Text-Conditioned Diffusion-Based Synthetic Data Generation for Turbine Engine Sensor Analysis and RUL Estimation

This paper introduces a novel framework for generating synthetic time-series data from turbine engine sensor readings using a text-conditioned diffusion model. The ap proach begins with dataset preprocessing, including correlation analysis, feature selection, and normalization. Principal Component A...

Descripción completa

Detalles Bibliográficos
Autores: Mora-de-León, Luis Pablo, Solís Martín, David, Galán Páez, Juan, Borrego Díaz, Joaquín
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2025
País:España
Institución:Universidad de Sevilla (US)
Repositorio:idUS. Depósito de Investigación de la Universidad de Sevilla
OAI Identifier:oai:idus.us.es:11441/174607
Acceso en línea:https://hdl.handle.net/11441/174607
https://doi.org/10.3390/machines13050374
Access Level:acceso abierto
Palabra clave:Predictive maintenance
Prognostics and health management (PHM)
Remaining useful life (RUL)
Descripción
Sumario:This paper introduces a novel framework for generating synthetic time-series data from turbine engine sensor readings using a text-conditioned diffusion model. The ap proach begins with dataset preprocessing, including correlation analysis, feature selection, and normalization. Principal Component Analysis (PCA) transforms the normalized sig nals into three components, mapped to the RGB channels of an image. These components, combined with engine identifiers and cycle information, form compact 19 × 19 × 3 pixel images, later scaled to 512 × 512 × 3pixels. Avariational autoencoder (VAE)-based diffusion model, fine-tuned on these images, leverages text prompts describing engine characteristics to generate high-quality synthetic samples. A reverse transformation pipeline reconstructs synthetic images back into time-series signals, preserving the original engine-specific at tributes while removing padding artifacts. The quality of the synthetic data is assessed by training Remaining Useful Life (RUL) estimation models and comparing performance across original, synthetic, and combined datasets. Results demonstrate that synthetic data can be beneficial for model training, particularly in the early epochs when working with limited datasets. Compared to existing approaches, which rely on generative adversarial networks (GANs) or deterministic transformations, the proposed framework offers en hanceddatafidelity andadaptability.