Definition of Signal-to-Noise Ratio of Health Indicators and Its Analytic Optimization for Machine Performance Degradation Assessment

Abstract

Machine performance degradation assessment (MPDA) aims to use health indicators (HIs) to first detect an incipient failure time (IFT) and then monotonically track machine degradation trajectory. The IFT can indicate the time when a machine is entering a defective stage and it is also termed as first predicting time (FPT). Moreover, the benefit of monotonic degradation trajectories of HIs in a defective stage can well describe irreversible machine degradation mechanism, which in turn is beneficial to the simplification of prognostic models. In the literature, most existing HI construction methodologies only focus on one aspect of the MPDA, namely either PFT detection or degradation tracking. In this article, in view of spectrum amplitude fusion, a new methodology that aims to enhance HIs of MPDA is proposed. Considering intuitive machine degradation characteristics, four essential properties of HIs for FPT detection and subsequently monotonical degradation assessment are put forward and they are integrated into a uniquely hybrid property coined as HI-signal-to-noise ratio (HI-SNR) in this article. After the HI-SNR of HIs is maximized, spectrum fusion weights can be analytically derived. Finally, the sum of weighted spectrum amplitudes (SOWSA) is used as a generalized HI for MPDA. To demonstrate the effectiveness of the proposed new methodology, several experimental bearing and gear degradation cases are studied to show that the proposed SOWSA can detect FPT and characterize monotonic gear and bearing deterioration processes in a unified manner.