簡易檢索 / 詳目顯示

回結果列表
研究生： 董昭宏
Dong, Zhao-Hong
論文名稱： 機台健康指標於異常偵測與診斷:以半導體封裝廠為實證
Equipment Health Index for Fault Detection and Classification: An Empirical Study of Semiconductor Assembly Fabrication
指導教授： 李家岩
Lee, Chia-Yen
學位類別： 碩士
Master
系所名稱： 電機資訊學院 - 製造資訊與系統研究所
Institute of Manufacturing Information and Systems
論文出版年： 2017
畢業學年度： 105
語文別： 中文
論文頁數： 108
中文關鍵詞： 資料探勘 、統計製程管控 、半導體製造 、機台健康指標 、目標層級架構法 、異常偵測與診斷 、問題決策支援模組
外文關鍵詞： Data Mining, Statistical Process Control, Semiconductor Manufacturing, Equipment Health Index, Analytic Hierarchy Process, Fault Detection and Classification, Trouble Decision Support Model
相關次數： 點閱：180  下載：34 
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

    • 由於半導體封裝廠之製程為大量生產且資本密集，其面臨一個重大的挑戰─監控數以千計的機台。一般而言，整體機台效率（overall equipment effectiveness, OEE）已被廣用於衡量機台之生產力與取得其資狀態。然而，有些其他因子未被OEE所定義，例如，某些零件或零組件的使用率。我們提出一個機台健康監控（equipment health monitoring, EHM）之流程來增加機台利用率，以達到增加OEE的效果。EHM 流程有許多模組包含:資料預處理、離群值偵測、統計SPC製程管控、目標層級架構法（analytic hierarchy process, AHP），最後提供機台之健康指標（equipment health index, EHI）由於具有不同型態之SVID（the status variable identifications），故使用數個之統計製程管制圖（statistic process control chart）個別用來監控不同之SVID，各個SVID之權重透過AHP方法，最後得到EHI，並提出一系列方法用以建構Hotelling’s T-square健康指標輔助EHI。實證研究以台灣龍頭半導體封裝製造商驗證所提出之模型。結果顯示當健康指標降低或是機台發出警訊，此方法可以透過EHI追蹤SVID問題發生之部分，最後透過資料探勘（data mining）之方法建構決策支援系統（decision support system），找出問題之原因，用以輔助人員進行問題決策支援模組。

    Due to the semiconductor assembly process is capital-intensive for mass production, the industry faces a major challenge of management issue: monitoring the thousands of equipment. In general, overall equipment effectiveness (OEE)has been widely used to measure the productivity and assess the status of equipment. However, there are some other indices not identified according to the OEE, for example, the usage of consumables and spare parts. This study proposed an equipment health monitoring (EHM) framework to improve the OEE, drive the productivity, and support preventive maintenance. The EHM framework has several modules including the data pre-processing, statistical process control (SPC), analytic hierarchy process (AHP), and finally provides an equipment health index (EHI) of the equipment. According to different types of the status variable identifications (SVIDs), several SPC control charts are developed to monitor each SVID individually and the weight of each SVID is extracted to build the EHI via AHP method. An empirical study of the Taiwan leading semiconductor assembly manufacturer is conducted to validate the proposed models. The result shows that the proposed framework supports the real-time monitoring of equipment health in the thousands of equipment. When EHI decreases and equipment alarms, the firm can trace the root cause by the decomposition of EHI for trouble decision support model.

