Fault Detection and Isolation of Wind Energy Conversion Systems using Recurrent Neural Networks

Reliability of Wind Energy Conversion Systems (WECSs) is greatly important regarding to extract the maximum amount of available wind energy. In order to accurately study WECSs during occurrence of faults and to explore the impact of faults on each component of WECSs، a detailed model is required in which mechanical and electrical parts of WECSs are properly involved. In addition، a Fault Detection and Isolation System (FDIS) is required by which occurred faults can be diagnosed at the appropriate time in order to ensure safe system operation and avoid heavy economic losses. This can be performed by subsequent actions through fast and accurate detection and isolation of faults. In this paper، by utilizing a comprehensive dynamic model of the WECS، an FDIS is presented using dynamic recurrent neural networks. In industrial processes، dynamic neural networks are known as a good mathematical tool for fault detection. Simulation results show that the proposed FDIS detects faults of the generator''s angular velocity sensor، pitch angle sensors and pitch actuators appropriately. The suggested FDIS is capable to detect and isolate the faults shortly while owing very low false alarms rate. The presented FDIS scheme can be used to identify faults in other parts of the WECS.