Two datasets are available for download (one can be used for training and the other for testing). Each dataset contains 31 TXT files corresponding to the 31 damage scenarios.
For each scenario, the acceleration signals were collected at the 30 joints under a white noise shaker excitation at a sampling frequency of 1024 Hz. The signals were recorded for 256 s. Therefore, each signal contains 262144 samples.
This process was conducted twice for each scenario, resulting in two datasets: Dataset A and Dataset B.
The TXT files are named as follows:
Dataset A:
- zzzAU.TXT: Undamaged scenario.
- zzzAD1.TXT: Damage at Joint 1
- zzzAD2.TXT: Damage at Joint 2
- …
- zzzAD30.TXT: Damage at Joint 30
Dataset B:
- zzzBU.TXT: Undamaged scenario.
- zzzBD1.TXT: Damage at Joint 1
- zzzBD2.TXT: Damage at Joint 2
- …
- zzzBD30.TXT: Damage at Joint 30
Each TXT file contains 31 columns:
- Column 1: timestamp.
- Column 2: Signal measured at Joint 1.
- Column 3: Signal measured at Joint 2.
- …
- Column 31: Signal measured at Joint 30.