The transformer is the most important equipment in the transmission and distribution system. This expert system is the principle of condition based maintenance strategy. The system consider discrete diagnostical results. For the comparison we need to consider some other parameters what do not indicate the status of the insulation but it has influence for that. In the research work, the expert system tested by real data from the Hungarian distribution system. The source of the testing data is 13 HV/MV distribution transformers in Hungary

1. Technical Seminar On
Transformer Diagnostic By
An Expert System
PRESENTATION BY :
GURURAJ B
RAWOOR

2. OVERVIEW OF SEMINAR
Objectives
Introduction
Expert System
TSI - Transformer Status Indicator
1.Environmental Parameters
2.Operational Parameters
Computation Method
1.Linear Evaluation
2.Non-linear Evaluation
3.TSI Code And TSI Factor
Test Data
Program And Results Of The Program
Conclusion
Bibliography

3. OBJECTIVES
• The transformer is the most important equipment in the
transmission and distribution system.
• This expert system is the principle of condition based maintenance
strategy. The system consider discrete diagnostical results.
• For the comparison we need to consider some other parameters
what do not indicate the status of the insulation but it has influence
for that.
• In the research work, the expert system tested by real data from the
Hungarian distribution system. The source of the testing data is 13
HV/MV distribution transformers in Hungary.

4. • The average age of the transformers is 25-30 years, more than the
planned lifetime.
• It is not necessary to change these equipment's only because of
their age.
• The Operators have to know and manage more information about
the insulation, because this is determined the expectation time.
• There is a lot of parameter what affect the status of the insulation
(loading, oil parameters etc).
• The Transformer Status Indicator (TSI) expert system considers
the essential parameters (environmental influences, operating
values and diagnostic results) to gives the status of the insulation.
INTRODUCTION

5. • The TSI is a computer aided expert system.
• The expert system provides a technical and economic evaluation
and comparison by means of only two numbers, the TSI factor
and its reliability.
• These introduces the advantages of Transformer Status Indicator
(TSI) expert system and present the results for 13 HV/MV
transformers.
CONTD…

6. • An expert system is
computer software that attempts
to act like a human expert on a
particular subject area.
• Expert systems are often used
to advise non-experts in
situations where a human expert
in unavailable (for example it
may be too expensive to employ
a human expert, or it might be a
difficult to reach location).
What is an Expert System?

7. How Do Expert Systems Work?
An expert system is made up of three parts:
A user interface - This is the system that allows a non-expert
user to query (question) the expert system, and to receive advice.
The user-interface is designed to be a simple to use as possible.
A knowledge base - This is a collection of facts and rules. The
knowledge base is created from information provided by human
experts.
An inference engine - This acts rather like a search engine,
examining the knowledge base for information that matches the
user's query.

9. Where Are Expert Systems Used?
• Medical diagnosis.
• Playing strategy games like chess against a computer.
• Providing financial advice whether to invest in a business, etc.
• Helping to identify items such as plants / animals / rocks / etc.
• Helping to discover locations to drill for water / oil.

10. Can Expert Systems Make Mistakes?
Expert systems have some problems
• Can't easily adapt to new circumstances
(e.g. if they are presented with totally
unexpected data, they are unable to process
it).
• Can be difficult to use (if the non-expert
user makes mistakes when using the
system, the resulting advice could be very
wrong).
• They have no 'common sense' (a human
user tends to notice obvious errors, whereas
a computer wouldn't).

