Wheel Defect Detection Using Attentive Feature Selection Sequential Network With Multidimensional Modeling of Acoustic Emission Signals

• Published in: IEEE transactions on instrumentation and measurement Vol. 72; pp. 1 - 14
• Main Authors: Wang, Kangwei, Zhang, Xin, Wan, Fengshuo, Chen, Rong, Zhang, Jun, Wang, Jun, Yang, Yong
• Format: Journal Article
• Language: English
• Published: New York IEEE 2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Acoustic emission; Acoustic emission (AE); Algorithms; attentive feature selection (AFS); cepstral coefficient (CC); Classifiers; Datasets; Defects; False alarms; Feature extraction; Feature selection; Mathematical models; Mel frequency cepstral coefficient; Modelling; Modules; multidimensional modeling; Neural networks; Rail transportation; Rails; Recurrent neural networks; Rescaling; Stability; Training; wheel defect detection; Wheels; Wheelsets

Wheel defects, such as flats, can have severe impacts on vehicles, seriously hindering railway running stability and safety. Thus, it is crucial to continuously monitor the condition of wheelsets using techniques such as acoustic emission (AE). In this article, we propose an attentive feature select...