Application of GEP to investigate the imbalance faults in direct-drive wind turbine using generator current signals

This study proposes a novel wind turbine generator (WTG) imbalance fault classifier using gene expression programming (GEP). Proposed GEP fault classifier is able to achieve very high classification accuracy with relatively small number of samples. Ours is a first attempt at designing a WTG imbalance fault identifier using GEP for fault segregation. The identifier does not assume prior knowledge of WTG model. Raw current data of permanent magnet synchronous generator stator side are processed through empirical mode decomposition to generate 16 intrinsic mode functions or IMFs. Classifier employs the J48 algorithm to further prune these 16 IMFs to eight most relevant input variables which serve as inputs to the GEP imbalance fault classifier. The authors compare performance of the proposed GEP classifier with other contemporary artificial intelligence (AI) based classifiers such as neural networks and support vector machines. Simulation results and performance comparison against other AI approaches elucidate that the proposed GEP-based identifier could serve as an important tool for WTG fault diagnosis.