品質與生產效率，健康評估及預測保養成為至關重要的議題。因此相關的主題，除了在近年來大幅受業界重視並投入許多資源，也有許多學者致力於此領域的研究。本研究針對皮帶傳動機構，建立了基於物理模型與摩擦力特性的健康評估方法。由於在資料蒐集上不需透過外部感測器，因此可將此方法應用於自動化線上檢測以減少維修保養成本。本研究亦將健康評估結果應用於預測保養，透過建立皮帶的壽命分配以進行處方性分析，藉以判斷皮帶最佳保養時機。本研究與台灣頂尖電子製造公司合作，透過皮帶傳動機構的實驗資料，驗證本研究所提出之方法。根據實驗結果，在不同的加工條件下本研究所提出之健康指標有穩健的表現，並可將預測保養策略結合既有預防保養策略以發揮綜效。本研究的貢獻在於，建立一具物理意義的自動化線上健康評估方法，並透過預測保養以預防機構過度維護或維護不足的狀況。

With the development in technology, more and more applications are developed in manufacturing industry to enhance the efficiency and lower the maintenance cost of the equipment. In order to make equipment operates in good condition to ensure product quality and production efficiency, health assessment and predictive maintenance (PdM) are significant especially when considering the cost. Therefore, prognostics and health management is not only valued by industry in recent years, but also many researchers are committed to this field. This study proposes a health assessment methodology for belt drive system based on physical model. Since no external sensors are needed for data acquisition, the proposed methodology can be applied for on-line detection which reduce maintenance costs. In addition, the health assessment result is further applied for predictive maintenance. The lifetime distribution of belt is built in this study to identify the best maintenance time for the belt. A designed experiment of a belt drive mechanism is conducted as a case study to verify the proposed methodology. The case study is cooperated with a leading electronics manufacturing company in Taiwan. Results show that the proposed health indicator is robust under different operation conditions, and the predictive maintenance result can be synergized with the existing preventive maintenance strategy. The contribution of this study is the development of a
physically meaningful on-line health assessment methodology for belt drive system. Additionally, predictive maintenance is also proposed to minimize the cost by avoiding potential over-maintenance and under-maintenance problems.

[1] Y. Liu, J. Li, Z. Zhang, X. Hu, and W. Zhang, “Experimental comparison of five friction models on the same test-bed of the micro stick-slip motion system,” Mechanical Sciences, vol. 6, no. 1, pp. 15–28, 2015.
[2] Y.-H. Hung, “Constrained particle swarm optimization and bayesian process monitoring for health maintenance in three-mass resonant servo control system with friction,” Master’s thesis, National Cheng Kung University, 2019.
[3] Y. Ran, X. Zhou, P. Lin, Y. Wen, and R. Deng, “A survey of predictive maintenance: Systems, purposes and approaches,” arXiv preprint arXiv:1912.07383, 2019.
[4] E. Pennestrì, V. Rossi, P. Salvini, and P. P. Valentini, “Review and comparison of dry friction force models,” Nonlinear dynamics, vol. 83, no. 4, pp. 1785–1801, 2016.
[5] F. Al-Bender, “Fundamentals of friction modeling,” in Proceedings, ASPE Spring Topical Meeting on Control of Precision Systems, MIT, April 11-13, 2010, vol. 48, pp. 117–122, ASPE-The American Society of precision Engineering, 2010.
[6] T. W. Bank, “Manufacturing, value added.” https://data.worldbank.org/
indicator/NV.IND.MANF.CD?end=2019&start=2011&view=chart. (Accessed on
2021/06/23).
[7] C.-Y. Lee and C.-F. Chien, “Pitfalls and protocols of data science in manufacturing practice,” Journal of Intelligent Manufacturing, pp. 1–19, 2020.
[8] A. Bonci, S. Longhi, and G. Nabissi, “Fault diagnosis in a belt-drive system under nonstationary conditions. an industrial case study,” in 2021 IEEE Workshop on Electrical Machines Design, Control and Diagnosis (WEMDCD), pp. 260–265, IEEE, 2021.
[9] 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.
[10] J. Lee, F. Wu, W. Zhao, M. Ghaffari, L. Liao, and D. Siegel, “Prognostics and health management design for rotary machinery systems—reviews, methodology and applications,” Mechanical systems and signal processing, vol. 42, no. 1-2, pp. 314–334, 2014.
[11] T. Plazenet, T. Boileau, C. Caironi, and B. Nahid-Mobarakeh, “An overview of shaft voltages and bearing currents in rotating machines,” in 2016 IEEE Industry Applications Society Annual Meeting, pp. 1–8, IEEE, 2016.
[12] W.-T. Rim and K.-J. Kim, “Identification of tension in a belt-driven system by analysing flexural vibrations,” Mechanical Systems and Signal Processing, vol. 8, no. 2, pp. 199–213, 1994.52
[13] H. Yamashina, S. Okumura, and I. Kawai, “Development of a diagnosis technique for failures of v-belts by a cross-spectrum method and a discriminant function approach,” Journal of intelligent manufacturing, vol. 7, no. 1, pp. 85–93, 1996.
[14] B. Fazenda, F. Gu, A. Ball, O. Gilkes, et al., “Acoustic diagnosis of driving belt physical condition in enclosures,” Proceedings of Internoise 2008, 2008.
[15] J. Yoon, D. He, and B. Van Hecke, “A phm approach to additive manufacturing equipment health monitoring, fault diagnosis, and quality control,” in Annual Conference of the PHM Society, vol. 6, 2014.
