Logo image
Physics-informed condition monitoring for wind turbines via change point detection under heteroscedasticity
Journal article   Open access   Peer reviewed

Physics-informed condition monitoring for wind turbines via change point detection under heteroscedasticity

Zhanzhongyu Gao, Xun Xiao, Huadong Mo and Daoyi Dong
Reliability engineering & system safety, Vol.272, 112458
24/02/2026
Handle:
https://hdl.handle.net/10523/49957

Abstract

Condition monitoring Heteroscedasticity Physics-informed model Power curve modeling SCADA data
Condition monitoring is essential for ensuring the reliable operation and effective maintenance of modern complex systems, where nonlinear behaviors, environmental variability, and sensor noise can complicate fault diagnosis. Wind turbines, as representative examples of such systems, have widely adopted power curve-based methods for performance assessment and anomaly detection. However, most existing approaches overlook the heteroscedastic nature of noise, which adds uncertainty to model training and condition monitoring. In this paper, we propose a Bi-level Piecewise Linear Model (Bi-PLM) with physics-informed constraints to improve resilience against potential data contamination. A data-driven procedure, combining a binning method with locally estimated scatterplot smoothing (LOESS), is developed to characterize the noise heteroscedastic structure, which is then incorporated into change point detection (CPD)-based condition monitoring. Experiments on two real-world datasets show that explicitly accounting for heteroscedasticity reduces variance-induced uncertainty in residuals and substantially lowers false positives in fault detection, yielding average increases in the area under the curve (AUC) of approximately 6.0% and 8.4% on the two datasets. Comparative results against benchmark models confirm the robustness and reliability of the proposed method.
pdf
1-s2.0-S0951832026002747-main19.76 MBDownloadView
Published (Version of record)CC BY V4.0 Open Access
url
https://doi.org/10.1016/j.ress.2026.112458View
Published (Version of record)CC BY V4.0 Open

Metrics

1 Record Views

Details

Logo image