Componential coding in the condition monitoring of electrical machines Part 2: Application to a conventional machine and a novel machine

Abstract

This paper (Part 2) presents the practical application of componential coding, the principles of which were described in the accompanying Part 1 paper. Four major issues are addressed, including optimization of the neural network, assessment of the anomaly detection results, development of diagnostic approaches (based on the reconstruction error) and also benchmarking of componential coding with other techniques (including waveform measures, Fourier-based signal reconstruction and principal component analysis). This is achieved by applying componential coding to the data monitored from both a conventional induction motor and from a novel transverse flux motor. The results reveal that machine condition monitoring using componential coding is not only capable of detecting and then diagnosing anomalies but it also outperforms other conventional techniques in that it is able to separate very small and localized anomalies.