Support Vector Machine for False Alarm Detection in Wind Turbine Management

Wind energy is one of the most growing renewable energy. A proper maintenance management policy is needed to ensure the viability of wind farms. Supervisory control and data acquisition systems are used to monitor and control the condition of wind turbines. The volume of data obtained by monitoring systems requires of advanced analytics based on artificial intelligence algorithms to process the information. The novelty developed in this work is the implantation of support vector machine algorithm for the prediction and detection of false alarms. A real case study is presented with dataset from a real wind turbine with the objective of identifying false alarms. The results show accuracy values around 98%.