Application of CRISP-DM Methodology in the Analysis of Dissolved Gases in Dielectric oil of Electrical Transformers in the Ecuadorian Electrical Sector
Article Sidebar
Main Article Content
Abstract
This study addresses the application of the Cross-Industry Standard Process for Data Mining (CRISP-DM) methodology in the analysis of dissolved gases in oil of power transformers, being this a critical component in electrical systems. The adoption of this six-phase structured method allowed a comprehensive evaluation of the condition of the transformer units of the Ecuadorian electrical system based on the analysis of investment and expansion data of the sector, as well as the study of 1 099 DGA (Dissolved Gas Analysis) profiles obtained from a population of 153 transformers located in the different regions of continental Ecuador. The findings described in this work have the potential to significantly improve investment and maintenance strategies and policies. In addition, the adoption of automation techniques in the DGA classification process is proposed, using supervised learning models to enhance the reliability and efficiency of the public energy service. The results suggest that this approach not only improves the diagnosis within the maintenance activities, but also provides a solid basis to draw a roadmap towards a predictive asset management, resulting in a substantial improvement of the reliability of the national power system.
Downloads
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Aviso de Derechos de Autor
La Revista Técnica "energía" está bajo licencia internacional Creative Commons Reconocimiento-NoComercial 4.0.
References
Ministerio de Energía y Recursos Naturales no Renovables del Ecuador, “Plan Maestro de Electricidad”.
Agencia de Regulación y Control de Energía y Recursos Naturales No Renovables, “Estadística Anual y Multianual 2023 DEL SECTOR ELÉCTRICO ECUATORIANO”, Quito.
A. Freire, J. Astudillo, C. Quinatoa, y F. Arias, “Interpretación de Gases Disueltos en Aceite Dieléctrico Mediante Bosques Aleatorios Para la Detección de Anomalías en Transformadores de Potencia”, Revista Técnica “energía”, vol. 19, no 2, pp. 90–98, ene. 2023, doi: 10.37116/revistaenergia. v19.n2.2023.544.
W. H. Tang y Q. H. Wu, “Condition Monitoring and Assessment of Power Transformers Using Computational Intelligence”, Power Systems, vol. 58, 2011, doi: 10.1007/978-0-85729-052-6.
X. Z. Wang, M. Z. Lu, y J. B. Huo, “Fault diagnosis of power transformer based on large margin learning classifier”, en Proceedings of the 2006 International Conference on Machine Learning and Cybernetics, 2006, pp. 2886–2891. doi: 10.1109/ICMLC.2006.259075.
T. Liu y Z. Wang, “Design of power transformer fault diagnosis model based on support vector machine”, en 2009 International Symposium on Intelligent Ubiquitous Computing and Education, IUCE 2009, 2009, pp. 137–140. doi: 10.1109/IUCE.2009.59.
R. J. Fiallos, “Dissolved gas content forecasting in power transformers based on Least Square Support Vector Machine (LSSVM)”, Latin American Journal of Computing, vol. IV, no 3, pp. 55–60, 2017.
A. K. Oktavius, S. R. Manalu, Sasmoko, Y. Indrianti, y J. V. Moniaga, “Artificial Intelligence in Entrepreneurial Mindfulness Using CRISP-DM Method”, en Proceedings of the 2022 IEEE 7th International Conference on Information Technology and Digital Applications, ICITDA 2022, Institute of Electrical and Electronics Engineers Inc., 2022. doi: 10.1109/ICITDA55840.2022.9971384.
Institute of Electrical and Electronics Engineers. y Institute of Electrical and Electronics Engineers. Columbia Section., Incorporation of both Pre-conceptual Schemas and Goal Diagrams in CRISP-DM, 2011.
M. T. Hayat Suhendar y Y. Widyani, “Machine Learning Application Development Guidelines Using CRISP-DM and Scrum Concept”, en Proceedings of 2023 IEEE International Conference on Data and Software Engineering, ICoDSE 2023, Institute of Electrical and Electronics Engineers Inc., 2023, pp. 168–173. doi: 10.1109/ICoDSE59534.2023.10291438.
S. Maataoui, G. Bencheikh, y G. Bencheikh, “Predictive Maintenance in the Industrial Sector: A CRISP-DM Approach for Developing Accurate Machine Failure Prediction Models”, en 2023 5th International Conference on Advances in Computational Tools for Engineering Applications, ACTEA 2023, Institute of Electrical and Electronics Engineers Inc., 2023, pp. 223–227. doi: 10.1109/ACTEA58025.2023.10193983.
J. Salcedo y K. (Consultant) McCormick, IBM SPSS modeler essentials: effective techniques for building powerful data mining and predictive analytics solutions. Packt Publishing, 2017.
M. Duval, “Dissolved gas analysis: It can save your transformer”, IEEE Electrical Insulation Magazine, vol. 5, no 6, pp. 22–27, nov. 1989, doi: 10.1109/57.44605.
JWG D1/A2.47, “Advances in DGA interpretation”, CIGRE Technical Brochure 771, no July, p. 15, 2013, doi: 10.1002/bapi.201390039.
IEEE Std C57.104, IEEE Guide for the Interpretation of Gases Generated in Oil-Immersed Transformers,2019-06-13, vol. 2019. 2019.
INTERNATIONAL ELECTROTECHNICAL y COMMISSION, “Mineral oil-filled electrical equipment in service - Guidance on the interpretation of dissolved and free gases analysis”, IEC 60599, vol. 4, 2022.
C. W. G. D1.01/A2.11, “Recent developments on the interpretation of dissolved gas analysis in transformers”, CIGRE Brochure 296, vol. 296, no June, pp. 1–33, 2006.
IBM, “IBM SPSS Modeler CRISP-DM Guide”. [En línea]. Disponible en: https://www.ibm.com/docs/en/spss-modeler/18.0.0?topic=spss-modeler-crisp-dm-guide
T. Committee of the IEEE Power y E. Society, “IEEE Guide for Loading Mineral-Oil-Immersed Transformers and Step-Voltage Regulators Sponsored by the Transformers Committee”, 2012.
L. V. Ganyun, C. Haozhong, Z. Haibao, y D. Lixin, “Fault diagnosis of power transformer based on multi-layer SVM classifier”, Electric Power Systems Research, vol. 74, no 1, pp. 1–7, abr. 2005, doi: 10.1016/J.EPSR.2004.07.008.
