Blind Source Separation as an Extraction Tool of the Useful Diagnostic Material in on Load Tap Changer Audio Based Diagnostics

Abstract

Audio-based machinery fault diagnostics has a lot of particularities when compared to similar (non-invasive) diagnostic methods. These particularities are most evident in the unavoidable influence of the machine environment which is reflected through a mixture of the useful diagnostic material with surrounding sounds. On the other hand, there are several obvious advantages of this approach. For instance, a recording microphone can be installed at a certain distance from the tested object, ensuring the complete non-invasiveness of the measuring process. This paper analyses the influence of the surrounding environment in audio-based On-Load Tap Changer transformer diagnostics as well as the ability to apply statistical methods for the purpose of extracting useful diagnostic material that can be used for its condition assessment.