Key Takeaways & Executive Findings
- •• • 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.
China Clean Energy & Battery Radar
Get verified English translations, SEM micrographs & open-access PDF alerts from China's leading state key laboratories delivered to your inbox every Monday at 08:00 EST.
Abstract
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.
1. Introduction
Wind turbine gearbox bearings operate under severe and highly variable conditions, making early fault detection critical to avoid catastrophic failures and costly downtime. Traditional condition monitoring relies on manually set fixed thresholds derived from statistical analysis of historical SCADA data. These thresholds are static and cannot adapt to the pronounced non-stationary operating conditions of wind turbines, particularly under low-load regimes where temperature deviations from normal statistical distributions may indicate incipient faults even when absolute temperatures remain below alarm limits. Consequently, fixed thresholds produce high false alarm rates during normal load fluctuations and missed alarms during subtle fault evolution, eroding operator trust and delaying maintenance interventions.
Existing anomaly detection methods, including statistical tests, mutual information, autoencoder reconstruction errors, and density clustering, have been applied but often lack a principled framework for dynamic threshold adaptation. The EWMA-Bi-DSPOT algorithm addresses this bottleneck by integrating exponentially weighted moving average smoothing to suppress high-frequency noise, extreme value theory via the peaks-over-threshold method with generalized Pareto distribution modeling, and a bilateral drift update mechanism that continuously absorbs non-alarming marginal extremes to recursively update GPD parameters and the alarm threshold. This two-stage approach—initialization with high quantile and GPD fitting, followed by online recursive updating—enables the threshold to evolve with system state drift, providing a robust solution for real-time fault warning under variable operating conditions.
Loading authentic research manuscript (Pages 1–5)...
LI Gang, MENG Xiang, YANG Rui, DUAN Changjiang, YAN Wenqian, YANG Yanjun (2026). Adaptive Threshold Algorithm for Condition Monitoring of Wind Turbine Gearbox Bearings. Acta Energiae Solaris Sinica. https://doi.org/10.19912/j.0254-0096.tynxb.202608_9719
Research & Educational Purpose Only: The translations, structured abstracts, analytical annotations, and data reports provided by SinoGreenTechare intended exclusively for academic research, internal corporate R&D, and educational benchmarking. They do not constitute formal engineering, chemical safety, legal, or professional advice.
Copyright & Intellectual Property Notice: Original copyright of the underlying source articles and experimental data remains with the respective authors, institutions, and original publishing journals. SinoGreenTech claims intellectual property only over its proprietary translations, analytical syntheses, and AEO structured enhancements in accordance with international fair use and academic citation principles.
Frequently Asked Questions
What is the false alarm rate and missed alarm rate of the proposed EWMA-Bi-DSPOT algorithm, and how do they compare to baseline methods?
The algorithm 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. These rates are lower than those of comparison models, demonstrating superior comprehensive detection performance. The low false alarm rate reduces unnecessary maintenance, while the low missed alarm rate ensures early fault capture.
How does the initialization window size affect the adaptive threshold performance?
A clean, small initialization window reliably sets the initial threshold, whereas a large window containing anomalies causes threshold drift and weakens warning capability. This is because anomalous data points in the initialization set bias the GPD parameter estimates, leading to an inflated or deflated initial threshold that propagates through online updates. Therefore, careful selection of an anomaly-free baseline window is essential for robust initialization.
What is the role of the anomaly probability q in the algorithm, and how sensitive is the detection to its value?
The anomaly probability q directly controls alarm sensitivity: smaller q values yield higher thresholds and fewer alarms, while larger q values increase sensitivity but may raise false alarms. Experiments show that upper-bound detection is robust to q variations, allowing a moderate q to balance detection sensitivity and model stability. This robustness simplifies parameter tuning in practical deployments.
How does the bilateral drift update mechanism handle non-stationary operating conditions?
The mechanism recursively updates GPD parameters and the alarm threshold using marginal extreme values that do not trigger alarms. This gradient-based update captures distribution drift without relying on single-point data to alter overall statistical properties. Consequently, the threshold tracks gradual changes in operating conditions, such as load variations, enabling sensitive and stable fault warning under non-stationary regimes.
