Abstract
Autonomous Underwater Vehicles (AUVs) are gradually becoming some of the most important equipment in deep-sea exploration. However, in the dynamic nature of the deep-sea environment, any unplanned fault of AUVs would cause serious accidents. Traditional fault diagnosis models are trained in static and fixed datasets, making them difficult to adopt in new and unknown deep-sea environments. To address these issues, this study explores incremental learning to enable AUVs to continuously adapt to new fault scenarios while preserving previously learned diagnostic knowledge, named the RM-MFKAN model. First, the approach begins by employing the Rainbow Memory (RM) framework to analyze data characteristics and temporal sequences, thereby delineating boundaries between old and new tasks. Second, the model evaluates data importance to select and store key samples encapsulating critical information from prior tasks. Third, the RM is combined with the enhanced KAN network, and the stored samples are then combined with new task training data and fed into a multi-branch feature fusion neural network. The proposed RM-MFKAN model was conducted on the "Haizhe" dataset, and the experimental results have demonstrated that the proposed model achieves superior performance in fault diagnosis for AUVs.