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.

Recent Advances on Optimization for Control, Observation, and Safety

“…Navarro et al [20] propose a method to detect, locate, and estimate the magnitude of leaks in a pipeline using only flow rate and pressure head measurements at both ends of the pipe. The method develops a mathematical model that builds an observer ensemble using genetic algorithms.…”

Gas pipeline safety management system based on neural network

“…The accuracy of the results is determined by how close the mathematical model being developed is to reality. Many studies employed a model‐based approach for leak detection and diagnostics (LDD) but assuming incompressible or steady flows 8–11 . However, there has been no other study on leak detection and diagnostics for compressible and dynamics flows except that of Pan et al 12 Pan et al 12 developed an observer‐based leak detection system considering a 10 km natural gas pipeline that was subjected to process disturbance.…”

Two Simultaneous Leak Diagnosis in Pipelines Based on Input–Output Numerical Differentiation

“…Thus, once a leak is identified, the repair technicians can fix the leak and avoid the water loss. Many works that address the LDI problem for one leak have been reported [ 2 , 3 , 4 , 5 , 6 ]. For instance, in [ 2 ], a leak isolation methodology using a fitting loss coefficient calibration is presented on the basis of two stages: in the first stage, the equivalent straight length ( ESL ) is fixed by a model-based observer designed as an extended Kalman filter ( EKF ); in the second stage, an algebraic observer is started with the ESL value fixed by the previous observer.…”

“…In other words, the solution provided by the EKF is less accurate by itself. In [ 4 ], authors propose a bank of observers together with a Genetic Algorithm ( GA ), which is exploited to minimize the integration of the square observation error. The minimum integral observation error is reached in the observer where the estimated leak parameters match the real values.…”