11. TSI-TRANSFORMER STATUS INDICATOR

12. • To make a computer aided evaluating for the transformers an
expert system was developed at the High Voltage Laboratory
of the Budapest University of Technology and Economics.
• The goal was to mark the status of a transformer only one
number for the technical and economical comparison.
• The name of this expert system is Transformer Status Indicator
(TSI), the result number is the TSI factor and its reliability.
• In the evaluation the expert system is considering the
electrical-, mechanical- and chemical parameters in two
groups; operational and environmental parameters.
CONTD…

13. A. Environmental parameters:
- Exterior and auxiliary equipment’s quality
- Age
- Maintenance history
- Geographical data
- Location in the grid
B. Operational parameters:
- Dissolved Gas Analyzing (DGA)
- Oil test
- Recovery Voltage Measurement (RVM)
- Operational history (loading)
- Insulation resistance
- Furan content
- Thermograph (infrared camera)

15. COMPUTATION METHOD
Linear evaluating system
• The considered parameters (physical effects) have one or
more physical values (PV). The PVs are the measurable
values, for example the breakdown voltage of the oil.
• A weight factor (Wi) assigned for each PV because the PVs
causes variant degradation in the insulation.
• Because of the variant scale of the PVs we need to use a
Classification Value (Si) in the computing method.
• The value of the Si is between 0-1 according to the higher
and lower limit of the PV .

16. Example for the breaking points of the characteristics for
thermograph.

17. • A non-linear method is combining the diagnostic factors and it may
be beneficial.
• In case the results reveal that a critical system is failing, the system
should calculate a health index that approaches zero, however
when no critical condition exists, it should observe the weighting
of the parameters.
• The system should additionally enable new diagnostic methods to
be easily incorporated.
Non-linear Evaluation

18. Non-linear (bottom) and linear (top) combination of
critical parameters.

19. TSI factor
The output of the expert system is the status of the insulation. This
number is the TSI factor. The TSI factor can be calculated by using
a TSI code and TSI weights (Ki).
TSI code
Now the TSI expert system is using the linear evaluation method
for computing the TSI factor. The typical equation for calculating
the TSI Code.

20. TEST DATA

21. TABLE IV. AVALIABILE DATA FOR A TRANSFORMER

22. PROGRAM
• For the presented evaluating method and for the necessary data
storage, a program was developed.
• The program handles the basic data (transformer ID,
manufacturing number, substation name and place, type, nominal
voltages) and the diagnostic results too, of the transformers.
• The program provides an evaluating in the necessary time period
and displays it.
• It is very important to prepare the program to connect or can be
integrated into a company asset management system to download
the diagnostic results and upload the evaluating results.

23. RESULTS OF THE PROGRAM
• The status of the insulation is represented by the TSI factor
(TSIF).
• It contains the ageing phenomena and other necessary information
for the evaluating.
• With these information’s the TSI expert system serves the
conditional based maintenance strategy in the asset management
system.

24. Diagram of a transformer evaluation between 2000-2011

25. There are some relevant evaluating parameter.
• Measured and calculated degradation speed (average)
• Increased TSI represents the reconstruction (time and volume).
• Fault level (calculated by statistical data).
• Increased lifetime (expectation of life).
Using these useful information’s the operator can plan the
reconstruction or maintenance of each transformers.

26. • The TSI factor gives a reliability volume of the status of the
transformer and its insulation system.
• The TSI support the condition based maintenance strategy, so it
helps for the operators to select the indigent transformer to get
maintenance or a reconstruction while minimized the cost of the
asset management.
• Further research needed the evaluation and have to evaluate more
transformers to get suitable information’s and statistical result for
the failure level.
• The other task is to improve the physical effect evaluating (e.g.:
RVM or dielectric loss factor or DGA using other research work
results.
CONCLUSION

27. • Cs. Vörös, B. Németh, S. Szabó, I. Berta, Diagnostic
evaluation of power transformers by an expert system,
International Symposium on Electrical Insulation, Puerto Rico,
2012,
• Cs. Vörös: Evaluating the transformer diagnostic results
according to Health Index “Transzgormátor diagnosztika
kiértékelése Health Index alapján”.Budapest University of
Technology and Economics,2010.(in Hungarian language)
• Csaba Vörös, Bálint Németh, István Kiss,Transformer Status
Indicator (TSI) as a new expert system for integrating the
diagnostic results of power transformesr, International Youth
Conference on Energy (IYCE) 2011, Portugal
• http://www.igcseict.info/theory/7_2/expert/
BIBLIOGRAPHY