General information on the data set The data set was generated at the ZeMA testbed. A working cycle lasts 2.8s and consists of a forward stroke, a waiting time and a return stroke. The data set does not consist of the entire working cycles. Only one second of the return stroke of each working cycle is used. Structure of the data data saved in HDF5 file as a 3D-matrix one row represents one second of the return stroke of one working cycle (6292 rows: 6292 cycles) one column represents one datapoint of the cycle, that is resampled to 2 kHz (2000 columns) one page represent one sensor (11 pages: 11 sensors) Allocation of the pages to the sensors page 1: microphone page 2: acceleration plain bearing page 3: acceleration piston rod page 4: acceleration ball bearing page 5: axial force page 6: pressure page 7: velocity page 8: active current page 9: motor current phase 1 page 10: motor current phase 2 page 11: motor current phase 3 Remark The datasets are not in SI units. For conversion, you can use the PDF documentation. Further information For an introduction and tutorial to this data, a set of Jupyter notebooks is available here. These notebooks contain Python code and a documentation of example machine learning tasks and analysis of this data set. In the near future, these will be extended to also include uncertainties in the input data.