Tram gearbox condition monitoring method based on trackside acoustic measurement

• Published in: Measurement : journal of the International Measurement Confederation 2023-02, Vol.207, p.112358, Article 112358
• Main Authors: Nowakowski, Tomasz, Tomaszewski, Franciszek, Komorski, Paweł, Szymański, Grzegorz M.
• Format: Article
• Language: English
• Subjects: Condition monitoring; Decision tree; Empirical mode decomposition; Gearbox fault diagnosis; Machine-learning; Tram
• ISSN: 0263-2241; 1873-412X
• DOI: 10.1016/j.measurement.2022.112358

•Gearbox failure has an impact on tram noise, especially described by psychoacoustic indicators - differences of up to 42% were observed.•The use of empirical mode decomposition in the array measurements made it possible to extract the modes related to the non-stationary pattern of the damaged gearbox.•Machine learning in the form of decision trees allowed the selection of the most important IMFs in the signals and reduced the number of microphones in measurements (reduction of the cost of measuring equipment by 33%).•The new approach in condition monitoring indicates the possibility of achieving a level of unnecessary repairs equal to 3%, with no damage omissions observed. The article presents the genesis of the work to develop a method of diagnosing a tram transmission from the track position using acoustic signals. Significant influence of the damaged gearbox on acoustic phenomena in the vicinity of a tram line was shown, especially visible changes in psychoacoustic indicators. Due to the non-stationary nature of the acoustic signals, analyses of the microphone matrix were carried out using the empirical mode decomposition. The developed quantitative measure of individual IMFs served as a classifier in decision trees. For the developed CART type decision trees, the indicators of the effectiveness of the diagnosis were calculated, i.e., the level of unnecessary repairs and the level of undetected damage. Based on these results, the most effective tree was selected, which was used to develop the final, not yet developed, algorithm to diagnose the tram transmission without the need to mount the equipment on the vehicle.