Abstract
An important and strategic instrument in energy market is wind turbine (WT). WT consists of many components, whose operation and maintenance of them are very sensitive due to their unstable dynamic and environmental conditions. Condition monitoring (CM) and fault prognosis approaches are typical methods in order to decrease the production cost of energy and WT downtime. In this paper, a new combinatory system of CM and fault prognosis based on feature extraction and prediction algorithm is proposed. Firstly, 3 phase current signals are collected. In the next step, proper features selection is done in time and frequency domain. The CM operation is based on a feature amplitude value crossing of an alarm threshold. The fault prognosis is conducted with improved support vector machine (SVM) method. The least squares (LS) type of SVM method is used for fault prediction and particle swarm optimization (PSO) is used for the optimum selection of SVM and kernel parameters. When the trend of fault symptom crosses through the specific alarm threshold, the prognostics unit is activated and remaining useful life (RUL) prediction is performed using PSO-LSSVM. For a scenario of the fault, generator rotor winding failure based on rotor electrical asymmetry is created with different percentages in the doubly-fed induction generator. The effectiveness of the proposed prognosis structure is evaluated using a WT simulation setup. For this setup, a 2.5 Mw WT experimental data and equipment parameters are used. The statistical investigations show the precision of PSO-LSSVM in RUL prediction. The different simulations confirm that improved condition-based maintenance performances can be obtained.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call