MODELING OF BREAKDOWN VOLTAGE

OF SOLID INSULATING MATERIAL USING

ARTIFICIAL NEURAL NETWORK

Debashis Mishra (109EE0284)

Department of Electrical Engineering

National Institute of Technology Rourkela
MODELING OF BREAKDOWN VOLTAGE OF
SOLID INSULATING MATERIAL USING
ARTIFICIAL NEURAL NETWORK

A Thesis submitted in partial fulfilment of the requirements for the degree of

Bacelor of Technology
in
Electrical Engineering

By

Debashis Mishra
Roll No.109EE0284

Under the Supervision of

Prof. Sanjeeb Mohanty

NATIONAL INSTITUTE OF TECHNOLOGY, ROURKELA

राष्ट्रीय प्रौद्योगिकी संस्थान, राउरकेऱा
PIN-769008
ODISHA, INDIA

ii
 Dedicated TO

BhagawanShriShirdiSai Baba

&
My beloved Parents

iii
 DEPARTMENT OF ELECTRICAL ENGINEERING
NATIONAL INSTITUTE OF TECHNOLOGY, ROURKELA- 769 008
ODISHA, INDIA

CERTIFICATE

This is to certify that the thesis report titled “Modelling of Breakdown Voltage of a Solid
Insulating Material using Artificial Neural Network”, submitted to the National Institute of
Technology, Rourkela by Mr. Debashis Mishra, Roll No: 109EE0284 for the award of
Bachelor of Technology in Electrical Engineering, is a bonafide record of research work
carried out by him under my supervision and guidance.

The candidate has fulfilled all the prescribed requirements.

The thesis report which is based on candidate’s own work, has not submitted elsewhere for
a degree/diploma.

In my opinion, the draft report is of standard required for the award of a Bachelor of
Technology in Electrical Engineering.

Supervisor

Department of Electrical Engineering

National Institute of Technology

Rourkela – 769 008 (ODISHA)

iv
 ACKNOWLEDGEMENTS

This work was carried out at the Department of Electrical Engineering, National Institute of
Technology, Rourkela, Orissa, under the supervision of Prof. Sanjeeb Mohanty.

I would like to express my sincerest gratitude to Prof. Sanjeeb Mohanty for his guidance and
support throughout my work. Without him I will never be able to complete my work with this
ease. He was very patient to hear my problems that I am facing during the project work and
finding the solutions. I am very much thankful to him for giving his valuable time for me.

I would like to express my sincere thanks to Prof. A.K Panda, Prof. K.B Mohanty and Prof.
B.Chitti Babu for their precious suggestions and encouragement to perform my project work.

My special thanks to all my friends who did their thesis computational work in Simulation &
Computing Lab, of Electrical Engineering department and providing me good company in the
lab. And I would like to thank my friends who helped me in completing my thesis in time.

I thank God for giving me the chance to pursue my academic goals and a wonderful,
complete life full of amazing people.

Finally, hearty thanks to my family member for their sacrifice that encouraged me to proceed
with the work.

Debashis Mishra

v
 ABSTRACT

The voids or cavities within the solid insulating material during manufacturing are potential

sources of electrical trees which can lead to continuous degradation and breakdown of

insulating material due to Partial Discharge (PD). To determine the suitability of use and

acquire the data for the dimensioning of electrical insulation systems breakdown voltage of

insulator should be determined. A major field of Artificial Neural Networks (ANN))

application is function estimation due to its some useful properties, such as, non-linearity and

adaptively especially when the equation describing the function is unknown. In this project,

the breakdown voltage due to PD in cavities for five insulating materials under AC conditions

has been predicted as a function of different input parameters namely the thickness of the

insulating sample „t,‟ the thickness of the void „t1‟ diameter of the void „d‟ and relative

permittivity of materials  r by using the ANN model. The requisite training data are obtained

from experimental studies performed on a Cylinder-Plane electrode. The voids are artificially

created with different measures. Detailed studies have been carried out to determine the ANN

model parameters which give the best results. On completion of training, it is found that the

ANN model is capable of predicting the breakdown voltage Vb = f (t, t1, d,  r ) very

efficiently and with a small value of Mean Absolute Error. The system has been predicted

using MATLAB.

vi
Table of Contents
ABSTRACT………………………………………………………………………………………………………………………………………… vi

CONTENTS……………………………………………………………………………………………………………………………………… vii

NOMENCLATURE.................................................................................................................................... ix
LIST OF FIGURES ..................................................................................................................................... xi
LIST OF TABLES ...................................................................................................................................... xii
CHAPTER 1 .............................................................................................................................................. 1
INTRODUCTION ....................................................................................................................................... 1
1.1 INTRODUCTION ....................................................................................................................... 2
1.2 BREAKDOWN OF SOLID INSULATING MATERIALS .................................................................. 3
1.2.1 INTRINSIC BREAKDOWN.................................................................................................. 4
1.2.2 ELECTROMECHANICAL BREAKDOWN ............................................................................. 6
1.2.3 BREAKDOWN DUE TO TREEING AND TRACKING............................................................. 7
1.2.4 THERMAL BREAKDOWN .................................................................................................. 7
1.2.5 ELECTROCHEMICAL BREAKDOWN .................................................................................. 8
1.2.6 BREAKDOWN DUE TO INTERNAL DISCHARGES ............................................................... 8
1.3 MOTIVATION ........................................................................................................................... 9
1.4 OBJECTIVES ........................................................................................................................... 10
1.5 THESIS OUTLINE .................................................................................................................... 11
CHAPTER 2 ............................................................................................................................................ 12
EXPERIMENTAL SET UP ......................................................................................................................... 12
2.1 INTRODUCTION ..................................................................................................................... 13
2.2 EXPERIMENTAL PROCEDURE ................................................................................................ 13
2.2.1 SAMPLE PREPARATION ................................................................................................. 13
2.2.2 CREATION OF VOID ....................................................................................................... 14
2.2.3 ELECTRODE GEOMETRY ................................................................................................ 14
2.2.4 MEASUREMENT OF AC BREAKDOWN VOLTAGE ........................................................... 15
2.2.5 MEASUREMENT OF RELATIVE PERMITTIVITY OF SOLID INSULATING MATERIALS ....... 16
2.3 SUMMARY ............................................................................................................................. 22
CHAPTER 3 ............................................................................................................................................ 23
MULTILAYER FEEDFORWARD................................................................................................................ 23
NEURAL NETWORK ............................................................................................................................... 23
3.1 INTRODUCTION ..................................................................................................................... 24
3.2 THEORY OF MFNN ................................................................................................................. 24

vii
 3.2.1 CHOICE OF HIDDEN NEURONS ...................................................................................... 25
3.2.2 CHOICE OF ANN PARAMETERS ..................................................................................... 26
3.2.3 WEIGHT UPDATE EQUATIONS....................................................................................... 27
3.2.4 EVALUATION CRITERIA .................................................................................................. 27
3.2.5 MEAN ABSOLUTE ERROR .............................................................................................. 27
3.3 RESULTS AND DISCUSSION.................................................................................................... 28

