Physics-Guided Adaptive DBSCAN for Sensor Data Quality Assurance in Wind Turbine SCADA Systems
IEEE Sensors Journal · 2026-08 · 26 (16) · 24675-24685
DOI: 10.1109/jsen.2026.3710027 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Sensors Journal, 2026-08. Verfasst von Haonan Cui und 3 weiteren Autor:innen. Die Arbeit nennt 35 Literaturangaben. Gefördert von: Science and Technology Project of SGCC.
Abstract (Originalsprache)
Raw wind turbine supervisory control and data acquisition (SCADA) records are contaminated by heterogeneous anomalies—sensor faults, operational shutdowns, and grid-mandated curtailment—that severely degrade the wind turbine power curve (WTPC) used for performance assessment and condition monitoring. Existing screening methods rely on 2-D wind-speed-power analysis, which cannot discriminate these physically distinct anomaly categories. This article proposes a two-stage physics-ruled framework. Stage 1 cross-validates wind speed, pitch angle, and generator speed through a 3-D physics-based constraint matrix to flag implausible operating states. Stage 2 applies a physics-guided adaptive DBSCAN (PG-DBSCAN) that incorporates the theoretical aerodynamic gradient and adaptively sets neighborhood parameters from local sensor noise characteristics, detecting subtle anomalies that evade conventional density-based methods. A parameter unification principle reduces effective tuning to a single interpretable threshold. PG-DBSCAN achieves a post-cleaning power curve $\textit {R}^{{2}} {\,}= {\,}{0}.{994}$ (RMSE = 34.8 kW) and fidelity $\textit {F} {\,}= {\,}{0}.{742}$ , outperforming five baselines; an ablation study attributes a 22.7% RMSE reduction to the gradient alignment criterion. Cross-site validation on the publicly available Kelmarsh SCADA dataset (Senvion MM92 2.05 MW, 24 214 records) confirms the framework’s generalizability without algorithmic retuning.
Förderung
- Science and Technology Project of SGCC
Zitieren
APA
Cui, H., Wang, X., Liu, B., & Liu, Y. (2026). Physics-Guided Adaptive DBSCAN for Sensor Data Quality Assurance in Wind Turbine SCADA Systems. IEEE Sensors Journal, 26(16), 24675-24685. https://doi.org/10.1109/jsen.2026.3710027
Vancouver
Cui H, Wang X, Liu B, Liu Y. Physics-Guided Adaptive DBSCAN for Sensor Data Quality Assurance in Wind Turbine SCADA Systems. IEEE Sensors Journal. 2026;26(16):24675-24685. doi:10.1109/jsen.2026.3710027
BibTeX
@article{Cui2026,
author = {Cui, Haonan and Wang, Xiaodong and Liu, Baosong and Liu, Yingming},
title = {Physics-Guided Adaptive DBSCAN for Sensor Data Quality Assurance in Wind Turbine SCADA Systems},
journal = {IEEE Sensors Journal},
year = {2026},
volume = {26},
number = {16},
pages = {24675--24685},
doi = {10.1109/jsen.2026.3710027}
}
EUVIMED