RT journal article
T1 Explainable Artificial Intelligence for Time Series Using Attention Mechanism: Application to Wind Turbine Fault Detection
A1 Ghahfarokhi, Anahita Farhang
A1 Schäfer, Jörg
A1 Wagner, Matthias F.
A1 Dorronsoro Díaz, Bernabé
A2 Ingeniería Informática
K1 Artificial intelligence
K1 attention mechanisms
K1 classification
K1 explainable artificial intelligence
K1 fault detection
K1 linear discriminant analysis
K1 machine learning
K1 transformer
K1 wavelet transforms
K1 wind turbines
AB The time series classification problem is highly relevant in many important domains, such as industry, finance, and healthcare. It is a long-known problem that has been addressed by a plethora of mathematical algorithms, including deep learning models. Despite the rapid growth of deep learning techniques, the opaque nature of these models prevents users from adopting them in real-life scenarios. In this paper, we propose a classification framework for time series using wavelet transformation and transformers. Furthermore, we explain the results using a novel combination of the attention mechanism and Linear Discriminant Analysis. The framework was evaluated on three real-world wind turbine datasets, and it achieved comparable or leading F1 scores of above 0.99. Moreover, the explanation framework highlights the key frequencies that differentiate between the healthy and faulty states. We show that these frequencies align by at least 70% with those identified using mechanical domain knowledge. This compliance increases the trustworthiness of Artificial Intelligence in industrial applications and supports informed decision-making.
SN 2169-3536
YR 2025
FD 2025
LK http://hdl.handle.net/10498/39273
UL http://hdl.handle.net/10498/39273
LA eng
DS Repositorio Institucional de la Universidad de Cádiz
RD 07-nov-2026