CHAPTER4………………………………………………………………………………………………………………………………………..33
CONCLUSION AND FUTURE WORK………………………………………………………………………………………………….33
4.1INTRODUCTION………………………………………………………………………………………………………………………34
4.2SUMMURY……………………………………………………………………………………………………………………………..34
4.3CONCLUSIONS…………………………………………………………………………………………………………………………34
REFERENCE……………………………………………………………………………………………………………………………………..35

viii
 NOMENCLATURE

AC Alternating Current

ANN Artificial Neural Network

BPA Back Propagation Algorithm

BV Breakdown Voltage

EBA Experimental value of Breakdown Voltage

E tr Mean Square Error

E ts Mean Absolute Error

m Number of Iteration

MFNN Multilayer Feed forward Neural Network

MAE Mean Absolute Error

N Number of Hidden Neurons

h

 Momentum Factor

 Learning Rate Parameter of BPA

PD Partial Discharge

 Learning Rate Parameter of LMS algorithm

2

w Weight connected between hidden layer and input layer of MFNN.

aj

w Weight connected between output layer and hidden layer of MFNN

bj

SC Soft Computing

PE Processing Element

w Weight vector

ix
b Bias term

i Lagrange multipliers

r Relative permittivity

C Cost function

x
 LIST OF FIGURES
Figure No Page No
1.1 VARIATION OF BREAKDOWN STRENGTH AFTER THE APPLICATION
OF VOLTAGE..............................................................................................................................4

2.1 CYLINDER-PLANE ELECTRODE SYSTEM USED FOR BREAKDOWN

VOLTAGE MEASUREMENT.....................................................................................................15

3.1 MULTILAYER FEEDFORWARD NEURAL NETWORK ………………………..…….……25

3.2 MFNN STRUCTURE ………………………………………………………………… .28

3.3 VARIATION OF Etr WITH NUMBER OF ITERATIONS ( 1 = 0.99,  =0.8, Nh=10) ….........31
 LIST OF TABLES
Table No Page No
1.1 DIFFERENCES BETWEEN DEGRADATION AND BREAKDOWN FOR
A SOLID INSULATING MATERIAL ............................................................................. .3

2.1 RELATIVE PERMITTIVITY AGAINST MATERIALS ................................................... 16

2.2 EXPERIMENTAL BREAKDOWN VOLTAGES FOR WHITE MINILEX

INSULATING SAMPLES UNDER AC TEST CONDITION .......................................... 17

2.3 EXPERIMENTAL BREAKDOWN VOLTAGES FOR LEATHEROID PAPER

INSULATING SAMPLES UNDER AC TEST CONDITION .......................................... ..18

2.4 EXPERIMENTAL BREAKDOWN VOLTAGES FOR GLASS CLOTH

INSULATING SAMPLES UNDER AC TEST CONDITION ............................................19

2.5 EXPERIMENTAL BREAKDOWN VOLTAGES FOR MANILA PAPER

INSULATING SAMPLES UNDER AC TEST CONDITION ............................................20

2.6 EXPERIMENTAL BREAKDOWN VOLTAGES FOR LATHER MINILEX

INSULATING SAMPLES UNDER AC TEST CONDITION ............................................21

3.1 VARIATION OF Etr WITH NH ( 1 = 0.1,  = 0.6, ITERATION = 400) ………...….........29

3.2 VARIATION OF Etr WITH 1 (ITERATION = 400,  = 0.6, Nh=10) ………….…..……30

3.3 VARIATION OF EtrWITH  ( 1 = 0.99, Nh = 10, ITERATION = 400) ………..….……30

3.4 COMPARISON OF THE EXPERIMENTAL AND MODELLED DATA USING

MFNN MODEL …………………………………………………………………..…........32

4.1 Etr OF ANN MODEL …………………………………...………………………….. …….34

xii
 CHAPTER 1

INTRODUCTION

1
1.1 INTRODUCTION

In modern times, industry, research laboratories and much power system are using high voltages
for wide variety of applications. And with ever increasing demand of electrical energy the power
system is expanding both in size and complexities. To get the modern civilization such
applications play the vital role. The generating capacities of power plants and transmission
voltage are on the increase because of their inherent advantages.So it‟s very much essential to
know the property of the insulation material for optimum solution in terms of cost and insulating
capability. The power transfer capability of the system becomes four times if the transmission
voltage is doubled and the line losses are also relatively diminished. Consequently it becomes a
stronger and economical system. In our country India we already using 400 KV lines in operation
and 800 KV lines are being planned. In big cities, for the distribution voltages we are using the
conventional transmission voltages (110 kV–220 kV etc.) because of increased demand. A
system (transmission, distribution, switchgear, insulator etc.) designed for 400 kV and above
using conventional insulating materials is both bulky and expensive and, therefore, latest
insulating materials are being investigated to bring down both the cost and space requirements.
On insulating materials the electrically live conductors are supported and sufficient air clearances
are provided to avoid flashover or short circuits between the live parts of the system and the
grounded structure. At times, a live conductor is to be immersed in an insulating liquid to bring
down the size of the container and at the same time provide sufficient insulation between the
grounded container and. the live conductor.The quality of a solid insulation is adjudged in several
ways, out of these, the breakdown voltage continues to evoke a lot of interest to the Electrical
Engineers in general and High Voltage Engineers in particular. Hence, it is extremely important
to develop solid insulating materials with excellent breakdown strength and any attempt at
modelling the phenomenon with the presence of void would go a long way in assessing the
insulation quality.

Under normal working conditions, insulation steadily loses its dielectric strength and overvoltage
capacity because of general aging as well as due to local defects appearing in the form of voids in
the insulation during manufacture, particularly in extruded and cast type insulation. The quality
of a solid insulation is judged in several ways, such as, hydrophobicity, electroluminescence,
crystallization kinetics, hydrothermal, breakdown voltage etc.

2
1.2 BREAKDOWN OF SOLID INSULATING MATERIALS

Fothergill [1] has very clearly differentiated between the breakdown and degradation of a solid
non conducting material. According to him, the breakdown is an event that is sudden and
catastrophic and the insulation cannot withstand the service voltage following the breakdown.
The degradation, on the other hand takes place over a period. It increases the probability of
breakdown and decreases the breakdown voltage. Erosion and pit formation are vital in the
degradation process and are followed by tree formation and/or final dielectric failure. The
degradation process after a period of hours to weeks, leads to breakdown. Well-designed
insulation system operated within the scope of various design parameters, should not breakdown
or degrade. Both these processes are irreversible. Table 1.1 shows some differences between
degradation and breakdown for a solid insulating material.

TABLE 1.1 DIFFERENCES BETWEEN DEGRADATION AND BREAKDOWN FOR A SOLID

INSULATING MATERIAL

Features Breakdown Degradation

Effect Catastrophic insulation cannot be used Leads to breakdown, reduces

afterwards breakdown voltage

Speed Fast occurs in << 1s Hours, years

Evidence Direct observation normally by eye Observation would require

microscope

Examples Intrinsic, Thermal, Electromechanical, Electrical Trees, Water trees

Electrochemical, Partial Discharge in
cavities

3
 FIG.1.1 VARIATION OF BREAKDOWN STRENGTH AFTER THE APPLICATION OF
VOLTAGE

The breakdown of solid dielectrics is an event that is sudden and catastrophic. Breakdown occurs
in a time duration which is very much less than a second [2]. Basically, breakdown of solid
insulating materials occur due to intrinsic, electromechanical [3], multi-stress aging [4] or failure
due to treeing and tracking, relative humidity [5], thermal, electrochemical, partial discharges
(PD) in the cavities [6].

1.2.1 INTRINSIC BREAKDOWN

When voltages are applied only for short durations of the order of 108 s the dielectric strength of
a solid dielectric increases very rapidly to an upper limit called the intrinsic electric strength. By
experimentally, this highest dielectric strength can be obtained only under the best experimental
conditions when all extraneous influences have been isolated and the value depends only on the
temperature and structure of the material. It is recorded that 15 MV/cm for polyvinyl-alcohol at
1960 C is the maximum electrical strength. The obtainable range of maximum strength is from
5MV/cm to 10MV/cm.

