簡易檢索 / 詳目顯示

回結果列表
研究生： 謝茗卉
Hsieh, Ming-Hui
論文名稱： 應用LSTM預測維護—以後段測試廠分類機為例
Predictive Maintenance using LSTM - application for handlers of final test process
指導教授： 葉維彰
YEH, WEI-CHANG
口試委員: 賴智明
Lai, Chyh-Ming
梁韵嘉
Liang, Yun-Chia
學位類別： 碩士
Master
系所名稱： 工學院 - 工業工程與工程管理學系碩士在職專班
Industrial Engineering and Engineering Management
論文出版年： 2022
畢業學年度： 110
語文別： 中文
論文頁數： 60
中文關鍵詞： 電腦整合製造 、分類機故障預測 、預測維護 、長短期記憶
外文關鍵詞： Computer-Integrated Manufacturing, Breakdown prediction of handler, Predictive Maintenance, Long Short-Term Memory
相關次數： 點閱：2  下載：0 
分享至:
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報

    • 隨著工業的進步，各種產業趨向於量產化的需求，機器逐漸取代人工作業。同時因應生管排程上的產能控管技術提升，實際生產時間與預定交期愈趨接近，進而衍生了機器非預期故障影響出貨時程的問題。然而傳統工業主流¬ 預防維護的做法雖能避免大部分故障的發生，但對於杜絕實務上的所有故障上仍有改善空間。故業界傾向於在機器內大量安裝感測器記錄機器狀態並做故障偵測，但此解決方案對於低成本或老舊的機器的適用性較低。
    本論文的適用範圍是透過機器內建報錯紀錄與電腦整合製造(CIM, Computer-Integrated Manufacturing)系統的機器稼動狀態有連動的工廠所做的研究。
    本研究提出一個不需要在機器內安裝感測器的低成本預測方法，透過紀錄機器內建報錯功能的時間、報錯區域、報錯訊息，以及工廠CIM系統連動的機器稼動狀態紀錄所產生的資料，應用長短期記憶(LSTM, Long Short-Term Memory)方法預測該機器可能會故障的時間及區域，透過上述的探討及驗證，期望使生管能夠將可能故障的因子考慮進排程中，提升產品出貨達交率。

    As industrial technology evolution and productive, manual producing was replacing by machines. And with the technology of scheduling increased, planning production due in going to meet the actual process. The problems of machine unplanned out of order make a big deal with productivity due. Although the transitional PM (Preventive Maintenance) way can save from most of problems happens, but still has a lot of space to be improve. Acknowledge that, many factories tend to install piles of sensor in equipment to detect and record machine status, but this solution was not really fit for lower cost and old class ones.
    This research is survey for factories which has high connection between machine and CIM (Computer-Integrated Manufacturing) system. We provide a solution of low-cost prediction for using build-in alarm function which include time stamp, alert area and alert message gearing with CIM equipment status. We use LSTM (Long Short-Term Memory) algorithm to predict the time and area that has high probability of breakdown without any sensors installed.
    Across discuss and verification above, we want to consider those breakdown factors into product scheduling to improve the on-time delivery rate.

    摘要 .............................................. i Abstract ...................................... ii 致謝 .............................................. iii 目錄 .............................................. vi 圖目錄 ..............................................viii 表目錄 ................................................ x 第一章、 緒論 ........................................ 1 1.1. 研究背景 ........................................ 1 1.2. 研究動機 ........................................ 4 1.3. 研究目的 ........................................ 5 1.4. 研究架構 ........................................ 9 第二章、 文獻回顧 ................................10 2.1. 維護方式定義 ................................10 2.1.1. 名詞定義 ........................................11 2.1.2. 機器維護的演變 ................................11 2.1.3. 機器維護的形式 ................................13 2.2. 預測維護與機器學習 ................................16 2.2.1. 機器學習在預測維護上的應用 ................16 2.2.2. 連續與離散模型混合應用 ........................19 2.3. 長短期記憶LSTM (Long Short-Term Memory) ........20 2.4. 文獻回顧小結 ................................22 第三章、 研究方法 ................................23 3.1. 資料前處理 ........................................24 3.1.1. 過濾資料 ........................................24 3.1.2. 計算時間間隔 ................................24 3.1.3. 資料轉換 ........................................25 3.1.4. 資料正規化 ................................26 3.2. 建構訓練模型 ................................28 3.2.1. 資料分割 ........................................28 3.2.2. 交叉驗證(CV, Cross-validation) ................29 3.2.3. 損失函數(Loss Function) ........................30 3.2.4. 優化器(Optimizer) ........................31 3.2.5. 訓練模型 ........................................31 第四章、 案例研討 ................................33 4.1. 案例說明 ........................................33 4.2. 比較實驗結果 ................................33 4.2.1. 績效指標說明 ................................34 4.2.2. 參數設定說明 ................................35 4.2.3. LSTM實驗比較 ................................37 4.3. 評估實驗結果 ................................42 4.3.1. 混淆矩陣 (Confusion Matrix) ................42 4.3.2. ROC (Receiver Operator Characteristic) curve 45 4.4. 預測結果 ........................................49 第五章、 結論 ........................................52 5.1. 研究貢獻 ........................................52 5.2. 實務應用 ........................................52 5.3. 未來展望 ........................................54 參考文獻 ........................................56

    [1] 吳昌崙 and 張景學, 半導體製造技術. 第二版 ed. 2003, 臺北縣中和市: 新文京開發.
