An approach for identifying corrosion damage from acoustic emission signals using ensemble empirical mode decomposition and linear discriminant analysis

Abstract

Mechanical structures, such as pressure vessels and pipes, need careful inspection and monitoring to avoid serious corrosion failures. Detecting and identifying corrosion damages from acoustic emission (AE) signals is of substantial importance for the safety and reliability of engineering structures in structural health monitoring. The identification accuracy depends largely on how well of damage features are being used. This paper presents a new approach for extracting effective damage features and accurately identifying different damages from AE signals during corrosion monitoring. Specifically, the proposed approach combines ensemble empirical mode decomposition (EEMD) and linear discriminant analysis (LDA) to analyze the AE signals generated from intergranular corrosion process. The results show that three damage modes including the environmental noises, the intergranular corrosion, and the formation and propagation of cracks, are successfully detected and identified from complicated AE waveforms. The proposed approach is capable of providing a reliable, direct and visualized corrosion damage detection and identification in structural health monitoring. Results from this study will guide complementary efforts aimed to detect and identify different damages from AE signals, and provide supporting knowledge regarding the industrial application of AE monitoring.

Monitoring of Atmospheric Corrosion of Aircraft Aluminum Alloy AA2024 by Acoustic Emission Measurements

“…However, this is a continuous process on an atomic level, i.e., low energy for AE, and thus it is also very unlikely to be a potential AE source. To fully identify the occurring corrosion mechanisms, further AE signal analysis by more advanced signal features [19,23] or post-mortem examination of the corrosion site by, e.g., SEM, is required. However, this is a matter for future research.…”

“…However, there are also numerous research works and industrial applications for the detection and monitoring of corrosion using AE. For example, AE is used in the petroleum and natural gas industry for the detection of leakages and corrosion of large tanks and pipelines made of different steels [19,[21][22][23]. Another sector where AE is used is civil engineering for the monitoring of the corrosion of steel-reinforced concrete [19,24,25].…”

Machine learning‐based approach for fatigue crack growth prediction using acoustic emission technique

“…The acoustic emission (AE) technique is now recognized as an important SHM technique and has been used in damage monitoring and evaluation of various engineering structures. 3,14,20,27 The most distinct advantage of the AE technique over traditional NDT methods is that it can realize online monitoring, accurate detection and localization of the damage such as cracks inside the material based on the change in multiple AE characteristic parameters. 8 For exploiting the advantage of AE, numerous studies have been performed to identify crack initiation and characterize the fatigue crack growth phenomenon of various metallic materials and structures.…”

“…To avoid the shortcomings of the NDT methods, structural health monitoring (SHM) techniques are thus developed to achieve real‐time monitoring, which helps to provide important information regarding damage identification and crack size prediction. The acoustic emission (AE) technique is now recognized as an important SHM technique and has been used in damage monitoring and evaluation of various engineering structures 3,14,20,27 . The most distinct advantage of the AE technique over traditional NDT methods is that it can realize online monitoring, accurate detection and localization of the damage such as cracks inside the material based on the change in multiple AE characteristic parameters 8 .…”

A Hybrid Leak Localization Approach Using Acoustic Emission for Industrial Pipelines

“…However, with a wavelet base, WT has no self-adaptability at different scales, and empirical mode decomposition (EMD) can separate mixed signals into several intrinsic mode function (IMF) components and identify feature signals [ 13 , 14 ]. However, there are still problems with this method [ 15 , 16 ]. Though the local mean decomposition (LMD) method can apply the local average and envelope estimation functions to signals, it is limited by the endpoint effect [ 13 , 17 ].…”