    摘要 ii 第一章緒論（Introduction） 1 1.1 研究背景與動機（RESEARCH BACKGROUND AND MOTIVATION） 1 1.2 研究目的與簡介（RESEARCH PURPOSES AND INTRODUCTION） 2 1.3 研究流程與論文架構（RESEARCH FRAMEWORK AND THESIS STRUCTURE） 4 第二章文獻探討（Literature discussion） 5 2.1 機台保養的發展與歷史（DEVELOPMENT AND HISTORY OF MAINTENANCE） 5 2.2 零截斷與零膨脹（ZERO-TRUNCATED AND ZERO-INFLATED）計數型資料 11 2.3 單邊卜瓦松計數型管制圖（ONE-SIDE POISSON COUNT CONTROL CHART） 12 2.4 單邊累積品質管制圖（ONE-SIDE CUMULATIVE QUANTITY CONTROL CHART） 13 2.5 預測區間管制圖（PREDICTIVE INTERVAL CONTROL CHARTS, PI） 14 2.6 目標層級架構法（ANALYTIC HIERARCHY PROCESS, AHP） 15 2.7 HOTELLING’S T-SQUARE管制圖 16 2.8 共線性（COLLINEARITY）問題偵測與解決 17 2.9 主成分分析（PRINCIPAL COMPONENTS ANALYSIS, PCA） 19 2.10 K最鄰近（K-NEAREST NEIGHBORHOOD）演算法 21 2.11 決策樹（DECISION TREE） 22 2.12 小結（SUMMARY） 24 第三章機台健康指標建立（Equipment health index） 25 3.1 資料前處理（DATA PRE-PROCESSING） 28 3.2 切割資料（DATA SPLITTING） 36 3.3 離群值刪除（OUTLIER REMOVE） 37 3.3 變數型態判定（VARIABLE TYPE DECISION） 39 3.4 建構資料標籤（DATA LABEL） 41 3.5 目標層級架構法（ANALYTIC HIERARCHY PROCESS, AHP） 42 3.6 機台健康指標（EQUIPMENT HEALTH INDEX, EHI） 47 3.7 實證研究結果–機台健康指標（EQUIPMENT HEALTH INDEX, EHI） 48 3.8 HOTELLING’S T^2指標 53 3.9 結論（CONCLUSION） 65 第四章問題決策支援模組（Trouble decision support model model） 67 4.1 資料收集（DATA COLLECTION） 68 4.2 資料預處理（DATA PRE-PROCESSIONG） 69 4.3 統計相關性檢定及變數篩選（CORRELATION TEST AND VARIABLE SELECTION） 73 4.4 資料探勘演算法（DATA MININIG ALGORITHM） 80 4.5 分析結果（RESULT） 84 4.5 二元變數縮減（BINARY VARIABLE REDUCTION） 89 4.6 結論（CONCLUSION） 94 第五章結論與未來研究及建議（Conclusion and future study） 95 5.1 研究貢獻（CONTRIBUTION） 95 5.2 結論（CONCLUSION） 97 5.3 未來研究及建議（FUTURE STUDY AND SUGGESTION） 102 參考文獻 （Reference） 104

    Ahuja, I. (2009). Total productive maintenance Handbook of Maintenance Management and Engineering (pp. 417-459).
    Alonso, J. A., & Lamata, M. T.(2006). Consistency in the analytic hierarchy process: A new approach. International Journal of Uncertainty Fuzziness and Knowledge-Based Systems, 14(4), 445-459.
    Altman, N. S. (1992). An Introduction to Kernel and Nearest-Neighbor Nonparametric Regression. American Statistician, 46(3), 175-185.
    Arinton, E., & Korbicz, J. (2004). Dynamic high order neural networks: Application for fault diagnosis. Artificial Intelligence and Soft Computing - Icaisc 2004, 3070, 145-150.
    Baldin, A. E. (1981). Condition-Based Maintenance. Chemical Engineering, 88(16), 89-95.
    Basu, A., Gandhi, J., Chang, J., Hill, M. D., & Swift, M. M. (2013). Efficient virtual memory for big memory servers. Paper presented at the ACM SIGARCH Computer Architecture News.
    Beckman, R. J. (1973). Probability and Statistics for Engineers and Scientists - Walpole,Re and Meyers,Rh. Journal of the American Statistical Association, 68(341), 247-247.
    Bunks, C., McCarthy, D., & Al-Ani, T. (2000). Condition-based maintenance of machines using Hidden Markov Models. Mechanical Systems and Signal Processing, 14(4), 597-612.
