Remaining Useful Life Prediction of Planetary Gear Sets Using a Novel Hybrid Pelican Optimization Algorithm Optimized CNN–BiLSTM Model
TL;DR
The results show that the proposed POA-CNN-BiLSTM model achieves accurate RUL prediction, and its prediction performance is improved by optimizing the number of hidden units, initial learning rate, and regularization parameters through POA.
Abstract
Remaining useful life (RUL) prediction of the gears is essential for the health management and predictive maintenance of planetary gear transmissions (PGTs), which are widely used in aero engines, helicopters, and wind turbines. However, due to run-to-failure data are usually limited, existing models still face challenges in accurately characterizing gear degradation trends under different fault modes. Deep learning (DL) algorithms have become effective tools for RUL prediction, but their performance is highly dependent on the selection of appropriate hyper-parameters. To address these issues, this paper proposes a hybrid convolutional neural network and bidirectional long short-term memory neural network (CNN-BiLSTM) model for predicting the RUL of the sun gear in a PGT. The pelican optimization algorithm (POA) is introduced to automatically optimize the key parameters of the CNN-BiLSTM model, thereby reducing the dependence on manual tuning. A run-to-failure experiment with four accelerometer channels was conducted to obtain vibration data from a planetary gearbox. The results show that the proposed POA-CNN-BiLSTM model achieves accurate RUL prediction, and its prediction performance is improved by optimizing the number of hidden units, initial learning rate, and regularization parameters through POA.