Power Quality Transient Detection and Characterization Using Deep Learning Techniques

Power quality issues can affect the performance of devices powered by grid and can, in severe cases, permanently damage connected devices. Events that power include sags, swells, waveform distortions transients. Transients are one most common disturbances caused lightning strikes or switching activities among power-grid-connected systems reach very high magnitudes, their duration spans from nanoseconds to milliseconds. This study proposed a deep-learning-based technique was supported convolutional neural networks bidirectional long short-term memory approach order detect characterize power-quality The method validated (i.e., benchmarked) using an alternative algorithm had been previously according digital high-pass filter morphological closing operation. training assessments were carried out actual power-grid-measured data events.