Improvement of dissolved gas analysis interpretation by combining Duval triangle method with machine learning techniques

Power transformer is one of the main components in any power transmission and distribution network. Transformers have complicated winding structures and are subjected to electrical, thermal and mechanical stresses. During the last few years, there has been a trend of continuous increasing of transfo...

Full description

Saved in:

Bibliographic Details
Main Author:	Dheyaa, Ghaith Anmar
Format:	Thesis
Language:	English English
Published:	2019
Subjects:	T Technology (General)
Online Access:	http://eprints.utem.edu.my/id/eprint/24945/1/Improvement%20Of%20Dissolved%20Gas%20Analysis%20Interpretation%20By%20Combining%20Duval%20Triangle%20Method%20With%20Machine%20Learning%20Techniques.pdf http://eprints.utem.edu.my/id/eprint/24945/2/Improvement%20Of%20Dissolved%20Gas%20Analysis%20Interpretation%20By%20Combining%20Duval%20Triangle%20Method%20With%20Machine%20Learning%20Techniques.pdf
Tags:	Add Tag No Tags, Be the first to tag this record!

id	my-utem-ep.24945
record_format	uketd_dc
institution	Universiti Teknikal Malaysia Melaka
collection	UTeM Repository
language	English English
advisor	Abu Bakar, Norazhar
topic	T Technology (General) T Technology (General)
spellingShingle	T Technology (General) T Technology (General) Dheyaa, Ghaith Anmar Improvement of dissolved gas analysis interpretation by combining Duval triangle method with machine learning techniques
description	Power transformer is one of the main components in any power transmission and distribution network. Transformers have complicated winding structures and are subjected to electrical, thermal and mechanical stresses. During the last few years, there has been a trend of continuous increasing of transformer failures. It is therefore vital to diagnose the incipient faults for safety and reliability of an electrical network. Thus, these transformers are needed to be routinely maintained. Due to the large number of transformers with different manufactures and capacities, routine maintenance and diagnosis of such transformers are difficult since different transformers exhibit different characteristics and problems. By means of dissolved gas analysis (DGA), it is possible to distinguish faults such as partial discharge (corona), overheating (pyrolysis) and arcing in oil-filled equipment. Dissolved gas analysis is one of the most effective tools for power transformer condition monitoring. There are several interpretation techniques for DGA results including Key Gas, Doernenburg, IEC Ratio, Roger’s Ratio and Duval Triangle. However, DGA interpretation is still a challenge issue as most of the techniques are relying on personnel experience more than standard mathematical formulation. As a result, various interpretation techniques do not necessarily lead to the same conclusion for the same oil sample. Furthermore, significant number of DGA results fall outside the proposed codes of the current based-ratio interpretation techniques and cannot be diagnosed by these methods. Moreover, ratio methods fail to diagnose multiple fault conditions due to the mixing up of produced gases. To overcome these limitations, this thesis proposes a new Artificial Intelligence (AI) approach to reduce dependency on expert personnel and to aid in standardizing DGA interpretation techniques. The approach relies on incorporating the Duval triangle method (DTM) with two machine learning classifiers named decision tree (DT) and random forest (RF), which the final interpretation will apply the voting combination method to get the final prediction of the incipient fault inside the power transformer. DGA results of oil samples where the real fault already known that were collected from different published papers were used to train and test the classifiers. The results demonstrate that combining the conventional method with artificial intelligence based on DGA interpretation methods gives reliable diagnosis of the incipient fault in the power transformer.
format	Thesis
qualification_name	Master of Philosophy (M.Phil.)