    [2] Baker, R.J., CMOS: circuit design, layout, and simulation. 2019: John Wiley & Sons.
    [3] Clein, D., CMOS IC layout: concepts, methodologies, and tools. 1999: Elsevier.
    [4] Sedra, A.S., et al., Microelectronic circuits. Vol. 4. 2004: Oxford university press New York.
    [5] Seeger, K., Semiconductor physics. 2013: Springer Science & Business Media.
    [6] 林明獻, 矽晶圓半導體材料技術. 六版 ed. Silicon wafer semiconductor. 2020, 新北市: 全華圖書.
    [7] Shimura, F., Semiconductor silicon crystal technology. 2012: Elsevier.
    [8] May, G.S. and C.J. Spanos, Fundamentals of semiconductor manufacturing and process control. 2006: John Wiley & Sons.
    [9] Nishi, Y. and R. Doering, Handbook of semiconductor manufacturing technology. 2000: CRC press.
    [10] Burns, M. and G.W. Roberts, An introduction to mixed-signal IC test and measurement. Vol. 2001. 2001: IET.
    [11] Ahmadi, A., et al. Wafer-level process variation-driven probe-test flow selection for test cost reduction in analog/RF ICs. in 2016 IEEE 34th VLSI Test Symposium (VTS). 2016. IEEE.
    [12] Tummala, R.R., Fundamentals of microsystems packaging. 2001.
    [13] Minges, M.L., Electronic materials handbook: packaging. Vol. 1. 1989: Asm International.
    [14] Adventest. M6242 Optimal Test Handler for Mass-Production DRAM with Double the Throughput. 2008; Available from: https://www3.advantest.com/documents/11348/146262/pdf_M6242-1E_en.pdf.
    [15] Adventest. T5588 A High-Throughput Tester Optimal for Mass-production of High-speed Devices such as DDR2-SDRAMs. 2005; Available from: https://www3.advantest.com/documents/11348/146262/pdf_M4841-2E_en.pdf.
    [16] John, K. Control system development for test handler. in ICONIP'02. Proceedings of the 9th International Conference on Neural Information Processing. Computational Intelligence for the E-Age (IEEE Cat. No. 02EX575). 2002. IEEE.
    [17] Lee, S.-C., S. Demidenko, and K.-H. Lee. IC Handler throughput evaluation for test process optimization. in 2007 IEEE Instrumentation & Measurement Technology Conference IMTC 2007. 2007. IEEE.
    [18] Lindley R. Higgins, P.E., R. Keith Mobley, Ricky Smith, maintenance-engineering-handbook. 6th ed. OPERATING POLICIES OF EFFECTIVE MAINTENANCE. 2002.
    [19] Sivakumar, A.I. Optimization of a cycle time and utilization in semiconductor test manufacturing using simulation based, on-line, near-real-time scheduling system. in Proceedings of the 31st conference on Winter simulation: Simulation---a bridge to the future-Volume 1. 1999.
    [20] Uzsoy, R., C.Y. Lee, and L.A. Martin‐Vega, Scheduling semiconductor test operations: Minimizing maximum lateness and number of tardy jobs on a single machine. Naval Research Logistics (NRL), 1992. 39(3): p. 369-388.
    [21] Bard, J.F., et al., Real-time decision support for assembly and test operations in semiconductor manufacturing. IIE Transactions, 2012. 44(12): p. 1083-1099.
    [22] Deng, Y., et al., Scheduling back-end operations in semiconductor manufacturing. IEEE Transactions on Semiconductor Manufacturing, 2010. 23(2): p. 210-220.
