Classification neutral to ground (NG) voltage using levenberg-marquardt neural network (LMNN)

Suzaryfazli Kamaruddin, Ahmad Farid Abidin, Mohd Abdul Talib Mat Yusoh


In electrical systems nowadays, power quality issues have become a major concern for customers and electrical utilities. The high Neutral to ground (NG) voltage are one of the power quality issues which could cause adverse effect such as malfunction the devices, neutral overheating and electricity shock. Thus, the high NG voltage should be classified in order to perform the mitigation work accurately. This paper presents the classification of neutral to ground voltage using Levenberg-Marquardt Neural Network (LMNN) technique. The Discrete Wavelet Transform (DWT) is applied in this method to extract the features of NG voltage which needed in classification process.  The result shows the LMNN perform accurately in classify the types of NG voltage, where its accuracy result is reach more than 90% accuracy.


Power Quality (PQ), Neutral to Ground (NG), Voltage, Wavelet Transform (DWT), Neural Network (NN)

Full Text:




  • There are currently no refbacks.

Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

The Indonesian Journal of Electrical Engineering and Computer Science (IJEECS)
p-ISSN: 2502-4752, e-ISSN: 2502-4760
This journal is published by the Institute of Advanced Engineering and Science (IAES) in collaboration with Intelektual Pustaka Media Utama (IPMU).

shopify stats IJEECS visitor statistics