Diseño, implementación y validación de herramienta de diagnóstico temprano de motores eléctricos basado en audio.

dc.contributor.advisorCamargo Bareño, Carlos Iván
dc.contributor.authorEscobar Mafla, Lennin Edmundo
dc.contributor.cvlacLEscobarspa
dc.contributor.orcid0000-0002-5676-6019spa
dc.contributor.researchgroupComputación Científicaspa
dc.date.accessioned2023-10-26T02:25:08Z
dc.date.available2023-10-26T02:25:08Z
dc.date.issued2023-10-24
dc.description.abstractEste documento presenta el diseño, implementación y validación de herramienta de diagnostico temprano de motores eléctricos basado en audio para compresores de referencia NC4AV80ALR de la marca SAMSUNG, los cuales se encuentran en neveras. El diseño se basa en un análisis preliminar de la señal acústica emitida por el compresor en campo cercano mediante el uso de un micrófono, con el fin de seleccionar el punto en el espacio que presente las mejores características en pro de la calidad en la toma de las muestras, para esto, se analizan características como el valor RMS, frecuencia de roll-off y el centroide espectral. Como siguiente paso se crea un conjunto de datos de audio que consta de 25 compresores distribuidos equitativamente en 5 clases de las cuales 2 clases pertenecen a compresores que operan dentro de sus parámetros normales y las 3 clases restantes provienen de compresores que presentan fallas en su funcionamiento. Posteriormente se extrae la transformada discreta de Fourier mediante la técnica de windowing, la cual es la característica de la señal, lo que permite entrenar un clasificador random forest y k-nearest neighbors para posteriormente evaluar y validar el rendimiento del sistema de clasificación. La implementación del sistema se realiza usando elementos comerciales y la validación del sistema consiste en cruzar el resultado de la clasificación con los reportes técnicos que ratifican el estado de los compresores en cuestión. (Texto tomado de la fuente)spa
dc.description.abstractThis document presents the design, implementation and validation of an audio based tool for early diagnosis of electric motors used in compressors NC4AV80ALR of SAMSUNG which are found in refrigerators of the same brand. The proposed design consists in a preliminary analysis of the acoustic signal emitted by the compressor in a near field captured using a microphone in order to select the spot with the best characteristics in terms of sample quality. The features taken into account are the RMS value, roll-off frequency and spectral centroid. After the samples were taken we built a dataset with the data of 25 different compressors equally distributed in 5 classes from which 2 of them correspond to compressors running under normal conditions and the 3 remaining came from compressors with malfunctions. We make the fourier transform and with that data we trained some random forests and k-nearest neighbors classifiers and then we evaluate and validate the performance of this training. The system implementation is made using commercially available elements and the validation consists in relating the results from the classification with the technical reports of the compressors that confirm said state.eng
dc.description.degreelevelMaestríaspa
dc.description.degreenameMagíster en Ingeniería - Ingeniería Electrónicaspa
dc.description.methodsSe propone una metodología en el desarrollo de este trabajo.spa
dc.description.researchareaDiagnóstico de fallas en compresores basado en audiospa
dc.format.extentxv, 124 páginasspa
dc.format.mimetypeapplication/pdfspa
dc.identifier.instnameUniversidad Nacional de Colombiaspa
dc.identifier.reponameRepositorio Institucional Universidad Nacional de Colombiaspa
dc.identifier.repourlhttps://repositorio.unal.edu.co/spa
dc.identifier.urihttps://repositorio.unal.edu.co/handle/unal/84834
dc.language.isospaspa
