Novelty detection of rotating machinery using a non-parametric machine learning approach

摘要

A novelty detection algorithm inspired by human audio pattern recognition is conceptualized and experimentally tested. Time-domain data obtained from a microphone is processed by applying a short-time FFT, which returns time-frequency patterns. Such patterns are fed to a probabilistic algorithm, which is designed to detect novel signals and identify windows in the frequency domain where such novelties occur. The probabilistic algorithm presented in this paper uses one-dimensional kernel density estimation for different frequency bins. This process eliminates the need for data dimension reduction algorithms. Experimental datasets containing synthetic and real novelties are used to illustrate and test the novelty detection algorithm. Novelties are clearly detected in all experiments.