{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T01:46:54Z","timestamp":1760060814935,"version":"build-2065373602"},"reference-count":31,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2025,9,18]],"date-time":"2025-09-18T00:00:00Z","timestamp":1758153600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"S\u00e3o Paulo State University (UNESP), Brazil"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["MAKE"],"abstract":"<jats:p>Power transformers represent critical assets within the electrical power system, and their unexpected failures may result in substantial financial losses for both utilities and consumers. Dissolved Gas Analysis (DGA) is a well-established diagnostic method extensively employed to detect incipient faults in power transformers. Although several conventional and machine learning techniques have been applied to DGA, most of them focus only on fault classification and lack the capability to provide predictive scenarios that would enable proactive maintenance planning. In this context, the present study introduces a novel approach to DGA interpretation, which highlights the trends and progression of faults by exploring the feature space through the algorithms k-Nearest Neighbors (KNN) and Optimum-Path Forest (OPF). To improve accuracy, the following strategies were implemented: statistical filtering based on normal distribution to eliminate outliers from the dataset; augmentation of gas-related features; and feature selection using optimization algorithms such as Cuckoo Search and Genetic Algorithms. The approach was validated using data from several transformers, with fault diagnoses cross-checked against inspection reports provided by the utility company. The findings indicate that the proposed method offers valuable insights into the progression, proximity, and classification of faults with satisfactory accuracy, thereby supporting its recommendation as a complementary tool for diagnosing incipient transformer faults.<\/jats:p>","DOI":"10.3390\/make7030102","type":"journal-article","created":{"date-parts":[[2025,9,18]],"date-time":"2025-09-18T14:45:46Z","timestamp":1758206746000},"page":"102","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Exploiting the Feature Space Structures of KNN and OPF Algorithms for Identification of Incipient Faults in Power Transformers"],"prefix":"10.3390","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9211-386X","authenticated-orcid":false,"given":"Andr\u00e9","family":"Gifalli","sequence":"first","affiliation":[{"name":"School of Engineering, S\u00e3o Paulo State University (UNESP), Bauru 17033-360, SP, Brazil"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8288-1758","authenticated-orcid":false,"given":"Marco Akio","family":"Ikeshoji","sequence":"additional","affiliation":[{"name":"Federal Institute of Education, Science and Technology (IFSP), Birigui 16201-407, SP, Brazil"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9945-9086","authenticated-orcid":false,"given":"Danilo Sinkiti","family":"Gastaldello","sequence":"additional","affiliation":[{"name":"Faculty of Engineering, University of Marilia (UNIMAR), Mar\u00edlia 17525-902, SP, Brazil"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-2000-4115","authenticated-orcid":false,"given":"Victor Hideki Saito","family":"Yamaguchi","sequence":"additional","affiliation":[{"name":"School of Engineering, S\u00e3o Paulo State University (UNESP), Bauru 17033-360, SP, Brazil"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9849-0102","authenticated-orcid":false,"given":"Welson","family":"Bassi","sequence":"additional","affiliation":[{"name":"High Voltage Laboratory, Institute of Energy and Environment (IEE), University of S\u00e3o Paulo (USP), S\u00e3o Paulo 05508-010, SP, Brazil"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2491-079X","authenticated-orcid":false,"given":"Talita","family":"Mazon","sequence":"additional","affiliation":[{"name":"Micro and NanoMaterials Division, Renato Archer Information Technology Center, Campinas 13069-901, SP, Brazil"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1075-9435","authenticated-orcid":false,"given":"Floriano Torres","family":"Neto","sequence":"additional","affiliation":[{"name":"School of Engineering, S\u00e3o Paulo State University (UNESP), Bauru 17033-360, SP, Brazil"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1495-633X","authenticated-orcid":false,"given":"Pedro da Costa","family":"da Costa Junior","sequence":"additional","affiliation":[{"name":"School of Engineering, S\u00e3o Paulo State University (UNESP), Bauru 17033-360, SP, Brazil"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9783-6311","authenticated-orcid":false,"given":"Andr\u00e9 Nunes","family":"de Souza","sequence":"additional","affiliation":[{"name":"School of Engineering, S\u00e3o Paulo State University (UNESP), Bauru 17033-360, SP, Brazil"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2025,9,18]]},"reference":[{"key":"ref_1","first-page":"33","article-title":"The effect of thermal stress and transformer materials towards stray gassing formation in uninhibited and inhibited oil","volume":"85","author":"Yong","year":"2023","journal-title":"J. Teknol. (Sci. Eng.)"