The presence of free electrons plays the vital role in intrinsic breakdown which are capable of
migration through the lattice of the dielectric. Mostly, a few number of conduction elections are

4
present in solid dielectrics, with some structural imperfection and small amount of impurities.
The molecules or impurity atoms or both act as traps for the conduction electrons up to certain
ranges of electric fields and temperatures. Exceeding these ranges, more electrons along with
trapped electrons are instantly released, and these electrons take part in the conduction process.
Depending on this principle, two types of intrinsic breakdown mechanisms have been proposed
and they are (a) Electronic Breakdown and (b) Avalanche or Streamer Breakdown.

1.2.1.1 ELECTRONIC BREAKDOWN

As mentioned earlier, intrinsic breakdown is assumed to be electronic in nature because it occurs

in time of the order of 10-8s.The initial density of conduction (free) electrons is very large, and
electron-electron collisions take place. When electric field is applied on, electrons gain energy
from the field it cross the forbidden energy gap from the valence to the conduction band. When
this process is repeated continuously, more electrons become available in the conduction band,
finally leading to breakdown.

1.2.1.2 AVALANCHE OR STREAMER BREAKDOWN

Avalanche or Streamer Breakdown is similar to breakdown in gases due to cumulative ionization.

Free electrons gain sufficient energy above a certain electric field and cause liberation of
electrons from the lattice atoms by collisions. Under certain uniform field conditions, if in the
specimen the electrodes are embedded, breakdown will occur when an electron avalanche
bridges the electrode gap.

An electron under the dielectric, starting from cathode will drift towards the anode and during
this motion profits energy from the field and loses it at collisions. When the energy gained by an
electron exceeds the lattice ionization potential and an additional electron will be liberated due to
collision of the first electron. This process repeats itself and resulting in the formation of an
electron avalanche. When the avalanche exceeds a certain critical size then breakdown will
occur.
In practice, breakdown does not occur by the single formation of avalanche itself, but it occurs as
a result of so many avalanches formed within the dielectric and extending step by step through
the entire full thickness of the material. This can be easily demonstrated in a laboratory by

5
applying an impulse voltage between point-plane electrodes with point embedded in a transparent
solid dielectric such as perspex.

1.2.2 ELECTROMECHANICAL BREAKDOWN

When solid dielectrics are put into high electric field, failure happens due to electrostatic
compressive forces which can exceed the mechanical compressive strength. If the thickness of
the specimen is d0 and it is compressed to a thickness d under an applied voltage V, the
electrically developed compressive stress is in equilibrium if

V2 d 
 0 r  Y ln  0  (1.1)
d 
2
2d

Where Y is the Young‟s modulus.

 2Y   d0 
V 2  d2   ln   (1.2)
  0 r   d 

Mechanical instability occurs when d  0.6 .

d0

Substituting this in Eq 1.2, the largest apparent electric stress before breakdown,

1
V  Y  2
Emax   0.6   (1.3)
d0   0 r 
The above equation is only approximate if Y depends upon the mechanical stress. When
subjected to high stresses then the elasticity theory does not stand good and plastic deformation
has to be taken into account.

6
1.2.3 BREAKDOWN DUE TO TREEING AND TRACKING

When a solid dielectric subjected to electrical stress for long time fails, two kinds of visible
markings are observed on the materials. They are:

(a) the presence of a conducting path across the the insulation;

(b) a mechanism where leakage current passes through the conducting path leading to the
formation of spark. Insulation degradation occurs as a result of these sparks.

The spreading of spark during tracking, in the form of branches of a tree is called treeing.

Consider a system of solid dielectric having a conducting film and a couple of electrodes on its
surface. The conducting film often is formed due to moisture. Applying voltage, the film starts
conducting, as a result generating heat, and the surface starts becoming dry. The conducting
films become apart due to drying, and so sparks are drawn damaging the surface. Organic
insulating materials such as paper and Bakelite, the dielectric carbonizes at the regions of
sparking, and the carbonized regions act as conducting channels resulting in increased stress over
the rest region. This is a cumulative process, and insulation failure takes place when carbonized
tracks bridge the distance between layers of Bakelite and similar dielectrics built of laminates.
On the other hand treeing occurs due to the erosion of materials at the tips of the spark. Erosion
results in roughening of the surfaces, hence becomes a source of contamination. This causes
more conductivity resulting either in forming a conducting path bridging the electrodes or a
mechanical failure of the dielectric.

1.2.4 THERMAL BREAKDOWN

The breakdown voltage of a solid dielectric must increase with its thickness. But this is true only
up to a fixed thickness above which the heat generated in the dielectric due to the current
determines the conduction.

When electric field is applied on a dielectric, conduction current, flows through the material. The
current heats up the specimen and the temperature increases. The heat generated is transferred to
the surroundings by conduction through the dielectric and radiation from its outer surface.

7
Equilibrium is reached when the heat needed to raise the temperature of the dielectric, plus the
heat radiated out, equals the generated heat.

This of huge importance to practicing engineers, as most of insulation failures in high voltage
power apparatus occur due to thermal breakdown. Thermal breakdown sets up an upper bound
for increasing the breakdown voltage when the thickness of insulation is increased. For a given
loss angle and the applied stress, heat generated is proportional to the frequency hence thermal
breakdown is much serious at higher frequencies.

1.2.5 ELECTROCHEMICAL BREAKDOWN

When cavities are formed inside solid dielectrics, dielectric strength in solid specimen decreases.
When the gas in the cavity breaks down, the surface of the specimen provides instantaneous
anode and cathode. Some electrons dashing against the anode with enough energy shall break the
chemical bonds of the insulating surface. Same way positive ions bombarding against the cathode
increase the surface temperature and produce thermal stability. Chemical degradation may also
occur from active discharge products e.g. O3, NO2 etc. formed in air. The overall effect of all
these processes is a steady erosion of the material and a consequent reduction in the thickness of
the specimen. Generally it is desired that with ageing the dielectric strength comes down with
time of voltage application or even without voltage application and in most cases; the decrease in
dielectric strength (Eb) with time follows the following empirical relation

t Ebn = constant (1.4)

where the exponent n depends upon the dielectric material, the ambient temperature humidity
and the quality of manufacture. This is the vital reason why a.c. voltage testing is not
recommended.

1.2.6 BREAKDOWN DUE TO INTERNAL DISCHARGES

Partial discharge is a localized discharge process in which the distance between two electrodes is
partially bridged i.e., the insulation between the electrodes is partly punctured. Partial discharges
may start directly at one of the electrodes or occur in a cavity in the dielectric.The Partial

8
Discharge study has been a topic in the field of solid insulations over the past few decades, which
is very much evident from the large number of literatures associated with it [7-16]. It is well
known that voids within the solid insulating materials are the main sources of Partial Discharge c
as Artificial Neural Network (ANN), Fuzzy Logic (FL), approximate reasoning, derivative-free
optimization methods, such as, Genetic Algorithms (GA) and Simulated Annealing (SA). The
seamless integration of all these paradigms forms the core of SC, aimed at solving real-world
decision-making, modeling problems. These problems are usually imprecisely defined and
require human intervention. Thus, the SC with their ability to incorporate human knowledge and
adapt their knowledge base via optimization techniques plays an important role in the design of
intelligent systems.

