Chair of Multimedia Communications and Signal Processing University Erlangen-Nuremberg Proposal for a Master thesis Topic: Deep Learning Methods for Bearing Fault Detection Description: The measurable vibrations of machines during operation contain much informa- tion about the machine’s condition. During normal operation a machine exhibits a characteristic vibration signature which is directly linked to periodic events in the machine’s operation. However, when a fault arises in one of the machine’s compo- nents this vibration signature is altered. By applying learning-based algorithms the operating condition can be classified and monitored. Vibration analysis is extremely important for monitoring machine parts that are difficult to access as it is the case for wind turbines or rail vehicles. Bearing in a rail vehicle Vibration signal Deep Neural Network Healthy Damaged In the case of a rolling element bearing (see Figure), high-frequency resonances are excited every time a local fault, e.g., a crack, is hit by the rolling elements, which is not the case for a bearing in normal condition. Consequently, the vibration signals differ for different bearing conditions. Starting with a literature survey and the investigation of promising network architectures for the classification of faults in rolling element bearings, the aim of this thesis is the implementation and evaluation of end-to-end deep learning methods for the detection of bearing faults. The selected approaches are to be trained and validated with data that was gathered from real locomotive bearings. Comprehensive reviews of state-of-art network architectures with application to condition monitoring of bearings are given in [1, 2] and shall serve as a starting point. As prerequisites, the student should have interest in signal processing, affinity to math and Matlab or Python programming experience. [1] Hamadache, M., Jung, J. H., Park, J., and Youn, B. D., “A comprehensive review of artificial intelligence-based approaches for rolling element bearing PHM: shallow and deep learning,” JMST Advances, pp. 1–27, 2019. [2] Zhang, S., Wang, B., and Habetler, T. G., “Deep learning algorithms for bearing fault diagnostics–a comprehensive review,” IEEE Access, vol. 8, pp. 29857– 29881, 2020. Supervisor: Matthias Kreuzer, M.Sc., room 05.018 (Cauerstr. 7), [email protected] Professor: Prof. Dr.-Ing. Walter Kellermann Available: Immediately

Chair of Multimedia Communications and Signal Processing ... · Chair of Multimedia Communications and Signal Processing University Erlangen-Nuremberg Proposal for a Master thesis

Download PDF Report

Upload
others
View
62
Download
0

Embed Size (px)

Citation preview

Chair of Multimedia Communicationsand Signal Processing

University Erlangen-Nuremberg

Proposal for a Master thesis

Topic: Deep Learning Methods for Bearing Fault Detection

Description: The measurable vibrations of machines during operation contain much informa-tion about the machine’s condition. During normal operation a machine exhibits acharacteristic vibration signature which is directly linked to periodic events in themachine’s operation. However, when a fault arises in one of the machine’s compo-nents this vibration signature is altered. By applying learning-based algorithms theoperating condition can be classified and monitored. Vibration analysis is extremelyimportant for monitoring machine parts that are difficult to access as it is the casefor wind turbines or rail vehicles.

Bearing in a rail vehicle

Vibration signalDeep Neural Network

Healthy

Damaged

In the case of a rolling element bearing (see Figure), high-frequency resonances areexcited every time a local fault, e.g., a crack, is hit by the rolling elements, which isnot the case for a bearing in normal condition. Consequently, the vibration signalsdiffer for different bearing conditions.Starting with a literature survey and the investigation of promising network architec-tures for the classification of faults in rolling element bearings, the aim of this thesisis the implementation and evaluation of end-to-end deep learning methods for thedetection of bearing faults. The selected approaches are to be trained and validatedwith data that was gathered from real locomotive bearings. Comprehensive reviewsof state-of-art network architectures with application to condition monitoring ofbearings are given in [1, 2] and shall serve as a starting point.As prerequisites, the student should have interest in signal processing, affinity tomath and Matlab or Python programming experience.

[1] Hamadache, M., Jung, J. H., Park, J., and Youn, B. D., “A comprehensive re-view of artificial intelligence-based approaches for rolling element bearing PHM:shallow and deep learning,” JMST Advances, pp. 1–27, 2019.

[2] Zhang, S., Wang, B., and Habetler, T. G., “Deep learning algorithms for bearingfault diagnostics–a comprehensive review,” IEEE Access, vol. 8, pp. 29857–29881, 2020.

Supervisor: Matthias Kreuzer, M.Sc., room 05.018 (Cauerstr. 7), [email protected]

Professor: Prof. Dr.-Ing. Walter Kellermann

Available: Immediately