Validation of acoustic emission railway track crack analysis using MFCC

dc.contributor.authorVongserewattana, Narate
dc.contributor.authorSuwansin, Wara
dc.contributor.authorPhasukkit, Pattarapong
dc.contributor.authorPhatsornsiri, Punnavich
dc.date.accessioned2026-08-06T10:24:59Z
dc.date.available2026-08-06T10:24:59Z
dc.date.issued2019-07-01
dc.description.abstractNowadays, railway track crack detection system has many techniques, such as Ultrasonic Techniques [1], Electromagnetic Techniques [2] and GSM Techniques [3]. For the propose of this research, we study characteristics of railway track using acoustic emission, the device which is widely used for application such as crack detection in aerospace space grade steel [4], detection of defect s in rolling element bearing [5], fatigue crack growth detection [6]. And use the MFCC ('Mel - Frequency Cepstral Coefficients') [7] method which is generally used for low frequency to extract the feature of each railway track. According to that, we chose to adjust the MFCC method for an acoustic feature extraction in order for condition to be suitable used for this system, because the railway track crack detection system, we are interested in concentrates at 100-400 kHz. According to the result of the experiment, it shows that this technique is able to extract and classify feature of the railway track crack.
dc.identifier.citationProceedings of the 16th International Conference on Electrical Engineering Electronics Computer Telecommunications and Information Technology Ecti Con 2019, 633-636, 2019
dc.identifier.doi10.1109/ECTI-CON47248.2019.8955231
dc.identifier.other2-s2.0-85078835704
dc.identifier.urihttps://dspace.kmitl.ac.th/handle/123456789/9970
dc.sourceProceedings of the 16th International Conference on Electrical Engineering Electronics Computer Telecommunications and Information Technology Ecti Con 2019
dc.subjectComponent
dc.subjectRailway track crack detection
dc.titleValidation of acoustic emission railway track crack analysis using MFCC
dc.typeConference Paper

Files

Collections