1.3 MOTIVATION

The SC model is an important and a flexible model in predicting the breakdown voltage due to
PD in voids. To overcome the modern energy demand, it‟s required highly complex and reliable
power system from transmission to distribution unit, for that it‟s very much essential to develop
the better quality insulating material. One of the main reasons of degradation of insulating
material is PD within the cavities. The breakdown voltage due to PD in cavities is a nonlinear
phenomenon. The magnitude of this voltage is critical for judging the quality of the insulation for
industrial purpose. However, it is extremely difficult to predict this voltage. Hence, it is
necessary to resort to the process of modeling in order to predict the magnitude of this
breakdown as a function of different variables. The use of this model in order to tackle this PD
issue needs further exploration as the prediction of this breakdown voltage is so important
industrially.

9
1.4 OBJECTIVES

The main objective of the research predicting the breakdown voltage using Least Square Support
Vector Machine (LS-SVM) and ANN structures, namely the Multilayer Feedforward Neural
Network (MFNN).

10
1.5 THESIS OUTLINE

This thesis primarily attempts at modelling of PD initiated breakdown voltage of solid

insulations by different SC techniques. The requisite experimental breakdown voltage data under
AC conditions are generated in the laboratory with artificially created void and insulation
dimensions using Cylinder-Plane Electrode System. This thesis contains five chapters; out of
which Chapter 3 and Chapter 4 are the contributory Chapters.

Chapter 1 has reviewed the existing literatures on the breakdown voltage of the solid insulating
materials in general while giving more emphasis on the breakdown due to PD in cavities. The
advantage of using SC models over the Conventional models in solving the prediction of
breakdown due to PD in cavities have been discussed thoroughly in this Chapter.

Chapter 2 has discussed the experimental set up for the Cylinder-Plane Electrode System used
for obtaining the breakdown voltage data under AC conditions.

Chapter 3 has described a brief theory of the Multiforward Neural Network. This structure is
then used to propose three breakdown voltage models using the experimental data obtained from
the Cylinder-Plane Electrode System.

Finally, Chapter 4 summarises the main findings, draws certain conclusions arising out of the
thesis work and compares of the MAE of the test data Ets obtained from the various models of
Chapter 3 and 4 using similar data to show the effectiveness of the SC techniques used here. At
the end, it outlines the scope for the future research.

11
 CHAPTER 2

EXPERIMENTAL SET UP

12
2.1 INTRODUCTION

As mentioned in Chapter 1, the primary objective of this thesis work is to develop different soft
computing models, which will be able to predict the breakdown voltage of solid insulating
materials due to PD in cavities. For modelling purpose, breakdown voltage data are generated
experimentally on application of AC power frequency voltages. The chapter 2 covers total
experimental procedure for predicting the experimental breakdown voltage of five insulating
materials namely, White Minilex, Leatheroid Paper, Glass Cloth, Manila Paper and Lather
Minilex

2.2 EXPERIMENTAL PROCEDURE

The procedure adopted for the generation of experimental value of the breakdown voltage is as
follows:

2.2.1 SAMPLE PREPARATION

The samples are prepared from three commercially available insulation sheets, namely White
Minilex, Leatheroid Paper, Glass Cloth, Manila Paper and Lather Minilex of different
thicknesses. The variation of thicknesses is as follows:

White Minilex Paper 0.26, 0.18 and 0.125 mm

Leatheroid Paper 0.235, 0.175 and 0.13 mm
Lather Minilex 0.245, 0.185 and 0.12 mm
Glass Cloth 0.195 and 0.155 mm
Manila Paper 0.06 and 0.035 mm

Thus, the thickness range is varying from 0.035 mm to 0.26 mm. Before testing, the conditioning
procedure was adopted to the test specimen in accordance with that laid in ASTM Handbook
[27]. This ensured that the surfaces of the insulating sample were cleaned, since the

13
contamination on the insulating specimen or absorption of moisture may affect the breakdown
voltage.

2.2.2 CREATION OF VOID

The voids of different sizes are artificially created by means of a spacer made up of Kapton film,
with a circular punched hole at the centre. The diameter of the voids is 1.5 mm, 2 mm, 3 mm, 4
mm and 5 mm. The thicknesses of the Kapton spacer used are of 0.025 mm and 0.125 mm. Thus,
the sizes of the void, that is, the volume of air space, depends on a typical diameter of the
punched hole and thickness of the spacer. Utmost care has been taken to maintain the surface
smoothness of the punched holes.

2.2.3 ELECTRODE GEOMETRY

The electrode system used in this work for breakdown voltage measurements is shown in Figure
2.1. To get a high reproducibility of the tests and low data scatter, the cell sample was built
following a standard assembling methodology. It consists of a cylinder-plane electrode
configuration, including a cavity in the middle. The depth of the void was fixed by the Kapton
film as explained before. The electrodes, both high voltage and low voltage, were made of brass.
They were polished, buffed and cleaned with ethanol before the start of the experiment. Again,
the electrodes contact surfaces are cleaned by ethanol between two consecutive applications of
voltage to avoid contaminations that may arise due to application of voltage. Sufficient care had
been taken to keep the electrode surfaces untouched and free from scratches, dust and other
impurities. The insulation sample is sandwiched between the electrodes with the help of
insulating supports as shown. The main characteristic of the employed electrode system is that
discharges occur in a concentrated area and continue corroding the insulation until breakdown
takes place. The breakdown was considered as due to a real puncture of the sample

14
 FIGURE 2.1 CYLINDER-PLANE ELECTRODE SYSTEM USED FOR BREAKDOWN
VOLTAGE MEASUREMENT

2.2.4 MEASUREMENT OF AC BREAKDOWN VOLTAGE

The 50 Hz AC voltage applied to the insulating samples was obtained from a 40 kV AC/DC
Series Hipot Tester (MODEL HD 100) that is manufactured by Hipotronics, USA. The voltage is
raised with steps of 200 V held constant for period of 30s each and every level until the
breakdown occurs. The total time from application of voltage to the instant of breakdown was
observed. Five data points were obtained for a particular type of sample and void condition and
the mean value of the voltage is taken for modeling. At room temperature and atmospheric
pressure all the five tests were carried out in air. The obtained breakdown data are then corrected
for atmospheric condition before being used for modeling.

15
2.2.5 MEASUREMENT OF RELATIVE PERMITTIVITY OF SOLID
INSULATING MATERIALS

The insulating samples of 12mm diameter were silver coated at the identical zone on the both
sides to measure the relative permittivity. The silver coated samples were then pressed between
the two brass sample holder electrodes of the dielectric interface of an impedance gain/phase
analyser (Solartron, UK). The samples from the impedance gain/phase analyzer are applied from
an AC voltage of 0.1 V (rms) at 50 Hz and relative permittivity values of the insulating materials
are recorded. Table 2.1 shows the measured values of the relative permittivity of materials at 50
Hz frequency.

TABLE 2.1 RELATIVE PERMITTIVITY AGAINST MATERIALS

Insulating Materials r

White Minilex 4.4

Leatheroid paper 4.21

Glass Cloth 4.97

Manila Paper 4.68

Lather Minilex 5.74

From Table 2.2 to Table 2.6 are the data of White Minilex, Leatheroid Paper, Glass Cloth,
Manila Paper and Lather Minilex of experimental breakdown voltage in kV with their thickness
t, depth of void t1, diameter of void d, and relative permittivity  r .

