Abstract
For early diagnosis of transformer oils condition according to a set of diagnostic attributes a model of multiple regression has been developed. A distinctive feature of the proposed model is that the values of the operating life is a function of the values of the oil indicators, and the decision about the condition of the oils is made on the basis of comparison of the real operating life with the operating life calculated by regression model. In order to take into account the peculiarities of oil ageing under conditions of long-term operation a complex analysis of stochastic correlation between the quality indicators of transformer oils has been carried out. The procedure of statistical processing of the results of operational tests is proposed, which allows filtering out the test results that contain gross errors and omissions. A multiple regression model is trained taking into account transformer loading and its adequacy is checked. Examples of practical use of the developed model for operating transformers are given. Practical use of the developed model allows detecting transformers with accelerated oil ageing at an early stage when oil indicators are in the range of permissible values. This allows the substation operating personnel to inhibit the oil ageing processes in time, which, in turn, makes it possible to extend the life of not only the liquid but also the main insulation of transformers.
Similar content being viewed by others
Data Availability
Not applicable.
Code Availability
Not applicable.
References
IEEE Std C57.91-2011: IEEE Guide for Loading Mineral-Oil-Immersed Transformers and Step-Voltage Regulators. Institute of Electrical and Electronics Engineers (2012). https://doi.org/10.1109/IEEESTD.2012.6166928
FIST 3-31: Transformer Diagnostics. United States Bureau of Reclamation (2003). https://www.usbr.gov/power/data/fist/fist3_31/fist3-31.pdf
IEC 60156:2018: Insulating liquids - Determination of the breakdown voltage at power frequency - Test method. International Electrotechnical Commission (2018)
IEC 60296:2012: Fluids for Electrotechnical Applications—Unused Mineral Insulating Oils for Transformers and Switchgears. International Electrotechnical Commission (2012)
SOU-N EE 20.302:2020: Standards testing of electrical equipment. National Power Company Ukrenergo, Kyiv, Ukraine (2020) (in Ukrainian)
Singh, H.D.; Singh, J.: Enhanced optimal trained hybrid classifiers for aging assessment of power transformer insulation oil. World J. Eng. (2020). https://doi.org/10.1108/WJE-11-2019-0339
Bhatia, N.K.; El-Hag, A.H.; Shaban, K.B.: Machine learning-based regression and classification models for oil assessment of power transformers. In: 2020 IEEE International Conference on Informatics, IoT, and Enabling Technologies (ICIoT) (2020). https://doi.org/10.1109/ICIoT48696.2020.9089647
Gautam, L.; Kumar, R.; Sood, Y.R.: Identifying transformer oil criticality using fuzzy logic approach. In: 2020 IEEE Students Conference on Engineering & Systems (SCES) (2020). doi:https://doi.org/10.1109/SCES50439.2020.9236724
Alqudsi, A.Y.; ElHag, A.H.: A cost effective artificial intelligence based transformer insulation health index. In: 2017 3rd International Conference on Condition Assessment Techniques in Electrical Systems (CATCON) (2017). https://doi.org/10.1109/CATCON.2017.8280194
Bhushan, U.; Jarial, R.; Jadoun, V.; Agarwal, A.: On condition monitoring aspects of in-service power transformers using computational techniques. Lect. Notes Mech Eng. (2020). https://doi.org/10.1007/978-981-15-5463-6_31
Forouhari, S.; Abu-Siada, A.: Application of adaptive neuro fuzzy inference system to support power transformer life estimation and asset management decision. IEEE Trans. Dielectr. Electr. Insul. (2018). https://doi.org/10.1109/TDEI.2018.006392
