Pipelines play a significant role in liquid and gas resource distribution. Pipeline leaks, however, result in severe consequences, such as wasted resources, risks to community health, distribution downtime, and economic loss. An efficient autonomous leakage detection system is clearly required. The recent leak diagnosis capability of acoustic emission (AE) technology has been well demonstrated. This article proposes a machine learning-based platform for leakage detection for various pinhole-sized leaks using the AE sensor channel information. Statistical measures, such as kurtosis, skewness, mean value, mean square, root mean square (RMS), peak value, standard deviation, entropy, and frequency spectrum features, were extracted from the AE signal as features to train the machine learning models. An adaptive threshold-based sliding window approach was used to retain the properties of both bursts and continuous-type emissions. First, we collected three AE sensor datasets and extracted 11 time domain and 14 frequency domain features for a one-second window for each AE sensor data category. The measurements and their associated statistics were transformed into feature vectors. Subsequently, these feature data were utilized for training and evaluating supervised machine learning models to detect leaks and pinhole-sized leaks. Several widely known classifiers, such as neural networks, decision trees, random forests, and k-nearest neighbors, were evaluated using the four datasets regarding water and gas leakages at different pressures and pinhole leak sizes. We achieved an exceptional overall classification accuracy of 99%, providing reliable and effective results that are suitable for the implementation of the proposed platform.

A hybrid deep learning approach was designed that combines deep learning with enhanced short-time Fourier transform (STFT) spectrograms and continuous wavelet transform (CWT) scalograms for pipeline leak detection. Such detection plays a crucial role in ensuring the safety and integrity of fluid transportation systems. The proposed model leverages the power of STFT and CWT to enhance detection capabilities. The pipeline’s acoustic emission signals during normal and leak operating conditions undergo transformation using STFT and CWT, creating scalograms representing energy variations across time–frequency scales. To improve the signal quality and eliminate noise, Sobel and wavelet denoising filters are applied to the scalograms. These filtered scalograms are then fed into convolutional neural networks, extracting informative features that harness the distinct characteristics captured by both STFT and CWT. For enhanced computational efficiency and discriminatory power, principal component analysis is employed to reduce the feature space dimensionality. Subsequently, pipeline leaks are accurately detected and classified by categorizing the reduced dimensional features using t-distributed stochastic neighbor embedding and artificial neural networks. The hybrid approach achieves high accuracy and reliability in leak detection, demonstrating its effectiveness in capturing both spectral and temporal details. This research significantly contributes to pipeline monitoring and maintenance and offers a promising solution for real-time leak detection in diverse industrial applications.

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.

Centrifugal pumps are the most vital part of any process industry. A fault in centrifugal pump can affect imperative industrial processes. To ensure reliable operation of the centrifugal pump, this paper proposes a novel automated health state diagnosis framework for centrifugal pump that combines a signal to time-frequency imaging technique and an Adaptive Deep Convolution Neural Network model (ADCNN). First, the vibration signals corresponding to different health conditions of the centrifugal pump are acquired. Vibration signals obtained from the centrifugal pump carry a great deal of information and generally, statistical features are extracted from the vibration signals to retain meaningful fault information. However, these features are either insensitive to weak incipient faults or unsuitable for tracking severe faults, thus, decreasing the fault classification accuracy. To tackle this problem, a signal to time-frequency imaging technique is applied to the pump vibration signals. For this purpose, Continuous Wavelet Transform (CWT) is applied to decompose the vibration signals over different time-frequency scales and extract the pump fault information in both the time and frequency domains. The CWT scales form two-dimensional time-frequency images commonly referred to as scalograms. The CWT scalograms are then converted into grayscale images (SGI). Over the past few decades, CNN models have been established as an effective practice to process images for classification and pattern recognition. Consequently, the extracted CWTSGIs are finally provided as inputs to the proposed ADCNN architecture to achieve feature extraction and classification for centrifugal pump faults. The performance of the proposed diagnostic framework (CWTSGI + ADCNN) is validated with a vibration dataset collected from a testbed specifically designed for centrifugal pump diagnosis. The experimental results suggest that the proposed technique based on CWTSGI and ADCNN outperformed existing methods with an average performance improvement of 4.7 - 15.6%.

Detecting pipeline leaks is an essential factor in maintaining the integrity of fluid transport systems. This paper introduces an advanced deep learning framework that uses continuous wavelet transform (CWT) images for precise detection of such leaks. Transforming acoustic signals from pipelines under various conditions into CWT scalograms, followed by signal processing by non-local means and adaptive histogram equalization, results in new enhanced leak-induced scalograms (ELIS) that capture detailed energy fluctuations across time-frequency scales. The fundamental approach takes advantage of a deep belief network (DBN) fine-tuned with a genetic algorithm (GA) and unified with a least squares support vector machine (LSSVM) to improve feature extraction and classification accuracy. The DBN-GA framework precisely extracts informative features, while the LSSVM classifier precisely distinguishes between leaky and non-leak conditions. By concentrating solely on the advanced capabilities of ELIS processed through an optimized DBN-GA-LSSVM model, this research achieves high detection accuracy and reliability, making a significant contribution to pipeline monitoring and maintenance. This innovative approach to capturing complex signal patterns can be applied to real-time leak detection and critical infrastructure safety in several industrial applications.

Raw statistical features can imitate the amplitude, average, energy and time, and frequency series distribution of a raw vibration signal. However, these raw statistical features are either not very sensitive to weak incipient faults or are unsuitable for more severe faults, thus affecting the fault detection and classification accuracy. To tackle this problem, this paper proposes a discriminant feature extraction method for Centrifugal Pump (CP) fault diagnosis. In order to obtain the discriminant feature pool, the proposed method is divided into three phases. In the first phase, a healthy baseline signal is selected. In the second phase, the healthy baseline signal is cross-correlated with the CP vibration signals of different classes, and a set of new features are extracted from the resulting correlation sequence. In the third phase, raw hybrid features in time, frequency, and the time-frequency domain are extracted from both the healthy baseline signals and the CP vibration signals of different classes. The correlation coefficient is calculated between the raw hybrid feature pools, which results in a new set of discriminant features. Discriminant features help the machine learning classifiers to effectively detect and classify the data into its respective classes. Furthermore, the proposed method combines all these features into a single feature vector that forms a vulnerable feature pool. The vulnerable feature pool describes the CP’s vulnerability to a fault and is provided as an input to a multiclass support vector machine (MSVM) for CP fault detection and classification. The experimental results illustrate that the accuracy obtained from the proposed method shows promising improvements over the state-of-the-art conventional methods.