Model based diagnosis using causal graph

• Autorzy: Sztyber A.

Warianty tytułu

PL

Zastosowanie grafu przyczynowo-skutkowego w diagnostyce wykorzystującej modele procesu

• Języki publikacji: EN

Abstrakty

EN

This paper concerns fault diagnosis of industrial plants and complex systems with special interest in fault diagnosis system design. Scope of research connected with using causal graphs to fault diagnosis is presented. Directed graph is used to describe causal relationships between process variables and faults. New method for finding set of model structures based on causal graph is presented. Model structure is understood as an output variable and set of input variables. Algorithm for determining model sensitivity to faults is described. Method for finding possible ability to detect and isolate each fault given calculated set of models is described. Main ideas are explained on simple example.

PL

Artykuł dotyczy zagadnień projektowania systemów diagnostyki procesów przemysłowych z wykorzystaniem grafów przyczynowo-skutkowych. Przedstawiono stan badań dotyczących zastosowania grafów w diagnostyce. Graf przyczynowo-skutkowy jest grafem skierowanym zawierającym wierzchołki reprezentujące zmienne i uszkodzenia oraz krawędzie obrazujące wzajemne oddziaływania. Zaprezentowano metodę znajdowana zbioru struktur wszystkich modeli, które mogą zostać wykorzystane w systemie diagnostycznym. Opisany jest sposób określania wrażliwości modeli na uszkodzenia oraz znajdowania możliwej do uzyskania wykrywalności i rozróżnialności uszkodzeń.

Słowa kluczowe

EN

fault diagnosis; causal graph; model

PL

diagnostyka przemysłowa; graf przyczynowo-skutkowy; modele

• Wydawca: Sieć Badawcza Łukasiewicz - Przemysłowy Instytut Automatyki i Pomiarów PIAP
• Czasopismo: Pomiary Automatyka Robotyka
• Rocznik: 2013
• Tom: R. 17, nr 1
• Strony: 83--88
• Opis fizyczny: Bibliogr. 20 poz., rys., tab.

Twórcy

autor

Sztyber A.

• Institute of Automation Control and Robotics, Warsaw University of Technology,

Bibliografia

• 1. Ira M., Aoki K., O’Shima E., Matsuyama H., An algorithm for diagnosis of system failures in the chemical process, “Computers&Chemical Engineering”, 3:489-493, 1979.
• 2. Ulerich N.H., Powers G.J., On-line hazard aversion and fault diagnosis in chemical processes: The digraph + fault-tree method. IEEE Transactions on Reliability, 171-177, 1988.
• 3. Fan Yang, Shah L.S., Deyun Xiao, Sdg modelbased analysis of fault propagation in control systems. Canadian Conference on Electrical and Computer Engineering, 1152-1157, 2009.
• 4. Chung-Chien Changt, Cheng-Ching Yu, Online fault diagnosis using the signed directed graph. “Industrial & Engineering Chemistry Research”, 29:1290-1299, 1990.
• 5. Blanke M., Kinnaert M., Lunze J., Staroswiecki M., Diagnosis and fault-tolerant control. Springer-Verlag, Berlin 2003.
• 6. Gang Xie, Xiue Wang, Keming Xie, Sdg-based fault diagnosis and application based on reasoning method of granular computing, Control and Decision Conference, 1718-1722, 2010.
• 7. Tarifa E.E., Scenna N.J., Fault diagnosis, direct graphs, and fuzzy logic, “Computers & Chemical Engineering”, 21:649-654, 1997.
• 8. Fang T., Pattipati K.R., Deb S., Malepati V.N., Computationally efficient algorithms for multiple fault diagnosis in large graph-based systems, “IEEE Transactions on Systems, Man and Cybernetics”, Part A: Systems and Humans, 73-85, 2003.
• 9. Hideo Nakano, Yoshiro Nakanishi, Graph representation and diagnosis for multiunit faults, “IEEE Transactions on Reliability”, 23(5):320-325, 1974.
• 10. Maurya M.R., Rengaswamy R., Venkatasubramanian V., A systematic framework for the development and analysis of signed digraphs for chemical processes, Industrial & Engineering Chemistry Research, 4789-4827, 2003.
• 11. Maurya M.R., Rengaswamy R., Venkatasubramanian V., A signed directed graph and qualitative trend analysis-based framework for incipient fault diagnosis, “Chemical Engineering Research and Design”, 85(29):1407-1422, 2007.
• 12. Fan Yang, Shah L.S., Deyun Xiao, Signed directed graph modeling of industrial processes and their validation by data-based methods. 2010 Conference on Control and Fault-Tolerant Systems (Sys-Tol), 387-392, 2010.
• 13. Bauer M., Cox J.W., Caveness M.H., Downs J.J., Thornhill N.F., Finding the direction of disturbance propagation in a chemical process using transfer entropy, “IEEE Transactions on Control Systems Technology”, 15(1), 12-21, 2007.
• 14. Bauer M., Thornhill N.F., A practical method for identifying the propagation path of plant-wide disturbances, “Journal of Process Control”, 18:707-719, 2008.
• 15. Wen-Liang Cao, Bing-ShuWang, Liang-Yu Ma, Ji Zhang, Jian-Qiang Gao. Fault diagnosis approach based on the integration of qualitative model and quantitative knowledge of signed directed graph. International Conference on Machine Learning and Cybernetics, 2251-2256, 2005.
• 16. Lakshmanan K.B., Rosenkrantz D.J., Ravi S.S., Alarm placement in systems with fault propagation. “Theoretical Computer Science”, 243:1217-1223, 2000.
• 17. Rao N.S.V., On parallel algorithms for single-fault diagnosis in fault propagation graph systems, “IEEE Transactions on Parallel and Distributed Systems”, 7(12):1217-1223, 1996.
• 18. Bingshu Wang, Wenliang Cao, Liangyu Ma, Ji Zhang, Fault diagnosis approach based on qualitative model of signed directed graph and reasoning rules. FSKD (2)’05, 339-343, 2005.
• 19. Ostasz A., Causal graph and its application to finding residual set and diagnostic relation (in polish). PhD thesis, Warsaw University of Technology, Warsaw 2006.
• 20. Cormen T.H., Leiserson C.E., Rivest R., Introduction to Algorithms. Massachusetts Institute of Technology, 2009.