Performance assessment of leak detection failure sensors used in a water distribution system

Khan, Asar; Widdop, Peter D.; Day, Andrew J.; Wood, Alastair S.; Mounce, S. R.; Machell, John

doi:10.2166/aqua.2005.0003

Cited by 11 publications

(2 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…N water distribution systems, a significant percentage of fluid is lost due to leakage from these pipelines [1,2], and it has been estimated that, as an example, within Asia region, at least 25% of the water supply is being lost [3]. This Manuscript figure is even higher for older pipes.…”

Section: Introductionmentioning

confidence: 99%

Information processing for leak detection on underground water supply pipelines

Yang

Wen

2010

Third International Workshop on Advanced Computational Intelligence

View full text Add to dashboard Cite

In the correlation-based leak location, it is supposed that the correlative components in the spatially separately collected acoustic signals merely result from a leak or leaks. This is why a false leak location will be produced when there is a non-leak acoustic source occurring outside a pipeline. To void a false leak location, it is necessary to detect whether or not a real leak exists in the pipeline beforehand. The traditional methods can detect leak only when the leak signal and non-leak signal are not acquired by the vibration sensors in the pipeline simultaneously. However, in practice, the leak signal is always blurred with the non-leak signal, and they will be picked up by the vibration sensors simultaneously. In this case, the traditional detection methods are infeasible. In this paper, a new feature extraction and leak identification method using autocorrelation analysis and approximate entropy algorithm is proposed to detect leak in the presence of non-leak acoustic sources. Due to the ability to analyze the coherent structure of time series, the autocorrelation function is used to describe the self-similarity of the signal. And the autocorrelation function values for the delay τ larger than the signal correlation length, not the signal itself or its entire autocorrelation function, is used to extract or evaluate the self-similarity degree of the signal by the approximate entropy algorithm. A neural-network approach has been developed as a classifier, which uses the identified self-similarity degrees as the network inputs. The method has been employed to identify the leak signals in the presence of some non-leak sounds, and achieved a 93.8% correct detection rate.

show abstract

Section: Introductionmentioning

confidence: 99%

Information processing for leak detection on underground water supply pipelines

Yang

Wen

2010

Third International Workshop on Advanced Computational Intelligence

View full text Add to dashboard Cite

show abstract

“…Water pipeline leaks are a growing concern around the world since water leaks will create risks to public safety and health as well as result in a waste of resources [1]. Thus, to reduce public health risk, to protect the environment and particularly to preserve public drinking water, the ideal way is to implement serious leakage control methods to predict and detect leaks in water distribution systems [2][3][4][5]. They can be used to prioritize areas for leak location procedures.…”

Section: Introductionmentioning

confidence: 99%

The genetic-algorithm-enhanced blind system identification for water distribution pipeline leak detection

Yang¹,

Wen²,

Li³

2007

Meas. Sci. Technol.

View full text Add to dashboard Cite

The conventional leak location is based on the correlation of leak acoustic signals acquired spatially separately. By correlation, the time lag is estimated for localizing the leakage. In these methods, the detection distance is a prerequisite that has to be known beforehand. However, in practice, this prerequisite is not always satisfied. In this case, the correlation-based methods are not feasible. Actually, the acquired signals contain the characteristics related to the acoustic propagation channels; thus the blind system identification strategy is applied to estimate the transmission performances of acoustic channels. Then the times due to the propagation of the leak source signal travelling from the leak point to sensors are determined. In this way, for leak location, the detection distance is no longer a prerequisite. In blind system identification, due to the long impulse responses of the leak acoustic channels, the channels are inevitably ill conditioned and sensitive to the initial values. To overcome the ill conditions, the overlap-save and cross-correlation fitting techniques are utilized to identify the long impulse sequences under a built constraint. In order to avoid converging to the local minima, the genetic algorithm is used to minimize the cost functions. The practical detection results show the validity of the proposed scheme.

show abstract