Compressed Air Leakage Detection Using Acoustic Emissions with Neural Networks

Compressed air is utilized in many branches of industry and one of the most expensive energy sources of industrial plants. Therefore, e cient detection of air pressure leaks goes hand in hand with cost savings and increased operational reliability. Some procedures of leakage detection for pressure lines are based upon the analysis of sound emissions. Such solutions use specific ultrasonic emission patterns to detect leakage; alternatively, personnel trained to hear leaks are deployed for detection. In this paper, we evaluate the potential of using airborne sound emissions in the audible hearing range for the automated detection of compressed air leakage using artificial neural networks. Therefore, a novel dataset was created and published. It contains recordings from several microphones at different distances of adjustable leakage from a pneumatic contraption with different pressure levels. Additionally, industrial background noises were applied at di erent levels to simulate real-world sound environments. Using this dataset, a deep neural network was trained for leakage detection. The results show that leakage detection by means of airborne sound in the audible range using machine learning techniques is possible, and is a promising contactless and automatic detection method.