Artículos

 

Fault Detection in a Heat Exchanger, Comparative Analysis between Dynamic Principal Component Analysis and Diagnostic Observers

 

Detección de fallas en un intercambiador de calor, análisis comparativo entre análisis de componentes principales dinámico y observadores de diagnóstico

 

Juan C. Tudón Martínez^1*, Rubén Morales Menéndez^1**, Ricardo A. Ramírez Mendoza^1***, Luis E. Garza Castañón^1**** and Adriana Vargas Martínez^1*****

 

¹ Tecnológico de Monterrey, Campus Monterrey, Monterrey N.L., México (A00287756@itesm.mx*, rmm@itesm.mx**, ricardo.ramirez@itesm.mx***, legarza@itesm.mx****, A00777924@itesm.mx*****

 

Article received on September 01, 2009
Accepted on February 08, 2010

 

Abstract

A comparison between the Dynamic Principal Component Analysis (DPCA) method and a set of Diagnostic Observers (DO) under the same experimental data from a shell and tube industrial heat exchanger is presented. The comparative analysis shows the detection properties of both methods when sensors and/or actuators fail online, including scenarios with multiple faults. Similar metrics are defined for both methods: robustness, quick detection, isolability capacity, explanation facility, false alarm rates and multiple faults identifiability. Experimental results show the principal advantages and disadvantages of both methods. DO showed quicker detection for sensor and actuator faults with lower false alarm rate. Also, DO can isolate multiple faults. DPCA required a minor training effort; however, it can not identify two or more sequential faults.

Keywords: Fault Detection and Diagnosis, Model Classification, Computer Application, Dynamic Principal Component Analysis, Diagnostic Observers.

 

Resumen

El artículo presenta una comparación entre dos métodos de detección de fallas, Análisis de Componentes Principales Dinámico (DPCA por sus siglas en inglés) y Observadores de Diagnóstico (DO por sus siglas en inglés), bajo los mismos datos experimentales extraídos de un intercambiador de calor industrial de tubo y coraza. El análisis comparativo muestra las propiedades de detección de ambos métodos cuando sensores y/o actuadores fallan en línea, incluyendo fallas múltiples. Para ambos métodos se definen métricas similares: robustez, tiempo de detección, capacidad de aislamiento y explicación de propagación de fallas, tasa de falsas alarmas y capacidad de identificar fallas múltiples. Los resultados experimentales muestran las ventajas y desventajas de ambos métodos. DO detecta más rápido las fallas de sensores y actuadores, presenta menor tasa de falsas alarmas y puede aislar fallas múltiples. DPCA requiere menor esfuerzo de entrenamiento; sin embargo, no puede identificar 2 o más fallas secuenciales.

Palabras clave: Detección y Diagnóstico de Fallas, Clasificación de modelos, Aplicación Computacional, Análisis de Componentes Principales Dinámico, Observadores de Diagnóstico.

 

DESCARGAR ARTÍCULO EN FORMATO PDF

 

References

1. Astorga–Zaragoza, C. M., Alvarado–Martínez, V. M., Zavala–Río, A. & Méndez–Ocaña R. M. (2008). Observer–based monitoring of heat exchangers. ISA Transactions, 47(1), 15–24.         [ Links ]

2. Caccavale, F. & Villani, L. (2004). An adaptive observer for fault diagnosis in nonlinear discrete–time systems. American Control Conference 2004, Boston Massachusetts, USA, 3, 2463–2468.         [ Links ]

3. Cui, P., Li, J. & Wang, G. (2008). Improved kernel principal component analysis for fault detection. Expert Systems with Applications, 34(2), 1210–1219.         [ Links ]

4. Chen, J. & Patton R. J. (1999). Robust model–based fault diagnosis for dynamic systems. Boston: Kluwer Academic Publishers.         [ Links ]

5. Dai, X., Liu G. & Long, Z. (2008). Discrete–time robust fault detection observer design: a genetic algorithm approach. 7^th World Congress Intelligent Control & Automation, Chongqing, China, 2843–2848.         [ Links ]

6. Detroja, K. P., Gudi, R. D. & Patwardhan, S. C. (2007). Plant–wide detection and diagnosis using correspondence analysis. Control Engineering Practice, 15(12), 1468–1483.         [ Links ]