qualification_level	Master's degree
author	Dheyaa, Ghaith Anmar
author_facet	Dheyaa, Ghaith Anmar
author_sort	Dheyaa, Ghaith Anmar
title	Improvement of dissolved gas analysis interpretation by combining Duval triangle method with machine learning techniques
title_short	Improvement of dissolved gas analysis interpretation by combining Duval triangle method with machine learning techniques
title_full	Improvement of dissolved gas analysis interpretation by combining Duval triangle method with machine learning techniques
title_fullStr	Improvement of dissolved gas analysis interpretation by combining Duval triangle method with machine learning techniques
title_full_unstemmed	Improvement of dissolved gas analysis interpretation by combining Duval triangle method with machine learning techniques
title_sort	improvement of dissolved gas analysis interpretation by combining duval triangle method with machine learning techniques
granting_institution	Universiti Teknikal Malaysia Melaka
granting_department	Faculty of Electrical Enginering
publishDate	2019
url	http://eprints.utem.edu.my/id/eprint/24945/1/Improvement%20Of%20Dissolved%20Gas%20Analysis%20Interpretation%20By%20Combining%20Duval%20Triangle%20Method%20With%20Machine%20Learning%20Techniques.pdf http://eprints.utem.edu.my/id/eprint/24945/2/Improvement%20Of%20Dissolved%20Gas%20Analysis%20Interpretation%20By%20Combining%20Duval%20Triangle%20Method%20With%20Machine%20Learning%20Techniques.pdf
_version_	1776103126851387392
spelling	my-utem-ep.249452023-07-03T15:21:05Z Improvement of dissolved gas analysis interpretation by combining Duval triangle method with machine learning techniques 2019 Dheyaa, Ghaith Anmar T Technology (General) TK Electrical engineering. Electronics Nuclear engineering Power transformer is one of the main components in any power transmission and distribution network. Transformers have complicated winding structures and are subjected to electrical, thermal and mechanical stresses. During the last few years, there has been a trend of continuous increasing of transformer failures. It is therefore vital to diagnose the incipient faults for safety and reliability of an electrical network. Thus, these transformers are needed to be routinely maintained. Due to the large number of transformers with different manufactures and capacities, routine maintenance and diagnosis of such transformers are difficult since different transformers exhibit different characteristics and problems. By means of dissolved gas analysis (DGA), it is possible to distinguish faults such as partial discharge (corona), overheating (pyrolysis) and arcing in oil-filled equipment. Dissolved gas analysis is one of the most effective tools for power transformer condition monitoring. There are several interpretation techniques for DGA results including Key Gas, Doernenburg, IEC Ratio, Roger’s Ratio and Duval Triangle. However, DGA interpretation is still a challenge issue as most of the techniques are relying on personnel experience more than standard mathematical formulation. As a result, various interpretation techniques do not necessarily lead to the same conclusion for the same oil sample. Furthermore, significant number of DGA results fall outside the proposed codes of the current based-ratio interpretation techniques and cannot be diagnosed by these methods. Moreover, ratio methods fail to diagnose multiple fault conditions due to the mixing up of produced gases. To overcome these limitations, this thesis proposes a new Artificial Intelligence (AI) approach to reduce dependency on expert personnel and to aid in standardizing DGA interpretation techniques. The approach relies on incorporating the Duval triangle method (DTM) with two machine learning classifiers named decision tree (DT) and random forest (RF), which the final interpretation will apply the voting combination method to get the final prediction of the incipient fault inside the power transformer. DGA results of oil samples where the real fault already known that were collected from different published papers were used to train and test the classifiers. The results demonstrate that combining the conventional method with artificial intelligence based on DGA interpretation methods gives reliable diagnosis of the incipient fault in the power transformer. 