Functional Logistic Regression for Motor Fault Classification Using Acoustic Data in Frequency Domain

Motor diagnostics is an important subject for consideration. Electric motors of different types are present in a multitude of object, from consumer goods through everyday use devices to specialized equipment. Diagnostic assessment of motors using acoustic signals is an interesting field, as microphones are present everywhere and are relatively easy sensors to process. In this paper, we analyze acoustic signals for the purpose of motor diagnostics using functional data analysis. We represent the spectrum (FFT) of the acoustic signals on a B-Spline basis and construct a classifier based on that representation. The results are promising, especially for binary classifiers, while multiclass (softmax regression) shows more sensitivity to dataset size. In particular, we show that while we are able to obtain almost perfect classification for binary cases, multiclass classifiers can struggle depending on the training/testing split. This is especially visible for determining the number of broken teeth, which is a non-issue for binary classifiers.

Automated summary

Motor diagnostics is an important research topic, and acoustic signal analysis can be applied to motor diagnostics. In this study, functional data analysis is used to represent the spectrum of acoustic signals using B-spline basis and construct a classifier for motor diagnostics. The results show that binary classifiers perform well in classification, while multiclass classifiers are more sensitive to dataset size.