The Study and Analysis of Passive Power Filter to Improve Power Quality by Using Deep Learning

Abstract

Passive power filter(PPFs) is widely used in large industries due to their ease of use, durability, and stability. Typically, a passive power filter's lifespan can be up to 14 years, but data has shown that it has a shorter service life because of damage to capacitors for a variety of reasons, such as capacitor's degeneration, overheating in reactor, reactor's vibration, and noise due to the flowing of harmonic current through the power filter excessively. This implies that the passive power filter system is in trouble. Furthermore, it has been found that maintaining the capacitor at a low temperature can keep the %THD level within the IEEE 519–2014 range and extend the life of the capacitor. Eventually, the collected data will be used to create a neural network for capacitor prediction and maintenance for further industrial applications.