Towards DSS: Enhancing Domain Knowledge through Knowledge Discovery

This paper presents the application of KDD techniques to identify factors which contribute to the failure of wind turbine generators. For many years KDD approaches have been used to identify patterns and hidden information in datasets from a variety of domains. We discuss the challenges presented by the dataset in terms of selection and preparation of data and also introduce the format and meaning of data encompassed by the area of study, namely effects of blade vibration. Investigation of blade vibration has been used as a test of KDD within the dataset as we are aware that blade vibration typically occurs within a specific range of wind speeds, through existing domain knowledge. Through application of NN and RI techniques we are able to validate the understanding that vibration occurs within a given range but we have also identified that other variables, namely rotor speed can contribute to blade vibration at lower than expected speeds. These discoveries add to the understanding of a young domain and could ultimately lead to a decision support system for predictive maintenance of wind parks