銲線封裝製程是將晶粒上的接點以極細小的金屬線連接到導線架上，藉此傳輸電路訊號至外界，將晶片與電子系統間連接，為半導體封裝的核心製程，若無法有效控管其生產品質，易造成晶片的損壞。在複雜的晶片設計中，銲線數量可多達數百根，因此銲線封裝通常為封裝製程中最為耗時之站點，多會部屬多部平行機台來縮短生產週期。然而銲線製程的複雜產品組合使機台多處於少量多樣的生產模式，亦增加了機台設備在管理上的難度，加上現行銲線機台的維護保養流程牽涉硬體調教，非常耗時，是機台維護單位的一大負擔。因此，本研究針對銲線製程，利用紫式決策架構提出一設備維護管理預測保養策略。首先以累積和管制圖（Cumulative Sum Control Chart）進行資料預處理，篩除發生偏移之產品資料，接著以指數加權移動平均（Exponential Weighted Moving Average）建立機台之健康指標，並依據機台健康指標和機台輸出值建立集成模型，提出機台設備預測保養架構。透過本架構，產線工程師得以在機台狀況可能發生異常時，即時透過預測模型獲得機台調整建議值，校正異常機台，機台健康指標亦可協助公司更加掌握各平行機台之生產狀態，達到降低產品變異、提升品質以及降低維護人力成本之目標。

The wire bonding packaging process is the core process of IC packaging. If the quality of wire bonding cannot be controlled effectively, it could easily cause damage to the chips. The number of bonding wires can be as many as hundreds in a complex chip designt. Therefore, wire bonding is usually the most time-consuming process in IC packaging, and multiple parallel machines are often deployed to shorten the production cycle. However, the complex product mix of the wire bonding process makes the machines mostly in a high-mix low-volume production mode, and also increases the difficulty to manage the machine. The current wire bonding machine maintenance process involves hardware adjustments, which is very time-consuming and also caused a great burden for the machine maintenance department. Therefore, this research proposes a predictive maintenance strategy based on UNISON framework for the wire bonding process. First, we use the Cumulative Sum Control Chart to preprocess the data and filter out the product data that has shifted. Then use Exponential Weighted Moving Average to establish the machine's health index, and build an ensemble model based on the health index and current factor. Through this framework, engineers can obtain machine adjustment recommendations through predictive models in real-time when abnormal machine conditions are likely to occur. Health index could also help the company better understand the production status of parallel machines and to achieve the goal of reducing product variation, improve product quality, and reducing maintenance labor costs.

摘要 ------------------------------iii
表目錄 ----------------------------iii
圖目錄------------------------------iv
第一章 緒論---------------------------1
1.1 研究背景、動機與重要性--------------1
1.2 研究目的--------------------------3
1.3 論文結構--------------------------3
第二章 文獻回顧------------------------4
2.1 封測產業與銲線製程------------------4
2.1.1 銲線封裝製程---------------------4
2.1.2 銲線製程品質量測－推球測試---------6
2.2 機台維護保養策略--------------------7
2.3 集成學習--------------------------9
第三章 研究架構-----------------------11
3.1 了解與定義問題--------------------12
3.2 界定利基-------------------------13
3.3 建構影響關係----------------------13
3.3.1 資料收集-----------------------13
3.3.2 資料預處理----------------------14
3.3.3 機台健康指標--------------------16
3.3.4 建構預測模型--------------------17
3.4 客觀敘述結果----------------------18
3.5 綜合判斷與權衡---------------------18
3.6 最適決策與執行---------------------19
第四章 實證研究------------------------20
4.1 了解與定義問題---------------------21
4.2 界定利基--------------------------21
4.3 建構影響關係-----------------------22
4.3.1 資料收集------------------------22
4.3.2 資料預處理-----------------------24
4.3.3 建利機台健康指標------------------27
4.4 客觀敘述結果-----------------------28
4.5 綜合判斷與權衡----------------------31
4.6 最適決策與執行----------------------32
第五章 結論----------------------------33
5.1 研究貢獻和限制----------------------33
5.2 未來研究方向------------------------34
參考文獻-------------------------------35

Ayvaz, S. and Alpay, K. (2021), "Predictive maintenance system for production lines in manufacturing: A machine learning approach using IoT data in real-time," Expert Systems with Applications, Vol. 173, No., pp. 114598.
Bukhsh, Z. A., Saeed, A., Stipanovic, I., and Doree, A. G. (2019), "Predictive maintenance using tree-based classification techniques: A case of railway switches," Transportation Research Part C: Emerging Technologies, Vol. 101, No., pp. 35-54.
