Knowledge Library Network for Non-Exemplar Incremental Remaining Useful Life Prediction
Top Cited Papers
- 1 October 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ASME Transactions on Mechatronics
- Vol. 31 (5) , 5066-5076
Abstract
Aiming at the difference of various incremental remaining useful life (RUL) prediction tasks, a novel nonexemplar incremental learning (IL) method is proposed, named knowledge library network (KLN). First, a multilevel focal self-attention (MLFSA) is developed to model the multiscale temporal dependencies and extract the key features. On this basis, a dual domain fusion temporal convolutional network (DDFTCN) is designed to mine the degradation information from both time-domain and frequency-domain data. Next, a task similarity judgment strategy specifically tailored for IL scenarios is proposed to assess the discrepancies between different tasks. Based on the task differences, a network augmentation rule is proposed for implementing the feature extraction network augmentation or task branch network augmentation. The feature extraction network augmentation is employed for the tasks with significant differences, while the task branch network augmentation is utilized for the tasks with small differences. Especially for the task branch network augmentation, a retention and absorption distillation strategy is proposed to enhance the model's capability to retain previous knowledge while adapting to new task. The network augmentation network rule is integrated into DDFTCN to form the KLN. Finally, the experimental results on the life-cycle bearing and gear datasets demonstrate that DDFTCN achieve an average accuracy of 93.6% across both datasets, surpassing the existing prediction methods. The experimental results on the incremental RUL prediction tasks validate the superiority of KLN over the typical and state-of-the-art IL methods.Keywords
Funding Information
- National Natural Science Foundation of China (T2421001)
This publication has 35 references indexed in Scilit:
- Gradient-enhanced physics-informed long short-term memory networks for stable and accurate prediction of the RUL of electronic componentsReliability Engineering & System Safety, 2025
- DG-Softmax: A new domain generalization intelligent fault diagnosis method for planetary gearboxesReliability Engineering & System Safety, 2025
- Fisher-informed continual learning for remaining useful life prediction of machining tools under varying operating conditionsReliability Engineering & System Safety, 2024
- Supervised contrastive learning based dual-mixer model for Remaining Useful Life predictionReliability Engineering & System Safety, 2024
- An aero-engine remaining useful life prediction model based on feature selection and the improved TCNFranklin Open, 2024
- Single gated RNN with differential weighted information storage mechanism and its application to machine RUL predictionReliability Engineering & System Safety, 2023
- A systematic method of remaining useful life estimation based on physics-informed graph neural networks with multisensor dataReliability Engineering & System Safety, 2023
- Remaining useful life prediction of bearings by a new reinforced memory GRU networkAdvanced Engineering Informatics, 2022
- Memory Aware Synapses: Learning What (not) to Forget2018
- Learning Deep Representations with Probabilistic Knowledge Transfer2018