A hybrid intelligence approach for power quality disturbances detection and classification

作者：Moravej Zahra^*; Pazoki Mohammad; Niasati Mohsen; Abdoos Ali Akbar

来源：International Transactions on Electrical Energy Systems, 2013, 23(7): 914-929.

DOI：10.1002/etep.1628

• Power quality events
• feature extraction
• classification
• Gabor Transform
• probabilistic neural network

This paper presents a new synthetic methodology for detection and classification of different Power Quality Disturbances (PQDs). Gabor Transform (GT) integrated by a Probabilistic Neural Network (PNN) model is designed for implementation of a pattern recognition system. The approach uses features extracted from the output Matrix of GT as an input vector of a PNN classifier. The key attribute of GT is that it yields good time-frequency resolution with low computation burden. The PNN learner without any iteration for tuning weights classifies nine types of the most common PQDs including simultaneous events. The performance of the algorithm based on the combination of the GT and PNN (GT-PNN) is evaluated by generated data using parametric equations and a simulated network in the PSCAD/EMTDC software environment. The obtained numerical results confirm the effectiveness of GT-PNN approach for recognition of the different PQDs. Moreover, the classification accuracy is evaluated in the noisy conditions.

• 出版日期2013-10