Abstract

The aim of this paper is to introduce a new method which combines data mining and signal processing techniques for identifying potential faults in electric motors. The vibration signals measured in the initial (healthy) state of the electric motor are used as source data for application of data mining technique. In this sense, a new data mining technique is introduced by the definition of a feature transfer function application which is best on the Continuous Wavelet Transform. Hence it constitutes a blind algorithm which can extract the features that are hidden in the data and also all characteristic features are detected by an auto associative neural network from the error variation.

Key words: Signal processing, data mining, wavelet transform, neural networks, feature extraction.

Abbreviation

FFT, Fast fourier transform; CWT, continuous wavelet transforms; FTF, feature-transfer function; APSD, auto-power spectral density;ANN, artificial neural network; AANN, auto-associative neural network; EDM,electrical discharge machining; tf-idf, term frequency - inverse document frequency; DWT, wavelet transform; DFT, discrete fourier transform; PSD, power spectral density; GUI, graphical user interface; NPSD, normalized power spectral density.