16
 TABLE 2.2: EXPERIMENTAL BREAKDOWN VOLTAGES FOR WHITE MINILEX
INSULATING SAMPLES UNDER AC TEST CONDITION

Serial no. Insulating Thickness Void Void Relative Breakdown

Material of Depth, t1 Diameter, Permittivity, Voltage, kV
Insulator, t in mm d in mm r
(experimental)
in mm
1 White 0.26 0.025 1.5 4.4 2.2000
2 Minilex 0.26 0.025 2 4.4 2.2000
3 0.26 0.025 3 4.4 2.2000
4 0.26 0.025 4 4.4 2.2000
5 0.26 0.025 5 4.4 2.2000
6 0.26 0.125 1.5 4.4 2.2000
7 0.26 0.125 2 4.4 2.2000
8 0.26 0.125 3 4.4 2.2000
9 0.26 0.125 4 4.4 2.2000
10 0.26 0.125 5 4.4 2.2000

11 0.125 0.025 1.5 4.4 2.3000

12 0.125 0.025 2 4.4 2.3000
13 0.125 0.025 3 4.4 2.3000
14 0.125 0.025 4 4.4 2.3000

15 0.125 0.025 5 4.4 2.3000

16 0.125 0.125 1.5 4.4 2.3000
17 0.125 0.125 2 4.4 2.3000
18 0.125 0.125 3 4.4 2.3000
19 0.125 0.125 4 4.4 2.3000
20 0.125 0.125 5 4.4 2.3000
21 0.18 0.025 1.5 4.4 2.2000
22 0.18 0.025 2 4.4 2.2000
23 0.18 0.025 3 4.4 2.2000
24 0.18 0.025 4 4.4 2.2000
25 0.18 0.025 5 4.4 2.2000
26 0.18 0.125 1.5 4.4 2.2000
27 0.18 0.125 2 4.4 2.2000
28 0.18 0.125 3 4.4 2.2000
29 0.18 0.125 4 4.4 2.2000
30 0.18 0.125 5 4.4 2.2000

17
 TABLE 2.3: EXPERIMENTAL BREAKDOWN VOLTAGES FOR LEATHEROID PAPER
INSULATING SAMPLES UNDER AC TEST CONDITION

Serial no. Insulating Thickness Void Void Relative Breakdown

Material of Depth, t1 Diameter, Permittivity, Voltage, kV
Insulator, t in mm d in mm r
(experimental)
in mm
31 Leatheroid 0.13 0.025 1.5 4.21 1.2000
Paper
32 0.13 0.025 2 4.21 1.2000
33 0.13 0.025 3 4.21 1.2000
34 0.13 0.025 4 4.21 1.2000
35 0.13 0.025 5 4.21 1.2000
36 0.13 0.125 1.5 4.21 1.2000
37 0.13 0.125 2 4.21 1.2000
38 0.13 0.125 3 4.21 1.2000
39 0.13 0.125 4 4.21 1.2000
40 0.13 0.125 5 4.21 1.2000
41 0.175 0.025 1.5 4.21 1.8000
42 0.175 0.025 2 4.21 1.8000
43 0.175 0.025 3 4.21 1.8000
44 0.175 0.025 4 4.21 1.8000
45 0.175 0.025 5 4.21 1.8000
46 0.175 0.125 1.5 4.21 1.8000
47 0.175 0.125 2 4.21 1.8000
48 0.175 0.125 3 4.21 1.8000
49 0.175 0.125 4 4.21 1.8000
50 0.175 0.125 5 4.21 1.8000
51 0.235 0.025 1.5 4.21 2.2000
52 0.235 0.025 2 4.21 2.2000
53 0.235 0.025 3 4.21 2.2000
54 0.235 0.025 4 4.21 2.2000
55 0.235 0.025 5 4.21 2.2000
56 0.235 0.125 1.5 4.21 2.2000
57 0.235 0.125 2 4.21 2.2000
58 0.235 0.125 3 4.21 2.2000
59 0.235 0.125 4 4.21 2.2000
60 0.235 0.125 5 4.21 2.2000

18
TABLE 2.4: EXPERIMENTAL BREAKDOWN VOLTAGES FOR GLASS CLOTH INSULATING
SAMPLES UNDER AC TEST CONDITION

Serial no. Insulating Thickness Void Void Relative Breakdown

Material of Depth, t1 Diameter, Permittivity, Voltage, kV
Insulator, t in mm d in mm r
(experimental)
in mm
61 Glass Cloth 0.195 0.025 1.5 4.97 2.2000

62 0.195 0.025 2 4.97 2.2000

63 0.195 0.025 3 4.97 2.2000

64 0.195 0.025 4 4.97 2.2000

65 0.195 0.025 5 4.97 2.2000

66 0.195 0.125 1.5 4.97 2.2000

67 0.195 0.125 2 4.97 2.2000

68 0.195 0.125 3 4.97 2.2000

69 0.195 0.125 4 4.97 2.2000

70 0.195 0.125 5 4.97 2.2000

71 0.155 0.025 1.5 4.97 2.3000

72 0.155 0.025 2 4.97 2.3000

73 0.155 0.025 3 4.97 2.3000

74 0.155 0.025 4 4.97 2.3000

75 0.155 0.025 5 4.97 2.3000

76 0.155 0.125 1.5 4.97 2.3000

77 0.155 0.125 2 4.97 2.3000

78 0.155 0.125 3 4.97 2.3000

79 0.155 0.125 4 4.97 2.3000

80 0.155 0.125 5 4.97 2.3000

19
TABLE 2.5: EXPERIMENTAL BREAKDOWN VOLTAGES FOR MANILA PAPER INSULATING
SAMPLES UNDER AC TEST CONDITION

Serial no. Insulating Thickness Void Void Relative Breakdown

Material of Depth, t1 Diameter, Permittivity, Voltage, kV
Insulator, t in mm d in mm r
(experimental)
in mm
81 Manila 0.035 0.025 1.5 4.68 0.8000
Paper
82 0.035 0.025 2 4.68 0.8000

83 0.035 0.025 3 4.68 0.8000

84 0.035 0.025 4 4.68 0.8000

85 0.035 0.025 5 4.68 0.8000

86 0.035 0.125 1.5 4.68 0.8000

87 0.035 0.125 2 4.68 0.8000

88 0.035 0.125 3 4.68 0.8000

89 0.035 0.125 4 4.68 0.8000

90 0.035 0.125 5 4.68 0.8000

91 0.06 0.025 1.5 4.68 0.9000

92 0.06 0.025 2 4.68 0.9000

93 0.06 0.025 3 4.68 0.9000

94 0.06 0.025 4 4.68 0.9000

95 0.06 0.025 5 4.68 0.9000

96 0.06 0.125 1.5 4.68 0.9000

97 0.06 0.125 2 4.68 0.9000

98 0.06 0.125 3 4.68 0.9000

99 0.06 0.125 4 4.68 0.9000

100 0.06 0.125 5 4.68 0.9000

20
 TABLE 2.6: EXPERIMENTAL BREAKDOWN VOLTAGES FOR LATHER MINILEX
INSULATING SAMPLES UNDER AC TEST CONDITION

Serial no. Insulating Thickness Void Void Relative Breakdown

Material of Depth, t1 Diameter, Permittivity, Voltage, kV
Insulator, t in mm d in mm r
(experimental)
in mm
101 Lather 0.245 0.025 1.5 5.74 2.4000
Minilex
102 0.245 0.025 2 5.74 2.4000
103 0.245 0.025 3 5.74 2.4000
104 0.245 0.025 4 5.74 2.4000
105 0.245 0.025 5 5.74 2.4000
106 0.245 0.125 1.5 5.74 2.4000
107 0.245 0.125 2 5.74 2.4000
108 0.245 0.125 3 5.74 2.4000
109 0.245 0.125 4 5.74 2.4000
110 0.245 0.125 5 5.74 2.4000
111 0.185 0.025 1.5 5.74 2.2000
112 0.185 0.025 2 5.74 2.2000
113 0.185 0.025 3 5.74 2.2000