7. Habbi, H., Kinnaert M. & Zelmat, M. (2009). A complete procedure for leak detection and diagnosis in a complex heat exchanger using data–driven fuzzy models. ISA Transactions, 48(3), 354–361.         [ Links ]

8. Hotelling, H. (1993). Analysis of a complex of statistical variables into principal components. Journal of Educational Psychology, 24(7), 498–520.         [ Links ]

9. Isermann, R. (2006). Fault–diagnosis systems, Berlin; New York: Springer.         [ Links ]

10. Jackson, J. E. & Mudholkar, G. S. (1979). Control procedures for residuals associated with principal component analysis. Technometrics, 21(3), 341–349.         [ Links ]

11. Krishnan, R. A. & Pappa, N. (2005). Real time fault diagnosis for a heat exchanger – a model based approach. 2005 Annual IEEE INDICON, Chennai, India, 78–82.         [ Links ]

12. Ku, W., Storer, R. H. & Georgakis, C. (1995). Disturbance detection and isolation by dynamic principal component analysis. Chemometrics and Intelligent Laboratory Systems, 30(1), 179–196.         [ Links ]

13. Lingfang, S., Yingying, Z. & Rina, S. (2009). Research on the fouling prediction of heat exchanger based on Support Vector Machine optimized by particle swarm optimization algorithm. International Conference on Mechatronics and Automation, Changchun, China, 2002–2007.         [ Links ]

14. Miller, P., Swanson, R. E. & Heckler, C. E. (1998). Contribution plots: a missing link in multivariate quality control. International Journal of Applied Mathematics and Computer Science, 8(4), pp: 775–792.         [ Links ]

15. Mina, J. & Verde, C. (2007). Fault detection for MIMO systems integrating multivariate statistical analysis and identification methods. American Control Conference 2007, New York, USA, 3234–3239.         [ Links ]

16. Morales–Menendez, R., de Freitas, N., & Poole, D. (2003). Estimation and control of industrial processes with particle filters. American Control Conference 2003, Denver Colorado, USA, 579–584.         [ Links ]

17. Parera, A., Papamichail, N., Barsan, N., Weimar, U. & Marco, S. (2006). On–line novelty detection by recursive dynamic principal component analysis and gas sensor arrays under drift conditions. IEEE Sensors Journal, 6(3), 770–783.         [ Links ]

18. Puig, V., Quevedo, J., Escobet T., Nejjari F. & de las Heras, S. (2008). Passive robust fault detection of dynamic processes using interval models. IEEE Transactions on Control Systems Technology, 16(5), 1083–1089.         [ Links ]

19. Rea–Palacios, C., Morales–Menendez, R. & Verde–Rodarte, C. (2008). Identificación de fallas en un intercambiador de calor. Research in Computing Science, México D.F., 36, 3–12.         [ Links ]

20. Simmani, S. & Patton, R. J. (2008). Fault diagnosis of an industrial gas turbine prototype using a system identification approach. Control Engineering Practice, 16(7), 769–786.         [ Links ]

21. Tudón–Martínez, J.C. (2008). Fault detection and diagnosis in a heat exchanger using DPCA and diagnostic observers. MSc thesis, Tecnológico de Monterrey, Monterrey Nuevo León, México.         [ Links ]

22. Tudón–Martínez, J. C., Morales–Menendez, R., & Garza–Castañón, L. E. (2009). Fault detection and diagnosis in a heat exchanger. 6^th International Conference on Informatics in Control, Automation and Robotics ICINCO 2009, Milan, Italy, 265–270.         [ Links ]

23. Venkatasubramanian, V., Rengaswamy, R., Kavuri, S., & Yin, K. (2003). A review of process fault detection and diagnosis part I quantitative model–based methods. Computers & Chemical Engineering, 27(3), 293–311.         [ Links ]

24. Verde, C. (2001). Multi–leak detection and isolation in fluid pipelines. Control Engineering Practice, 9(6), 673– 682.         [ Links ]

25. Wu, D. & Ho, W. C. (2009). Fuzzy filter design for itô stochastic systems with application to sensor fault detection. IEEE Transactions on Fuzzy Systems, 17(1), 233–242.         [ Links ]