Data-driven condition monitoring of sliding bearings in large engines based on acoustic emissions

The combination of acoustic emissions and machine learning offers great potential for gaining deeper insights into the condition of large combustion engines. In particular, sliding bearings, which play a key role in ensuring the performance and safety of large engines, are a promising target for such monitoring.

Target

The aim of the present thesis is to develop a non-invasive method for monitoring sliding bearings using acoustic emissions (AE). The objective is to detect undesirable mixed friction events between the crankshaft and the sliding bearing using data-driven methods from the field of machine learning. To this end, a measurement database was generated using bearing test rig tests. The test bearing was instrumented with different AE sensors at different positions. The tests were carried out under different operating conditions to represent those of large engines.

Tasks

Familiarization with the experimental test setup (bearing test rig, measurement technology and measurement parameters)
Preprocessing of the measurement data from the bearing test rig and AE sensors
Investigation of the relationships between mixed friction events and AE sensor signals through an exploratory data analysis
Development of a data-driven model for the detection of mixed friction events based on AE sensor signals

Your profile

Programming skills in Python or R; experience in data analysis

Starting date: As soon as possible
Duration: Approximately 6 months

Contact:

Univ.-Prof. Dr.-Ing. Nicole Wermuth, +43 (316) 873-30087, nicole.wermuth@lec.tugraz.at
Dipl.-Ing. Christian Laubichler, +43 (316) 873-30089, christian.laubichler@lec.tugraz.at