UPI-JRAECE-2018-3 (Abstract)

Research Article

Optimized Neural Network Based Classifier for Effective Classification of Power Quality Disturbances

Swapnil B. Mohod1, Vikramsingh R. Parihar2*, Ketki R. Ingole3

1Department of Electrical Engineering, PRMCEAM, Amravati, India.

2Department of Electrical Engineering, PRMCEAM, Amravati, India.

3Department of Computer science and Engineering, Sipna College of Engineering and Technology, Amravati, India.


An exponential increase of nonlinear loads in power-system, mostly consisting of power electronic devices, hampered the quality of power supply. Deterioration of power quality often termed as power quality disturbance. This paper presents a Multilayer Perceptron Neural Network based classifier for effective classification of power quality disturbances. For feature extraction, wavelet transform technique was used. Optimized neural network based classifier using principal component analysis classifies the six types of power quality disturbances with the classification accuracy of 96.72%.

Key words: Artificial intelligence, Fourier transform, Power quality, Wavelet transform, Neural network. 

  Full Article PDF