Remaining Useful Life Prediction for Aero-Engines Using a Time-Enhanced Multi-Head Self-Attention Model

Data-driven Remaining Useful Life (RUL) prediction is one of the core technologies Prognostics and Health Management (PHM). Committed to improving accuracy RUL for aero-engines, this paper proposes a model that entirely based on attention mechanism. The divided into multi-head self-attention timing feature enhancement models. employs scaled dot-product extract dependencies between time series; used accelerate enhance selection process. This utilises Commercial Modular Aero-Propulsion System Simulation (C-MAPSS) turbofan engine simulation data obtained from NASA Ames’ Center Excellence compares proposed algorithm other experiments conducted validate superiority our model’s approach.