According computational burden that would require later stage

Published by admin on

According to the proposed method shown in Fig. 4, The current signal at measuring node (feeder 6) is observed and it is decomposed using WT to obtain relevant features such as energy, skewness, standard deviation and kurtosis. These feature vectors are used to frame a Decision Tree (DT) model with good features that has discriminated ability for classification of HIF from Non-HIF (Linear and Non-Linear load switching, Capacitance switching) disturbances  and the final decision on relay trip signal.


A. Signal decomposition using Wavelet Transform

              Wavelet is an effective tool to analyze non-stationary signal. A set of filters (Low pass and High pass filters) is used in WT to decompose the original signal into low frequency and high frequency component. The low pass filter generates approximate coefficient, which are described as high scaled and low frequency decomposition. In contrast, the high pass filter generates detailed coefficient, which are described as low scaled and high frequency decomposition. Moreover, In this work, Discrete Wavelet Transform (DWT) instead of continuous wavelet transform is used to reduce huge amount of computational burden that would require later stage of work. The signal decomposition process utilizes Daubechies basis fourth order (db4), five level decomposition, the sampling rate of 3 kHZ with the data window length of three cycles.

We Will Write a Custom Essay Specifically
For You For Only $13.90/page!

order now


B. Feature extraction

The following are the features that are extracted from the signal after processing with DWT.

1. Standard deviation: It is a value expressing that, by what extent the signal differs from the mean.

2. Energy: The total energy content of the current signal.

3. Kurtosis: Bigger kurtosis point represents more outlier in the signal 15.

4. Skewness: It is a measure of the irregularity of the probability distribution about its mean 15.


C. Data Mining Model for Classification

              The objective of a data mining model is to create an understandable structure by taking the data set into account. Based on the model, the system behavior can be identified. Usually, the data mining model may be classified as descriptive model or predictive model. In the design of HIF detection method, predictive data mining model is preferred because of the requirement of the work i.e. Classification.

              There are several data mining models reported 16-18, However, DT model is chosen because of its transparency, efficiency and popularity. The proposed method utilizes open source data mining package ‘R’ for creating the DT model 19. For HIF detection, DT model is generated by considering the feature set into account. 

Categories: Behavior


I'm Iren!

Would you like to get a custom essay? How about receiving a customized one?

Check it out