IDMT-ISA-COMPRESSED-AIR

Reference

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.

Dataset Overview

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.

More audio datasets

Fraunhofer IDMT has compiled further audio data sets for various research areas such as instrument recognition, fingerings or game analysis.

Research topic

Audio and Visual Content Analysis

Extracting meaningful data from audiovisual content

Research topic

Environmental Sound Analysis

AI-based analysis of complex acoustic scenes and sounds

Research topic

Media Forensics

Trustworthy media content

Research topic

Industrial Sound Analysis

AI-based acoustic monitoring in production