dc.publisherUniversidad Nacional de Colombiaspa
dc.publisher.branchUniversidad Nacional de Colombia - Sede Bogotáspa
dc.publisher.facultyFacultad de Ingenieríaspa
dc.publisher.placeBogotá, Colombiaspa
dc.publisher.programBogotá - Ingeniería - Maestría en Ingeniería - Ingeniería Electrónicaspa
dc.relation.referencesWahyu Caesarendra, Buyung Kosasih, Anh Kiet Tieu, Hongtao Zhu, Craig A.S. Moodie, and Qiang Zhu. Acoustic emission-based condition monitoring methods: Review and application for low speed slew bearing. Mechanical Systems and Signal Processing, 72-73:134 – 159, 2016.spa
dc.relation.referencesT. d. M. Prego, A. A. de Lima, S. L. Netto, and E. A. B. da Silva. Audio anomaly detection on rotating machinery using image signal processing. In 2016 IEEE 7th Latin American Symposium on Circuits Systems (LASCAS), pages 207–210, Feb 2016.spa
dc.relation.referencesPaulo Antonio Delgado-Arredondo, Daniel Morinigo-Sotelo, Roque Alfredo Osornio- Rios, Juan Gabriel Avina-Cervantes, Horacio Rostro-Gonzalez, and Rene de Jesus Romero-Troncoso. Methodology for fault detection in induction motors via sound and vibration signals. Mechanical Systems and Signal Processing, 83:568–589, 2017.spa
dc.relation.referencesAdam Glowacz. Fault diagnosis of single-phase induction motor based on acoustic signals. Mechanical Systems and Signal Processing, 117:65–80, 2019.spa
dc.relation.referencesAdam Glowacz, Witold Glowacz, Zygfryd Glowacz, and Jaroslaw Kozik. Early fault diagnosis of bearing and stator faults of the single-phase induction motor using acoustic signals. Measurement, 113:1 – 9, 2018.spa
dc.relation.referencesPatricia Henriquez, Jesus B. Alonso, Miguel A. Ferrer, and Carlos M. Travieso. Re- view of automatic fault diagnosis systems using audio and vibration signals. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 44(5):642–652, 2014.spa
dc.relation.referencesRam Bihari Sharma and Anand Parey. Condition monitoring of gearbox using experi- mental investigation of acoustic emission technique. Procedia Engineering, 173:1575 – 1579, 2017. Plasticity and Impact Mechanics.spa
dc.relation.referencesKATSUHIKO SHIBATA, ATSUSHI TAKAHASHI, and TAKUYA SHIRAI. Fault diag- nosis of rotating machinery through visualisation of sound signals. Mechanical Systems and Signal Processing, 14(2):229 – 241, 2000.spa
dc.relation.referencesN Tandon and A Choudhury. A review of vibration and acoustic measurement methods for the detection of defects in rolling element bearings. Tribology International, 32(8):469 – 480, 1999.spa
dc.relation.referencesR. Vilela, J. C. Metrolho, and J. C. Cardoso. Machine and industrial monitorization system by analysis of acoustic signatures. In Proceedings of the 12th IEEE Mediterra- nean Electrotechnical Conference (IEEE Cat. No.04CH37521), volume 1, pages 277–279 Vol.1, May 2004.spa
dc.relation.referencesS. K. Yadav, K. Tyagi, B. Shah, and P. K. Kalra. Audio signature-based condition monitoring of internal combustion engine using fft and correlation approach. IEEE Transactions on Instrumentation and Measurement, 60(4):1217–1226, April 2011.spa
dc.relation.referencesPaulo Antonio Delgado-Arredondo, Daniel Morinigo-Sotelo, Roque Alfredo Osornio- Rios, Juan Gabriel Avina-Cervantes, Horacio Rostro-Gonzalez, and Rene de Jesus Romero-Troncoso. Methodology for fault detection in induction motors via sound and vibration signals. Mechanical Systems and Signal Processing, 83:568 – 589, 2017.spa
dc.relation.referencesAdam Glowacz. Acoustic based fault diagnosis of three-phase induction motor. Applied Acoustics, 137:82–89, 2018.spa
dc.relation.referencesAhmad Qurthobi, Rytis Maskeli ̄unas, and Robertas Damaˇseviˇcius. Detection of mecha- nical failures in industrial machines using overlapping acoustic anomalies: A systematic literature review. Sensors, 22(10), 2022.spa
