Data augmentation based on diffusion probabilistic model for remaining useful life estimation of aero-engines

Predicting the remaining useful life (RUL) of aero-engines is essential for their prognostics and health management (PHM). Deep learning technologies are effective in this area, but their success depends critically on acquiring sufficient engine monitoring data from operation to failure, a process that is expensive and challenging in practice. Insufficient data limit the training of deep learning methods, thereby affecting their predictive performance. To address this issue, this study proposes a novel method named DiffRUL for augmenting multivariate engine monitoring data and generating high-quality samples mimicking degradation trends in real data. Initially, a specialized degradation trend encoder is designed to extract degradation trend representations from monitoring data, which serve as generative conditions. Subsequently, the diffusion model is adapted to the scenario of generating multivariate monitoring data, reconstructing and synthesizing data from Gaussian noise through a reverse process. Additionally, a denoising network is developed to incorporate generative conditions and capture spatio-temporal correlations in the data, accurately estimating noise levels during the reverse process. Experimental results on C-MAPSS and N-CMAPSS datasets show that DiffRUL successfully generates high-fidelity multivariate monitoring data. Furthermore, these generated data effectively support the RUL prediction task and significantly enhance the predictive ability of the underlying deep learning models.