Power Quality Disturbance Detection and Classification

Power quality (PQ) monitoring is an essential service that many utilities perform for their industrial and larger commercial customers. Detecting and classifying the different electrical disturbances which can cause PQ problems is a difficult task that requires a high level of engineering knowledge. The vast majority of the disturbances are non-stationary and transitory in nature subsequently it requires advanced instruments and procedures for the examination of PQ disturbances. In this work a hybrid procedure is utilized for describing PQ disturbances utilizing wavelet transform and fuzzy logic. A no of PQ occasions are produced and decomposed utilizing wavelet decomposition algorithm of wavelet transform for exact recognition of disturbances. It is likewise watched that when the PQ disturbances are contaminated with noise the identification gets to be troublesome and the feature vectors to be separated will contain a high amount of noise which may corrupt the characterization precision. Consequently a Wavelet based denoising system is proposed in this work before feature extraction process. Two extremely distinct features basic to all PQ disturbances like Energy and Total Harmonic Distortion (THD) are separated utilizing discrete wavelet transform and is nourished as inputs to the fuzzy expert system for precise recognition and order of different PQ disturbances. The fuzzy expert system classifies the PQ disturbances as well as demonstrates whether the disturbance is unadulterated or contains harmonics. A neural network based Power Quality Disturbance (PQD) recognition framework is additionally displayed executing Multilayer Feedforward Neural Network (MFNN)