Abstract:

Remaining Useful Life (RUL) prediction for aircraft engines based on the available run-to-failure measurements 5 of similar systems becomes more prevalent in Prognostic Health Management (PHM) thanks to the new advanced 6 methods of estimation. However, feature extraction and RUL prediction are challenging tasks, especially for data-driven 7 prognostics. The key issue is how to design a suitable feature extractor that is able to give a raw of time-varying sensors 8 measurements more meaningful representation to enhance prediction accuracy with low computational costs. In this 9 paper, a new Denoising Online Sequential Extreme Learning Machine (DOS-ELM) with double dynamic forgetting factors 10 (DDFF) and Updated Selection Strategy (USS) is proposed. First, depending on the characteristics of the training data that 11 comes from aircraft sensors, robust feature extraction using a modified Denoising Autoencoder (DAE) is introduced to 12 learn important patterns from data. Then, USS is integrated to ensure that only the useful data sequences pass through 13 the training process. Finally, OS-ELM is used to fit the non-accumulative linear degradation function of the engine and to 14 address dynamic programming by trucking the new coming data and forgetting gradually the old ones based on the 15 proposed DDFF. The proposed DOS-ELM is tested on the public dataset of commercial modular aeropropulsion system 16 simulation (C-MAPSS) of a turbofan engine and compared with OS-ELM trained with ordinary Autoencoder (AE), basic 17 OS-ELM and pervious works from the literature. Comparison results prove the effectiveness of the new integrated robust 18 feature extraction scheme by showing more stability of the network responses even under random solutions.

Publisher's Version