dc.relation.referencesP.J. Tavner. Review of condition monitoring of rotating electrical machines. IET Electric Power Applications, 2:215–247(32), July 2008.spa
dc.relation.referencesXiangwei Liu, Deli Pei, Gabriel Lodewijks, Zhangyan Zhao, and Jie Mei. Acoustic signal based fault detection on belt conveyor idlers using machine learning. Advanced Powder Technology, 31(7):2689–2698, 2020.spa
dc.relation.referencesMd Junayed Hasan, M.M. Manjurul Islam, and Jong-Myon Kim. Acoustic spectral imaging and transfer learning for reliable bearing fault diagnosis under variable speed conditions. Measurement, 138:620–631, 2019.spa
dc.relation.referencesShengnan Tang, Yong Zhu, and Shouqi Yuan. An adaptive deep learning model towards fault diagnosis of hydraulic piston pump using pressure signal. Engineering Failure Analysis, 138:106300, 2022.spa
dc.relation.referencesJiachi Yao, Chao Liu, Keyu Song, Xiaochen Zhang, and Dongxiang Jiang. Fault de- tection of complex planetary gearbox using acoustic signals. Measurement, 178:109428, 2021spa
dc.relation.referencesVamsi Inturi, Sabareesh G R, and Vaibhav Sharma. Integrated vibro-acoustic analysis and empirical mode decomposition for fault diagnosis of gears in a wind turbine. Pro- cedia Structural Integrity, 14:937–944, 2019. SICE 2018 (2nd International Conference on Structural Integrity and Exhibition 2018).spa
dc.relation.referencesAdam Glowacz, Ryszard Tadeusiewicz, Stanislaw Legutko, Wahyu Caesarendra, Muhammad Irfan, Hui Liu, Frantisek Brumercik, Miroslav Gutten, Maciej Sulowicz, Jose Alfonso Antonino Daviu, Thompson Sarkodie-Gyan, Pawel Fracz, Anil Kumar, and Jiawei Xiang. Fault diagnosis of angle grinders and electric impact drills using acoustic signals. Applied Acoustics, 179:108070, 2021.spa
dc.relation.referencesAyhan Altinors, Ferhat Yol, and Orhan Yaman. A sound based method for fault detec- tion with statistical feature extraction in uav motors. Applied Acoustics, 183:108325, 2021.spa
dc.relation.referencesChen Peng, ZhiPeng Li, Minjing Yang, Minrui Fei, and Yulong Wang. An audio-based intelligent fault diagnosis method for belt conveyor rollers in sand carrier. Control Engineering Practice, 105:104650, 2020.spa
dc.relation.referencesB. Rubhini and P. Vanaja Ranjan. Machine condition monitoring using audio signature analysis. In 2017 Fourth International Conference on Signal Processing, Communication and Networking (ICSCN), pages 1–6, 2017.spa
dc.relation.referencesXin Wang, Dongxing Mao, and Xiaodong Li. Bearing fault diagnosis based on vibro- acoustic data fusion and 1d-cnn network. Measurement, 173:108518, 2021.spa
dc.relation.referencesNing Dayong, Sun Changle, Gong Yongjun, Zhang Zengmeng, and Hou Jiaoyi. Extrac- tion of fault component from abnormal sound in diesel engines using acoustic signals. Mechanical Systems and Signal Processing, 75:544–555, 2016.spa
dc.relation.referencesEmin Germen, Murat Basaran, and Mehmet Fidan. Sound based induction motor fault diagnosis using kohonen self-organizing map. Mechanical Systems and Signal Processing, 01 2014.spa
dc.relation.referencesDingcheng Zhang, Edward Stewart, Mani Entezami, Clive Roberts, and Dejie Yu. Inte- lligent acoustic-based fault diagnosis of roller bearings using a deep graph convolutional network. Measurement, 156:107585, 2020.spa
dc.relation.referencesAnand Parey and Amandeep Singh. Gearbox fault diagnosis using acoustic signals, con- tinuous wavelet transform and adaptive neuro-fuzzy inference system. Applied Acous- tics, 147:133–140, 2019. Special Issue on Design and Modelling of Mechanical Systems conference CMSM’2017.spa
dc.relation.referencesMingjin Yang, Wenju Zhou, and Tianxiang Song. Audio-based fault diagnosis for belt conveyor rollers. Neurocomputing, 397:447–456, 2020.spa
dc.relation.referencesNilesh W. Nirwan and Hardik B. Ramani. Condition monitoring and fault detection in roller bearing used in rolling mill by acoustic emission and vibration analysis. Materials Today: Proceedings, 51:344–354, 2022. CMAE’21.spa
