Recent Developments in the Implementation of a Bidirectional LSTM Deep Neural Network for Aircraft Operational Loads Monitoring

The NextGen SHM system, known commonly as Prognostics and Health Management (PHM), focuses on pro-active condition-based maintenance. Therefore, the need to develop and integrate operational airframe loads monitoring capabilities predictive of fatigue is paramount. This work presents recent developments towards using state-of-the-art deep learning algorithms for high-fidelity aircraft loads monitoring systems. A Bidirectional Long Short-Term Memory (LSTM) recurrent neural network is used to predict several load cases from strain sensors. The results presented here demonstrate how the proposed framework can predict most loads with high fidelity.