2019 Thesis http://eprints.utem.edu.my/id/eprint/24945/ http://eprints.utem.edu.my/id/eprint/24945/1/Improvement%20Of%20Dissolved%20Gas%20Analysis%20Interpretation%20By%20Combining%20Duval%20Triangle%20Method%20With%20Machine%20Learning%20Techniques.pdf text en public http://eprints.utem.edu.my/id/eprint/24945/2/Improvement%20Of%20Dissolved%20Gas%20Analysis%20Interpretation%20By%20Combining%20Duval%20Triangle%20Method%20With%20Machine%20Learning%20Techniques.pdf text en staffonly https://plh.utem.edu.my/cgi-bin/koha/opac-detail.pl?biblionumber=117709 mphil masters Universiti Teknikal Malaysia Melaka Faculty of Electrical Enginering Abu Bakar, Norazhar 1. A.Akbari, A. S., 2008. A Software Implementation of the Duval Triangle method. IEEE Transection , pp. 124-127. 2. A.Setayeshmehr, A. A. H. B., 2004. A procedure for diagnosis and condition based maintenance for power transformers. Indianapolis, IEEE, pp. 67-88. 3. Ajay Kumar Mishra, B. K. R., 2016. Study of Random Tree and Random Forest Data Mining Algorithms for Microarray Data Analysis. ISSN, pp. 2349-9338. 4. Amin, R. K., 2015. Implementation of Decision Tree Using C4.5 Algorithm. Tahran, IEEE. 5. Boss P, L. P., 2000. Economical aspects and experiences of power transformer. london: CIGRE Session. 6. Azcarraga C. G., Garcia-Colon V.R. and Nava G. A. On-site testing of Instrument Transformers, IEEE Conference on Electrical Insulation and Dielectric Phenomena (2006) 39-42. 7. Homagk, K. M., 2008. Investigation on Degradation of Power Transformer Solid Insulation Material. Quebec, IEEE, pp. 50-62. 8. Duval, M., 1989. Dissolved gas analysis: It can save your transformer. IEEE Electrical Insulation Magazine, pp. 22 - 27. 9. Duval, M., 2001. Interpretation of gas-in-oil analysis using new IEC publication 60599 and IEC TC 10 databases. IEEE Electrical Insulation Magazine, pp. 31-41. 10. David G. and Rajaram M. Prediction of faults using hydrocarbon gases data of mineral oil immersed power transformers using computer intelligence, Journal of Asian Scientific Research 2 (2011) 6-13 11. Emsley A.M., Xiao X., Heywood R.J. and Ali M. Degradation of cellulosic insulation in power transformers. Part 3: Effects of oxygen and water on ageing in oil, IEE Proceedings- Science, Measurement and Technology 147 (2000) 115-119. 12. Enokizono M., Suzuki T., Sievert J. and Xu J. Rotational power loss of silicon steel sheet, IEEE Transactions on Magnetics 26 (1990) 2562 -2564. 13. Enokizono M., Todaka T., Kanao S. and Sievert J. Two-dimensional magnetic properties of silicon steel sheet subjected to a rotating field, IEEE Transactions on Magnetics 29 (1993) 3550 -3552. 14. Enokizono M. and Soda N. Iron loss analysis of three-phase transformer by using finite element method, Proceedings of International Conference on Engineering Education 1(1998) 852 -855. 15. Fofana I., Borsi H., Gockenbach E. and Farzaneh M. Aging of transformer insulating materials under selective conditions, European Transactions on Electric Power (2006) 1–21. 16. Pradhan M.K. Assessment of the status of insulation during thermal stress accelerated experiments on transformer prototypes, IEEE Transactions on Dielectrics and Electrical 17. Insulation 13 (2006) 227 – 237. 18. Fábio R. Barbosa, O. M. A., 2012. Application of an Artificial Neural Network in the Use of Physicochemical Properties as a Low Cost Proxy of Power Transformers DGA Data. Transactions on Dielectrics and Electrical Insulation, pp. 239-246. 