RUL prediction of oil filter based on random process-failure mechanism model integration

Due to the considerable randomness in contaminant size and arrival, as well as unavoidable epistemic uncertainties and manufacturing/installation variations, both parametric and model uncertainties in practice pose a challenge to the oil filter's remaining useful life prediction. The oil filter is a crucial component in guaranteeing hydraulic fluid cleanliness. This paper introduces a remaining useful life prediction method that fuses a physics-based degradation model with data-driven stochastic process models. Based on Bayesian inference, the method achieves effective RUL prediction for oil filters by synthesizing real-time degradation observations with the respective advantages of different candidate models. In comparison to the Ergun and Wiener models, experimental validation shows that the root mean square error（RMSE）of real-time degradation prediction for oil filter achieves 0.003 9 MPa, resulting in drops of 79.9% and 77.5%, respectively. The results indicate that the proposed method exhibits superior prediction accuracy and strong generalization capability, highlighting its practical value for engineering applications.