Effective wind turbine fault diagnostic algorithms are crucial for wind turbine intelligent condition monitoring. An unscented Kalman filter approach is proposed to successfully detect and isolate two types of gearbox failures of a wind turbine in this paper. The state space models are defined for the unscented Kalman filter model by a detailed wind turbine nonlinear systematic principle analysis. The three failure modes being studied are gearbox damage, lubrication oil leakage and pitch failure. The results show that unscented Kalman filter model has special response to online input parameters under different fault conditions. Such property makes it effective on fault identification. It also shows that properly defining unscented Kalman filter state space vectors and control vectors are crucial for improving its sensitivity to different failures. Online fault detection capability of this approach is then proved on SCADA data. The developed unsented Kalman filter model provides an effective way for wind turbine fault detection using supervisory control and data acquisition data. This is essential for further intelligent WT condition monitoring.
Although Permanent Magnet Synchronous Generator (PMSG) wind turbines (WTs) mitigate gearbox impacts, they requires high reliability of generators and converters. Statistical analysis shows that the failure rate of direct-drive PMSG wind turbines’ generators and inverters are high. Intelligent fault diagnosis algorithms to detect inverters faults is a premise for the condition monitoring system aimed at improving wind turbines’ reliability and availability. The influences of random wind speed and diversified control strategies lead to challenges for developing intelligent fault diagnosis algorithms for converters. This paper studies open-circuit fault features of wind turbine converters in variable wind speed situations through systematic simulation and experiment. A new fault diagnosis algorithm named Wind Speed Based Normalized Current Trajectory is proposed and used to accurately detect and locate faulted IGBT in the circuit arms. It is compared to direct current monitoring and current vector trajectory pattern approaches. The results show that the proposed method has advantages in the accuracy of fault diagnosis and has superior anti-noise capability in variable wind speed situations. The impact of the control strategy is also identified. Experimental results demonstrate its applicability on practical WT condition monitoring system which is used to improve wind turbine reliability and reduce their maintenance cost.
This paper focuses on the electro-thermal analysis of a doubly-fed induction generator (DFIG) in a wind turbine (WT) with gear transmission configuration. The study of the thermal mechanism plays an important role in the development of cost-effective fault diagnostic techniques, design for reliability and premature failure prevention. Starting from an analysis of the DFIG system control and its power losses mechanism, a model that synthesizes the thermal mechanism of the DFIG and a WT system principle is developed to study the thermodynamics of generator stator winding. The transient-state and steady-state temperature characteristics of stator winding under constant and step-cycle patterns of wind speed are studied to show an intrinsic thermal process within a variable-speed WT generator. Thermal behaviors of two failure modes, i.e., generator ventilation system failure and generator stator winding under electric voltage unbalance, are examined in details and validated by both simulation and data analysis. The effective approach presented in this paper for generator fault diagnosis using the acquired SCADA data shows the importance of simulation models in providing guidance for post-data analysis and interpretation. WT generator winding lifetime is finally estimated based on a thermal ageing model to investigate the impacts of wind speed and failure mode.
Quantifying wind turbine (WT) gearbox fatigue life is a critical problem for preventive maintenance when unsolved. This paper proposes a practical approach that uses ten minutes’ average wind speed of Supervisory Control and Data Acquisition (SCADA) data to quantify a WT gearbox’s gear fatigue life. Wind turbulence impacts on gearbox fatigue are studied thoroughly. Short-term fatigue assessment for the gearbox is then performed using linear fatigue theory by considering WT responses under external and internal excitation. The results shows that for a three stage gearbox, the sun gear in the first stage and pinions in the 2nd and 3rd stage are the most vulnerable parts. High mean wind speed, especially above the rated range, leads to a high risk of gearbox fatigue damage. Increase of wind turbulence may not increase fatigue damage as long as a WT has an instant response to external excitation. An approach of using SCADA data recorded every ten minutes to quantify gearbox long-term damages is presented. The calculation results show that the approach effectively presents gears’ performance degradation by quantifying their fatigue damage. This is critical to improve WT reliability and meaningful for WT gearbox fatigue assessment theory. The result provides useful tools for future wind farm prognostic maintenance.