Butte, S., Prashanth, A., and Patil, S. (2018), "Machine learning based predictive maintenance strategy: a super learning approach with deep neural networks," Proceedings of 2018 IEEE Workshop on Microelectronics and Electron Devices (WMED).
Carvalho, T. P., Soares, F. A., Vita, R., Francisco, R. d. P., Basto, J. P., and Alcalá, S. G. (2019), "A systematic literature review of machine learning methods applied to predictive maintenance," Computers & Industrial Engineering, Vol. 137, No., pp. 106024.
Chien, C.-F. (2005), "Decision analysis and management: A unison framework for total decision quality enhancement," Yeh-Yeh Book Gallery, Taipei, Taiwan.
Chien, C.-F., Chen, Y.-J., and Peng, J.-T. (2010), "Manufacturing intelligence for semiconductor demand forecast based on technology diffusion and product life cycle," International Journal of Production Economics, Vol. 128, No. 2, pp. 496-509.
Chien, C.-F., Hsu, C.-Y., and Hsiao, C.-W. (2012), "Manufacturing intelligence to forecast and reduce semiconductor cycle time," Journal of Intelligent Manufacturing, Vol. 23, No. 6, pp. 2281-2294.
Chien, C.-F., Hu, C.-H., and Lin, C.-Y. (2008), "Analysing inspection frequency for wafer bumping process and an empirical study of UNISON decision framework," International journal of manufacturing technology and management, Vol. 14, No. 1-2, pp. 130-144.
Chien, C.-F., Wang, H.-J., and Wang, M. (2007), "A UNISON framework for analyzing alternative strategies of IC final testing for enhancing overall operational effectiveness," International Journal of Production Economics, Vol. 107, No. 1, pp. 20-30.
Chowdhury, M. F. R., Selouani, S.-A., and O’Shaughnessy, D. (2012), "Bayesian on-line spectral change point detection: a soft computing approach for on-line ASR," International Journal of Speech Technology, Vol. 15, No. 1, pp. 5-23.
Fu, W. and Chien, C.-F. (2019), "UNISON data-driven intermittent demand forecast framework to empower supply chain resilience and an empirical study in electronics distribution," Computers & Industrial Engineering, Vol. 135, No., pp. 940-949.
Hammoudeh, S. and Li, H. (2008), "Sudden changes in volatility in emerging markets: The case of Gulf Arab stock markets," International Review of Financial Analysis, Vol. 17, No. 1, pp. 47-63.
Hu, Y.-F., Hou, J.-L., and Chien, C.-F. (2019), "A UNISON framework for knowledge management of university–industry collaboration and an illustration," Computers & Industrial Engineering, Vol. 129, No., pp. 31-43.
Huang, X., Lee, S.-W., Yan, C. C., and Hui, S. (2001), "Characterization and analysis on the solder ball shear testing conditions," Proceedings of 2001 Proceedings. 51st Electronic Components and Technology Conference (Cat. No. 01CH37220).
Itoh, N. and Kurths, J. (2010), "Change-point detection of climate time series by nonparametric method," Proceedings of Proceedings of the world congress on engineering and computer science.
Jardine, A. K., Lin, D., and Banjevic, D. (2006), "A review on machinery diagnostics and prognostics implementing condition-based maintenance," Mechanical systems and signal processing, Vol. 20, No. 7, pp. 1483-1510.
Killick, R. and Eckley, I. (2014), "changepoint: An R package for changepoint analysis," Journal of statistical software, Vol. 58, No. 3, pp. 1-19.
Kinghorst, J., Geramifard, O., Luo, M., Chan, H.-L., Yong, K., Folmer, J., Zou, M., and Vogel-Heuser, B. (2017), "Hidden Markov model-based predictive maintenance in semiconductor manufacturing: A genetic algorithm approach," Proceedings of 2017 13th IEEE Conference on Automation Science and Engineering (CASE).
Li, Z., Wu, D., Hu, C., and Terpenny, J. (2019), "An ensemble learning-based prognostic approach with degradation-dependent weights for remaining useful life prediction," Reliability Engineering & System Safety, Vol. 184, No., pp. 110-122.
Lin, K.-Y., Chien, C.-F., and Kerh, R. (2016), "UNISON framework of data-driven innovation for extracting user experience of product design of wearable devices," Computers & Industrial Engineering, Vol. 99, No., pp. 487-502.
