An Adaptive Anomaly Detection and Fault Diagnosis in Wind Turbine

In recent days, Condition Monitoring is the process of monitoring a parameter of condition in a wind turbine, in order to identify a significant change that is indicative of a developing fault. By identifying the fault and removing it will increase the accuracy of the dataset. Data imputation will give additional advantages for increasing the accuracy of the dataset. The main objective of this work is to detect the anomalies from the dataset and remove the outlier from the dataset and replace imputed missing data for the removed anomalies. This algorithm utilizes the auto-encoder neural network in order to detect anomalies in the performance of the wind turbine (system layer), and for removing it and then applies k-nearest neighbors (KNN) algorithm is a simple, easy to implement machine learning algorithm that can be used for imputation of removed data. By eliminating inconsistent information and attributing the new information regularly brings about a measurably critical expansion inaccuracy.