Professional Documents
Culture Documents
Intelligent System For Transformer Condition Assessment
Intelligent System For Transformer Condition Assessment
An intelligent
system for condition
assessment of power
transformers
ABSTRACT
Health index (HI) approach has been
adopted widely as a tool that assists
the asset managers to prioritise their
plans and actions. However, the con-
ventional computation of HI, which is
based on scoring and ranking, has sev-
eral drawbacks. In this work, the fuzzy
logic approach is utilised to build up an
intelligent HI system to assess the con-
dition of power transformers based on
oil quality and DGA results.
KEYWORDS
fuzzy logic, health index, power
transformers, predictive mainte-
nance
1. Introduction sult, the use of quantitative indicators, ational, offline, visual inspection, etc.
such as health index (HI), is gaining
The continuous demand for optimis- wide popularity, especially when it Several methods are developed to con-
ing the lifetime cost of transformers comes to prioritising maintenance and vert the existing diagnostic data into a
through informed decisions has led to replacement activities. HI. For instance, binary logistic regres-
adopting condition monitoring tools sion is used in [1] for this purpose. The
in addition to the traditional offline HI is an approach that combines all input data are classified into categories,
testing methods. Many utilities have the information of a transformer in healthy or unhealthy. Weights, assigned
migrated from the conventional time- order to provide a single quantitative to each input, are calculated using the
based to condition-based maintenance. index that expresses the overall con- maximum likelihood criterion. An-
The outcome of the current diagnostic dition based on the measured data. other approach is introduced in [2-5]
methods, online and offline, is large The available data can be online, from to calculate the HI using the weighting
volumes of accumulated data. As a re- condition monitoring systems, oper- average such that:
w w w . t ra n sfo r m e r s - m a g a z i n e . co m 15
CONDITION ASSESSMENT
0, x ≤ a
x-a,
c1 -a a ≤ x ≤ c1
A= 1, c1 ≤ x ≤ c2 (2)
b - x , c2 ≤ x ≤ b
b - c2
0, x ≥ b
w w w . t ra n sfo r m e r s - m a g a z i n e . co m 17
CONDITION ASSESSMENT
Figure 4. MF of H2 gas
Gas a c1 c2 b a c1 c2 b a c1 c2 b a c1 c2 b
H2 0 0 95 105 95 105 695 705 695 705 1790 1810 1790 1810 2000 3000
CH4 0 0 118 122 118 122 396 403 396 403 994 1004 994 1004 3000 5000
CO 0 0 345 355 345 355 565 575 565 575 1390 1420 1390 1420 2000 3000
CO2 0 0 2470 2520 2470 2520 3970 4020 3970 4020 9900 10100 10050 10100 10100 50000
The lower and upper limits and the two in Table 1. The lower and upper limits DGAI index is composed of two main
centres for each of the seven MFs for were selected in accordance with IEEE modules oil arcing and PD, and oil ther-
each input gas concentration are given Std C57.10-2008 [12]. mal, as shown in Fig. 5. Due to the ther-
w w w . t ra n sfo r m e r s - m a g a z i n e . co m 19
CONDITION ASSESSMENT
4.3 Oil quality index (OQI) of the oil with sludge. The output of ‘oil useful tool to make decisions and priori
characteristics’ module is an input of tise maintenance plans of power trans-
OQI is a combination of three modules OQI module. formers.
for moisture, oil characteristics, and sol-
id insulation, as shown in Fig. 10. MFs Similarly, the ‘solid insulation’ module Bibliography
are developed for the input data: break output is dependent on CO and CO2 gas
down voltage (BDV), acidity, interfacial levels in addition to the absolute value of [1] W. Zuo, H. Yuan, Y. Shang, Y. Liu, T.
tension (IFT), water content, oil tem- 2FAL in the oil. Chen, Calculation of a health index of
perature, CO, CO2, and the absolute oil-paper transformers insulation with
value of 2FAL. Since the water content Conclusion binary logistic regression, Mathemati-
values, in ppm, are dependent on oil cal Problems in Engineering, Vol. 2016,
temperature, a separate module for the The fuzzy logic method is utilised to 2016
moisture is used with its own imple- build up an intelligent system to evalu-
mented fuzzy rules, and the output of ate the condition of power transformers [2] I. Hernanda, A. Mulyana, D. As-
moisture module is the input to OQI. based on oil data. Hundreds of fuzzy fani, I. Negara, D. Fahmi, Application of
rules are developed in the proposed health index method for transformer
The output score of ‘oil characteristics’ model to mimic the behaviour of an oil condition assessment, Annual Interna-
module is based on the three inputs of transformer expert and generate a reli- tional TENCON Conference, Thailand,
BDV, acidity, and IFT. The BDV test is able HI. The proposed model can be a 2015
one of the prominent diagnostic tests.
This test gives an indication of contam-
inants, such as oil degradation products
and water. The acidity in the oil deteri- Prognostic index is estimated using the
orates the dielectric properties of paper
insulation and accelerates the oxidation measured rate of change of dissolved
process in the oil. An increase in the
acidity of the oil in a transformer gives
gasses in time, combined with fuzzy logic
an indication of the rate of degradation model
w w w . t ra n sfo r m e r s - m a g a z i n e . co m 21
CONDITION ASSESSMENT
Oil quality index is estimated using the fuzzy Health index calculation for power
transformers using technical and
logic model, which uses measurement data economical parameters, IET Science,
such as break down voltage, acidity, interfa- Measurement & Technology, Vol. 10,
no. 7, pp. 823-830, 10 2016
cial tension, water content, oil temperature,
[10] M. Duval, A. dePabla, Interpreta-
CO, CO2, etc. tion of gas-in-oil analysis using new
IEC publication 60599 and IEC TC
10 databases, IEEE Electrical Insula-
[3] A. Naderian, S. Cress, R. Piercy, Guide to the expression of uncertainty tion Magazine, Vol. 17, no. 2, pp. 31-41,
F. Wang, J. Service, An Approach to in measurement, 2008 March-April 2001
determine the health index of power
transformers, Conference Record of [8] P. H. Mukti, F. A. Pamuji, B. S. Mu- [11] IEC 60599 Ed. 3, Mineral oil-im-
the 2008 IEEE International Sympo- nir, Implementation of artificial neu- pregnated electrical equipment in ser-
sium on Electrical Insulation, pp. 192- ral networks for determining power vice – Guide to the interpretation of
196, 2008 transfomer condition, 5th International dissolved and free gases analysis, 2015
Symposium on Advanced Control of
[4] F. Ortiz, I. Fernandez, A. Ortiz, Industrial Processes (ADCONIP 2014), [12] IEEE Std C57.104-2008, IEEE
C. J. Renedo, F. Delgado, C. Fernandez, pp. 473-477, 28–30 May, 2014 Guide for the Interpretation of gases
Health indexes for power transform- generated in oil-immersed transform-
ers: A case study, IEEE Electrical Insu- [9] H. Zeinoddini-Meymand, B. Vahidi, ers, 2008
lation Magazine, Vol. 32, pp. 7-17, 2016