The Enhancement of Leak Detection Performance for Water Pipelines through the Renovation of Training Data

Self Cite

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.

Section: Introductionmentioning

confidence: 99%

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

Ahmad

Kim

et al. 2022

Self Cite

“…The AE generated during machining and grinding processes has been proved to be related to the process state and to the surface condition of the tool and workpiece [ 17 , 18 ]. Therefore, AE technology has been widely used as a non-destructive inspection method for monitoring a wide variety of machining processes and industrial applications [ 19 ], including grinding [ 20 , 21 , 22 , 23 , 24 , 25 , 26 , 27 , 28 , 29 , 30 ], turning [ 31 , 32 , 33 ], electro-discharge grinding [ 20 ], sawing [ 34 ], abrasive water jet machining [ 35 ], rock bridge stability [ 36 ], welding [ 37 ], vibroarthrography [ 38 ], monitoring of concrete materials [ 39 , 40 ], leakage [ 41 ], and power system [ 42 ].…”

Section: Introductionmentioning

confidence: 99%

Grinding Wheel Loading Evaluation by Using Acoustic Emission Signals and Digital Image Processing

Liu

2020

In the manufacturing industry, grinding is used as a major process for machining difficult-to-cut materials. Grinding is the most complicated and precise machining process. For grinding machines, continuous generating gear grinding machines are widely used to machine gears which are essential machine elements. However, due to its complicated process, it is very difficult to design a reliable measurement method to identify the grinding wheel loading phenomena during the grinding process. Therefore, this paper proposes a measurement method to identify the grinding wheel loading phenomenon in the grinding process for continuous generating gear grinding machines. In the proposed approach, an acoustic emission (AE) sensor was embedded to monitor the grinding wheel conditions; an offline digital image processing technique was used to determine the loading areas over the surface of Al2O3 grinding wheels; and surface roughness of the ground workpiece was measured to quantify its machining quality. Then these three data were analyzed to find their correlation. The experimental results have shown that there are two stages of grinding in the grinding process and the proposed measurement method can provide a quantitative grinding wheel loading evaluation from the AE signals online.

“…Fault diagnosis (FD) performs tasks such as fault detection [ 7 , 8 , 9 ] and fault tolerance [ 10 , 11 ] There are three main types of FD methods: hardware-redundant, model-based, and data-driven methods. Hardware-redundant FD handles the faults using redundant devices [ 12 , 13 , 14 ].…”

Section: Introductionmentioning

confidence: 99%

Method for Fault Diagnosis of Temperature-Related MEMS Inertial Sensors by Combining Hilbert–Huang Transform and Deep Learning

Gao

Wei

Zhou

et al. 2020

In this paper, we propose a novel method for fault diagnosis in micro-electromechanical system (MEMS) inertial sensors using a bidirectional long short-term memory (BLSTM)-based Hilbert–Huang transform (HHT) and a convolutional neural network (CNN). First, the method for fault diagnosis of inertial sensors is formulated into an HHT-based deep learning problem. Second, we present a new BLSTM-based empirical mode decomposition (EMD) method for converting one-dimensional inertial data into two-dimensional Hilbert spectra. Finally, a CNN is used to perform fault classification tasks that use time–frequency HHT spectrums as input. According to our experimental results, significantly improved performance can be achieved, on average, for the proposed BLSTM-based EMD algorithm in terms of EMD computational efficiency compared with state-of-the-art algorithms. In addition, the proposed fault diagnosis method achieves high accuracy in fault classification.