Condition monitoring and early fault detection of wind turbine faults can reduce maintenance costs and prevent cascaded failures. This paper proposes a new Normal Behavior Modeling (NBM) method to predict wind turbine electric pitch system failures using supervisory control and data acquisition (SCADA) information. The proposed method is particularly effective for online monitoring applications at a reasonable computational complexity. Briefly, in the data preprocessing stage of the proposed method, in order to remove interferential information and improve data quality, the operational state codes from turbine programmable logic controller are applied to filter SCADA data. In the modeling process, we designed a NBM method using optimized relevance vector machine (RVM) regression, which is relatively fast and computationally efficient. An adaptive threshold by the probabilistic output of RVM is proposed and used as the rule of anomaly detection. One normal case and three typical fault cases have been studied to demonstrate the feasibility of the proposed method. The performance of the method is assessed using 38 actual pitch system faults compared with two existing methods.

With the rapid development of wind energy, it is important to reduce operation and maintenance (O&M) costs of wind turbines (WTs), especially for a pitch system, which suffers the highest failure rate and downtime. This paper proposes a data-driven method for pitch- system condition monitoring (CM) by only using supervisory control and data acquisition (SCADA) data without any faults, which could be applied to reduce O&M costs of pitch system by providing fault alarms. The pitch-motor temperature is selected as the indicator, and three feature-selection algorithms are employed to select the most appropriate input parameters for modeling. Six data-driven algorithms are applied to model pitch-motor temperature and the support vector regression (SVR) model has the highest accuracy. The control-chart method based on the residual errors between model output and measured value is utilized to calculate the outliers, thus the abnormal condition could be clearly identified once the outliers appear for a period of time. The effectiveness of the proposed method is demonstrated by several case studies, and compared with the classification models. Due to the adaptive ability and low cost, the proposed approach is suitable for online CM of pitch systems, and provides a strategy for CM of new WTs.

Due to the recent rapid development of the wind energy industry, many wind turbines that have been operational over long periods will face degradation caused by aging effects; hence, an appropriate aging assessment method for wind turbines and their components is essential for optimizing the asset management and maintenance strategy of a wind farm. An aging assessment method is proposed for wind‐turbine electric‐pitch systems by introducing four individual aging indicators based on the examination of supervisory control and data acquisition (SCADA) and failure data, i.e. function, energy‐consumption, temperature, and reliability indicators. To obtain a reliable comprehensive assessment, an information‐fusion method has been developed based on a given reference value; the weighting factors in the information fusion were calculated based on the reference value, while reliability and robustness were verified using the SCADA and failure data from a wind farm over three years.

Wind farm operators are overwhelmed by a large amount of supervisory control and data acquisition (SCADA) alarms when faults occur. This paper presents an online root fault identification method for SCADA alarms to assist operators in wind turbine fault diagnosis. The proposed method is based on the similarity analysis between an unknown alarm vector and the feature vectors of known faults. The alarm vector is obtained from segmented alarm lists, which are filtered and simplified. The feature vector, which is a unique signature representing the occurrence of a fault, is extracted from the alarm lists belonging to the same fault. To mine the coupling correspondence between alarms and faults, we define the weights of the alarms in each fault. The similarities is measured by the weighted Euclidean distance and the weighted Hamming distance, respectively. One year of SCADA alarms and maintenance records are used to verify the proposed method. The results show that the performance of the weighted Hamming distance is better than that of the weighted Euclidean distance; 84.1% of alarm lists are labeled with the right root fault.

The alarm data contain abundant fault information related to almost all components of the wind turbine. Reasonable analysis and utilization of alarm data can assist wind farm maintenance personnel in quickly identifying the types of turbine faults, reducing operation and maintenance costs. This paper proposes a clustering analysis method that groups similar alarm sequences with the same fault type. Firstly, the alarm data are preprocessed, where alarm sequences are segmented, and redundant alarms are removed. Then, a domain knowledge-fused Word2vec (DK-Wrod2vec) method is introduced to transform non-numeric alarm codes into numeric vector representations. Finally, new distance metrics are incorporated into the K-means clustering algorithm to improve clustering performance. The performance of the proposed clustering method is assessed by applying it to labeled alarm sequences. The results demonstrate that the clustering performance is the best when using DK-Word2vec and the word rotator’s distance compared with other methods. Additionally, with the optimal parameter combination, the fault types of unlabeled alarm sequences are also analyzed.

Alarms generated by a wind turbine alarm system indicate the need for emergency action by operators to protect the turbine from running into risky conditions. However, it can be challenging for operators to identify the fault types that trigger alarms, particularly with few labeled fault samples. This paper proposes a novel fault diagnosis method for wind turbines with alarms that collaboratively uses labeled and unlabeled alarms to improve diagnosis accuracy. First, the proposed method distinguishes different alarm sequences using a designed Siamese convolutional neural network with an embedding layer (S-ECNN) model. Then, the fault category of an unknown alarm sequence is diagnosed based on similarity scores. Specifically, the Skip-gram model is used to mine potential relationships among alarms in unlabeled alarm sequences, and pretrained alarm vectors are obtained. In the S-ECNN model, the pretrained alarm vectors are further optimized and trained using labeled alarm sequences. The similarity scores are calculated based on the distance between the extracted discriminative features of alarm sequences. The effectiveness of the proposed method is validated using actual alarm data from a wind farm.