Lenze Motor Bearing Fault Dataset (Lenze-MB)

The vast majority of approaches developed in the field of condition monitoring rely on public data recorded in laboratory conditions with high-performance measurement equipment. Moreover, primarily vibration data is used for condition monitoring tasks, which is particularly sensitive to typical error patterns in rotating machinery. These conditions are difficult to maintain in industrial environments since using high-performance measurement systems would not be economically feasible. This experiment investigates the simulation of realistic bearing damage with data from sensors that already exist. The test bench allows for the examination of bearings outside the engine with defined faults. Fault detection is performed exclusively using the existing drive, consisting of a Lenze i950 inverter and a permanently excited synchronous machine with a SinCos-encoder. The following variations within the setup can be investigated: bearings with defined faults; coupling with a load engine via a defined tensioned belt and defined tension force to apply radial forces; mechanical load torque.

For a detailed description of the experiment, refer to the technical report included in the files section, please.

For details on the dataset structure, please refer to the Quick_Start_Script, also found in the files.

Also you might have a look in some scientific work building on top of Lenze-QI found in the reference section below.