Multi-waveform transfer learning for predicting electromagnetic sensitivity of integrated modular avionics power modules in complex environment

Understanding the electromagnetic compatibility of power modules in complex electromagnetic environments is critical for the safety of integrated modular avionics. However, fully testing the module against various ElectroMagnetic Interference (EMI) waveforms is time-consuming and labor-intensive. To address this challenge, we propose a deep-learning-based approach, termed Multi-waveform Transfer Learning (MWTL), building a unified model to predict module responses across multiple interference waveforms. MWTL utilizes a Convolutional Neural Network-Long Short-Term Memory (CNN-LSTM) architecture to effectively extract the temporal features and build the relation between the interference signals and the response signals. In addition, by leveraging shared features across different scenarios, a Transfer Learning (TL) strategy is applied, generalizing the model into unseen interference waveforms, thereby reducing the need for extensive training data in new tasks. The experimental results show that the proposed method delivers excellent predictive performance across various types of interference, maintaining high accuracy even with limited data. In particular, by transferring shared features from multitask learning to new tasks, the approach significantly reduces data requirements for new scenarios while preserving prediction accuracy.