Evaluation of Flashover Voltage Levels of Contaminated Hydrophobic Polymer Insulators Using Regression Trees, Neural Networks, and Adaptive Neuro-Fuzzy
[...]flashover voltage could lead to service outage and affects negatively the reliability of the power system. [...]the authors of this work are motivated to consider and develop numerical evaluation or accurate modeling of flashover voltages levels plays a significant role in studying the dynamic...
Saved in:
Published in | Telkomnika Vol. 16; no. 2; pp. 495 - 512 |
---|---|
Main Authors | , |
Format | Journal Article |
Language | English |
Published |
Yogyakarta
Ahmad Dahlan University
01.04.2018
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | [...]flashover voltage could lead to service outage and affects negatively the reliability of the power system. [...]the authors of this work are motivated to consider and develop numerical evaluation or accurate modeling of flashover voltages levels plays a significant role in studying the dynamic behavior of polymeric materials. In order to estimate prediction performance of the pruned regression tree model, a comparison was made between the perceptron results of a multilayer feed-forward neural network with back propagation and the adaptive neuro-fuzzy approach. Since the multilayer feed-forward neural network is a well-known universal estimator for researchers, half of the measured data is used for training. Using a computer with a processor Intel(R) Core(TM) Í3-4160 CPU of speed 3.5GHz and 8GB ram, the required time for training the data is reported in Table 6. Because of the aforementioned appeal of the regression trees technique, it will be used to investigate the behavior of EPDM composite insulators against the SiR contents based on the recorded experimental work. |
---|---|
ISSN: | 1693-6930 2302-9293 |
DOI: | 10.12928/telkomnika.v16i2.5103 |