    Chan, L. Y., Xie, M., & Goh, T. N. (2000). Cumulative quantity control charts for monitoring production processes. International Journal of Production Research, 38(2), 397-408.
    Chen, X. Y., Ma, L. Z., Chu, N., Zhou, M., & Hu, Y. Y. (2013). Classification and Progression Based on CFS-GA and C5.0 Boost Decision Tree of TCM Zheng in Chronic Hepatitis B. Evidence-Based Complementary and Alternative Medicine.
    Couturier, D. L., & Victoria-Feser, M. P. (2010). Zero-Inflated Truncated Generalized Pareto Distribution for the Analysis of Radio Audience Data. Annals of Applied Statistics, 4(4), 1824-1846.
    de Ron, A. J., & Rooda, J. E. (2005). Equipment effectiveness: OEE revisited. Ieee Transactions on Semiconductor Manufacturing, 18(1), 190-196.
    Feng, C. X. J., & Wang, X. F. D. (2004). Data mining techniques applied to predictive modeling of the knurling process. Iie Transactions, 36(3), 253-263.
    Fugate, M. L., Sohn, H., & Farrar, C. R. (2001). Vibration-based damage detection using statistical process control. Mechanical Systems and Signal Processing, 15(4), 707-721.
    Garcia, M. C., Sanz-Bobi, M. A., & del Pico, J. (2006). SIMAP: Intelligent System for Predictive Maintenance - Application to the health condition monitoring of a windturbine gearbox. Computers in Industry, 57(6), 552-568.
    Guerrero, S. (2014). Dealing with Missing Data in R: Omit, Approx, or Spline.
    Hadoop, A. (2011). Apache hadoop.
    Hoerl, A. E., & Kennard, R. W. (1970). Ridge Regression - Biased Estimation for Nonorthogonal Problems. Technometrics, 12(1), 55-67.
    Hopp, W. J., & Spearman, M. L. (2011). Factory physics: Waveland Press.
    Hotelling, H. (1931). The generalization of Student's ratio. Annals of Mathematical Statistics, 2, 360-378.
    Hung, S.-Y., Lin, Y.-L., & Lee, C.-Y. (2017). Data Mining for Delamination Diagnosis in the Semiconductor Assembly Process. Paper presented at the The 27th International Conference on Flexible Automation and Intelligent Manufacturing, Modena, Italy.
    Jaccard, P. (1901). Étude comparative de la distribution florale dans une portion des Alpes et des Jura. Bull Soc Vaudoise Sci Nat, 37, 547-579.
    Jardine, A. K. S., Lin, D. M., & Banjevic, D. (2006). A review on machinery diagnostics and prognostics implementing condition-based maintenance. Mechanical Systems and Signal Processing, 20(7), 1483-1510.
    Kass, G. V. (1980). An exploratory technique for investigating large quantities of categorical data. Applied statistics, 119-127.
    Kaufman, L., & Rousseeuw, P. (1987). Clustering by means of medoids: North-Holland.
    Kim, Y. W., Rizzoni, G., & Utkin, V. I. (2001). Developing a fault tolerant power-train control system by integrating design of control and diagnostics. International Journal of Robust and Nonlinear Control, 11(11), 1095-1114.
    Lang, S. (1987). Linear Algebra. Undergraduate texts in mathematics: Springer-Verlag, New Yoirk.
    Lee, C.-Y. (2017). 製造資料科學：從預測性思維到處方性決策. from https://www.slideshare.net/tw_dsconf/ss-71780267
    Lee, J. M., Kim, S. J., Hwang, Y., & Song, C. S. (2004). Diagnosis of mechanical fault signals using continuous hidden Markov model. Journal of Sound and Vibration, 276(3-5), 1065-1080.
    Macrosson, W. D. K. (1999). Scree, plots, data structure, and random variance. Psychological Reports, 84(2), 533-540.
    Magro, M. C., & Pinceti, P. (2009). A confirmation technique for predictive maintenance using the Rough Set Theory. Computers & Industrial Engineering, 56(4), 1319-1327.
    Mahalanobis, P. C. (1936). A Note on the Statistical and Biometric Writings of Karl Pearson. Sankhya, 2, 411-422.
