Development of a baseline as a novel strategy for a condition monitoring system for the assessment of wind turbine generators

摘要

Existing wind turbine condition monitoring methodologies can be time-consuming and costly processes that fail to achieve the reliability and operational efficiency required by the industry. Present studies on monitoring data for wind turbines is restricted to a few case histories and for certain sensors is yet scarcer. In order to overcome this issue, the development of a reliable baseline is desirable. In this paper, motor current signature analysis (MCSA) is proposed in order to generate a baseline to define the normal operating conditions of the induction generator in a wind turbine. Electrical current data is collected for an initial period of time, serving as a training process. Different signal processing methods are used to extract the wind turbine generator's features. The features extracted during this initial period are used to create a baseline that defines the behaviour of the generator under normal operation. A range of maximum and minimum values for these features is calculated using statistical methods. Using this approach, the generator monitoring process can be performed by comparing each new set of data acquired to the original baseline created during the initial stage.