Bondarenko, V.O.; Shutenko, O.V.: Improving decision-making procedures in assessing the degree of aging of transformer oils. ELECTRO Electr. Eng. Electr. Power Ind. Electr. Ind. 1, 17–21 (2009) ((in Russian))
Setiawati, N.E.; Rosmaliati Lystianingrum, V.; Priyadi, A.; Purnomo, M.H.: Distribution transformer oil age prediction using neuro wavelet. In: 2018 10th International Conference on Information Technology and Electrical Engineering (ICITEE) (2018). https://doi.org/10.1109/iciteed.2018.8534830
Su, Y.; Liu, M.; Kong, X.; Guo, C.; Zhu, J.; Li, X.; Zhou, Q.: Evaluation of breakdown voltage and water content in transformer oil using multi frequency ultrasonic and generalized regression neural network. J. Nanoelectron. Optoelectron. 16, 387–394 (2021). https://doi.org/10.1166/jno.2021.2971
Gouda, O.; El Dein, A.: Prediction of aged transformer oil and paper insulation. Electr. Power Compon. Syst. 47, 406–419 (2019). https://doi.org/10.1080/15325008.2019.1604848
Abdi, S.; Harid, N.; Safiddine, L.; Boubakeur, A.; Haddad, A.: The correlation of transformer oil electrical properties with water content using a regression approach. Energies 14, 2089 (2021). https://doi.org/10.3390/en14082089
Leauprasert, K.; Suwanasri, T.; Suwanasri, C.; Poonnoy, N.: Intelligent machine learning techniques for condition assessment of power transformers. In: 2020 International Conference on Power, Energy and Innovations (ICPEI) (2020). https://doi.org/10.1109/ICPEI49860.2020.9431460
Paul, D.; Goswami, A.: A multi-gene symbolic regression approach of determining insulating oil interfacial tension. In: 2020 IEEE International Conference on Power Electronics, Drives and Energy Systems (PEDES) (2020). https://doi.org/10.1109/PEDES49360.2020.9379528
Hu, C.; Zhang, C.; Zhang, Z.; Xie, S.: Comparative Study on defects and faults detection of main transformer based on logistic regression and naive bayes algorithm. J. Phys. Conf. Ser. 1732, 012075 (2021). https://doi.org/10.1088/1742-6596/1732/1/012075
Shutenko, O.; Ponomarenko, S.: Diagnostics of transformer oils using the multiple linear regression model. In: 2020 IEEE Problems of Automated Electrodrive. Theory and Practice (PAEP) (2020). https://doi.org/10.1109/PAEP49887.2020.9240875
Shutenko, O.; Ponomarenko, S.: Reliability assessment of the results of periodic monitoring of the transformer oils condition. In: 2020 IEEE 4th International Conference on Intelligent Energy and Power Systems (IEPS) (2020). https://doi.org/10.1109/IEPS51250.2020.9263141
Gmurman, V.E.: Probability Theory and Mathematical Statistics. High school, Moscow (1977)
Shteger, G.: Insulating Material: Translation from German. Gosenergoizdat, Moscow (1961)
Johnson, N.L.; Leone, F.C.: Statistics and Experimental Design in Engineering and the Physical Sciences: v. 1 (Probability & Mathematical Statistics S.). Wiley, New York (1977)
Shutenko, O.; Ponomarenko, S.: Analysis of the impact of power transformer loading on the transformer oil aging intensity. In: 2020 IEEE KhPI Week on Advanced Technology (KhPIWeek) (2020). https://doi.org/10.1109/KhPIWeek51551.2020.9250159
Shutenko, O.; Ponomarenko, S.: Analysis of distribution laws of transformer oil indicators in 110–330 kV transformers. Electr. Eng. Electromech. (2021). https://doi.org/10.20998/2074-272X.2021.5.07
Funding
None.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
There are no conflicts of interest or competing interests.
Rights and permissions
About this article
Cite this article
Shutenko, O., Ponomarenko, S. Development of a Multiple Regression Model for Early Diagnosis of Transformer Oil Condition. Arab J Sci Eng 47, 14119–14132 (2022). https://doi.org/10.1007/s13369-021-06418-5
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s13369-021-06418-5