Residual Life Prediction Based on Nonlinear Fatigue Damage Accumulation Model

When a nonlinear fatigue damage accumulation model based on damage curve approach is used to get better residual life prediction results, it is necessary to solve the problem caused by the uncertain exponent of the model. Considering the effects of load interaction, the assumption that there is a linear dependence between the exponent ratio and the loading ratio is established to predict fatigue residual life of materials. Three experimental data sets are used to validate the rightness of the proposition. The comparisons of experimental data and predictions show that the predictions based on the proposed proposition are in good accordance with the experimental results as long as the parameters that represent the linear correlativity are set an appropriate value. Meanwhile, the accuracy of the proposition is approximated to that of an existing model. Therefore, the proposition proposed in this paper is reasonable for residual life prediction.

Ensemble Recurrent Neural Network-Based Residual Useful Life Prognostics of Aircraft Engines

Residual useful life(RUL)prediction is a key issue for improving efficiency of aircraft engines and reducing their maintenance cost.Owing to various failure mechanism and operating environment,the application of classical models in RUL prediction of aircraft engines is fairly difficult.In this study,a novel RUL prognostics method based on using ensemble recurrent neural network to process massive sensor data is proposed.First of all,sensor data obtained from the aircraft engines are preprocessed to eliminate singular values,reduce random fluctuation and preserve degradation trend of the raw sensor data.Secondly,three kinds of recurrent neural networks(RNN),including ordinary RNN,long shortterm memory(LSTM),and gated recurrent unit(GRU),are individually constructed.Thirdly,ensemble learning mechanism is designed to merge the above RNNs for producing a more accurate RUL prediction.The effectiveness of the proposed method is validated using two characteristically different turbofan engine datasets.Experimental results show a competitive performance of the proposed method in comparison with typical methods reported in literatures.