工業製程的控制可分為統計製程管制(SPC)與自動製程控制(APC)兩大範疇，SPC多應用在批次製程，而APC則多應用於連續製程。隨著工業製程日漸精密化與多元化，SPC與APC之整合技術逐漸受到重視，也獲得廣泛的應用。
本論文提出可提供自動控制製程前饋調整功能之統計監控方法，主要包括製程線上監控、確定性擾動之定性定量分析以及結合回饋控制之前饋調整三個部分。首先，利用EWMA管制圖對製程輸出進行線上監控，針對造成產品品質變差的可指派原因，發出製程異常警報。
當SPC管制圖監控系統偵測到製程異常輸出(均值改變或確定性擾動)時，利用互相關(cross correlation)法與最小均方差法分別對製程確定性擾動進行即時定性與定量分析。互相關法乃檢測所架構之模擬系統與真實系統之相似程度，可估測出確定性擾動的類型及發生的時間，而最小化均方差法則是利用最大概似估測量來估算確定性擾動的大小。
由於擾動分析可即時得知確定性擾動的特性，本論文發展與原回饋控制器結合之前饋調整策略，該APC策略針對已知的確定性擾動以前饋控制器進行補償，而回饋控制器負責消除未知隨機性擾動的影響。

The control of industrial processes can be divided into two categories: statistical process control (SPC) and automatic process control (APC). SPC methods are often used in batch processes, while APC methods are often used in continuous processes. With sophistication and diversification in industrial processes, integrated SPC and APC strategies have attracted much attention and gained wide applications.
This thesis proposes a statistical monitoring method to provide feedforward regulation for automatically controlled processes. The method consists of three major portions: on-line monitoring of the process, qualitative and quantitative analyses of deterministic disturbance properties, and feedforward compensation that combines feedback control. First, the EWMA control chart is applied to monitor the process output on line, and will give an alarm of abnormal processing for assignable causes that may deteriorate product quality.
As the SPC control chart monitoring system detects the abnormal output of the process (a mean change or a deterministic disturbance), the cross-correlation method and minimum mean squared error (MMSE) method are employed to perform respectively the qualitative and quantitative analyses for the deterministic disturbance in real time. The cross-correlation method could estimate the type and occurring time of the deterministic disturbance by examining the degree of similarity between the actual system and the simulated system. The MMSE method determines the magnitude of the deterministic disturbance using the concept of maximum likelihood estimation.
Because the properties of the deterministic disturbance can be revealed by the disturbance analyses in real time, this thesis then develops a feedforward regulation strategy to combine the original feedback control. This APC control strategy uses the feedforward regulator to compensate for the known deterministic disturbance, and uses the feedback controller to eliminate the influence of random disturbances.

[1] 潘浙楠, 李文瑞, 品質管理, 華泰, 台北市, 2000.
[2] 劉漢容, 品質管理(Quality Control), 三民, 台北市, 2003.
[3] Seborg, D. E., Edgar, T. F., Mellichamp, D. A. Process Dynamics and Control, 2nd edition, John Wiley, 2003.
[4] Shewat, W. A. Economic Control of Quality of Manufactured Product, American Society for Quality Control, 1980.
[5] Page, E. S. “Continuous Inspection Schemes”, Biometrika, Vol. 41, 100-115, 1954.
[6] Page, E. S. “Cumulative Sum Control Charts”, Technometrics, Vol. 3, 1-9, 1961.
[7] Page, E. S. “Controlling the Standard Deviation by Cusums and Warning Lines”, Technometrics, Vol. 5, 307-315, 1963.
[8] Roberts, S. W. “Control Chart Tests Based on Geometric Moving Averages”, Technometrics, Vol. 1, 239-267, 1959.
[9] Box, G. E. P., Jenkins, G. M., and Reinsel, G. M. Time Series Analysis: Forecasting and Control, Holden-Day, 1976.
[10] Oakland, J. S. and Followell, R. F. Statistical Process Control, Butterworth-Heinemann, 1990.
[11] Farnum, N. Modern Statistical Quality Control and Improvement, Duxbury, 1993.
[12] Woodall, W. H. “The Design of CUSUM Quality Control Chart”, Journal of Quality Technology, Vol. 18, 99-102, 1986.
[13] Box, G. E. P., and Kramer, T. “Statistical Process Monitoring and Feedback Adjustment-A Discussion”, Technometrics, Vol. 34, 251-267, 1992.
[14] Montgomery, D. C., Keats, J. B., Runger, G. C. and Messina, W. S. “Integrating Statistical Process Control and Engineering Process Control”, Journal of Quality Technology, Vol. 26, 79-86, 1994.
[15] Sachs, E., Hu, A., Ingolfsson, A. “Run to Run Process Control: Combining SPC and Feedback Control ”, IEEE Transaction on Semiconductor Manufacturing, Vol. 8, 26-43, 1995.
[16] Tsung, F., Shi, J. “Integrated Design of Run-to-Run PID Controller and SPC Monitoring for Process Disturbance Rejection,” IIE Transactions, Vol.31, 517-527, 1999.
[17] Tsung, F., Tsui, K. L. “A Mean-shift Pattern Study on Integration of SPC and APC for Process Monitoring,” IIE Transactions, Vol. 35, 231-242, 2003.
[18] Hu, S.J. and Roan, C. “Change Patterns of Time Seriesbased Control Charts”, Journal of Quality Technology, Vol. 28, 302-312, 1996.
[19] Venkatesan, G. “Process Control of Product Quality,” ISA Transactions, Vol. 42, 631-641, 2003.
[20] Gültekin, M., Elsayed, E.A., English, J. R. and Hauksdóttir, A. S. “Monitoring Automatically Controlled Processes Using Statistical Control Charts”, INT. J. PROD. RES., Vol. 40, 2303-2320, 2002.
[21] Montgomery, D. C. Introduction to Statistical Quality Control, 4th edition, John Wiley, New York, 2001.
[22] Crowder, S. V. “A Simple Method for Studying Run-Length Distributions of Exponentially Weighted Moving Average Charts”, Technometrics, Vol. 29, 401-407, 1987.
[23] Crowder, S. V. “Design of Exponentially Weighted Moving Average Schemes”, Journal of Quality Technology, Vol. 21, 155-162, 1989.
[24] Lucas, J. M., and M. S. Saccucci, “Exponentially Weighted Moving Average Control Schemes: Properties and Enhancements”, Technometrics, Vol. 32, 1-12, 1990.
[25] 方世榮, 基礎統計學, 華泰, 台北市, 1999.
[26] 戴久永, 統計概念與方法, 三民, 台北市, 1991.
[27] 陳超塵, 統計學原理, 陳超塵印行, 台北市, 1981.
[28] 林元興, 統計理論與方法, 華泰, 台北市, 1981.
[29] Bequette, B. W., Process Control: Modeling Design, and Simulation, Prentice Hall, 2002.
[30] Coughanowr, D. R., Process Systems Analysis and Control, 2nd edition, McGraw-Hill, 1990.
[31] Smith, C. A., and Corripio, A. B., Principles and Practice of Automatic Process Control, 2nd edition, John Wiley, 1996.