An Interval-Valued Prediction Method for Remaining Useful Life of Aero Engine

Aero engine is the core power unit of aircraft. A satisfactory prediction of remaining useful life (RUL) for an aero engine can ensure timely replacement and maintenance of engine and can avoid huge loss caused by engine failure during flight mission. In this paper, a multi-layer perceptron (MLP) prediction model based on information granular theory is proposed to estimate the RUL interval of aero engine. Firstly, the principal component analysis (PCA) method is considered to reduce dimension of inputs due to large number of sensor measurements of aero engines. Then a method to find the degradation interval of engine by the principle of justifiable granularity is designed, and the expected maximum RUL of each engine can be determined dynamically. Furthermore, a multi-layer perceptron is used to find the relation between aero engine sensor measurements and remaining useful life, by which the RUL interval of aero engine is obtained. Some numerical simulations show that the proposed model can obtain satisfactory performance.

[1]  Donald L. Simon,et al.  A Survey of Intelligent Control and Health Management Technologies for Aircraft Propulsion Systems , 2013, J. Aerosp. Comput. Inf. Commun..

[2]  Yong Zhang,et al.  A recurrent neural network approach for remaining useful life prediction utilizing a novel trend features construction method , 2019, Measurement.

[3]  F.O. Heimes,et al.  Recurrent neural networks for remaining useful life estimation , 2008, 2008 International Conference on Prognostics and Health Management.

[4]  Brigitte Chebel-Morello,et al.  Direct Remaining Useful Life Estimation Based on Support Vector Regression , 2017, IEEE Transactions on Industrial Electronics.

[5]  Li Lin,et al.  Remaining useful life estimation of engineered systems using vanilla LSTM neural networks , 2018, Neurocomputing.

[6]  Witold Pedrycz,et al.  Designing Fuzzy Sets With the Use of the Parametric Principle of Justifiable Granularity , 2016, IEEE Transactions on Fuzzy Systems.

[7]  Allan J. Volponi,et al.  Gas Turbine Engine Health Management: Past, Present, and Future Trends , 2014 .

[8]  Dong Ping,et al.  Remaining Useful Life Prediction for AeroEngines Combining Sate Space Model and KF Algorithm , 2017 .

[9]  A. Savitzky,et al.  Smoothing and Differentiation of Data by Simplified Least Squares Procedures. , 1964 .

[10]  Abhinav Saxena,et al.  Damage propagation modeling for aircraft engine run-to-failure simulation , 2008, 2008 International Conference on Prognostics and Health Management.

[11]  Kai Goebel,et al.  Damage Propagation Modeling for Aircraft Engine Prognostics , 2008 .

[12]  Guigang Zhang,et al.  Aero-Engine Remaining Useful Life Estimation based on 1-Dimensional FCN-LSTM Neural Networks , 2019, 2019 Chinese Control Conference (CCC).

[13]  Oliver Schütze,et al.  A Neural Network-Evolutionary Computational Framework for Remaining Useful Life Estimation of Mechanical Systems , 2019, Neural Networks.

[14]  Xiaoli Li,et al.  Deep Convolutional Neural Network Based Regression Approach for Estimation of Remaining Useful Life , 2016, DASFAA.

[15]  Noureddine Zerhouni,et al.  A New Multivariate Approach for Prognostics Based on Extreme Learning Machine and Fuzzy Clustering , 2015, IEEE Transactions on Cybernetics.

[16]  Kay Chen Tan,et al.  A time window neural network based framework for Remaining Useful Life estimation , 2016, 2016 International Joint Conference on Neural Networks (IJCNN).

[17]  Lovekesh Vig,et al.  Predicting Remaining Useful Life using Time Series Embeddings based on Recurrent Neural Networks , 2017, International Journal of Prognostics and Health Management.