Lin, Y.-H., Chien, C.-F., and Yu, C.-M. (2015), "UNISON DECISION ANALYSIS FRAMEWORK FOR WORKFORCE PLANNING FOR SEMICONDUCTOR FABS AND AN EMPIRICAL STUDY," International Journal of Industrial Engineering, Vol. 22, No. 5, pp.
Malladi, R., Kalamangalam, G. P., and Aazhang, B. (2013), "Online Bayesian change point detection algorithms for segmentation of epileptic activity," Proceedings of 2013 Asilomar Conference on Signals, Systems and Computers.
Manoharan, S., Hunter, S., and McCluskey, P. (2017), "Bond pad effects on the shear strength of copper wire bonds," Proceedings of 2017 IEEE 19th Electronics Packaging Technology Conference (EPTC).
Manoharan, S., Patel, C., Hunter, S., and McCluskey, P. (2018), "Mechanism of wire bond shear testing," Microelectronics Reliability, Vol. 88, No., pp. 738-744.
Mathew, V., Toby, T., Singh, V., Rao, B. M., and Kumar, M. G. (2017), "Prediction of Remaining Useful Lifetime (RUL) of turbofan engine using machine learning," Proceedings of 2017 IEEE International Conference on Circuits and Systems (ICCS).
Moore, G. E. (1998), "Cramming More Components Onto Integrated Circuits," Proceedings of the IEEE, Vol. 86, No. 1, pp. 82-85.
Moreno, S. R., Coelho, L. d. S., Ayala, H. V., and Mariani, V. C. (2020), "Wind turbines anomaly detection based on power curves and ensemble learning," IET Renewable Power Generation, Vol. 14, No. 19, pp. 4086-4093.
Munirathinam, S. and Ramadoss, B. (2016), "Predictive models for equipment fault detection in the semiconductor manufacturing process," IACSIT International Journal of Engineering and Technology, Vol. 8, No. 4, pp. 273-285.
Paolanti, M., Romeo, L., Felicetti, A., Mancini, A., Frontoni, E., and Loncarski, J. (2018), "Machine learning approach for predictive maintenance in industry 4.0," Proceedings of 2018 14th IEEE/ASME International Conference on Mechatronic and Embedded Systems and Applications (MESA).
Polikar, R. (2006), "Ensemble based systems in decision making," IEEE Circuits and systems magazine, Vol. 6, No. 3, pp. 21-45.
Ran, Y., Zhou, X., Lin, P., Wen, Y., and Deng, R. (2019), "A survey of predictive maintenance: Systems, purposes and approaches," arXiv preprint arXiv:1912.07383, Vol., No., pp.
Reeves, J., Chen, J., Wang, X. L., Lund, R., and Lu, Q. Q. (2007), "A review and comparison of changepoint detection techniques for climate data," Journal of applied meteorology and climatology, Vol. 46, No. 6, pp. 900-915.
Sagi, O. and Rokach, L. (2018), "Ensemble learning: A survey," Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, Vol. 8, No. 4, pp. e1249.
Schuettler, M. and Stieglitz, T. (2013), "Microassembly and micropackaging of implantable systems," in: (eds.), Implantable Sensor Systems for Medical Applications, Elsevier, pp. 108-149.
Susto, G. A., Beghi, A., and De Luca, C. (2012), "A predictive maintenance system for epitaxy processes based on filtering and prediction techniques," IEEE Transactions on Semiconductor Manufacturing, Vol. 25, No. 4, pp. 638-649.
Susto, G. A., Schirru, A., Pampuri, S., McLoone, S., and Beghi, A. (2014), "Machine learning for predictive maintenance: A multiple classifier approach," IEEE Transactions on Industrial Informatics, Vol. 11, No. 3, pp. 812-820.
Susto, G. A., Schirru, A., Pampuri, S., Pagano, D., McLoone, S., and Beghi, A. (2013), "A predictive maintenance system for integral type faults based on support vector machines: An application to ion implantation," Proceedings of 2013 IEEE international conference on automation science and engineering (CASE).
Swanson, L. (2001), "Linking maintenance strategies to performance," International journal of production economics, Vol. 70, No. 3, pp. 237-244.
Vanzile, D. and Otis, I. (1992), "Measuring and controlling machine performance," Handbook of Industrial Engineering, John Wiley, New York, NY, Vol., No., pp.
Zhang, W., Yang, D., and Wang, H. (2019), "Data-driven methods for predictive maintenance of industrial equipment: A survey," IEEE Systems Journal, Vol. 13, No. 3, pp. 2213-2227.
陳麒安 (2019). 工業3.5設備維護管理架構及積體電路封裝焊線之實證研究. 工業工程與工程管理學系, 國立清華大學. 碩士: 46.