🤖 AI Summary
To address weak generalization under limited samples and difficulty in modeling long-range temporal dependencies in remaining useful life (RUL) prediction for optical amplifiers, this paper proposes a lightweight Transformer tailored for predictive maintenance. We introduce a novel sparse low-rank self-attention mechanism that preserves long-range dependency modeling while substantially mitigating overfitting. Additionally, a dual-encoder parallel architecture is designed to separately capture sensor-channel-specific and time-dynamic features, enabling effective fusion of heterogeneous time-series information. Evaluated on both an EDFA optical amplifier dataset and the benchmark C-MAPSS turbofan engine dataset, our method reduces RUL prediction error by 12.7% compared to state-of-the-art approaches. Notably, it achieves significantly improved generalization performance under small-sample conditions. This work provides an efficient, robust technical foundation for intelligent operation and maintenance of optical networks.
📝 Abstract
Optical fiber amplifiers are key elements in present optical networks. Failures of these components result in high financial loss of income of the network operator as the communication traffic over an affected link is interrupted. Applying Remaining useful lifetime (RUL) prediction in the context of Predictive Maintenance (PdM) to optical fiber amplifiers to predict upcoming system failures at an early stage, so that network outages can be minimized through planning of targeted maintenance actions, ensures reliability and safety. Optical fiber amplifier are complex systems, that work under various operating conditions, which makes correct forecasting a difficult task. Increased monitoring capabilities of systems results in datasets that facilitate the application of data-driven RUL prediction methods. Deep learning models in particular have shown good performance, but generalization based on comparatively small datasets for RUL prediction is difficult. In this paper, we propose Sparse Low-ranked self-Attention Transformer (SLAT) as a novel RUL prediction method. SLAT is based on an encoder-decoder architecture, wherein two parallel working encoders extract features for sensors and time steps. By utilizing the self-attention mechanism, long-term dependencies can be learned from long sequences. The implementation of sparsity in the attention matrix and a low-rank parametrization reduce overfitting and increase generalization. Experimental application to optical fiber amplifiers exemplified on EDFA, as well as a reference dataset from turbofan engines, shows that SLAT outperforms the state-of-the-art methods.