Reliability Assessment Method Based on Condition Information by Using Improved Proportional Covariate Model

If sufficient historical failure life data exist, the distribution of system can be estimated to identify initial hazard function. The conventional proportional covariate model (PCM) reveal dynamic relationship between response covariates and rate. rate function constantly updated by through basic (BCF). Under circumstances sparse or zero data, key point PCM reliability assessment method is determine factor for getting BCF. Being devoid experiments abundant experience experts, it very hard accurately. In this paper, an improved (IPCM) put forward based on logistic regression (LRM). salient features reflecting equipment degradation process are extracted from existing monitoring signals, which considered as input LRM. state defined threshold output first Combined with responding covariates, calculated. Then, incorporated into implement estimation other equipment. IPCM methods respectively applied aero-engine rotor bearing assessment. comparative results show that assessing accuracy superior small sample. It provides a new under conditions.