Abstract
An improved time-domain analysis method combining with the sliding window and Local Mean Decomposition (LMD) is proposed for a large amount of data volume when using acoustic emission signals to diagnose axle faults. In this paper, the sliding window is used to slice the acoustic emission (AE) data. PF component is obtained by LMD algorithm and the time domain characteristic parameters and the energy values of each component are calculated. The fault signals of axle acoustic emission data are identified and classified by BP neural network. In order to solve the huge data problem, sliding window, LMD algorithm, BP neural network and the whole process of the experiment are deployed to the distributed real-time processing Spark framework. The experiment shows that the method of LMD and BP neural network based on large data stream is feasible. It not only improves the speed of the algorithm, but also makes the identification and classification of the axle damage more accurate.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
