An Adaptive ICA-Based Cross-Correlation Techniques for Water Pipeline Leakage Localization Utilizing Acousto-Optic Sensors

Kothandaraman, Mohanaprasad; Law, Zijian; Morris, Ezra; Pua, Chang Hong

doi:10.1109/jsen.2020.2991639

Cited by 21 publications

(4 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Cross-correlation is the most common method used in leak localization (Kothandaraman et al 2020b). The difference in time of the leak signal taken to reach both sensors help to localize the leak, and the cross-correlation help to calculate the time difference.…”

Section: Leak Localizationmentioning

confidence: 99%

“…Here SVM is implemented within CNN by having the activation function as 'linear' in the preferred convolutional layer. (Kothandaraman et al 2020b) proposed an Adaptive ICA-based correlation to remove noise based on the impulse response in a pipeline using Acousto-optic sensors. The adaptive ICA effectively removes convolved impulse response noises and improves the localization's accuracy.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Water Pipeline Leak Detection and Localization With 1DCNN and Novel Adaboost Classifier

Kothandaraman

Rajasekaran

Pua

2023

Preprint

Self Cite

View full text Add to dashboard Cite

A pipeline leak localization technique is crucial in a structural health monitoring system to prevent water wastage at an early stage. Recent advancements include machine learning and deep learning techniques to detect a leak with great accuracy, and cross-correlation is the widely used tool for localization. All the existing algorithms use two architectures to detect and localize a leak. The main aim of this paper is to propose a standalone architecture for leak detection and localization with 1DCNN and novel AdaBoost architecture. The data collected from a real-time pipeline setup is redundant, very dynamic, and contains a substantial amount of surrounding noise. So an appropriate feature extraction technique helps to capture essential information from pipeline data. In the proposed method, the 1DCNN extracts the essential features from the data collected from the real-time pipeline setup located in UTAR, Malaysia, using an Acousto-optic vibration sensor. The proposed novel AdaBoost architecture localizes the leak with the help of the features extracted using 1DCNN. The performance metrics used in this paper to evaluate the proposed method are training accuracy, validation accuracy, precision, recall, F1 score, and R-squared, and the results are 99.23, 97.26, 98.18, 98.19, 98.14, and 98.55, respectively which is better compared to the implemented existing method. The results show that the proposed 1DCNN-novel AdaBoost localizes the leak with high training and validation accuracy and performs well in other metrics.

show abstract

Section: Leak Localizationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Water Pipeline Leak Detection and Localization With 1DCNN and Novel Adaboost Classifier

Kothandaraman

Rajasekaran

Pua

2023

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…However, a drawback of the study is that accurate leak localization in long distance pipes without foregoing accuracy is an area that needs attention. Kothandaraman et al (2020a) extended their study in Kothandaraman et al (2020b) and used a non-Gaussianity adaptive algorithm to separate leak vibration waves from the convoluted impulse response of the pipe with the noise. The study explored a new time delay estimation method to locate water leaks in a real-time distribution system.…”

Section: Hydrophone-based Fiber Opticsmentioning

confidence: 99%

“…Steady-state methods are further classified into model-based and data-driven methods (Zaman et al 2020). Kothandaraman et al (2020a) noted the downsides of available methods and technology. For example, acoustic techniques are not appropriate for plastic pipes, whereas physical inspection and mechanical excavation require extensive human resources.…”

Section: Introductionmentioning

confidence: 99%

Application of fiber optics in water distribution networks for leak detection and localization: a mixed methodology-based review

et al. 2021

View full text Add to dashboard Cite

This study reviews the state-of-the-art application of fiber optics in water distribution networks for leak detection and localization. The use of fiber optics in the oil and gas sector has been well-established; however, its potential in water pipelines is not evident owing to limited research. This study, therefore, presents the research developments of fiber optics in water leak detection and localization using the mixed methodology approach by integrating bibliometric and systematic analyses. A scientometric analysis is carried out to analyze the science maps of (1) journal sources, (2) contributing countries, and (3) co-occurrence of influential keywords. The systematic analysis evaluates the use of eight types of fiber optics, such as accelerometer-based fiber optics and hydrophone-based fiber optics, in water leak detection and localization. The review reveals five important directions for future research such as real network-based studies and the development of hybrid techniques.

show abstract

Water Pipeline Leak Measurement Using Wavelet Packet-based Adaptive ICA

Kothandaraman

Law

Morris

et al. 2022

Water Resour Manage

View full text Add to dashboard Cite

An Adaptive ICA-Based Cross-Correlation Techniques for Water Pipeline Leakage Localization Utilizing Acousto-Optic Sensors

Cited by 21 publications

References 30 publications

Water Pipeline Leak Detection and Localization With 1DCNN and Novel Adaboost Classifier

Water Pipeline Leak Detection and Localization With 1DCNN and Novel Adaboost Classifier

Application of fiber optics in water distribution networks for leak detection and localization: a mixed methodology-based review

Water Pipeline Leak Measurement Using Wavelet Packet-based Adaptive ICA

Contact Info

Product

Resources

About