Voltage THD Analysis Using Knowledge Discovery in Databases With a Decision Tree Classifier

Industrial production has evolved significantly over the last decade. For this reason, it is necessary to obtain mathematical and computational tools that enable power systems engineers to make decisions that reduce harmonic distortions in accordance with international standards. This paper presents...

Full description

Saved in:
Bibliographic Details
Published in:IEEE access 2018-01, Vol.6, p.1177-1188
Main Authors: de Oliveira, Edson Farias, de Lima Tostes, Maria Emilia, de Freitas, Carlos Alberto Oliveira, Leite, Jandecy Cabral
Format: Article
Language:English
Subjects:
Analyzers
Artificial intelligence
Classifiers
Collection
computational intelligence
Computers
Data mining
Decision analysis
decision tree
Decision trees
Electric power systems
Electrical networks
Harmonic analysis
Harmonic distortion
Industrial applications
KDD
Knowledge discovery
Mathematical analysis
power quality
Software
Total harmonic distortion
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Industrial production has evolved significantly over the last decade. For this reason, it is necessary to obtain mathematical and computational tools that enable power systems engineers to make decisions that reduce harmonic distortions in accordance with international standards. This paper presents a total harmonic distortion (THD) assessment based on full knowledge discovery in databases (KDD) using power quality (PQ) standards and computational intelligence tools. The materials and methods of THD assessment consist of load and layout analysis; choice and installation of PQ analyzers; and the application of the full KDD process, including collection, selection, cleaning, integration, transformation and reduction, mining, interpretation, and evaluation of the data. This research methodology was used in an electrical and electronic industry; the results obtained have characteristics that can be used as a reference for other types of analyses. The results indicate that these methods can be applied to several industrial applications such as: 1) the description of the complete KDD process for THD assessment of the point of common coupling; 2) simultaneous collection using five PQ analyzers at several points in the electrical network; and (3) the use of a decision tree classifier.
ISSN:2169-3536
2169-3536
DOI:10.1109/ACCESS.2017.2778028