Enhanced acoustic monitoring for industrial predictive maintenance using semi-coprime microphone array and joint spatial-frequency filtering

This paper analyzes the problem of the acquisition and separation of sound sources in industrial environments that concentrate the energy in different frequency bands, using microphone arrays. Their very different spectral characteristics make the application of spatial filtering algorithms difficult, as beamformers are usually designed for specific frequency bands. Separation of sound sources is essential for the application of anomaly detection algorithms in predictive maintenance applications. The anomaly detectors must be fed with signals emitted by the machine under study, isolated from other sounds in the environment. Sound separation can be implemented in the time domain if sounds are not simultaneous, in the frequency domain if the energy appears in different bands for the different machines, or by spatial filtering if they are produced in different places. Unfortunately, the nature of signals makes this process difficult, motivating the research to obtain multiband microphone arrays with narrow main lobes and high difference between the main beam level and the highest sidelobe level. In this paper, a semi-coprime array (SCA)–based non-uniform array structure and non-uniform filter banks are combined to separate the sound sources in an industrial environment. The proposed SCA-based architecture addresses this requirement by providing a large effective aperture with fewer microphones, narrow main lobes, improved mainlobe–sidelobe contrast across multiple bands, and mitigation of grating lobes via a minimum processor. This approach can be applied with very few adaptations to any environment with many sound sources, emitting at different bands from different positions.