應用類免疫網路非線性系統鑑別與錯誤診斷

Nonlinear System Identification and Fault Diagnosis Using Artificial Immune Network

鄭維崇(Wei-chong Cheng)

指導教授 ： 陸冠群

大同大學/工程學院/機械工程學系所/博士(2004年)

摘要

為增進系統之性能，可靠性，與安全性，許多研究致力於系統鑑別與錯誤診斷之相關課題。系統鑑別能有效地改進控制的效能，特別是對於複雜未知的非線性系統。此外，早期診斷出錯誤能避免設備的損壞與損失。因此，發展有效且具有強健性之錯誤診斷成為工程應用領域裡的重要研究課題。
本論文中提出以類免疫系統為基礎之非線性系統鑑別與錯誤診斷之方法，包括：正向與逆向類免疫系統鑑別，殘值濾波產生機制，錯誤警報濃度方法，與類免疫調節機制。在本研究中採用多種非線性系統之電腦模擬，以探討與驗證本研究所提之相關方法，結果顯示所提出之系統鑑別與錯誤診斷之方法具有良好之效能與強健性。

關鍵字

系統鑑別 ； 類免疫網路 ； 錯誤診斷

並列摘要

In order to improve the system performance, reliability, and safety, many researchers have focused their attention on the issues of system identification and fault diagnosis during the last two decades. Nonlinear system identification can improve control performance significantly, especially when the system behaviors are complex, unknown, and with great nonlinearity. In addition, the early detection of faults can prevent the destruction of equipment and avoid great losses. Therefore, the development of effective and robust methods for fault diagnosis has become an important field of research in engineering applications
In this dissertation, a novel approach to immune model-based fault diagnosis methodology for nonlinear systems is presented. The diagnosis scheme consists of forward/inverse immune model identification, filtered residual generation method, the fault alarm concentration (FAC) scheme, and the artificial immune regulation (AIR) mechanism. To verify and demonstrate the effectiveness of the proposed schemes, several simulations are employed to validate the effectiveness and robustness of the system identification and diagnosis approach.

並列關鍵字

Artificial Immune Network ； Fault Diagnosis ； System Identification

參考文獻

M.A. Abido, and Y.L. Abdel-Magid, Online identification of a synchronous machine using a radial basis function network, American Control Conference, 1997. Proceedings of the 1997, Volume: 3, (1997), 1946 -1950.

L.A. Aguirre, and C.R.F. Jácome, Cluster analysis of NARMAX models for signal-dependent systems, IEE Proceedings-Control Theory Application, 145(4), (1998), 409-414.

P.F. Baldi, and B. Soren, Bioinformatics: The machine Learning approach, (The MIT Press, 1999).

P. Balle, Fuzzy-model-based parity equations for fault isolation, Control Engineering Practice, Volume: 7, Issue: 2, (February, 1999), 261-270.

S. Barada and H. Singh, Generating optimal adaptive fuzzy-neural models of dynamical systems with applications to control, IEEE Transactions on Systems, Man and Cybernetics, Part C, Volume: 28 Issue: 3, (Aug. 1998), 371 –391.