    Mcgill, R., Tukey, J. W., & Larsen, W. A. (1978). Variations of Box Plots. American Statistician, 32(1), 12-16.
    Meng, X., Bradley, J., Yavuz, B., Sparks, E., Venkataraman, S., Liu, D., . . . Owen, S. (2016). Mllib: Machine learning in apache spark. Journal of Machine Learning Research, 17(34), 1-7.
    Mukaka, M. M. (2012). Statistics Corner: A guide to appropriate use of Correlation coefficient in medical research. Malawi Medical Journal, 24(3), 69-71.
    Norberg, R. (2016). Understanding data.table Rolling Joins.
    Pearson, K. (1895). Note on regression and inheritance in the case of two parents. Proceedings of the Royal Society of London, 58, 240-242.
    Pearson, K. (1901). On lines and planes of closest fit to systems of points in space. Philosophical Magazine, 2(7-12), 559-572.
    Quinlan, J. R. (1987). Simplifying Decision Trees. International Journal of Man-Machine Studies, 27(3), 221-234.
    Quinlan, J. R. (1996). Improved use of continuous attributes in C4.5. Journal of Artificial Intelligence Research, 4, 77-90.
    Saaty, T. L. (1990). How to Make a Decision - the Analytic Hierarchy Process. European Journal of Operational Research, 48(1), 9-26.
    Saaty, T. L., & Tran, L. T. (2007). On the invalidity of fuzzifying numerical judgments in the Analytic Hierarchy Process. Mathematical and Computer Modelling, 46(7-8), 962-975.
    Skydome. (2016, 2016/06/06). 遺漏值處理(Impute Missing Value). from http://rpubs.com/skydome20/R-Note10-Missing_Value
    Suits, D. B. (1957). Use of Dummy Variables in Regression Equations. Journal of the American Statistical Association, 52(280), 548-551.
    Susto, G. A., Schirru, A., Pampuri, S., McLoone, S., & Beghi, A. (2015). Machine Learning for Predictive Maintenance: A Multiple Classifier Approach. Ieee Transactions on Industrial Informatics, 11(3), 812-820.
    Talbot, F. B. (1982). Resource-Constrained Project Scheduling with Time-Resource Tradeoffs - the Non-Preemptive Case. Management Science, 28(10), 1197-1210.
    Tate, R. F. (1954). Correlation between a Discrete and a Continuous Variable - Point-Biserial Correlation. Annals of Mathematical Statistics, 25(3), 603-607.
    Tsai, T.-L., & Lee, C.-Y. (2017). Data Mining for Yield Improvement of Photo Spacer Process in Color Filter Manufacturing. Paper presented at the The 27th International Conference on Flexible Automation and Intelligent Manufacturing, Modena, Italy.
    Wang, W. B., & Zhang, W. J. (2005). A model to predict the residual life of aircraft engines based upon oil analysis data. Naval Research Logistics, 52(3), 276-284.
    Wang, Y., & Boyd, S. (2010). Fast model predictive control using online optimization. IEEE Transactions on Control Systems Technology, 18(2), 267-278.
    Wang, Y., & Witten, I. H. (1996). Induction of model trees for predicting continuous classes.
    Ward, J. H. (1963). Hierarchical Grouping to Optimize an Objective Function. Journal of the American Statistical Association, 58(301), 236-244.
    Yu, H. C., Lin, K. Y., & Chien, C. F. (2014). Hierarchical indices to detect equipment condition changes with high dimensional data for semiconductor manufacturing. Journal of Intelligent Manufacturing, 25(5), 933-943.
    Zahedi, F. (1986). The Analytic Hierarchy Process - a Survey of the Method and Its Applications. Interfaces, 16(4), 96-108.
    Zhao, Y. H., & Zhang, Y. X. (2008). Comparison of decision tree methods for finding active objects. Advances in Space Research, 41(12), 1955-1959.

    下載圖示 校內：2022-01-01公開
    校外：2022-01-01公開
    QR CODE