19. Fathiah Zakaria, D. J., 2012. Artificial Neural Network (ANN) Application in Dissolved Gas Analysis (DGA) Methods for the Detection of Incipient Faults in Oil-Filled Power Transformer. Penang, International Conference on Control System, Computing and Engineering, pp. 328-332. 20. Gaganjot Kaur, A. C., 2014. Improved J48 Classification Algorithm for the Prediction of Diabetes. International Journal of Computer Applications, pp. 234-240. 21. Ghalkhani, M., 2012. Contribution to the Improvement of the Dissolved Gas, s.l.: s.n. 22. Golarz, J., 2016. Understanding Dissolved Gas Analysis (DGA). IEEE Transaction on Industry Application, pp. 40-54. 23. Hasmat Malik, S. M., 2016. Application of Gene Expression Programming (GEP) in Power Transformers Fault Diagnosis Using DGA IEEE Transaction on Industry Application., pp. 4556-4565. 24. Hasmat Malik, S. M., 2016. Application of Gene Expression Programming (GEP) in Power Transformers Fault Diagnosis Using DGA. IEEE Transaction on Industry Application, pp. 4556-4565. 25. Huaren Wu, X. L., 2011. RMP Neural Network Based Dissolved Gas Analyzer for Fault Diagnostic of Oil-filled Electrical Equipment. IEEE Transactions on Dielectrics and Electrical Insulation, pp. 495-498. 26. Hui Ma, T. K. S., 2012. Statistical Learning Techniques and Their Applications for Condition Assessment of Power Transformer. IEEE Transactions on Dielectrics and Electrical Insulation, pp. 481-489. 27. Huo-Ching Sun, Y.-C. H. C.-M. H., 2012. A Review of Dissolved Gas Analysis in Power Transformers. sciencedirect, p. 1220 – 1225. 28. Huo-Ching Sun, Y.-C. H. C.-M. H., 2012. Review of Dissolved Gas Analysis in Power Transformers. sciencedirect, p. 1220 – 1225. 29. Ibrahim B. M. Taha, S. S. M. G. A. S. A. D., 2016. Refining DGA Methods of IEC Code and Rogers Four Ratios for Transformer Fault Diagnosis. IEEE Transactions on Dielectrics and Electrical Insulation , pp. 330-335. 30. Heywood R.J. Kinetics and mechanisms of degradation of cellulose insulation in power transformers, PhD, University of Surrey (1997). 31. Hill D.J.T, Le T.T., Darvenzia and Saha T. A study of degradation of cellulosic insulation materials in a power transformer, part 1.Molecular weight study of cellulose insulation paper, Polymer Degradation and Stability 48 (1995) 79-87. 32. Hindmarsh John Electrical Machines and their Applications, 4th edition, Exeter: Pergammon (1977) ISBN 008- 030573-3. 33. Huang X. and Yan Z. Study on trend analysis method for on-line insulation diagnosing of capacitive-type equipment, International Symposium on Electrical Insulating Materials, Toyohashi, Japan (1998) 2-40. 34. Irungu, G. K. A. ,. A. O., 2016. Comparison of IEC 60599 Gas Ratios and an Integrated Fuzzy-Evidential Reasoning Approach in Fault Identification using Dissolved Gas Analysis. IEEE Transactions on Dielectrics and Electrical Insulation , pp. 1-6. 35. Jeff Golarz, L. T. S. C., 2016. Understanding Dissolved Gas Analysis (DGA) Techniques and Interpretations. IEEE Transactions on Dielectrics and Electrical Insulation , pp. 455-459. 36. Jiawei Han, M. K., 2012. Data Mining Concepts and Techniques. Third Edition ed. Waltham: Elsevier. 37. Jinkui Zhang, Y. Z. W. S., 2015. An Improved Machine Learning Scheme for Datadriven Fault Diagnosis of Power Grid Equipment. Shandong, IEEE Transactions on Dielectrics and Electrical Insulation. 38. Jinzhong Li, Q. Z., 2016. Optimal Dissolved Gas Ratios Selected by Genetic Algorithm for Power Transformer Fault Diagnosis Based on Support Vector Machine. IEEE Transactions on Dielectrics and Electrical Insulation, pp. 1198-1206. 39. Khaled Bashir Shaban, A. H. E.-H., 2016. Prediction of Transformer Furan Levels. IEEE Transactions on Dielectrics and Electrical Insulation, pp. 322-329. 