[16] A. Banakar, B. Ghobadian, M. Mirsalim, S. Minaei, S. M. Jafari, P. Sharghi, et al.,
“Analyzing of timing belt vibrational behavior during a durability test using artificial neural network (ann),” Modares Mechanical Engineering, vol. 16, no. 3, pp. 311–318, 2016.
[17] A. A. Jaber and K. M. Ali, “Artificial neural network based fault diagnosis of a pulley-belt rotating system,” Int J Adv Sci Eng Inform Technol, vol. 9, pp. 544–551, 2019.
[18] T.-J. Kang, C. Yang, Y. Park, D. Hyun, S. B. Lee, and M. Teska, “Electrical monitoring of mechanical defects in induction motor-driven v-belt–pulley speed reduction couplings,” IEEE Transactions on Industry Applications, vol. 54, no. 3, pp. 2255–2264, 2018.
[19] A. Picot, E. Fournier, J. Régnier, M. TientcheuYamdeu, J.-M. Andréjak, and P. Maussion, “Statistic-based method to monitor belt transmission looseness through motor phase currents,” IEEE Transactions on Industrial Informatics, vol. 13, no. 3, pp. 1332–1340, 2017.
[20] P. R. Dahl, “A solid friction model,” tech. rep., Aerospace Corp El Segundo Ca, 1968.
[21] P. R. Dahl, “Measurement of solid friction parameters of ball bearings,” tech. rep., Aerospace Corp El Segundo Ca Engineering Science Operations, 1977.
[22] K. Johanastrom and C. Canudas-De-Wit, “Revisiting the lugre friction model,” IEEE control systems magazine, vol. 28, no. 6, pp. 101–114, 2008.
[23] K. L. Tsui, N. Chen, Q. Zhou, Y. Hai, and W. Wang, “Prognostics and health management: A review on data driven approaches,” Mathematical Problems in Engineering, vol. 2015, 2015.
[24] Y.-C. Huang, Y.-H. Hsieh, and S.-C. Chiu, “The optimal preventive maintenance under multi-fault patterns,” Journal of Technology, vol. 32, no. 1, 2017.
[25] A. Grall, C. Bérenguer, and L. Dieulle, “A condition-based maintenance policy for stochastically deteriorating systems,” Reliability Engineering & System Safety, vol. 76, no. 2, pp. 167–180, 2002.
[26] L. Dieulle, C. Bérenguer, A. Grall, and M. Roussignol, “Sequential condition-based maintenance scheduling for a deteriorating system,” European Journal of operational research, vol. 150, no. 2, pp. 451–461, 2003. 53
[27] A. K. Jardine, D. Lin, and D. Banjevic, “A review on machinery diagnostics and prognostics implementing condition-based maintenance,” Mechanical systems and signal processing, vol. 20, no. 7, pp. 1483–1510, 2006.
[28] A. Ray and S. Tangirala, “Stochastic modeling of fatigue crack dynamics for on-line failure prognostics,” IEEE Transactions on Control Systems Technology, vol. 4, no. 4, pp. 443–451, 1996.
[29] Y. Li, S. Billington, C. Zhang, T. Kurfess, S. Danyluk, and S. Liang, “Adaptive prognostics for rolling element bearing condition,” Mechanical systems and signal processing, vol. 13, no. 1, pp. 103–113, 1999.
[30] C.-Y. Lee, T.-S. Huang, M.-K. Liu, and C.-Y. Lan, “Data science for vibration heteroscedasticity and predictive maintenance of rotary bearings,” Energies, vol. 12, no. 5, p. 801, 2019.
[31] P. Baraldi, F. Cadini, F. Mangili, and E. Zio, “Model-based and data-driven prognostics under different available information,” Probabilistic Engineering Mechanics, vol. 32, pp. 66–79, 2013.
[32] J. Luo, M. Namburu, K. Pattipati, L. Qiao, M. Kawamoto, and S. Chigusa, “Modelbased prognostic techniques [maintenance applications],” in Proceedings AUTOTESTCON 2003. IEEE Systems Readiness Technology Conference., pp. 330–340, Ieee, 2003.
[33] M. Schwabacher, “A survey of data-driven prognostics,” in Infotech@ Aerospace, p. 7002, 2005.
[34] X.-S. Si, W. Wang, C.-H. Hu, and D.-H. Zhou, “Remaining useful life estimation–a review on the statistical data driven approaches,” European journal of operational research, vol. 213, no. 1, pp. 1–14, 2011.
[35] J. F. Trevor Hastie, Robert Tibshirani, The Elements of Statistical Learning. Springer, New York, NY, 2nd ed., 2009.
[36] J. H. Friedman, “Stochastic gradient boosting,” Comput. Stat. Data Anal., vol. 38, p. 367–378, Feb. 2002.
[37] R. Koenker and G. Bassett, “Regression quantiles,” Econometrica, vol. 46, no. 1, pp. 33–50, 1978.
[38] Q. Huang, H. Zhang, J. Chen, and M. He, “Quantile regression models and their applications: a review,” Journal of Biometrics & Biostatistics, vol. 8, no. 10.4172, pp. 2155–6180, 2017.
[39] J. Yang, X. Shi, and J. Zhang, “A new processing method for accelerated degradation data based on quantile regression and pseudo-failure lifetime,” Microelectronics Reliability, vol. 88, pp. 1141–1145, 2018.