A Sensor Data Processing Algorithm for Wind Turbine Hydraulic Pitch System Diagnosis

Modern wind turbines depend on their blade pitch systems for start-ups, shutdowns, and power control. Pitch system failures have, therefore, a considerable impact on their operation and integrity. Hydraulic pitch systems are very common, due to their flexibility, maintainability, and cost; hence, the relevance of diagnostic algorithms specifically targeted at them. We propose one such algorithm based on sensor data available to the vast majority of turbine controllers, which we process to fit a model of the hydraulic pitch system to obtain significant indicators of the presence of the critical failure modes. This algorithm differs from state-of-the-art, model-based algorithms in that it does not numerically time-integrate the model equations in parallel with the physical turbine, which is demanding in terms of in situ computation (or, alternatively, data transmission) and is highly susceptible to drift. Our algorithm requires only a modest amount of local sensor data processing, which can be asynchronous and intermittent, to produce negligible quantities of data to be transmitted for remote storage and analysis. In order to validate our algorithm, we use synthetic data generated with state-of-the-art aeroelastic and hydraulic simulation software. The results suggest that a diagnosis of the critical wind turbine hydraulic pitch system failure modes based on our algorithm is viable.

Review and Perspectives of Machine Learning Methods for Wind Turbine Fault Diagnosis

Wind turbines (WTs) generally comprise several complex and interconnected systems, such as hub, converter, gearbox, generator, yaw system, pitch system, hydraulic system control system,integration control system, and auxiliary system. Moreover, fault diagnosis plays an important role in ensuring WT safety. In the past decades, machine learning (ML) has showed a powerful capability in fault detection and diagnosis of WTs, thereby remarkably reducing equipment downtime and minimizing financial losses. This study provides a comprehensive review of recent studies on ML methods and techniques for WT fault diagnosis. These studies are classified as supervised, unsupervised, and semi-supervised learning methods. Existing state-of-the-art methods are analyzed and characteristics are discussed. Perspectives on challenges and further directions are also provided.

Simulation study on pitch system of floating wind turbine

Due to the complex sea conditions, floating wind turbines produce unbalanced loads. Firstly, this paper will take NERL-5MW floating wind turbine as the model, and apply brainstorming algorithm (BSO) to the independent pitch system based on PID azimuth weight coefficient. Then, a joint simulation will be carried out in OpenFAST-Matlab/Simulink to study its impact on the load of floating wind turbine. Finally, the simulation results reveal that compared with the independent pitch system based on PID azimuth weight coefficient, the proposed method can reduce the load of the floating platform to a certain extent.

Investigation of Isolation Forest for Wind Turbine Pitch System Condition Monitoring Using SCADA Data

Wind turbine pitch system condition monitoring is an active area of research, and this paper investigates the use of the Isolation Forest Machine Learning model and Supervisory Control and Data Acquisition system data for this task. This paper examines two case studies, turbines with hydraulic or electric pitch systems, and uses an Isolation Forest to predict failure ahead of time. This novel technique compared several models per turbine, each trained on a different number of months of data. An anomaly proportion for three different time-series window lengths was compared, to observe trends and peaks before failure. The two cases were compared, and it was found that this technique could detect abnormal activity roughly 12 to 18 months before failure for both the hydraulic and electric pitch systems for all unhealthy turbines, and a trend upwards in anomalies could be found in the immediate run up to failure. These peaks in anomalous behaviour could indicate a future failure and this would allow for on-site maintenance to be scheduled. Therefore, this method could improve scheduling planned maintenance activity for pitch systems, regardless of the pitch system employed.

Fault Detection of Wind Turbine Electric Pitch System Based on IGWO-ERF

It is difficult to optimize the fault model parameters when Extreme Random Forest is used to detect the electric pitch system fault model of the double-fed wind turbine generator set. Therefore, Extreme Random Forest which was optimized by improved grey wolf algorithm (IGWO-ERF) was proposed to solve the problems mentioned above. First, IGWO-ERF imports the Cosine model to nonlinearize the linearly changing convergence factor α to balance the global exploration and local exploitation capabilities of the algorithm. Then, in the later stage of the algorithm iteration, α wolf generates its mirror wolf based on the lens imaging learning strategy to increase the diversity of the population and prevent local optimum of the population. The electric pitch system fault detection method of the wind turbine generator set sets the generator power of the variable pitch system as the main state parameter. First, it uses the Pearson correlation coefficient method to eliminate the features with low correlation with the electric pitch system generator power. Then, the remaining features are ranked by the importance of the RF features. Finally, the top N features are selected to construct the electric pitch system fault data set. The data set is divided into a training set and a test set. The training set is used to train the proposed fault detection model, and the test set is used for testing. Compared with other parameter optimization algorithms, the proposed method has lower FNR and FPR in the electric pitch system fault detection of the wind turbine generator set.