},{"key":"ref_2","unstructured":"(2019). IEEE Guide for the Interpretation of Gases Generated in Mineral Oil-Immersed Transformers (Standard No. IEEE Std C57.104-2019 (Revision of IEEE Std C57.104-2008))."},{"key":"ref_3","unstructured":"(2015). Mineral Oil-Filled Electrical Equipment in Service: Guidance on the Interpretation of Dissolved and Free Gases Analysis, 3rd ed (Standard No. IEC 60509)."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Dladla, V.M.N., and Thango, B.A. (2025). Fault Classification in Power Transformers via Dissolved Gas Analysis and Machine Learning Algorithms: A Systematic Literature Review. Appl. Sci., 15.","DOI":"10.3390\/app15052395"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"109064","DOI":"10.1016\/j.epsr.2022.109064","article-title":"Conventional methods of dissolved gas analysis using oil-immersed power transformer for fault diagnosis: A review","volume":"216","author":"Ali","year":"2023","journal-title":"Electr. Power Syst. Res."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"e25975","DOI":"10.1016\/j.heliyon.2024.e25975","article-title":"Machine learning based multi-method interpretation to enhance dissolved gas analysis for power transformer fault diagnosis","volume":"10","author":"Suwarno","year":"2024","journal-title":"Heliyon"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Gifalli, A., Bonini Neto, A., de Souza, A.N., de Mello, R.P., Ikeshoji, M.A., Garbelini, E., and Neto, F.T. (2024). Fault Detection and Normal Operating Condition in Power Transformers via Pattern Recognition Artificial Neural Network. Appl. Syst. Innov., 7.","DOI":"10.3390\/asi7030041"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Saravanan, D., Hasan, A., Singh, A., Hannan, M., and Shaw, R.N. (2020, January 2\u20134). Fault Prediction of Transformer Using Machine Learning and DGA. Proceedings of the 2020 IEEE International Conference on Computing, Power and Communication Technologies (GUCON), Greater Noida, India.","DOI":"10.1109\/GUCON48875.2020.9231086"},{"key":"ref_9","unstructured":"Li, Y. (2023). The state of the art in transformer fault diagnosis with artificial intelligence and dissolved gas analysis: A review of the literature. arXiv."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"110647","DOI":"10.1016\/j.ijepes.2025.110647","article-title":"An interpretable machine learning method for fault diagnosis of oil-immersed transformers based on edge inference","volume":"168","author":"Hu","year":"2025","journal-title":"Int. J. Electr. Power Energy Syst."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Jiao, F., Ma, Z., Chen, Q., Zhang, F., and Zhao, D. (2024). A causal reasoning approach for power transformer failure diagnosis. Front. Energy Res., 12.","DOI":"10.3389\/fenrg.2024.1340421"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"52","DOI":"10.1186\/s42162-025-00519-3","article-title":"Transformer fault diagnosis using machine learning: A method combining SHAP feature selection and intelligent optimization of LGBM","volume":"8","author":"Liu","year":"2025","journal-title":"Energy Inform."},{"key":"ref_13","unstructured":"Mahmoodiyan, H., Ahang, M., Abbasi, M., and Najjaran, H. (2025). Feature-weighted MMD-CORAL for domain adaptation in power transformer fault diagnosis. arXiv."},{"key":"ref_14","unstructured":"Saravanan, B., Pasanth Kumar, M.D., and Vengateson, A. (2025). Benchmarking traditional machine learning and deep learning models for fault detection in power transformers. arXiv."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"2718","DOI":"10.1109\/TDEI.2015.005220","article-title":"Stray gassing cases of insulating liquids in HV equipment","volume":"22","year":"2015","journal-title":"IEEE Trans. Dielectr. Electr. Insul."},{"key":"ref_16","first-page":"1420","article-title":"A new distance-weighted k-nearest neighbor classifier","volume":"9","author":"Gou","year":"2012","journal-title":"J. Inf. Compul. Sci."