Multi-leak Diagnosis in Pipelines A Comparison of Approaches

Author

Verde, C. ; Morales-Menendez, R. ; Garza, L.E. ; Vargas, A. ; Velasquez-Roug, P. ; Rea, C. ; Aparicio, C.T. ; De la Fuente, J.O.

Author_Institution

Inst. de Ing., UNAM, Coyoacan

fYear

2008

fDate

27-31 Oct. 2008

Firstpage

352

Lastpage

357

Abstract

Leaks on pipelines can cause strong economic losses and environmental problems if these are not detected on time. The problem of detecting leaks is even more complicated when the pipelines are too large, difficult to reach by maintenance personnel, and equipped with minimum instrumentation. A comparison of four fault diagnosis approaches based on Output Observers, Artificial Neural Networks, Particle Filtering and Principal Components Analysis are presented. Simulated results of multi-leaks in pipelines showed that Particle Filtering techniques outperform the other approaches. However, a combined solution is proposed.

Keywords

fault diagnosis; mechanical engineering computing; neural nets; observers; particle filtering (numerical methods); pipelines; principal component analysis; artificial neural networks; economic losses; environmental problems; fault diagnosis; multi-leak diagnosis; output observers; particle filtering; pipelines; principal components analysis; Artificial neural networks; Environmental economics; Environmental factors; Fault diagnosis; Filtering; Instruments; Leak detection; Personnel; Pipelines; Principal component analysis; Fault Detection and Isolation; Fault Diagnosis; Leak Pipeline;

fLanguage

English

Publisher

ieee

Conference_Titel

Artificial Intelligence, 2008. MICAI '08. Seventh Mexican International Conference on

Conference_Location

Atizapan de Zaragoza

Print_ISBN

978-0-7695-3441-1

Type

conf

DOI

10.1109/MICAI.2008.33

Filename

4682487