114 0.185 0.025 4 5.74 2.2000

115 0.185 0.025 5 5.74 2.2000

116 0.185 0.125 1.5 5.74 2.2000
117 0.185 0.125 2 5.74 2.2000

118 0.185 0.125 3 5.74 2.2000

119 0.185 0.125 4 5.74 2.2000
120 0.185 0.125 5 5.74 2.2000
121 0.125 0.025 1.5 5.74 2.4000
122 0.125 0.025 2 5.74 2.4000
123 0.125 0.025 3 5.74 2.4000
124 0.125 0.025 4 5.74 2.4000
125 0.125 0.025 5 5.74 2.4000
126 0.125 0.125 1.5 5.74 2.4000
127 0.125 0.125 2 5.74 2.4000

128 0.125 0.125 3 5.74 2.4000

129 0.125 0.125 4 5.74 2.4000
130 0.125 0.125 5 5.74 2.4000

21
2.3 SUMMARY

This Chapter has provided the groundwork for prediction of the breakdown voltage of five
insulating materials namely White Minilex, Leatheroid Paper, Glass Cloth, Manila Paper and
Lather Minilex due to PD in cavities by carrying out experimental data generation with the help
of cylinder-plane electrode system.

22
 CHAPTER 3

MULTILAYER FEEDFORWARD

NEURAL NETWORK

23
3.1 INTRODUCTION

Artificial Neural Networks (ANNs) have become the subject of widespread interest, largely
because of their wide range of applicability and the ease with which they handle complex and
non-linear problems. They are massively parallel-interconnected networks of simple elements
intended to interact with the real world in the same way as the biological nervous system. They
offer an unusual scheme based programming standpoint and exhibit higher computing speeds
compared to other conventional methods [28]. ANNs are characterized by their topology, that is,
the number of interconnections, the node characteristics that are classified by the type of
nonlinear elements used and the kind of learning rules employed. The ANN is composed of an
organized topology of Processing Elements (PEs) called neurons. In Multilayer Feedforward
Neural Network (MFNN) the PEs are arranged in layers and only PEs in adjacent layers are
connected.

3.2 THEORY OF MFNN

The MFNN used here consists of three layers namely input layer, hidden layer and output layer
as represented in figure no 3.1. The Input layer of MFNN consists of different number of inputs
variables according to the modeling of MFNN. The input variables are thickness of the material,
void diameter, void depth and permittivity of the insulating material. The number of output
neuron is decided by the number of estimated parameters; therefore in this model only one output
neuron is taken corresponding to breakdown voltage Vb.
The Back Propagation Algorithm (BPA) is used to train the network. The sigmoid function
represented by equation (3.1) is used as the activation function for all the neurons except for
those in the input layer.

S(x) = 1 / (1+e-x) (3.1)

24
 Input 1

wb(j, k)

Input 2

Output

Input Ni

wa(i, j)

Input Layer Hidden Layer Output Layer

FIG.3.1 MULTILAYER FEEDFORWARD NEURAL NETWORK

3.2.1 CHOICE OF HIDDEN NEURONS

The optimal choice of number of hidden neurons, Nh is one of the most interesting and
demanding aspect in designing MFNN. There are lots of schools on thought in determining the
value of Nh. Simon Haykin [29] has mentioned that Nh should lie between 2 and ∞. Hecht-
Nielsen [30] makes use of ANN interpretation of Kolmogorov‟s theorem to reach at the upper
bound on Nh for a mono hidden layer network as 2(Ni+1), where Ni is the number of input
neurons. But, this value should be decided very intelligently depending on the requirement of
problem. Large value of Nh reduces the training error associated with MFNN, but at the expense
of increasing computational complexity and time. For instance, if one gets a tolerably small value
of training error with certain specific value of Nh, there is no gain in further increasing the value
to enhance the performance of MFNN. The input and the output data are standardized before
processing in the network as follows:

In this way of normalization, the maximum values of input and output vector components:

25
ni ,max  max  ni  p   p=1 …Np,i= 1,…….Ni (3.2)

Where Np is the number of patterns in the training set and Ni is the number of neurons in the input
layer. Again,
Ok ,max  max  ok  p   p =1,........Np,k=1,.....Nk (3.3)

Where, Nkis the number of neurons in the output layer.

Normalized by these maximum values, the input and output variables are given asfollows.
ni  p 
ni ,nor  p   ,p = 1,…….Np, i = 1,……Ni (3.4)
ni ,max

and

ok  p 
ok ,nor  p   ,p = 1,…….N (3.5)
ok ,max

After normalization, the input and output variable lay [31] in the range of 0to 1.

3.2.2 CHOICE OF ANN PARAMETERS

The learning rate, η and the momentum factor, α have a very important effect on the learning rate
of the BPA. BPA provides an approximation to the path in the weight space computed using the
method of steepest descent [29]. If the value of ηis very small, this results in very slow rate of
learning, whereas if the value of η is too huge in order to accelerate the rate of learning, the
MFNN may become unstable (oscillatory). A simple method of improving the rate of learning
without making MFNN unstable is by addition of the momentum factor α [32]. The values of η
and α should lie between 0 and 1 [29].

The weights between the hidden layer and the output layer are updated based upon the equation

26
3.2.3 WEIGHT UPDATE EQUATIONS
as follows:
wb  j, k , m  1  wb  j, k , m   1   k  m   Sb  j      wb  j , k , m   wb  j , k , m  1  (3.6)

p, i = 1,……Nk

Where m is the number of iterations, j varies from 1 to Nh and k varies from 1 to Nk. δk(m) is the
error for the kth output at the mth iteration. Sb(j) is the output from the hidden layer.
Similarly, the weights between the hidden layer and the input layer are updated as follows:

wa  i, j, m  1  wa  i, j, m   1   j  m   Sa  i      wa i, j , m   wa i, j , m  1  (3.7)

Where i varies from 1 to Ni as there are Ni inputs to the network, δj(m) is the error for the jth
output after the mth iteration and Sa(i) is the output from the first layer. The δk(m) in equation
(3.6) and δj(m) in equation ( 3.7) are related as
K
 j  m     k  m   wb  j, k , m  (3.8)
k 1

3.2.4 EVALUATION CRITERIA

The Mean Square Error Etr for the training patterns after the mth iteration is defined as:
 P 2  1 
Etr    Vb1 p  Vb 2 p  m       (3.9)
 p 1  P
Where V1p is the experimental value of breakdown voltage, P is the number of training patterns
and V2p (m) is the estimated value of the breakdown voltage after mth iteration. The training is
stopped when the least value of Etr has been obtained and this value does not change much with
the number of iterations.

3.2.5 MEAN ABSOLUTE ERROR

The Mean Absolute Error Ets is a good performance measure for judging the accuracy of the
MFNN System. The Etr tells how well the network has adopted to fit the training data only, even
if the data are contaminated. On the other hand, the Ets indicates how well a trained network
behaves on a new data set not included in the training set. The value of E ts is calculated based on
the least value of Etr. The Ets for the test data expressed in percentage is given by

27
  S     V 
S
Ets  1 b4s  Vb3s  / Vb3s  100 (3.10)
s 1 
Where V3s is the experimental value of the breakdown voltage taken for testing purpose, V4s is
the estimated value of the breakdown voltage after the testing input data is passed through the
trained network and S is the number of testing patterns.

