Please use this identifier to cite or link to this item: http://repositorio.ugto.mx/handle/20.500.12059/10213
Full metadata record
DC FieldValueLanguage
dc.rights.licensehttp://creativecommons.org/licenses/by-nc-nd/4.0es_MX
dc.contributorDAVID CAMARENA MARTINEZes_MX
dc.creatorDANIEL ALEJANDRO ZAMBRANO ROMÁNes_MX
dc.date.accessioned2023-12-04T19:51:11Z-
dc.date.available2023-12-04T19:51:11Z-
dc.date.issued2023-10-
dc.identifier.urihttp://repositorio.ugto.mx/handle/20.500.12059/10213-
dc.language.isoengen
dc.publisherUniversidad de Guanajuatoes_MX
dc.rightsinfo:eu-repo/semantics/openAccesses_MX
dc.subject.classificationCIS- Maestría en Ingeniería Eléctrica (Instrumentación y Sistemas Digitales)es_MX
dc.titleShort circuit detection in electrical transformers through statistical analysis of vibration signals in the time and frequency domainsen
dc.typeinfo:eu-repo/semantics/masterThesises_MX
dc.creator.idinfo:eu-repo/dai/mx/cvu/1161100es_MX
dc.subject.ctiinfo:eu-repo/classification/cti/7es_MX
dc.subject.ctiinfo:eu-repo/classification/cti/33es_MX
dc.subject.ctiinfo:eu-repo/classification/cti/3306es_MX
dc.subject.keywordsVibration signalsen
dc.subject.keywordsElectric Transformersen
dc.subject.keywordsMachine learningen
dc.subject.keywordsStatistic analysisen
dc.subject.keywordsClassificationen
dc.subject.keywordsShort circuiten
dc.subject.keywordsSeñales de vibraciónes_MX
dc.subject.keywordsTransformadores eléctricoses_MX
dc.subject.keywordsAprendizaje automáticoes_MX
dc.subject.keywordsAnálisis estadísticoes_MX
dc.subject.keywordsClasificaciónes_MX
dc.subject.keywordsCortocircuitoes_MX
dc.contributor.idinfo:eu-repo/dai/mx/cvu/329800es_MX
dc.contributor.roledirectores_MX
dc.type.versioninfo:eu-repo/semantics/publishedVersiones_MX
dc.contributor.twoARTURO GARCIA PEREZes_MX
dc.contributor.idtwoinfo:eu-repo/dai/mx/cvu/64698es_MX
dc.contributor.roletwodirectores_MX
dc.description.abstractEnglishElectrical transformers are essential elements in industrial processes where the reliability and life span of these machines can be significantly improved by modeling a diagnosis strategy to monitor the working conditions in these devices. The short circuit turns (SCTs) in the windings significantly contribute to damage in electrical transformers; therefore, early detection during the initial stages is vital to prevent more extensive deterioration and schedule the appropriate maintenance. This work proposes a methodology based on the vibration signals analysis in the time and frequency domain to detect and classify a healthy state and several levels of SCTs. For both studies, the proposal consists of several steps. Starting with signal processing of the steady state, decimation, and computing of the Fast Fourier Transform (FFT) in the frequency domain, and the use of the raw steady state signal in the time domain. Followed by the extraction of statistical parameters. Subsequently, two techniques are used to select and reduce the features and keep those with the highest quality to distinguish the damage severity. Finally, three machine learning algorithms are trained and validated to classify the conditions under test. A comparative examination is made with the classification results achieved in each domain after applying the methodology to ensure a feasible and satisfactory assessment of the operating conditions of the transformer. Each step of the procedure was developed using mathematical software, and the results achieved show the effectiveness of this proposal in precisely identifying and classifying the severity of short circuit damage in the windings with the addition of low computational cost and fast processing time.en
Appears in Collections:Maestría en Ingeniería Eléctrica (Instrumentación y Sistemas Digitales)

Files in This Item:
File Description SizeFormat 
DANIEL ALEJANDRO ZAMBRANO ROMÁN_Tesis24.pdf6.16 MBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.