    [23] Chen, T.-R.M. and T. Hsia, Scheduling for IC sort and test facilities with precedence constraints via Lagrangian relaxation. Journal of Manufacturing Systems, 1997. 16(2): p. 117-128.
    [24] Błażewicz, J., et al., Handbook on scheduling: From theory to practice. 2019: Springer.
    [25] Kress, D. and D. Müller, Semiconductor final-test scheduling under setup operator constraints. Computers & Operations Research, 2022. 138: p. 105619.
    [26] Uzsoy, R., et al., Production scheduling algorithms for a semiconductor test facility. IEEE transactions on semiconductor manufacturing, 1991. 4(4): p. 270-280.
    [27] Zhang, Z., et al., Semiconductor final test scheduling with Sarsa (λ, k) algorithm. European Journal of Operational Research, 2011. 215(2): p. 446-458.
    [28] Ahmad, R. and S. Kamaruddin, An overview of time-based and condition-based maintenance in industrial application. Computers & Industrial Engineering, 2012. 63(1): p. 135-149.
    [29] Yasuda, S., et al., Chamber and recipe-independent FDC indicator in high-mix semiconductor manufacturing. IEEE Transactions on Semiconductor Manufacturing, 2021. 34(3): p. 301-306.
    [30] Williams, B., T. Nowalk, and C. Reeves. Advancing Advanced Process Control in Backend Factories. in 2018 International Wafer Level Packaging Conference (IWLPC). 2018. IEEE.
    [31] Sheng-Luen, C. and J. MuDer. Manufacturing execution system (MES) for semiconductor manufacturing. in IEEE International Conference on Systems, Man and Cybernetics. 2002.
    [32] Ljungberg, Õ., Measurement of overall equipment effectiveness as a basis for TPM activities. International Journal of Operations & Production Management, 1998.
    [33] Dal, B., P. Tugwell, and R. Greatbanks, Overall equipment effectiveness as a measure of operational improvement–a practical analysis. International Journal of Operations & Production Management, 2000.
    [34] Melton, T., The benefits of lean manufacturing: what lean thinking has to offer the process industries. Chemical engineering research and design, 2005. 83(6): p. 662-673.
    [35] Bhamu, J. and K.S. Sangwan, Lean manufacturing: literature review and research issues. International Journal of Operations & Production Management, 2014.
    [36] Feld, W.M., Lean manufacturing: tools, techniques, and how to use them. 2000: CRC press.
    [37] Kumar, S.A. and N. Suresh, Production and operations management. 2006: New Age International.
    [38] Rahman, N.A.A., S.M. Sharif, and M.M. Esa, Lean Manufacturing Case Study with Kanban System Implementation. Procedia Economics and Finance, 2013. 7: p. 174-180.
    [39] Ahmad, M.O., J. Markkula, and M. Oivo. Kanban in software development: A systematic literature review. in 2013 39th Euromicro conference on software engineering and advanced applications. 2013. IEEE.
    [40] Sowmya, K. and N. Chetan, A review on effective utilization of resources using overall equipment effectiveness by reducing six big losses. International Journal of Scientific Research in Science, Engineering and Technology, 2016. 2(1): p. 556-562.
    [41] Deuel, A.C., The benefits of a manufacturing execution system for plantwide automation. ISA Transactions, 1994. 33(2): p. 113-124.
    [42] Kroll, B., et al. System modeling based on machine learning for anomaly detection and predictive maintenance in industrial plants. in Proceedings of the 2014 IEEE emerging technology and factory automation (ETFA). 2014. IEEE.
    [43] Arunraj, N.S. and J. Maiti, Risk-based maintenance--techniques and applications. J Hazard Mater, 2007. 142(3): p. 653-61.
    [44] Smith, A.M., Reliability-centered maintenance. 1993: McGraw-Hill New York.
    [45] Aarset, M.V., How to identify a bathtub hazard rate. IEEE Transactions on Reliability, 1987. 36(1): p. 106-108.
    [46] Biswal, S. and G. Sabareesh. Design and development of a wind turbine test rig for condition monitoring studies. in 2015 international conference on industrial instrumentation and control (icic). 2015. IEEE.
    [47] Peres, R.S., et al., IDARTS–Towards intelligent data analysis and real-time supervision for industry 4.0. Computers in industry, 2018. 101: p. 138-146.
    [48] Praveenkumar, T., et al., Fault diagnosis of automobile gearbox based on machine learning techniques. Procedia Engineering, 2014. 97: p. 2092-2098.
    [49] Carvalho, T.P., et al., A systematic literature review of machine learning methods applied to predictive maintenance. Computers & Industrial Engineering, 2019. 137: p. 106024.
