A Method for Pipeline Leak Detection Based on Acoustic Imaging and Deep Learning

Abstract

This paper proposes a reliable technique for pipeline leak detection using acoustic emission signals. The acoustic emission signal of a pipeline contains leak-related information. However, the noise in the signal often obscures the leak-related information, making traditional acoustic emission features, such as count and peaks, less effective. To obtain leak-related features, first, acoustic images were obtained from the time series acoustic emission signals using continuous wavelet transform. The acoustic images (AE images) were the wavelet scalograms that represent the time–frequency scales of the acoustic emission signal in the form of an image. The acoustic images carried enough information about the leak, as the leak-related information had a high-energy representation in the scalogram compared to the noise. To extract leak-related discriminant features from the acoustic images, they were provided as input into the convolutional autoencoder and convolutional neural network. The convolutional autoencoder extracts global features, while the convolutional neural network extracts local features. The local features represent changes in the energy at a finer level, whereas the global features are the overall characteristics of the acoustic signal in the acoustic image. The global and local features were merged into a single feature vector. To identify the pipeline leak state, the feature vector was fed into a shallow artificial neural network. The proposed method was validated by utilizing a data set obtained from the industrial pipeline testbed. The proposed algorithm yielded a high classification accuracy in detecting leaks under different leak sizes and fluid pressures.

Development of an AI-based image/ultrasonic convergence camera system for accurate gas leak detection in petrochemical plants

“…In another study [ 71 ], researchers compared the efficacy of YOLOv4 [ 60 ] and Faster R–CNN [ 55 ] for pipe leak detection. Ahmad et al [ 72 ] conducted a study based on acoustic imaging and deep learning and obtained a higher accuracy than that seen in previous studies. However, the proposed method can only detect leaks, and cannot provide information regarding leak localization.…”

Machine Learning Model for Leak Detection Using Water Pipeline Vibration Sensor

“…Tijani et al propose a reliable technique for pipeline leak detection using acoustic emission signals and deep learning to extract leak-related discriminant features from acoustic images obtained from time series acoustic emission signals using continuous wavelet transform [17]. Ahmad et al propose a reliable technique for pipeline leak detection using acoustic emission signals and deep learning to extract leak-related features from acoustic images obtained from time series acoustic emission signals using continuous wavelet transform [18]. Xu et al propose a method for identifying leaks in water pipes using an explainable ensemble tree model of vibration signals based on the wave propagation model and the leakage noise mechanism [19].…”

The effect of data variations on the leakage detection model performance using a convolutional neural network (CNN)

“…Therefore, it is important to develop effective leak detection using deep learning utilizing acoustic signals. Hold-out methods Nam et al 2021;Ahmad et al 2022) have been used to build and evaluate models using images and recurrence plots (RPs).…”