A Comparison of Machine Health Indicators Based on the Impulsiveness of Vibration Signals

Abstract

Vibration signals collected from machines can contain rich machine degradation information, such as impulsiveness and cyclo-stationarity. In the field of machine condition monitoring (MCM), quantification of impulsiveness has attracted many researchers’ interests because impulsiveness often indicates an occurrence of incipient faults. Impulsiveness-based health indicators (HIs) (e.g., Gini index, kurtosis, entropy, smoothness index, etc.) are some kinds of statistical parameters that can quantify the impulsiveness of vibration signals. Hence, they have been widely studied during recent years for MCM. However, a thorough comparitive study of those HIs is seldom reported. This paper aims to compare seven impulsiveness-based HIs including kurtosis, skewness, smoothness index, negative entropy, Gini index, Hoyer measure, and the ratio of L2 to L1 norm for MCM according to three properties including the robustness to the length of a signal, the gradient for sparsity or impulsiveness, and quantification of impulsiveness and cyclo-stationarity. Among the seven HIs, it was experimentally found that the Gini index is better than the other indicators to satisfy the three suggested properties for MCM.