Adaptive Threshold Algorithm for Condition Monitoring of Wind Turbine Gearbox Bearings
Fixed alarm thresholds in wind turbine gearbox bearing monitoring rely on manual experience and fail to adapt to non-stationary operating conditions, causing false and missed alarms. This paper proposes an adaptive threshold algorithm, EWMA-Bi-DSPOT, combining exponentially weighted moving average (EWMA) smoothing with bilateral drift streaming peaks-over-threshold (POT) modeling. The method operates in two stages: initialization and online update. In initialization, EWMA suppresses high-frequency noise in raw SCADA temperature sequences; a high quantile is selected as an initial threshold, and a generalized Pareto distribution (GPD) is fitted to exceedances via maximum likelihood estimation to obtain an initial alarm threshold. In the online stage, the algorithm continuously absorbs marginal extreme values that do not trigger alarms, recursively updating GPD parameters and the alarm threshold to track system state drift. Experiments on a 1.5 MW doubly-fed wind turbine gearbox bearing temperature dataset demonstrate that EWMA-Bi-DSPOT achieves a false alarm rate of 3.2% and a missed alarm rate of 3.1%, outperforming comparison models. The algorithm enables dynamic adaptive threshold updates, improving real-time fault warning reliability while maintaining low false and missed alarm rates. The results confirm that EWMA filtering effectively suppresses random fluctuations and improves extreme value structure, and the bilateral extreme value update mechanism solves the inability of a single threshold to follow operating condition drift.