Transformer Model for Remaining Useful Life Prediction of Aeroengine

Abstract

Accurate aeroengine remaining useful life (RUL) prediction plays a vital role in ensuring safe operation and reducing maintenance losses. In order to improve the accuracy of aeroengine RUL prediction, an aeroengine RUL prediction method based on the Transformer model is proposed, which gives greater weight to the characteristics of important time steps through self attention mechanism, and solves the memory degradation problem caused by too long sequence in engine RUL prediction, and excavates the complex mapping relationship between input features and aeroengine RUL. Experiments on the C-MAPSS data set show that the Transformer model can better predict the aeroengine RUL based on the aeroengine degradation data. Compared with the long short term memory network model, the root mean square error of the two sub data sets is reduced by 6.57% and 5.63% respectively.

A remaining useful life prediction method based on PSR-former

“…In order to compare the methods in this paper with those adopted in the current field, the algorithms are classified into two categories: the method based on deep learning and the method based on traditional machine learning. In deep learning methods, Transformer 29 , RNN 30 , LSTM 31 , GRU 32 , 1D-CNN 33 , and CNN combined with LSTM 34 were chosen under the same data settings as proposed method in this paper to analyze and they were all connected in three layers whose hidden dimension is 14 and 64 to be as close as possible to the PSR-former model. The other parameters of the networks such as batch size and learning rate were adjusted to the best.…”

Remaining useful life estimation of bearing using spatio-temporal convolutional transformer

“…With the proposal of transformer [18], the monopoly position of CNN, RNN, and other variants has been broken in the past. Li and Yang [19] introduced the transformer for aeroengine, which captured global information to make predictions through a multi-head attention (MHA) mechanism. Chen et al [20] provided the RUL prediction model based on the combination of spatial attention and the transformer.…”