An adaptive prediction method of remaining useful lifetime for the aviation product based on the proportional degradation model

Abstract

The traditional prediction methods of the remaining useful lifetime (RUL) for the product require a large amount of historical data as support. But for the expensive aviation product, the degradation experiments with large sample sizes are unacceptable. Aiming at this problem, an adaptive RUL prediction method for the single aviation product based on the proportional degradation model is proposed. Firstly, a nonlinear Wiener degradation model with a proportional process is built. Then, based on the small sample or single sample degradation data, the degradation state update method based on the EM-KF is proposed. Finally, using the aviation product performance degradation data to verify the effectiveness of the method.