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"120","DOI":"10.1002\/ima.20188","article-title":"Supervised pattern classification based on optimum-path forest","volume":"19","author":"Papa","year":"2009","journal-title":"Int. J. Imaging Syst. Technol."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"169","DOI":"10.1007\/s00521-013-1367-1","article-title":"Cuckoo search: Recent advances and applications","volume":"24","author":"Yang","year":"2014","journal-title":"Neural Comput. Appl."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Salesi, S., and Cosma, G. (2017, January 21\u201323). A novel extended binary cuckoo search algorithm for feature selection. Proceedings of the 2017 2nd International Conference on Knowledge Engineering and Applications (ICKEA), London, UK.","DOI":"10.1109\/ICKEA.2017.8169893"},{"key":"ref_20","first-page":"87","article-title":"An efficient multi-objective cuckoo search algorithm for design optimization","volume":"1","author":"Kaveh","year":"2016","journal-title":"Adv. Comput. Des."},{"key":"ref_21","first-page":"139","article-title":"A Study on Genetic Algorithm and its Applications","volume":"4","author":"Haldurai","year":"2016","journal-title":"Int. J. Comput. Sci. Eng."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Yang, X.-S. (2014). Genetic Algorithms. Nature-Inspired Optimization Algorithms, Elsevier.","DOI":"10.1016\/B978-0-12-416743-8.00005-1"},{"key":"ref_23","unstructured":"Melanie, M. (1998). An Introduction to Genetic Algorithms, MIT Press."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"703","DOI":"10.1109\/JAS.2019.1911447","article-title":"An embedded feature selection method for imbalanced data classification","volume":"6","author":"Liu","year":"2019","journal-title":"IEEE\/CAA J. Autom. Sin."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1109\/57.917529","article-title":"Interpretation of gas-in-oil analysis using new IEC publication 60599 and IEC TC 10 databases","volume":"17","author":"Duval","year":"2001","journal-title":"IEEE Electr. Insul. Mag."},{"key":"ref_26","unstructured":"Li, E. (2020, March 13). Dissolved Gas Data in Transformer Oil: Fault Diagnosis of Power Transformers with Membership Degree. Available online: http:\/\/dx.doi.org\/10.21227\/h8g0-8z59."},{"key":"ref_27","unstructured":"Filho, G.L. (2012). Compara\u00e7\u00e3o Entre os Crit\u00e9rios de Diagn\u00f3sticos por An\u00e1lise Cromatogr\u00e1fica de Gases Dissolvidos em \u00f3leo Isolante de Transformador de Pot\u00eancia. [Master\u2019s Thesis, Universidade de S\u00e3o Paulo]."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"77","DOI":"10.3906\/elk-1704-229","article-title":"Transformer incipient fault diagnosis on the basis of energy-weighted DGA using an artificial neural network","volume":"26","author":"Equbal","year":"2018","journal-title":"Turk. J. Electr. Eng. Comput. Sci."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Soni, R., and Chaudhari, K. (2016, January 3\u20135). An Approach to Diagnose Incipient Faults of Power Transformer Using Dissolved Gas Analysis of Mineral Oil by Ratio Methods Using Fuzzy Logic. Proceedings of the 2016 International Conference on Signal Processing, Communication, Power and Embedded System (SCOPES), Paralakhemundi, India.","DOI":"10.1109\/SCOPES.2016.7955775"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"270","DOI":"10.1177\/1094428112470848","article-title":"Best-Practice Recommendations for Defining, Identifying, and Handling Outliers","volume":"16","author":"Aguinis","year":"2013","journal-title":"Organ. Res. Methods"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"2","DOI":"10.1016\/j.patrec.2013.08.030","article-title":"A comparison between k-Optimum Path Forest and k-Nearest Neighbors supervised classifiers","volume":"39","author":"Souza","year":"2014","journal-title":"Pattern Recognit. Lett."}],"container-title":["Machine Learning and Knowledge Extraction"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2504-4990\/7\/3\/102\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T18:48:27Z","timestamp":1760035707000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2504-4990\/7\/3\/102"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,18]]},"references-count":31,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2025,9]]}},"alternative-id":["make7030102"],"URL":"https:\/\/doi.org\/10.3390\/make7030102","relation":{},"ISSN":["2504-4990"],"issn-type":[{"type":"electronic","value":"2504-4990"}],"subject":[],"published":{"date-parts":[[2025,9,18]]}}}