    [50] Wuest, T., et al., Machine learning in manufacturing: advantages, challenges, and applications. Production & Manufacturing Research, 2016. 4(1): p. 23-45.
    [51] Vlachas, P.R., et al., Backpropagation algorithms and Reservoir Computing in Recurrent Neural Networks for the forecasting of complex spatiotemporal dynamics. Neural Netw, 2020. 126: p. 191-217.
    [52] Hochreiter, S. and J. Schmidhuber, Long short-term memory. Neural Comput, 1997. 9(8): p. 1735-80.
    [53] Bello, I., et al. Neural optimizer search with reinforcement learning. in International Conference on Machine Learning. 2017. PMLR.
    [54] Liang, Y.C., et al., Thermal error prediction for heavy-duty CNC machines enabled by long short-term memory networks and fog-cloud architecture. Journal of Manufacturing Systems, 2022. 62: p. 950-963.
    [55] Chen, Z., Y. Liu, and S. Liu. Mechanical state prediction based on LSTM neural netwok. in 2017 36th Chinese Control Conference (CCC). 2017.
    [56] Wojciechowski, M. and M. Zakrzewicz, Dataset filtering techniques in constraint-based frequent pattern mining, in Pattern detection and discovery. 2002, Springer. p. 77-91.
    [57] Moore, A.W. and J.W. Jorgenson, Median filtering for removal of low-frequency background drift. Analytical chemistry, 1993. 65(2): p. 188-191.
    [58] Li, H., X. Jiang, and Z. Li, Robust estimation in Gaussian filtering for engineering surface characterization. Precision Engineering, 2004. 28(2): p. 186-193.
    [59] Raschka, S., Model evaluation, model selection, and algorithm selection in machine learning. arXiv preprint arXiv:1811.12808, 2018.
    [60] Yadav, S. and S. Shukla. Analysis of k-Fold Cross-Validation over Hold-Out Validation on Colossal Datasets for Quality Classification. in 2016 IEEE 6th International Conference on Advanced Computing (IACC). 2016.
    [61] Erdogan, H. and T. Yoshioka. Investigations on Data Augmentation and Loss Functions for Deep Learning Based Speech-Background Separation. in Interspeech. 2018.
    [62] Köksoy, O., Multiresponse robust design: Mean square error (MSE) criterion. Applied Mathematics and Computation, 2006. 175(2): p. 1716-1729.
    [63] Kingma, D.P. and J. Ba, Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980, 2014.
    [64] Wang, W. and Y. Lu. Analysis of the mean absolute error (MAE) and the root mean square error (RMSE) in assessing rounding model. in IOP conference series: materials science and engineering. 2018. IOP Publishing.
    [65] Kim, S. and H. Kim, A new metric of absolute percentage error for intermittent demand forecasts. International Journal of Forecasting, 2016. 32(3): p. 669-679.
    [66] De Myttenaere, A., et al., Mean absolute percentage error for regression models. Neurocomputing, 2016. 192: p. 38-48.
    [67] Makridakis, S., Accuracy measures: theoretical and practical concerns. International journal of forecasting, 1993. 9(4): p. 527-529.
    [68] Hyndman, R., et al., Forecasting with exponential smoothing: the state space approach. 2008: Springer Science & Business Media.
    [69] Ostertagová, E. and O. Ostertag. The simple exponential smoothing model. in The 4th International Conference on Modelling of Mechanical and Mechatronic Systems, Technical University of Košice, Slovak Republic, Proceedings of conference. 2011.
    [70] Deng, X., et al., An improved method to construct basic probability assignment based on the confusion matrix for classification problem. Information Sciences, 2016. 340: p. 250-261.
    [71] Visa, S., et al., Confusion matrix-based feature selection. MAICS, 2011. 710: p. 120-127.
    [72] Ruuska, S., et al., Evaluation of the confusion matrix method in the validation of an automated system for measuring feeding behaviour of cattle. Behavioural processes, 2018. 148: p. 56-62.
    [73] Zweig, M.H. and G. Campbell, Receiver-operating characteristic (ROC) plots: a fundamental evaluation tool in clinical medicine. Clinical chemistry, 1993. 39(4): p. 561-577.
    [74] Swets, J.A., Measuring the Accuracy of Diagnostic Systems. Science, 1988. 240(4857): p. 1285-1293.
    [75] PINTEA, S. and R. MOLDOVAN, The Receiver-Operating Characteristic (ROC) analysis: Fundamentals and applications in clinical psychology. Cognitive and Behavioral Psychotherapies, 2009: p. 49-66

    QR CODE