Abstract
Electric motors use about 68% of total generated electricity. Fault diagnosis of electrical motors is an important task, because it allows saving a large amount of money and time. An analysis of acoustic signals is a promising tool to improve the accuracy of fault diagnosis. It is essential to analyze acoustic signals to assess the state of the motor. In this paper, three electric impact drills (EID) were analyzed using acoustic signals: healthy EID, EID with damaged rear bearing, EID with damaged front bearing. Three angle grinders (AG) were analyzed: healthy AG, AG with 1 blocked air inlet, AG with 2 blocked air inlets. The authors proposed a method for feature extraction: SMOFS-NFC (Shortened Method of Frequencies Selection Nearest Frequency Components). Acoustic features vectors were classified by the nearest neighbor classifier and Naive Bayes classifier. The classification accuracy were in the range of 89.33-97.33% for three electric impact drills. The classification accuracy were in the range of 90.66-100% for three angle grinders. The presented method is very useful for diagnosis of bearings, ventilation faults and other mechanical faults of power tools. It can be also useful for diagnosis of similar power tools. (C) 2021 Elsevier Ltd. All rights reserved.