Skip to Main content Skip to Navigation
Journal articles

Evolutionary Observer Ensemble for Leak Diagnosis in Water Pipelines

Abstract : This work deals with the Leak Detection and Isolation (LDI) problem in water pipelines based on some heuristic method and assuming only flow rate and pressure head measurements at both ends of the duct. By considering the single leak case at an interior node of the pipeline, it has been shown that observability is indeed satisfied in this case, which allows designing an observer for the unmeasurable state variables, i.e., the pressure head at leak position. Relying on the fact that the origin of the observation error is exponentially stable if all parameters (including the leak coefficients) are known and uniformly ultimately bounded otherwise, the authors propose a bank of observers as follows: taking into account that the physical pipeline parameters are well-known, and there is only uncertainty about leak coefficients (position and magnitude), a pair of such coefficients is taken from a search space and is assigned to an observer. Then, a Genetic Algorithm (GA) is exploited to minimize the integration of the square observation error. The minimum integral observation error will be reached in the observer where the estimated leak parameters match the real ones. Finally, some results are presented by using real-noisy databases coming from a test bed plant built at Cinvestav-Guadalajara, aiming to show the potentiality of this method
Document type :
Journal articles
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-02434570
Contributor : Gildas Besancon <>
Submitted on : Friday, January 10, 2020 - 10:54:49 AM
Last modification on : Wednesday, October 7, 2020 - 11:36:04 AM

Links full text

Identifiers

Collections

Citation

A. Navarro, J. Delgado-Aguiñaga, J. Sánchez-Torres, O. Begovich, Gildas Besancon. Evolutionary Observer Ensemble for Leak Diagnosis in Water Pipelines. Processes, MDPI, 2019, 7 (12), pp.913. ⟨10.3390/pr7120913⟩. ⟨hal-02434570⟩

Share

Metrics

Record views

58