A hierarchical approach for the online, on-board detection and localisation of brake squeal using microphone arrays

We present here a hierarchical approach for the detection and localisation of brake squeal. The proposed system exploits the spatial diversity of microphone arrays to localise a squealing brake. As brake squeal is emitted from a priori known regions, i.e. near the wheels, localisation of a squeal may be seen as a hypothesis testing problem. However, in contrast to standard hypothesis testing approaches, the propagation environment is complex and time-varying, making modelling difficult. Additionally, we have inaccuracies in sensor positioning, source position knowledge and sensor gain mismatch. Thus, standard approaches fail in this case. Therefore, we develop a robust approach that implicitly considers such incomplete system knowledge. The algorithm detects squeal events (which may be overlapping in time and frequency) and performs localisation by allocating to each source (brake) a measure that indicates its contribution to the acoustic event. The algorithm is evaluated in a real setting.