Dealing With Data Uncertainty for Transformer Insulation System Health Index

Health index has been widely accepted as a powerful tool for monitoring the condition of power transformer insulation system based on various diagnostic parameters. While this approach has been extensively discussed in the literature, not much attention was given to provide effective solutions to the uncertainty in the used data. According to CIGRE 761, data quality issues may arise due to measurement accuracy as well as incompleteness and unavailability of the required data. Therefore, this article presents the implementation and evaluation of a certainty level model for transformer insulation system health index to deal with data uncertainty. The impact of data unavailability on the health index results is also investigated. Certainty level of the health index is determined by the criticality level of available data, and is reported along with the health index result. A method to handle unavailable data by predicting the oil interfacial tension (IFT) using Random Forest approach is also presented. The proposed certainty level model is designed to accommodate the predicted value of missed data into the health index model while considering its prediction accuracy. The robustness of the developed model is validated through its application in assessing the health condition of six in-service power transformers. The results indicate that by including the proposed certainty level and the prediction approach to eliminate the issue of uncertain and missed diagnostic data, an asset management decision can be taken on operating power transformer fleets with high level of confidence.

[1]  Suwarno Suwarno,et al.  Power Transformer Paper Insulation Assessment based on Oil Measurement Data using SVM-Classifier , 2018 .

[2]  Bhavesh R. Bhalja,et al.  Fault discrimination scheme for power transformer using random forest technique , 2016 .

[3]  Kittanut Taengko,et al.  Risk assessment for power transformers in PEA substations using health index , 2013, 2013 10th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology.

[4]  H. Gumilang.  Hydrolysis process in PLN P3BJB transformers as an effect of oil insulation oxidation , 2012, 2012 IEEE International Conference on Condition Monitoring and Diagnosis.

[5]  Jianying Li,et al.  Condition monitoring and diagnosis of power equipment: review and prospective , 2017 .

[6]  K. Assaleh,et al.  Estimating transformer oil parameters using polynomial networks , 2008, 2008 International Conference on Condition Monitoring and Diagnosis.

[7]  R. Piercy,et al.  An Approach to Determine the Health Index of Power Transformers , 2008, Conference Record of the 2008 IEEE International Symposium on Electrical Insulation.

[8]  Thomas L. Saaty,et al.  DECISION MAKING WITH THE ANALYTIC HIERARCHY PROCESS , 2008 .

[9]  Shuaibing Li,et al.  Bayesian information fusion for probabilistic health index of power transformer , 2018 .

[10]  Wang Fan,et al.  An approach to power transformer asset management using health index , 2009, IEEE Electrical Insulation Magazine.

[11]  Suwarno,et al.  Transformer Paper Expected Life Estimation Using ANFIS Based on Oil Characteristics and Dissolved Gases (Case Study: Indonesian Transformers) , 2017 .

[12]  Suwarno,et al.  Transformer paper condition assessment using Adaptive Neuro-Fuzzy Inference System model , 2017, 2017 International Conference on Electrical Engineering and Computer Science (ICECOS).

[13]  Suwarno,et al.  A Multiple Expert Consensus Model for Transformer Assessment Index Weighting Factor Determination , 2020, 2020 8th International Conference on Condition Monitoring and Diagnosis (CMD).

[14]  L. Breiman.  Random Forests--random Features , 1999 .

[15]  Harry Gumilang.  Unique relationship between interfacial tension test (IFT) and neutral number test (Acidity) of transformer insulation oil in PLN P3B JB - Jakarta and Banten Regional , 2009, 2009 IEEE 9th International Conference on the Properties and Applications of Dielectric Materials.

[16]  Enze Zhang,et al.  A Synthetic Condition Assessment Model for Power Transformers Using the Fuzzy Evidence Fusion Method , 2019, Energies.

[17]  Haiying Dong,et al.  Probabilistic Health Index-Based Apparent Age Estimation for Power Transformers , 2020, IEEE Access.

[18]  Suwarno,et al.  Development of Analytic Hierarchy Process Technique in Determining Weighting Factor for Power Transformer Health Index , 2019, 2019 2nd International Conference on High Voltage Engineering and Power Systems (ICHVEPS).

[19]  Ayman H. El-Hag,et al.  Two-Layer Ensemble-Based Soft Voting Classifier for Transformer Oil Interfacial Tension Prediction , 2020, Energies.

[20]  Brian G. Stewart,et al.  Improved power transformer condition monitoring under uncertainty through soft computing and probabilistic health index , 2019, Appl. Soft Comput..

[21]  Suwarno,et al.  High voltage power transformer condition assessment considering the health index value and its decreasing rate , 2021, High Voltage.

[22]  Khaled Bashir Shaban,et al.  Prediction of Transformer Furan Levels , 2016, IEEE Transactions on Power Delivery.

[23]  Fernando Delgado,et al.  Health indexes for power transformers: a case study , 2016, IEEE Electrical Insulation Magazine.

[24]  Qian Yu,et al.  Application of fuzzy analytic hierarchy process and neural network in power transformer risk assessment , 2012, Journal of Central South University.

[25]  Aleksandar Janjic,et al.  Integrated Transformer Health Estimation Methodology Based on Markov Chains and Evidential Reasoning , 2020 .

[26]  Song Bin,et al.  Transformer health status evaluation model based on multi-feature factors , 2014, 2014 International Conference on Power System Technology.

[27]  Suwarno,et al.  Partial Discharge Defect Recognition in Power Transformer using Random Forest , 2019, 2019 IEEE 20th International Conference on Dielectric Liquids (ICDL).

[28]  Georg Brandtzæg.  Health Indexing of Norwegian Power Transformers , 2015 .

[29]  A. El-Hag,et al.  A cascade of artificial neural networks to predict transformers oil parameters , 2009, IEEE Transactions on Dielectrics and Electrical Insulation.

[30]  Jie Guan,et al.  Partial Discharge Pattern Recognition of Transformer Based on Deep Forest Algorithm , 2020 .

[31]  S. Suwarno,et al.  Thermal Aging of Mineral Oil -Paper Composite Insulation for High Voltage Transformer , 2016 .

[32]  Ashwani Kumar Chandel,et al.  Expert System for Health Index Assessment of Power Transformers , 2017 .

[33]  Daniar Fahmi,et al.  Application of health index method for transformer condition assessment , 2014, TENCON 2014 - 2014 IEEE Region 10 Conference.