A Two-Phase Lifetime Prediction Model of Generator Stator Main Wall Insulation Driven by Digital Twin

Currently, most existing remaining useful life (RUL) prediction models for generators' main wall insulation (MI) focus on the statistical life distributions for a large population of products. The shortcoming of these models is that they cannot incorporate individual degradation information of a single product. To address the challenge of fusing common and individual degradation information, this article proposes a digital-twin-driven two-phase RUL prediction model, composing of three parts: common representation model (CRM), individual representation model (IRM), and dynamic evolution model. The proposed digital twin framework integrates the Wiener process model, Kalman filtering (KF) algorithm, and support vector machine (SVM) model. Specifically, a CRM based on the two-phase Wiener process was established to reflect common features. Then, with CRM acting as the state equation, an IRM was established based on KF, which can fuse MI's individual degradation information with common degradation information to reflect the individual features of single product. In addition, SVM is used to address the issue that the covariance matrix of KF algorithm cannot be updated in prediction domains of long-life products, achieving the dynamic evolution of the digital twin system. Finally, the effectiveness and engineering application value of the model were verified through experiments.