An Effective Fault Diagnosis Technique for Wind Energy Conversion Systems Based on an Improved Particle Swarm Optimization

The current paper proposes intelligent Fault Detection and Diagnosis (FDD) approaches, aimed to ensure the high-performance operation of Wind energy conversion (WEC) systems. First, an efficient feature selection algorithm based on particle swarm optimization (PSO) is proposed. main idea behind use PSO remove irrelevant features extract only most significant ones from raw data in order improve classification task using a neural networks classifier. Then, overcome problem premature convergence local sub-optimal areas when classical algorithm, improved extension basic this proposal Euclidean distance as dissimilarity metric between observations which single observation kept case redundancies. In addition, proposed reduced PSO-NN (RPSO-NN) technique not enhances results terms accuracy but also provides reduction computation time storage cost by reducing size training dataset removing redundant samples. experimental showed robustness high performance diagnosis paradigms.