Novel method for in situ damage monitoring during ultrasonic fatigue testing by the advanced acoustic emission technique

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

“…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. 1,6,13,37,41 Most of these studies typically investigated the qualitative relationship between the crack growth and the AE signals. By analyzing the crack growth behavior and AE characteristics, different damage states such as crack initiation, stable crack growth, rapid crack growth, and final fracture can be effectively identified.…”

“…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 1,6,13,37,41 . Most of these studies typically investigated the qualitative relationship between the crack growth and the AE signals.…”

Early Detection of Subsurface Fatigue Cracks in Rolling Element Bearings by the Knowledge-Based Analysis of Acoustic Emission

“…Subsurface cracking is readily observed as a key feature and prevailing mechanism in the very high cycle fatigue of structural materials [ 45 , 46 ], including bearing steels [ 27 , 28 ]. Recently, it was shown [ 47 ] that the contemporary AE technique powered by the temporal-frequency short-time Fourier analysis is capable of detecting subsurface damage initiated during the laboratory ultrasonic fatigue testing in the gigacycle regime. Nevertheless, none of the methods proposed in the above-cited works can be regarded as robust enough to become a widely deployed and effective tool for condition monitoring systems capable of reliable subsurface crack detection in noisy industrial settings.…”

Multichannel intelligent fault diagnosis of hoisting system using differential search algorithm‐variational mode decomposition and improved deep convolutional neural network

“…In general, AE‐based fault diagnosis approach mainly concentrates on two stages (i.e., AE feature extraction and source localization) 13,14 . Currently, a considerable number of experimental methods to investigate the AE characteristics of structural materials are presented by many scholars, in order to improve the engineering applications of AE technology 15–17 . Chen et al 18 proposed a fault diagnosis method for low‐speed rolling bearing based on AE signal and subspace embedded feature distribution alignment.…”

“…13,14 Currently, a considerable number of experimental methods to investigate the AE characteristics of structural materials are presented by many scholars, in order to improve the engineering applications of AE technology. [15][16][17] Chen et al 18 proposed a fault diagnosis method for low-speed rolling bearing based on AE signal and subspace embedded feature distribution alignment. Elforjani et al 19 utilized three supervised machine learning techniques to extract AE features for the remaining useful life prediction of bearing machine components.…”