3.3 RESULTS AND DISCUSSION

The equations of MFNN model have been used to predict the breakdown voltage of White
Minilex, Leatheroid paper, Glass cloth, Lather minilex and Manila paper under AC condition in
the presence of voids. Figure 3.2 has been derived from Figure 3.1 by substituting Ni=4. The
inputs are the thickness of the insulating material, void depth, void diameter and relative
permittivity of the insulating materials while the output is the breakdown voltage.

r

FIG.3.2 MFNN STRUCTURE

With the help of 130 sets of experimental input-output patterns, the proposed modeling are
carried out; 115 sets of five insulating materials (27 sets of White Minilex, 27 sets of Leatheroid
Paper, 17 sets of Glass Cloth, 17 sets of Manila Paper and 27 sets of Lather Minilex) are chosen
input-output patterns used for training both networks and for testing purpose the remaining 15

28
sets of the five materials are used. The software programs developed are used for implementation
using MATLAB version 9.1.

From Tables 3.1 to 3.3 and Fig. 3.2, it is quite obvious that when Nh = 10,  = 0.8 and 1 = 0.99,

the MSE for training data is the lowest at 2.3905 107 . The sequential mode of training has
been adopted. It may be noted that the range of the values of 1 and  should be between 0 and
1and value of Nh should not more than 10 as per the Hecht-Nielsen criteria. Hence we have
stopped at Nh = 10 in Table 3.1 and in Table 3.2 we have stopped at 1 = 0.99.

TABLE 3.1 VARIATION OF Etr WITH Nh ( 1 = 0.1,  = 0.6, ITERATION = 400)

Nh Etr

2 0.0018

3 0.0012

4 3.7045  10-4

5 2.7368  10-4

6 2.7116  10-4

7 1.4882  10-4

8 1.4074  10-4

9 1.2278  10-4

10 1.1770  10-4

29
 TABLE 3.2 VARIATION OF Etr WITH 1 (ITERATION = 400,  = 0.6, Nh=10)

1 Etr

0.1 1.1770 104

0.2 2.0896 105

0.5 2.8671 106

0.6 2.2232 106

0.7 1.8396 106

0.8 1.5777 106

0.9 1.3834 106

0.99 1.2454 106

TABLE 3.3 VARIATION OF Etr WITH  (1 = 0.99, Nh = 10, ITERATION = 400)

 Etr

6
0.6 1.2456 10

6
0.65 1.0191 10

7
0.7 7.9460 10

7
0.75 5.5291 10

30
 7
0.8 2.3905 10

0.85 0.0012

-3
x 10
2.5

2
Etr FOR TRAINING DATA

1.5

0.5

0
0 50 100 150 200 250 300 350 400
NUMBER OF ITERATIONS (25 TO 400)

FIGURE 3.3 VARIATION OF Etr WITH NUMBER OF ITERATIONS (1 = 0.99,  =0.8, NH=10)

Finally, the function Vb  f  t , t1 , d ,  r  for the test data are calculated by simply passing the input

data in the forward path of the network and using the updated weights of the network. Table 3.4
shows a comparison of the experimental and modeled data test data using MFNN model after
400 iterations.

From Table 3.4 it may be seen that the measured values and the modeled values are almost same
and Ets is found to be 0.0774%, thus shows the effectiveness of the proposed breakdown voltage
modeling.

31
 TABLE 3.4 COMPARISON OF THE EXPERIMENTAL AND MODELLED DATA USING
MFNN MODEL

Insulating t, mm t1, d, €r Breakdown Breakdown Ets, %

material mm mm voltage, kV voltage, kV
(experimental) (modelled)

White 0.26 0.025 3 4.4 2.2 2.2000 0.0774

Minilex
0.125 00125 2 4.4 2.3 2.3000

0.18 0.025 1.5 4.4 2.2 2.2000

Leatheroid 0.13 0.125 5 4.21 1.2 1.2000

Paper
0.175 0.125 4 4.21 1.8 1.8000

0.235 0.025 2 4.21 2.2 2.2000

Glass Cloth 0.195 0.025 5 4.97 2.2 2.2000

0.155 0.025 3 4.97 2.2 2.2000

0.155 0.125 1.5 4.97 2.3 2.3000

Manila 0.035 0.125 3 4.68 0.8 0.8000

Paper
0.06 0.025 2 4.68 0.9 0.9000

0.06 0.125 4 4.68 0.8 0.8000

Lather 0.245 0.025 5 5.74 2.2 2.2000

Minilex
0.185 0.125 1.5 5.74 2.4 2.3861

0.125 0.025 2 5.74 2.4 2.3861

32
 CHAPTER 4

CONCLUSION AND FUTURE WORK

33
4.1 INTRODUCTION

This thesis work deals with the modeling using ANN. Detailed discussions have been
presented in Chapter 3 and conclusions have been made at the end of each chapter. Therefore,
this concluding chapter is devoted to the summarization of the main contributions of the work
and arriving at general conclusions.

4.2 SUMMARY

The major studies reported in this thesis pertain to:

1. The experimental procedure adopted in the laboratory in order to generate breakdown voltage
data under AC conditions has described in Chapter 2. The experimental data are obtained
with artificially created voids of various dimensions and with different insulation thicknesses
of five common insulating materials, namely, White Minilex Paper, Leatherite Paper, Glass
Cloth, Lather Minilex and Manila Paper using Cylinder-Plane Electrode System.

2. In Chapter 3, MFNN model is proposed for the prediction of the breakdown voltage of solid
insulating materials due to PD in cavities as a function of four input parameters. The Mean
Square Error Etr for the training patterns and the Mean Absolute Error Ets for the testing
patterns has been calculated.

4.3 CONCLUSIONS

Before the thesis draws to a close, the general conclusions that emerge out from this work
are highlighted. These conclusions are mainly arrived at based on the performance and the
capabilities of the soft computing techniques presented here for breakdown voltage modeling.
Based on such a critical appraisal, the current state of technology, its promises and pitfalls are
charted. This finally leads to an outline of the future directions for research and development
efforts in this subject area.

The main conclusions drawn are:

34
 1. The combination of parameters for the best results in each of the models has been
identified. A comparison of modeled and experimental results indicates that Soft
Computing techniques can be very well employed for estimation of breakdown voltage as
a function of insulation and void dimensions.

2. Tables 4.1 depict the the MSE for the training data Etr obtained from the ANN model.
TABLE 4.1 Etr OF ANN MODEL

Model Etr

MFNN 1.2454 × 10-6

Thus, this work is successful in applying ANN for prediction of breakdown voltages under AC
conditions as a function of insulation and void parameters.

As a future work a more generalization of the models to be developed, it would be interesting to

include more parameters responsible for breakdown of insulating materials.

35
 REFERENCES
[1] J. C. Fothergill, “Ageing, Space Charge and Nanodielectrics: Ten things we don‟t know
about dielectrics”, IEEE 9th International Conference on Solid Dielectrics,
U.K.,Winchester, July 2007, pp. 1-10.

[2] C.L.Wadhwa, High Voltage Engineering, 2nd edition, Wiley Eastern Limited, 1994, pp.32-
41.

