EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Improving Vibration-Based Classification in a Wind Turbine Jacket Structure and Rotor Through Multitask Learning and Spectral Representations

Mario Eduardo González Niño, Oscar H. Sierra Herrera, Edwin Francis Cárdenas Correa, Jersson X. Leon-Medina, Francesc Pozo

Wind · 03.11.2026 · 6 (4) · 65

DOI: 10.3390/wind6040065 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Wind, online erschienen am 03.11.2026. Verfasst von Mario Eduardo González Niño und 4 weiteren Autor:innen. Die Arbeit nennt 51 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: European Union, FEDER, UE, Generalitat de Catalunya.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This work proposes and evaluates a supervised classification framework based on multichannel vibration signals to analyze two systems associated with wind turbines: rotor imbalance in a laboratory-adapted Enair E30Pro wind turbine and structural damage in a jacket-type structure. The methodology compares single-task and multitask learning models using spectral representations obtained from the Fast Fourier Transform (FFT) in log-magnitude format, the Short-Time Fourier Transform (STFT) in log-power format, and the Welch power spectral density (Welch PSD) in log-power format. During the single-task stage, TabNet (Attentive Interpretable Tabular Learning) models, a deep learning architecture designed for tabular data, were independently trained for each system and representation to establish baseline performance levels. Subsequently, a multitask scheme composed of a shared encoder and two task-specific classification heads was implemented: one for the jacket-type structure and another for the rotor. In addition to the original TabNet baselines, a capacity-matched single-task MLP control was evaluated using the same encoder architecture, preprocessing, optimization settings, epoch budget, and cross-validation folds as the multitask model. Relative to the TabNet baselines, the multitask model achieved higher performance in several configurations, particularly for the more challenging rotor task; however, the capacity-matched control showed that these gains cannot be attributed uniquely to multitask parameter sharing because the multitask model did not consistently outperform an equivalently structured single-task network. For the jacket-type structure, all three spectral representations achieved near-perfect classification performance, with Macro-F1 values above 0.99 in both the single-task and multitask settings. For the rotor imbalance problem, the multitask model using Welch PSD log-power achieved a global accuracy of 0.9125 and a Macro-F1 of 0.8909. Negative-control experiments further showed that replacing the auxiliary-task labels with random permutations reduced target-task performance in several configurations, indicating that informative auxiliary supervision influences the shared optimization process, although this effect did not translate into a consistent predictive advantage over the capacity-matched single-task control. The multitask architecture nevertheless provides a parameter-efficient joint formulation: one shared multitask network contains 4,481,354 trainable parameters, compared with 8,958,218 parameters required by two independent capacity-matched single-task networks, corresponding to an approximately 49.97% reduction in total model parameters. Overall, the results support multitask learning as a compact joint modeling strategy for physically different vibration-based classification problems, while indicating that its principal benefit in the present study is architectural efficiency rather than a consistently superior predictive effect attributable to positive cross-task transfer.

Förderung

  • European Union
  • FEDER, UE
  • Generalitat de Catalunya

Zitieren

APA

Niño, M. E. G., Herrera, O. H. S., Correa, E. F. C., Leon-Medina, J. X., & Pozo, F. (2026). Improving Vibration-Based Classification in a Wind Turbine Jacket Structure and Rotor Through Multitask Learning and Spectral Representations. Wind, 6(4), 65. https://doi.org/10.3390/wind6040065

Vancouver

Niño MEG, Herrera OHS, Correa EFC, Leon-Medina JX, Pozo F. Improving Vibration-Based Classification in a Wind Turbine Jacket Structure and Rotor Through Multitask Learning and Spectral Representations. Wind. 2026;6(4):65. doi:10.3390/wind6040065

BibTeX
@article{Nio2026,
  author = {Niño, Mario Eduardo González and Herrera, Oscar H. Sierra and Correa, Edwin Francis Cárdenas and Leon-Medina, Jersson X. and Pozo, Francesc},
  title = {Improving Vibration-Based Classification in a Wind Turbine Jacket Structure and Rotor Through Multitask Learning and Spectral Representations},
  journal = {Wind},
  year = {2026},
  volume = {6},
  number = {4},
  pages = {65},
  doi = {10.3390/wind6040065}
}
Kostenlos starten →