Remaining useful life prediction based on the mixed effects model with mixture prior distribution

Modern engineering systems are gradually becoming more reliable and premature failure has become quite rare. As a result, degradation signal data used for prognosis are often imbalanced as most units are reliable and only few tend to fail at early stages of their life cycle. Such imbalanced data may hinder accurate Remaining Useful Life (RUL) prediction especially in terms of detecting premature failures as early as possible. This aspect is detrimental for developing cost-effective condition-based maintenance strategies. In this article, we propose a degradation signal-based RUL prediction method to address the imbalance issue in the data. The proposed method introduces a mixture prior distribution to capture the characteristics of different groups within the same population and provides an efficient and effective online prediction method for the in-service unit under monitoring. The advantageous features of the proposed method are demonstrated through a numerical study as well as a case study with real-world data in the application to the RUL prediction of automotive lead-acid batteries.