IDMT-ISA-Compressed-Air Dataset
Description
The IDMT-ISA-Compressed-Air (IICA) dataset aims to foster research in compressed air leak detection with acoustic emissions in the audible hearing range with recordings of air leaks in a simulated industrial compressed air network. The dataset contains recordings of multiple leak types with different types of industrial background noises played via external loudspeakers at two different volumes during the recording process.
Leak Types:
- Vent Leak
- Vent Leak Low Pressure
- Tube Leak
Noise Types:
- Lab Noise (no added background noise)
- Hydraulic machine noise
- Hydraulic machine noise, low volume
- General factory workshop noise
- General factory workshop noise, low volume
For each combination of leak and noise types, there were three recording sessions. During each session, four Earthworks M30 omnidirectional measurement microphones placed in different configurations recorded the acoustic emission of the compressed air network. Each recording session contains 128 files of 30 seconds each, corresponding to each combination of leak, noise and microphone.
- Total Files: 5592
- Sampling Rate: 48 kHz
- Resolution: 32-bit
- Mono Audio
See the above referenced paper and README contained with the data folder for further details.
Files
IDMT-ISA-COMPRESSED-AIR-TUBELEAK.zip
Additional details
References
- David Johnson, Jakob Kirner, Sascha Grollmisch, and Judith Liebetrau Compressed Air Leakage Detection Using Acoustic Emissions with Neural Networks. Proceedings of the 49th International Congress and Exposition on Noise Control Engineering (Inter-Noise 2020), Seoul, South Korea. 2020