40. Kulkarni S.V. and Khaparde S.A. Transformer Engineering: design and practice, CRC Press (2004) ISBN 08247- 5653-3. 41. L. V. Badicu, B. G. L. M. D., 2012. Assessment of transformer mineral oil condition based on dc and ac conductivity. IEEE Transactions on Dielectrics and Electrical Insulation, pp. 1544 - 1551. 42. Lezhen, Z. Y., 2002. Prediction of electrical equipment failure rate for condition-based maintenance decision-making. Electric Power Automation Equipment, pp. 544-677. 43. Lu HongXing, Y. Y., 2015. Transformer Fault Diagnosis Algorithm based on Entropy-weighting Information Bottleneck Method. Zhengzhou, IEEE, pp. 1-4. 44. M. Jovalekic, D. V. S. T., 2011. Dissolved gas analysis of alternative dielectric fluids under thermal and electrical stress. Trondheim, IEEE Transactions on Dielectrics and Electrical Insulation. 45. Lachman M.F., Walter W. and Guggenberg P.A. On-line diagnostics of high-voltage bushings and current transformers using the sum current method, IEEE Transactions on Power Delivery 15 (2000) 155-162. 46. M. Wang, A. V. K. S., 2002. Review of condition assessment of power transformers in service. IEEE Electrical Insulation Magazine , pp. 12 - 25. 47. Mehrdad Beykverdi, F. F., 2014. New Approach for Transformer Incipient Fault Diagnosis Based on Dissolved Gas Analysis (DGA). Nova Journal of Engineering and Applied Sciences, pp. 1-7. 48. Mehrdad Beykverdi, F. F. A. M. p., 2014. A New Approach for Transformer Incipient Fault Diagnosis Based on Dissolved Gas Analysis (DGA). Nova Journal of Engineering and Applied Sciences, pp. 1-7. 49. Nagpal, T., 2014. Development of An Intelligent Novel Algorithim For Tramsformer Fault Detection Using Various Emission Signals, s.l.: Punjab. 50. Oommen T.V. and Prevost T.A. Cellulose insulation in oil-filled power transformers: part II-Maintaining insulation integrity and life, IEEE Electrical Insulation Magazine 22 (2006) 5 – 14. 51. Piotr Mirowski, Y. L., 2012. Statistical Machine Learning and Dissolved Gas Analysis: A Review. IEEE Transactions on Dielectrics and Electrical Insulation, pp. 1791-1799. 52. Pahlavanpour B. and Roberts I. A. Transformer oil condition monitoring, IEE Colloquium on Transformer Life Management (1998) 1-6. 53. Qianjin L., Huiming X., Chao S. and Shengxuan W. The application of intelligent control technology in power systems, IEEE International Conference on Mechatronics and Automation (2014) 2034-2038. 54. Rahmat Allah Hooshmand, M. P., 2012. Adaptive Neuro-Fuzzy Inference System Approach for Simultaneous Diagnosis of the Type and Location of Faults in Power Transformer. IEEE Electrical Insulation Magazine, pp. 32-42. 55. Rosa A., Castro G. and Miranda V. Knowledge discovery in neural networks with application to transformer failure diagnosis.IEEE Transactions on Power System 20 (2005) 717–24. 56. Rao U.M., Reddy M.V.P. and Jarial R.K. Fuzzy logic based system to diagnose internal faults of power transformer, IEEE International Conference on Communication and Industrial Application, Kolkata, West Bengal, (2011) 1-5. 57. S. Hmood, A. A.-S. M. A. M., 2012. Standardization of DGA Interpretation Techniques using Fuzzy Logic Apoach. Bali, IEEE Transactions on Dielectrics and Electrical Insulation, pp. 929-932. 58. Shakeb A. Khan, M. D. E. T. I., 2015. A Comprehensive Comparative Study of DGA Based transformer fault diagnosis Using fuzzy Logic and ANFIC Models. IEEE Transactions on Dielectrics and Electrical Insulation, pp. 590-596. 59. Suzuki T., Nakayama H., Yamamoto T. and Taguchi S. The transformer characteristics of orient core HI-B, IEEE Transactions on Magnetics 8 (1972) 321- 323. 60. Saha T. K. and Prithwiraj Investigation of an Expert System for the Condition Assessment of Transformer Insulation Based on Dielectric Response Measurements”, IEEE Trans. Power Delivery 19 (2004) 1127-1134. 