以碎形編碼與小波轉換為基礎之批次監控系統

在化工產業邁向高度自動化的今日，製程操作大都擁有數量龐大、及種類繁多的操作數據資料，因此發展一套監控系統偵測，並察覺製程操作狀態是否發生異常是必要的。本研究發展一結合小波轉換（Wavelet Transform, WT）與碎形編碼（Fractal Encoding, FE）模式為基礎的線上即時批次監控系統，除了利用小波轉換的多重解析架構，改進了以往只針對時間面上的監控，更進一步利用FE在多重解析空間上，隨著觀測數據變異考慮其存在的聚集與持續性兩個特徵，建立不同的局部區塊特徵模型，而在擷取過去操作的資訊建立模型之後，該監控方法的原理與傳統的統計程序控制（Statistical Process Control, SPC）相似，建立簡單的監控管制圖，可以很容易追蹤每一個批次製程的進行，和監控製程錯誤的發生。此外，在建立線上即時監控製程的管制方法上，因為FE具有區域之特性，僅需補足部分數據，可有效提升線上即時製程監控效果，改善以往線上即時製程監控需補足未發生數據的缺點。本研究將利用杜邦批次聚合反應以及饋料批次盤尼西林（penicillin）發酵製程，與過去傳統的線上即時批次監控方法做比較，並說明所提出的線上即時批次製程監控系統的優點。

關鍵字

碎形編碼；多維度主成份分析；小波轉換

並列摘要

In today, chemical industry march toward increasingly automated, abundant real-time data gathered in the automatic system contain the complexity and uncertainty, so develop one monitoring system to monitor the operation status is essential. In this paper, develop on-line monitoring batch operation system based on the wavelet transform (WT) analysis and the fractal encoding (FE) technique. Using WT with a local-time frequency analysis, this strategy takes the advantage of the multiresolution representation. FE is used to extract the features from the cluster and persistence in the time-frequency representation. By extracting fractal models, the proposed method, like the philosophy of the traditional statistical process control (SPC), can generate simple monitoring charts, track the progress in each batch run, and monitor the occurrence of observable upsets. However, due to the local property of FE, the on-line batch monitoring based on the proposed method is better than the conventional methods, because without fulfilling data set from the current time to the end of the batch run, filling the missing value at some local regions is good enough for detecting the current status. Additionally, the applications are demonstrated through two set of benchmark data, a DuPont industrial batch polymerization reactor and a fed-batch penicillin production, to illustrate the advantages of the proposed method in comparison to some conventional methods.

並列關鍵字

wavelet transform ； multi-way PCA ； fractal encoding

參考文獻

1. Aradhye, H. B.; Bakshi, B. R.; Strauss, R. A.; Davis, J. F., “Multiscale SPC Using Wavelets – Theoretical Analysis and Properties,” American Institute of Chemical Engineers Journal, 49, 939（2003）

2. Bakshi, B. R., “Multiscale PCA with Application to Multivariate Statistical Process Monitoring,” American Institute of Chemical Engineers Journal, 44, 1596（1998）

3. Barnsley, M. F., “Fractals Everywhere, ” New York: Academic, （1988）.

4. Barthel, K. U., Cycon, H. L., Marpe, D., “Image Denoising using Fractal and Wavelet-based Methods,” Proceedings of SPIE, 5266, 39（2004）

5. Birol G.; Ündey C. and Cinar A., “A Modular Simulation Package for Fed-batch Fermentation: Penicillin Production,” Computers and Chemical Engineering, 26, 1553 (2002).

國際替代計量

以碎形編碼與小波轉換為基礎之批次監控系統

未授權

主題瀏覽