Remaining Useful Life Prediction for Turbofan based on a Multilayer Perceptron and Kalman Filter*

Today, maintenance programs are required to guarantee the reliability and availability of engineering systems. In order to do so, a system needs a degradation model to predict its remaining useful life (RUL) and act before any failure occurs. Ideally, physics-based models are used as they are accurate, but they are difficult to develop, and in complex systems, where there are many interactions, it is practically impossible. This work presents a degradation model composed of a Multilayer Perceptron (MLP) and a Kalman Filter (KF) for a common complex system, consisting of an aircraft turbine or turbofan, in order to predict its RUL. The results indicate that the model outperforms other models which are even more complex.

[1]  Kay Chen Tan,et al.  Multiobjective Deep Belief Networks Ensemble for Remaining Useful Life Estimation in Prognostics , 2017, IEEE Transactions on Neural Networks and Learning Systems.

[2]  Ivo Paixao de Medeiros,et al.  Remaining useful life estimation in aeronautics: Combining data-driven and Kalman filtering , 2018, Reliab. Eng. Syst. Saf..

[3]  Alaa Mohamed Riad,et al.  Conception and implementation of a data-driven prognostics algorithm for safety–critical systems , 2019, Soft Comput..

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

[5]  A. Abu-Hanna,et al.  Prognostic Models in Medicine , 2001, Methods of Information in Medicine.

[6]  T. Başar,et al.  A New Approach to Linear Filtering and Prediction Problems , 2001 .

[7]  Byeng D. Youn,et al.  Engineering Design under Uncertainty and Health Prognostics , 2018, Springer Series in Reliability Engineering.

[8]  Xiang Li,et al.  Remaining useful life estimation in prognostics using deep convolution neural networks , 2018, Reliab. Eng. Syst. Saf..

[9]  Daming Lin,et al.  A review on machinery diagnostics and prognostics implementing condition-based maintenance , 2006 .

[10]  Jie Liu,et al.  A multi-step predictor with a variable input pattern for system state forecasting , 2009 .

[11]  Jay Lee,et al.  Prognostics and health management design for rotary machinery systems—Reviews, methodology and applications , 2014 .

[12]  Emmanuel Ramasso,et al.  Investigating computational geometry for failure prognostics , 2014, International Journal of Prognostics and Health Management.

[13]  L. Peel,et al.  Data driven prognostics using a Kalman filter ensemble of neural network models , 2008, 2008 International Conference on Prognostics and Health Management.

[14]  Alaa Mohamed Riad,et al.  Prognostics: a literature review , 2016, Complex & Intelligent Systems.

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

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

[17]  Gang Niu,et al.  Development of an optimized condition-based maintenance system by data fusion and reliability-centered maintenance , 2010, Reliab. Eng. Syst. Saf..