Avaliação da Distorção Harmônica Total de Tensão no Ponto de Acoplamento Comum Industrial Usando o Processo KDD Baseado em Medição

Abstract

In recent decades, the transformation industry has introduced increasingly faster and more energy-efficient products for residential, commercial, and industrial use. However, these loads, due to their non-linearity, have significantly contributed to increased voltage harmonic distortion levels, according to Power Quality indicators. This thesis proposes a procedure based on the Knowledge Discovery in Databases (KDD) process to identify impactful loads on voltage harmonic distortions at the Point of Common Coupling (PCC). The methodology involves data collection and analysis with data mining techniques such as Decision Tree and Naïve Bayes applied to data collected by quality meters installed at the main loads and the PCC of an industrial consumer. The process includes data collection, cleaning, transformation, and evaluation steps. The results showed that the KDD process is applicable in analyzing Total Harmonic Distortion of Voltage, allowing the identification of the most impactful loads, with the most significant being the seventh current harmonic of the air conditioning units.