Leak State Detection and Size Identification for Fluid Pipelines with a Novel Acoustic Emission Intensity Index and Random Forest

Abstract

In this paper, an approach to perform leak state detection and size identification for industrial fluid pipelines with an acoustic emission (AE) activity intensity index curve (AIIC), using b-value and a random forest (RF), is proposed. Initially, the b-value was calculated from pre-processed AE data, which was then utilized to construct AIICs. The AIIC presents a robust description of AE intensity, especially for detecting the leaking state, even with the complication of the multi-source problem of AE events (AEEs), in which there are other sources, rather than just leaking, contributing to the AE activity. In addition, it shows the capability to not just discriminate between normal and leaking states, but also to distinguish different leak sizes. To calculate the probability of a state change from normal condition to leakage, a changepoint detection method, using a Bayesian ensemble, was utilized. After the leak is detected, size identification is performed by feeding the AIIC to the RF. The experimental results were compared with two cutting-edge methods under different scenarios with various pressure levels and leak sizes, and the proposed method outperformed both the earlier algorithms in terms of accuracy.

Novel EMD with Optimal Mode Selector, MFCC, and 2DCNN for Leak Detection and Localization in Water Pipeline

“…A few monitoring devices used in pipeline leak detection and localization are acoustic emission sensors [8][9][10][11][12][13][14][15][16][17][18][19], infrared thermography [20,21], microphones [22], CCTV, vibration sensors [23,24], accelerometers [25], pressure sensors [26][27][28][29], flow meters [30,31], and pipeline robots [32]. The acoustic emission and vibration sensors capture the vibration in the pipeline.…”

“…Widely used machine learning (ML) and DL algorithms to detect a pipeline leak are the support vector machine (SVM) [15,[29][30][31], naïve Bayes (NB) [31], logistic regression (LR), decision tree (DT) [24,30,31,33], multi-layer perceptron (MLP), k-nearest neighbors (KNN) [24,34], random forest (RF) [18,24], gradient boosting [24], LightGBM [24], XG-Boost [24], CatBoost [24], long short-term memory (LSTM) [35], and convolutional neural network (CNN) [8][9][10]14,16,17,[20][21][22][23][36][37][38][39][40][41][42]. Data collected from acoustic emission sensors, acousto-optic sensors, microphones, and vibration sensors must be feature-extracted for ML classifiers like SVM, NB, and DT.…”

“…The XGBoost gave the best leak detection accuracy of 99.79% among the classifiers. Nguyen et al implemented a leak size identification system using an acoustic emission intensity index using RF [18]. The data were collected using an acoustic emission sensor.…”