What is the computational complexity of the online update stage, and is it suitable for real-time SCADA implementation?
The online update involves recursive maximum likelihood estimation of GPD parameters using only the marginal extreme values, which is computationally lightweight and can be executed at SCADA sampling intervals. The algorithm does not require reprocessing the entire historical dataset, making it suitable for real-time implementation on standard industrial controllers or edge devices.
Related Chinese Research & Cross-Citations
Wind Turbine Gearbox Fault Diagnosis Method Based on Improved CNN-XGBoost Fusion Model Under Gramian Angular Difference Field
Gearbox failures account for 20–30% of total wind turbine faults and incur maintenance costs equivalent to 10–15% of overall turbine value. Conventional vibration diagnostic pipelines—complementary ensemble empirical mode decomposition with singular value energy spectrum, time-varying filtering empirical mode decomposition, and Teager energy spectrum analysis—remain bounded below 90% accuracy and depend on expert-driven feature engineering that is sensitive to non-stationary operating conditions and noise. This study proposes an intelligent diagnostic architecture that converts one-dimensional gearbox vibration signals into two-dimensional images via Gramian angular difference field (GADF) transformation, preserving intrinsic temporal correlation and time-frequency structure while exploiting matrix sparsity to suppress interference. An improved convolutional neural network (CNN) extracts multi-dimensional features: a convolutional block attention module (CBAM) is embedded in the convolutional layers to weight critical channels and focus on fault-sensitive spatial regions, and a modified βc-ACONC activation function replaces ReLU to mitigate neuron necrosis and enable selective activation. The extracted composite features are then fed into an XGBoost network whose hyperparameters are optimized by an improved sparrow search algorithm (ISSA). Validation on a laboratory wind turbine gearbox dataset yields diagnostic accuracy exceeding 99%, demonstrating robust fault identification capability under complex operating conditions.
Joint Forecasting of Wind and Photovoltaic Power Considering Complementarity
The inherent spatiotemporal complementarity between wind and solar resources offers a theoretical basis for improving renewable power forecasting accuracy. This study proposes a joint wind-photovoltaic (PV) power forecasting strategy that explicitly exploits this complementarity. A bidirectional long short-term memory (BiLSTM) neural network serves as the baseline forecasting model, and a novel sorting and comparative optimization (SCO) algorithm is developed to optimize the model's hyperparameters. The SCO algorithm ranks individuals in ascending order and compares adjacent fitness values to escape local optima, a known deficiency in conventional metaheuristics such as genetic algorithms and particle swarm optimization. For wind farms and PV plants exhibiting significant complementarity, the joint forecasting strategy first aggregates their power outputs, normalizes the combined signal, and then feeds it into the optimized BiLSTM model. Experimental results demonstrate that the proposed SCO-BiLSTM model reduces the eMAPE by 10.313% compared with PSO-BiLSTM. Furthermore, joint forecasting under SCO-BiLSTM lowers the eRMSE by 27.443% relative to standalone PV power forecasting. The study also establishes that forecasting accuracy improves with stronger wind-solar complementarity but degrades as the forecasting horizon extends. These findings confirm that exploiting complementarity in joint forecasting substantially enhances predictive performance for renewable energy integration.
Ultra-Short-Term Wind Power Forecasting Based on Fluctuation Continuation Scenario Identification
Existing ultra-short-term wind power forecasting methods exhibit limited performance due to insufficient extraction of fluctuation information and inadequate analysis of evolution patterns. This paper proposes an ultra-short-term wind power forecasting method based on fluctuation continuation scenario identification. First, the coupling mechanism of wind power fluctuations under multiple turbulence processes is investigated, and historical wind power dynamics are decoupled into a combination of nonlinear and linear fluctuation components. A fluctuation continuation concept is introduced, and the future continuation scale of wind power fluctuations is derived from nonlinear and linear decoupling parameters, thereby classifying fluctuation continuation scenarios. A sparse neural network (SNN) oriented to high-dimensional sparse features is constructed to identify historical fluctuation continuation scenarios, and ultra-short-term power forecasting is conducted separately for each scenario. Validation using measured wind speed and power data from three wind farms shows that, compared with baseline models, the proposed model improves root mean square error (RMSE), mean absolute error (MAE), and mean absolute percentage error (MAPE) by at least 1.46%, 2.44%, and 14.67%, respectively, demonstrating superior accuracy and stability. The method addresses the limitations of signal decomposition techniques that lack physical interpretability and are sensitive to hyperparameters, and overcomes the high-dimensional sparsity challenges faced by traditional scenario identification models.
