Power Quality Disturbance Detection Using Artificial Intelligence: A Hardware Approach

Identification and classification of voltage and current disturbances in power systems is an important task in power system monitoring and protection. Most power quality disturbances are non-stationary and transitory and the detection and classification have proved to be very demanding. New intelligent system technologies using wavelet transform, expert systems and artificial neural networks provide some unique advantages regarding fault analysis. This paper presents new approach aimed at automating the analysis of power quality disturbances including sag, swell, transient, fluctuation, interruption and normal waveform. The approach focuses on the application of discrete wavelet transform technique to extract features from disturbance waveforms and their classification using a powerful combination of neural network and fuzzy logic. The system is modelled using VHDL followed by extensive testing and simulation to verify the correct functionality of the system. Then, the design is synthesized to APEX EP20K200EBC652-1X FPGA, tested and validated. Comparisons, verification and analysis made from the results obtained from the application of this system on software-generated and utility sampled disturbance signals validate the utility of this approach and achieved a classification accuracy of 98.17%.