The degradation process of high-reliability products commonly has two-phase characteristics. For such products, accurate change point estimation and proper degradation model play crucial roles in remaining useful life (RUL) prediction. However, due to the long-lifetime nature of high-reliability products, lacking sufficient condition monitoring data will result in inaccurate parameter estimation, which further leads to a large error in RUL prediction. To address the issue, this article proposes a RUL prediction method that integrates two-phase accelerated degradation data and field information. Specifically, change points are estimated based on accelerated degradation data, which effectively solves the difficulty of deriving the change point distribution owing to the lack of data. On this basis, a two-phase degradation model considering change point distribution is proposed by combining the Wiener process and acceleration equation, which can be extrapolated to predict the lifetime at any stress level. In addition, taking the accelerated degradation data as prior information, all model parameters are updated by integrating field information using the Bayesian method. When new change points are detected, their distribution is also updated to improve the accuracy of the next individual RUL prediction. The effectiveness of the proposed method is validated through simulation studies and empirical analysis of motor insulation.

中文翻译：

---

结合两相加速退化数据和现场信息的剩余使用寿命预测方法

高可靠性产品的退化过程通常具有两阶段特征。对于此类产品，准确的变化点估计和适当的退化模型在剩余使用寿命 (RUL) 预测中发挥着至关重要的作用。然而，由于高可靠性产品的长寿命特性，缺乏足够的状态监测数据会导致参数估计不准确，进而导致RUL预测出现较大误差。针对这一问题，本文提出了一种融合两相加速退化数据和现场信息的 RUL 预测方法。具体而言，基于加速退化数据来估计变点，有效解决了由于数据缺乏而难以推导变点分布的问题。在此基础上，结合维纳过程和加速度方程，提出了考虑变点分布的两相退化模型，可以外推预测任何应力水平下的寿命。此外，以加速退化数据为先验信息，利用贝叶斯方法整合现场信息更新所有模型参数。当检测到新的变化点时，它们的分布也会更新，以提高下一个单独 RUL 预测的准确性。通过电机绝缘的仿真研究和实证分析验证了该方法的有效性。