Search

A pipeline is the most efficient way to transport water from one place to another. Due to aging, corrosion, and external factors, the pipeline is prone to damage, which causes leaks. Many machine learning (ML) and deep learning (DL) methods are available to address this issue. This paper does an experimental study on available methods in ML and DL for leak detection for the collected data using an acousto-optic sensor. The experimental setup comprises of an acousto-optic sensor made of an erbium-doped fiber laser (EDFL), galvanized iron pipeline, a tank, a pump, and a data acquisition unit. The dimensions of the galvanized pipeline looped with the water tank are a length of 40 m, an inner diameter of 89 mm, and an outer diameter of 90 mm. The diameter of the simulated leak aperture is 5 mm. The methods analyzed in this study are k-means, k-medoids, Naive Bayes (NB), support vector machines (SVM), k-nearest neighbor (KNN), decision tree (DT), categorical boosting (CatBoost), random forest (RF), XGBoost, AdaBoost, and one-dimensional convolutional neural network (1DCNN). ML algorithms need a feature extraction technique because the data collected from the experiment is too large and contains redundant information. Feature extraction reduces the data size by extracting essential information. This paper extracts ten features from raw data. Among the ML algorithms, AdaBoost gives the highest prediction accuracy of 98.02%. This paper also implements eight models of 1DCNN, and Model 1 shows the best prediction accuracy of 98.16%, which is the highest compared with all the other classifiers in ML and DL for one-dimensional time series acousto-optic sensor data. [ABSTRACT FROM AUTHOR]

The localization of the leaks is estimated using the time difference method in the past decade. Generalized and Basic Cross-correlation techniques are frequently applied to estimate the time difference between leak signals. The acoustic or vibration sensors detect the vibration of the leak. The pipe's convolved impulse response and external disturbances can corrupt the leak signal. It is challenging to detect a leak from the corrupted signal using conventional cross-correlational methods. The proposed method has implemented a novel wavelet packet adaptive ICA (Independent Component Analysis) based leak detection method to eliminate the leak signals' convolved impulse response and external disturbances. The proposed method uses an Acousto-optic sensor to localize the leaks in the water pipelines. The wavelet packet decomposition allows more flexibility and dimensionality reduction in leak signals. The adaptive ICA separates the signal generated by a leak from the pipe's impulse response along with the external disturbances. Investigation of the proposed technique verified using an experimental setup for leak detection at UTAR (Universiti Tunku Abdul Rahman) University, Sungai Long Campus, Malaysia. The results proclaim that the wavelet packet adaptive ICA works better than other recent techniques, with an accuracy of 95%-99%. [ABSTRACT FROM AUTHOR]