61. Shuaibing Li, G. W., 2016. Interpretation of DGA for Transformer Fault Diagnosis with Complementary SaE-ELM and Arctangent Transform. IEEE Transactions on Dielectrics and Electrical Insulation, pp. 586-595. 62. Sukhbir Singh, M. N. B., 2010. Dissolved gas analysis technique for incipient fault diagnosis in power transformers: A bibliographic survey. IEEE Electrical Insulation Magazine, pp. 41 - 46. 63. Sabau J. and Stokhuyzen R. The side effects of gassing in transmission power transformers, Annual Reports of Conference on Electrical Insulation and Dielectric Phenomenon 1(2000) 264-267 64. Seyed M.M.A., Hamed H., Ehsan A., Hamed N. and Arman S. Effect of distributed generations on aging failure probability of distribution tranformers, Electric Power Components and Systems 40 (2012) 1470–1485. 65. Sood Y. R., Sharma N. K. and TiwariP. K.Review of Artificial Intelligence Techniques Application to Dissolved Gas Analysis on Power Transformer, International Journal of Computer and Electrical Engineering 4 (2011) 577-582. 66. Suzuki T., Nakayama H., Yamamoto T. and Taguchi S. The transformer characteristics of orient core HI-B, IEEE Transactions on Magnetics 8 (1972) 321- 323. 67. Saha T. K. and Prithwiraj Investigation of an Expert System for the Condition Assessment of Transformer Insulation Based on Dielectric Response Measurements”, IEEE Trans. Power Delivery 19 (2004) 1127-1134. 68. Tawadros M.,Rizk J. and Nagrial M.Sensorless Control of Brushless Drives Using Back emf Mapping, IEEE International Conference on Computer and Electrical Engineering, Dubai (2009) 135-138. 69. Thomas P., Shukla A. K. and Raghuveer Ageing studies on paper and oil To assess the condition of solid insulation used in power transformers, IEEE International Conference on Solid Dielectrics (2001) 69–72. 70. Verma P., Roy M., Tiwari R.K. and Chandra S. Generation of furanic compounds in transformer oil under accelerated thermal and electrical stress,Electrical Insulation Conference and Electrical Manufacturing Expo. (2005) 112 – 116 71. Venkatesh S. and Gopal S. Orthogonal least square center selection technique – A robust scheme for multiple source Partial Discharge pattern recognition using Radial Basis Probabilistic Neural Network, Expert Systems with Applications 38 (2011) 8978-8989. 72. W.H. Hagman, J. K., 1997. An improved transformer top oil temperature model for use in an on-line monitoring and diagnostic system. IEEE Transactions on Power Delivery, pp. 249 - 256. 73. Wang Zhan, GuoJi Wei, Xie Jing Dong and Tang Guoqing An introduction of a condition monitoring system of electrical equipment, International symposium on electrical insulating materials, Himeji, Japan (2001) 221–224. 74. Wang Yongqiang, Zhao Jun and Lu Fangcheng Test research of environment influence to tan δ of capacitive equipment IEEE International Conference on the Properties and Applications of Dielectric Materials (2009) 366-369. 75. Y. Benmahamed, M. T., 2017. Application of SVM and KNN to Duval Pentagon 1 for Transformer Oil Diagnosis. IEEE Transactions on Dielectrics and Electrical Insulation, pp. 3443-3451. 76. Y. Han, Y. S., 2003. Condition monitoring techniques for electrical equipment-a literature survey. IEEE Transactions on Power Delivery, pp. 4-13. 77. Yann-Chang Huang, H.-C. S., 2013. Dissolved Gas Analysis of Mineral Oil for Power Transformer fault diagnosis Using Fuzzy Logic. IEEE Transactions on Dielectrics and Electrical Insulation, pp. 974-981. 78. Z. Yang, W. H. T., 2009. Association Rule Mining-Based Dissolved Gas Analysis for Fault Diagnosis of Power Transformers. IEEE Transactions on Dielectrics and Electrical Insulation, pp. 597-610.

Improvement of dissolved gas analysis interpretation by combining Duval triangle method with machine learning techniques

Similar Items