An EGTM-Based RUL Prediction Method for Auxiliary Power Unit of Aircraft

The performance and health condition of the auxiliary power unit (APU) directly affect the safe operation and economical maintenance of the aircraft. However, due to the limitations of APU report recording mode, the small amount of APU reports makes it difficult for many traditional machine learning methods to evaluate their performance accurately. To address the above problems, this paper proposes a method for predicting the remaining useful life of APU based on the exhaust gas temperature (EGT) margin. First, data preprocessing is performed, and EGT, a key parameter of APU, is extracted from its trend by the X11 method, which is affected by the external environment factors. Then, the remaining useful life of the APU can be obtained by combining the EGT margin with the EGT decay rate. The real APU report is finally applied to verify the efficiency and superiority of the proposed method. Experimental results show that the performance of this proposed method outperforms comparison methods in terms of predicting the remaining useful life of aircraft APU.