Problem Diagnosis and mitigation using intelligent soft modules for improved power quality and system reliability

Providing effective classification techniques for various Power Quality (PQ) events is gaining the attention of reassures community, The process of power quality analysis and diagnosis is a complex one for many reasons, including the complex modeling of PQ, the extensive amount of system data that is currently available through PQ monitors and the lack of expert knowledge. Therefore, it is evident that computerized system analysis is vital for the realization of effective and efficient power quality diagnosis systems.This thesis develops several intelligent techniques that perform several power quality classification functions, among these techniques are wavelet analysis, subtractive cluster algorithm and Artificial Neural Network (ANN).Many signals are generated to simulate different types of power quality phenomena then wavelet analysis is applied upon these signals. Different feature extraction methods are proposed to reduce the amount of processed data which dramatically improve the performance of the proposed PQ classifier compared to other techniques proposed by other researchers. The extracted features are used to train different ANNs.