Enhanced fault diagnosis of wind energy conversion systems using ensemble learning based on sine cosine algorithm

Abstract This paper investigates the problem of incipient fault detection and diagnosis (FDD) in wind energy conversion systems (WECS) using an innovative effective approach called ensemble learning-sine cosine optimization algorithm (EL-SCOA). The evolved strategy involves two primary steps: first, a sine-cosine is used to extract optimize features order only select most descriptive ones. Second, further improve capability, thereby providing highest accuracy performance, newly gathered dataset introduced as input learning paradigm, which merges benefits boosting bagging techniques with artificial neural network classifier. essential goal developed proposal discriminate between diverse operating conditions (one healthy six faulty conditions). Three potential frequent types faults that can affect system behaviors including short-circuit, open-circuit, wear-out are considered injected at locations sides (grid generator sides) evaluate availability performance proposed technique when compared conventional FDD methods. analyzed terms accuracy, recall, precision, computation time. acquired outcomes demonstrate efficiency suggested diagnostic paradigm (accuracy rate has been successfully achieved 98.35%).