DIAGNOSTICS OF DC MACHINE BASED ON ANALYSIS OF ACOUSTIC SIGNALS WITH APPLICATION OF MFCC AND CLASSIFIER BASED ON WORDS

摘要

Technical diagnostics is concerned with the assessment of technical conditions of the machine through the study of properties of machine processes. Diagnostics is particularly important for factories and ironworks. In paper is presented method of diagnostics of imminent failure conditions of DC machine. This method is based on a study of acoustic signals generated by DC machine. System of sound recognition uses algorithms for data processing, such as Mel Frequency Cepstral Coefficient and classifier based on words. Software to recognize the sounds of DC machine was implemented on PC computer. Studies were carried out for sounds of faultless machine and machine with shorted coils. The results confirm that the system can be useful for diagnostics of dc and ac machines used in metallurgy.