Feature Analysis of Numerical Calculated Data from Sweep Frequency Analysis (SFRA) Traces Using Self Organizing Maps

Bohari, Zul Hasrizal; Ghani, Sulaiman Ab; Baharom, Mohamad Faizal; Nasir, Mohamad Na'im Mohd; Jali, Mohd Hafiz; Thayoob, Yasmin Hanum Md

doi:10.11113/jt.v67.2762

Cited by 7 publications

(9 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Table III shows the results of optimization for the selection of SOM visualization. Low quantization and topographic error indicates good and smooth classification for normalization method [16]. Therefore, in this work, 600 numbers of neurons was selected to visualize the result.…”

Section: B Self-organization Map(som)mentioning

confidence: 99%

See 1 more Smart Citation

AC breakdown voltage of natural ester mixed with Iron Oxide for oil-immersed power transformer application

Mohamad

Zainuddin

Ghani

et al. 2015

2015 IEEE Student Conference on Research and Development (SCOReD)

View full text Add to dashboard Cite

Nowadays, nanoscale materials are increasingly popular in academic and industrial research. It is expected that the combination of nanoscale materials with other material can contribute more benefits. The use of nanoscale materials often require their dispersion in variety of liquids, to enable them to become part of the liquid product, also known as nanofluids. For example, one of the applications is the nanoparticles dispersed with transformer oil in oil-immersed transformer application. Traditionally, mineral oil is used as dielectric liquid and cooling medium in power transformer. In this paper, dielectric strength of ester oil when mixed with nanoparticles is investigated. For that purpose, AC breakdown voltage test is compliance with ASTM D1816 standard is performed. Statistical analysis and high dimension visualization have been done to analyse and compare the result between fresh ester oil taken from tank and the similar ester oil that mixed with nanoparticles. The results suggest that ester oil mixed with nanoparticles of 0.02 % by volume performs well compared to other samples.

show abstract

Section: B Self-organization Map(som)mentioning

confidence: 99%

“…This is purpose to estimating the withstand voltage at the probability of distribution data [15]. Other than that, the interpretation of data can be analysed by using visualization tools as reported in [16].…”

Section: Introductionmentioning

confidence: 99%

AC breakdown voltage of natural ester mixed with Iron Oxide for oil-immersed power transformer application

Mohamad

Zainuddin

Ghani

et al. 2015

2015 IEEE Student Conference on Research and Development (SCOReD)

View full text Add to dashboard Cite

show abstract

“…Classification using SOM: Based on neurological studies, all human sensory inputs are mapped onto certain areas at the cerebral cortex that form a map called Topographic Map (Bohari et al, 2014). It has two most essential assets:…”

Section: Root Mean Squarementioning

confidence: 99%

“…SOM is an unsupervised learning (learning by observation) refers to the method that learns by itself according to input attributes and also applies competitive learning that made the output nodes to compete to be activated. Only one of the node will activated at any one time or we called winning neuron (Bohari et al, 2014). Such a competition can be induced through negative feedbacks between neurons.…”

Section: Introductionmentioning

confidence: 99%

Classification of EMG Signal Based on Human Percentile using SOM

Jali¹,

Bohari²,

Sulaima³

et al. 2014

RJASET

View full text Add to dashboard Cite

Electromyography (EMG) is a bio signal that is formed by physiological variations in the state of muscle fibre membranes. Pattern recognition is one of the fields in the bio-signal processing which classified the signal into certain desired categories with subject to their area of application. This study described the classification of the EMG signal based on human body percentile using Self Organizing Mapping (SOM) technique. Different human percentile definitively varies the arm circumference size. Variation of arm circumference is due to fatty tissue that lay between active muscle and skin. Generally the fatty tissue would decrease the overall amplitude of the EMG signal. Data collection is conducted randomly with fifteen subjects that have numerous percentiles using noninvasive technique at Biceps Brachii muscle. The signals are then going through filtering process to prepare them for the next stage. Then, five well known time domain feature extraction methods are applied to the signal before the classification process. Self Organizing Map (SOM) technique is used as a classifier to discriminate between the human percentiles. Result shows that SOM is capable in clustering the EMG signal to the desired human percentile categories by optimizing the neurons of the technique.

show abstract

“…Artificial Neural Networks (ANN) has manipulated in multiple research tools such as in biomedical engineering [2,3], electrical system [4,8], load forecasting [5], load contingency analysis [6] and etc. There are three main ANN learning type, the most common type is supervised learning and the other two are supervised and reinforcement learning.…”

Section: Introductionmentioning

confidence: 99%

Transformer mechanical integrity evaluation via unsupervised neural network (UNN) in smart grid network

Bohari

Jali

Baharom

et al. 2015

2015 IEEE International Conference on Control System, Computing and Engineering (ICCSCE)

Self Cite

View full text Add to dashboard Cite

This paper describes the classification of mechanical integrity of transformers using unsupervised neural networks (UNN). Transformers are the integral part of electrical system or smart grid networks since the last century. Self-Organizing Maps (SOM) is one type of UNN the widely used to do assessment on any system such as biomedical engineering, load contingency analysis and etc. The application of CIGRE standard and SOM in the research are enhancing the ability to do mechanical integrity assessment on the transformers for condition monitoring. Motivation for this research is to fill in the gap of excess FRA raw data for better assessment. This research proved that the new proposed method using SOM integrated with CIGRE standard able to do mechanical examination especially on core, winding and magnetic part of the transformer compared to current OMICRON SFRAnalyzer tool that employed Chinese Standard.

show abstract

Feature Analysis of Numerical Calculated Data from Sweep Frequency Analysis (SFRA) Traces Using Self Organizing Maps

Cited by 7 publications

References 3 publications

AC breakdown voltage of natural ester mixed with Iron Oxide for oil-immersed power transformer application

AC breakdown voltage of natural ester mixed with Iron Oxide for oil-immersed power transformer application

Classification of EMG Signal Based on Human Percentile using SOM

Transformer mechanical integrity evaluation via unsupervised neural network (UNN) in smart grid network

Contact Info

Product

Resources

About