[3] Jones J.P., Llewellyn J.P., Lewis T.J.: “The contribution of field-induced morphological
change to electrical aging and breakdown of polyethylene”, IEEE Transaction. Dielectric
and Electrical Insulation 2005, 12, (5), pp. 951-956

[4] Fabiani D., Simoni L.: “Discussion on application of Weibull distribution to electrical
breakdown of insulating materials”, IEEE Transaction. Dielectric and Electrical Insulation
2005, 12, (1), pp. 11-16
[5] Basappa P., Jang S., Kim J.: “Electrical breakdown studies on electro-active paper”, IEEE
Transaction. Dielectric and Electrical Insulation., 2007,14, (5), pp. 1125-1132
[6] Garton C.G., Day A.G., Church H,F, : “Intrinsic related forms of breakdown in solids” , in
Alston L.L. (ED.): “High voltage technology” (Oxford University Press, 1993, 3rd edition.),
pp. 144-183
[7] C.A. Bailey, “A study of internal discharges in cable insulation”, IEEE Transactions on
Electrical Insulation, Vol. EI-2, No. 3, 1967, pp.155-159.
[8] F. J. Pohnan, “Voids and wax in solid high-voltage cables”, AIEE Transactions on
Electrical Insulation, Vol. 70, Issue 2, 1951, pp. 1372-1376.
[9] C. Laurent, C. Mayoux and A. Sergent, “Electrical breakdown due to discharges in
different types of insulation”, IEEE Transactions on Electrical Insulation, Vol. EI-16, No.
1, 1981, pp.52-58.
[10] A.W.W. Cameron, “Diagnoses of ac generator insulation condition by nondestructive
tests”, Power Apparatus and Systems, Part III, Transactions of A.I.E.E., Vol. 71, 1952, pp.
263-274.
[11] G.L. Atkinson and W.R. Thomas, “An Epoxy-paper insulation system for high-voltage
applications”, IEEE Transactions on Electrical Insulation, Vol. EI-2, No. 1, 1967, pp. 18-
24.
[12] D.A. Nattrass, “Partial discharge XVIII: The early history of partial discharge research”,
IEEE Electrical Insulation Magazine, Vol. 9, No. 4, 1993,pp. 27-31.

36
[13] F.H. Kreuger, M.G. Wezelenburg, A.G. Wiemer and W.A. Sonneveld, “Partial discharge
part XVIII: errors in the location of partial discharges in high voltage cables”, IEEE
Electrical Insulation Magazine, Vol. 9, No. 6, 1993, pp. 15-25.
[14] T. Tanaka, Y. Ohki, M. Ochi , M. Harada and T. Imai, “Enhanced partial discharge
resistance of Epoxy/ Clay nano composite prepared by newly developed organic
modification and solubilization methods” ,IEEE Transactions on Dielectrics and Electrical
Insulation ,Vol. 15, No. 1, 2008, pp. 81-89.
[15] Y. Kikuchi, T. Murata, Y.Uozumi, N. Fukumoto, M. Nagata, “Effects of ambient humidity
and temperature on partial discharge characteristics of conventional and nano composite
enameled magnet wires” ,IEEE Transactions on Dielectrics and Electrical Insulation , Vol.
15, No. 6, 2008, pp. 1617-1625.
[16] P. H.F. Morshuis , “Degradation of solid dielectrics due to internal partial discharge: some
thoughts on progress made and where to go now”, IEEE Transactions on Dielectrics and
Electrical Insulation , Vol.12, No. 5, 2005, pp. 905-913.
[17] S. A. Boggs, “Partial discharge- Part III: Cavity-induced PD in solid dielectrics”, IEEE
Electrical Insulation Magazine, Vol. 6, No. 6, 1990, pp. 11-18.
[18] J.C. Devins, “The physics of partial discharges in solid dielectrics”, IEEE Transactions on
Electrical Insulation, Vol. EI-19, 1984, pp.475-495.
[19] J. H. Mason, “Effect of thickness and area on the electric strength of polymers”, IEEE
Transactions on Electrical Insulation, Vol. 26, No. 2, April 1991, pp. 318-322
[20] S. Ghosh and N. K. Kishore, “Breakdown voltage behaviour of Leatheroid paper with or
without a void,” Proceedings of IEEE Conference, ICET, India, Mumbai, 2006, pp. 2990-
2992.
[21] P. Bjellheim and B. Helgee, “AC breakdown strength of aromatic polymers under partial
discharge reducing conditions”, IEEE Transactions on Dielectrics and Electrical Insulation,
Vol. 1, No.1, Feb. 1994,pp. 89-96.
[22] N.P. Kolev and N. M. Chalashkanov, “Modeling of partial discharge inception and
extinction voltages using adaptive neuro-fuzzy inference system (ANFIS)”, IEEE 9th
International Conference on Solid Dielectrics, U.K. Winchester, July 2007, pp. 605-608.
[23] S. Ghosh, “ Study of some aspects of artificial neural network modeling of partial
discharge phenomenon”, Ph. D. Dissertation, IIT, Kharagpur, 1999.
[24] [24] GHOSH S., MOHANTY S.: „Modeling of breakdown voltage behavior of Leatheroid
Paper in the presence of voids using artificial neural networks‟. Proc. IEEE Ninth Int. Conf
on Solid Dielectrics, Winchester, UK, July 2007, pp. 94–97.
37
[25] S. Ghosh and N.K. Kishore, “Modeling of partial discharge inception and extinction
voltages of sheet samples of solid insulating materials using an artificial neural network”,
IEE Proc- Sci. Meas. Technol, Vol. 149, No. 2 , 2002, pp. 73-78 .
[26] J.S.R. Jang, C.T. Sun and E. Mizutani, “Neuro-Fuzzy and soft computing: A
computational approach to learning and machine intelligence”, (Prentice Hall International,
Inc., (2nd Edition 1997), pp. 24-79.
[27] ASTM Designation: D202-97: „Standard test methods for sampling and testing untreated
paper used for electrical insulation‟, 2002.
[28] S. Mohanty, S. Ghosh: “Artificial neural networks modeling of breakdown voltage of solid
insulating materials in the presence of void”, Institution of Engineering and Technology
Science. Measurement and Technology, 2010, Vol. 4, Iss. 5, pp 278-288.
[29] Simon Haykin.: „Neural networks a comprehensive foundation‟ (Prentice Hall
International Inc, New Jersey, USA, 1999), pp. 161–175, 270–300
[30] Hecht-Nielsen R.: (Addison-Wesley Publishing Company, Inc, 1990).
[31] S.Ghosh and N. K Kishore, “Modeling PD inception voltage of Epoxy Resin post
insulators using an adaptive neural network”, IEEE Transaction. Dielectrics and Electrical
Insulation, Vol. 6, No. 1, 1999, pp. 131-134.
[32] Rumelhart D.E., Mcclelland J.L. (EDS.): „Parallel distributed processing: explorations in
the microstructure of cognition‟ (MIT Press, 1986, vol. 1).
[33] V.Vapnik, The Nature of Statistical Learning Theory, Springer, New York, 1995.
[34] V.Vapnik, Statistical Learning Theory, Wiley, New York, 1998.
[35] J.A.K Suykens, T Van Gestel, J De Brabanter, B De Moor, J Vandewalle, Least Square
SVM. Singapore: World Scientific, 2002
[36] D Hanbay,. “An expert system based on least square support vector machines for diagnosis
of the valvular heart disease”, Expert Systems with Application, 36(4), part-1, 8368-
8374.2009
[37] Z Sahli,, A.Mekhaldi, R.Boudissa, S.Boudrahem, “Prediction parameters of dimensioning
of insulators under non-uniform contaminated condition by multiple regression analysis”,
Electric Power System Research, Elsevier 2011 (in press.)
[38] B.Zegnini, A.H. Mahdjoubi and M.Belkheiri ,“ A Least Squares Support Vector Machines
(LS-SVM) Approach for Predicting Critical Flashover Voltage of Polluted Insulators,”
2011 IEEE Conference on Electrical Insulation and Dielectric Phenomena,
Mexico,pp.403-406, 16-19 0ct 2011.

38