Multi-Classifier Open Adversarial Network for Rolling Bearing Fault Diagnosis in Wind Turbine Generator Systems
Rolling bearings in wind turbine generator systems operate under variable speed and load conditions that induce significant data distribution shifts between training and field data, while unknown fault modes absent from the source domain are frequently misclassified as known classes. This study proposes a multi-classifier open adversarial network (MCOAN) for open-set fault diagnosis. Within an adversarial domain adaptation framework, a K-way classifier and an additional K+1-way one-vs-all classifier independently estimate target-sample similarity to the source domain. These similarity scores drive a dynamic weighting mechanism that adaptively reweights target samples during open-set adversarial training and supplies per-sample dynamic thresholds for known/unknown discrimination, thereby promoting cross-domain alignment of shared-class features while suppressing negative transfer from unknown samples. A non-adversarial domain classifier is introduced to stabilize dynamic weight estimation. Validation on two datasets demonstrates high-precision shared-class distribution alignment and unknown-class recognition with favorable robustness. The method removes reliance on empirically preset thresholds that plague conventional open-set back-propagation approaches, where a fixed threshold of 0.5 in the binary cross-entropy adversarial loss provides no per-sample adaptivity. By coupling K-way and K+1-way similarity estimates, MCOAN achieves simultaneous known-class alignment and unknown-class separation without prior knowledge of the unknown-class cardinality, addressing a persistent bottleneck in wind turbine drivetrain condition monitoring where unanticipated bearing failure modes emerge under field conditions.
Unsupervised Automated Identification Method for Abnormal States of Wind Turbine Gearboxes
Addressing the scarcity of labeled data for training classification models in wind turbine planetary gearbox anomaly identification, this study proposes an unsupervised automated detection method. Log Mel-band energy features are extracted from raw vibration signals and fed into an unsupervised anomaly recognition model centered on a U-net autoencoder. A health-state threshold is established based on reconstruction error between model input and output, enabling anomaly identification. The method is validated using factory gearbox test data and operational data from a wind farm in Yangtouya, Shanxi. For factory gearboxes, dual validation is performed using a spectrum amplitude modulation-based signal processing method. Results demonstrate that the proposed method achieves 93.34% recognition accuracy on both factory and wind farm test sets, confirming its capability to automatically and correctly separate abnormal wind turbine gearboxes. The approach eliminates reliance on labeled fault data, offering a scalable solution for full-lifecycle health monitoring, from factory acceptance testing to in-service early anomaly detection, adaptable across different operating conditions and turbine models.
Improved Adaptive Super-Twisting Sliding Mode Control for Permanent Magnet Synchronous Motors
Adaptive super-twisting sliding mode control (ASTSMC) for permanent magnet synchronous motors (PMSM) suffers from prolonged convergence and insufficient disturbance rejection under complex operating conditions. This paper proposes an improved ASTSMC incorporating a fixed-time disturbance observer (FTDO). A power term is introduced into the adaptive super-twisting controller to accelerate convergence far from the origin, while the discontinuous sign function is replaced by a continuous h(s) function to mitigate chattering. The FTDO ensures disturbance estimation converges within a fixed time independent of initial states, overcoming the limitations of traditional and finite-time observers. The estimated disturbance is fed forward to the sliding mode controller for compensation, enhancing robustness. The FTDO design is based on an auxiliary state variable z and its derivative, with error dynamics analyzed via Lyapunov stability. Comparative simulations against conventional disturbance observers and sliding mode controllers validate the proposed strategy. The results demonstrate shorter convergence time, improved dynamic performance, and superior disturbance rejection, making the approach suitable for high-performance servo systems. The method addresses the critical need for robust, fast-response control in electric vehicles, rail transit, and aerospace applications where PMSM drives face significant uncertainties and external disturbances.