Adaptive Threshold Algorithm for Condition Monitoring of Wind Turbine Gearbox Bearings

• • EWMA-Bi-DSPOT achieves a false alarm rate of 3.2% and a missed alarm rate of 3.1% on a 1.5 MW doubly-fed wind turbine gearbox bearing temperature dataset, outperforming comparison models. This dual low-error performance directly reduces unnecessary maintenance dispatches and undetected incipient faults, cutting operational expenditure in wind farms. • • The initialization window size critically affects threshold stability: a clean small window reliably sets the initial threshold, whereas a large window containing anomalies causes threshold drift and weakens warning capability. This imposes a practical constraint on commissioning data selection, requiring operators to curate anomaly-free baseline data for reliable initialization. • • The anomaly probability q directly controls alarm sensitivity; upper-bound detection exhibits robust performance across a range of q values, allowing selection of a moderate q to balance detection sensitivity and model stability. This provides a tunable parameter for site-specific calibration without frequent retuning. • • The recursive gradient update mechanism based on marginal extreme value streams captures distribution drift without relying on single-point data to alter overall statistical properties, enabling sensitive tracking of non-stationary operating conditions. This solves the engineering challenge of fixed thresholds failing under variable loads, ensuring reliable early fault detection.