Remaining Useful Life Prediction Method Based on an Improved Wiener Process Considering Multiple Performance Indicators Correlations

To improve the accuracy of remaining useful life (RUL) prediction under complex multi‐indicator dependencies, this paper proposes an RUL prediction method that integrates multi‐indicator correlation modeling with an enhanced Wiener process. Kendall rank correlation is used to identify key performance indicators that are highly related to equipment lifespan, thereby reducing the influence of redundant variables on dependency modeling. C‐Vine Copula model is employed to jointly model higher‐order dependencies among multiple degradation features, with the optimal Copula type for each pair of indicators automatically selected based on the AIC criterion, enabling flexible characterization of complex nonlinear and asymmetric interdependencies. Based on the joint modeling results, principal component analysis is used to fuse high‐dimensional health indicators, extracting a comprehensive indicator that effectively reflects the overall health condition of the equipment. In degradation modeling, machine learning methods are introduced by employing long short‐term memory networks to adaptively fit the drift coefficient, and the Wiener process is used to characterize prediction uncertainty, thereby enabling dynamic modeling of the fused health indicator degradation trajectory and probabilistic prediction of the remaining useful life.