Articles | Volume 9, issue 1
J. Sens. Sens. Syst., 9, 143–155, 2020

Special issue: Sensors and Measurement Systems 2019

J. Sens. Sens. Syst., 9, 143–155, 2020

Regular research article 12 May 2020

Regular research article | 12 May 2020

Data-driven vibration-based bearing fault diagnosis using non-steady-state training data

Kurt Pichler et al.

Related subject area

Applications: Automation
An internet of things (IoT)-based optimum tea fermentation detection model using convolutional neural networks (CNNs) and majority voting techniques
Gibson Kimutai, Alexander Ngenzi, Said Rutabayiro Ngoga, Rose C. Ramkat, and Anna Förster
J. Sens. Sens. Syst., 10, 153–162,,, 2021
Short summary
Test method for narrowband F/TDMA-based wireless sensor/actuator networks including radio channel emulation in severe multipath environments
Christoph Cammin, Dmytro Krush, Ralf Heynicke, and Gerd Scholl
J. Sens. Sens. Syst., 7, 183–192,,, 2018
Short summary
Chain of refined perception in self-optimizing assembly of micro-optical systems
S. Haag, D. Zontar, J. Schleupen, T. Müller, and C. Brecher
J. Sens. Sens. Syst., 3, 87–95,,, 2014

Cited articles

Alattas, M. and Basaleem, M.: Statistical Analysis of Vibration Signals for Monitoring Gear Condition, Damascus Univ. Journal, 23, 67–92, 2007. a, b
Albarbar, A., Mekid, S., Starr, A., and Pietruszkiewicz, R.: Suitability of MEMS accelerometers for condition monitoring: An experimental study, Sensors, 8, 784–799, 2008. a
Antoni, J. and Randall, R.: The spectral kurtosis: application to the vibratory surveillance and diagnostics of rotating machines, Mech. Syst. Signal Pr., 20, 308–331, 2006. a
Assaad, B., Eltabach, M., and Antoni, J.: Vibration based condition monitoring of a multistage epicyclic gearbox in lifting cranes, Mech. Syst. Signal Pr., 42, 351–367, 2014. a
Bajric, R., Zuber, N., Skrimpas, G., and Mijatovic, N.: Feature Extraction Using Discrete Wavelet Transform for Gear Fault Diagnosis of Wind Turbine Gearbox, Shock and Vibration, 2016, 6748469,, 2016. a, b
Short summary
Detecting faults in bearings is indispensable for the maintenance of many industrial machines or components. The faults are detected by recognizing patterns in vibration data that are measured at the bearing housing. The method can be trained with data of variable revolution speeds, therefore reducing the effort for the acquisition of training data. Moreover, incipient faults can be detected before they cause severe damage to the equipment.