dc.relation.referencesKATSUHIKO SHIBATA, ATSUSHI TAKAHASHI, and TAKUYA SHIRAI. Fault diag- nosis of rotating machinery through visualisation of sound signals. Mechanical Systems and Signal Processing, 14(2):229–241, 2000.spa
dc.relation.referencesR. Vilela, J.C. Metrolho, and J.C. Cardoso. Machine and industrial monitorization system by analysis of acoustic signatures. In Proceedings of the 12th IEEE Mediterra- nean Electrotechnical Conference (IEEE Cat. No.04CH37521), volume 1, pages 277–279 Vol.1, 2004.spa
dc.relation.referencesN. BAYDAR and A. BALL. Detection of gear failures via vibration and acoustic signals using wavelet transform. Mechanical Systems and Signal Processing, 17(4):787–804, 2003.spa
dc.relation.referencesMICHAEL L. FUGATE, HOON SOHN, and CHARLES R. FARRAR. Vibration-based damage detection using statistical process control. Mechanical Systems and Signal Pro- cessing, 15(4):707–721, 2001.spa
dc.relation.referencesWenbo Lu, Weikang Jiang, Guoqing Yuan, and Li Yan. A gearbox fault diagnosis scheme based on near-field acoustic holography and spatial distribution features of sound field. Journal of Sound and Vibration, 332(10):2593–2610, 2013.spa
dc.relation.referencesAndrew K.S. Jardine, Daming Lin, and Dragan Banjevic. A review on machinery diagnostics and prognostics implementing condition-based maintenance. Mechanical Systems and Signal Processing, 20(7):1483 – 1510, 2006.spa
dc.relation.referencesAleksi Sepp ̈anen et al. Utilizing acoustic measurements in equipment condition moni- toring. 2016.spa
dc.relation.referencesF. Keddar, A. Kaddour, and A. Maache. Analysis of the sound field emitted by a doubly salient switched reluctance motor using acoustic intensity measurement. In IECON 2006 - 32nd Annual Conference on IEEE Industrial Electronics, pages 1453–1458, Nov 2006.spa
dc.relation.referencesXiang Duanqi, Wang Zheng, and Chen Jinjing. Acoustic design of an anechoic chamber. Applied Acoustics, 29(2):139 – 149, 1990.spa
dc.relation.referencesRuonan Liu, Boyuan Yang, Enrico Zio, and Xuefeng Chen. Artificial intelligence for fault diagnosis of rotating machinery: A review. Mechanical Systems and Signal Processing, 108:33 – 47, 2018.spa
dc.relation.referencesBarbara Kitchenham, O. Pearl Brereton, David Budgen, Mark Turner, John Bailey, and Stephen Linkman. Systematic literature reviews in software engineering – a systema- tic literature review. Information and Software Technology, 51(1):7–15, 2009. Special Section - Most Cited Articles in 2002 and Regular Research Papers.spa
dc.relation.referencesIan Sutton. Chapter 2 - maintenance. In Ian Sutton, editor, Plant Design and Operations (Second Edition), pages 25 – 45. Gulf Professional Publishing, second edition edition, 2017.spa
dc.relation.referencesJohn Semmlow. Chapter 2 - signal analysis in the time domain. In John Semmlow, editor, Circuits, Signals and Systems for Bioengineers (Third Edition), Biomedical En- gineering, pages 51 – 110. Academic Press, third edition edition, 2018.spa
dc.relation.referencesNúñez-Pérez Ricardo Francisco. The tendency of the crest factor helps detect nas- cent events; electronic circuit, software and applications to signals from diverse fields. Ingeniería Investigación y Tecnología, 15(1):63 – 81, 2014.spa
dc.relation.referencesJohn Semmlow. Chapter 3 - signal analysis in the frequency domain: The fourier series and the fourier transformation. In John Semmlow, editor, Circuits, Signals and Systems for Bioengineers (Third Edition), Biomedical Engineering, pages 111 – 168. Academic Press, third edition edition, 2018.spa
dc.relation.referencesA.V. Oppenheim, A.S. Willsky, S.H. Nawab, and G.M. Hern ́andez. Se ̃nales y sistemas. Pearson Educaci ́on, 1998.spa
dc.relation.referencesWim van Drongelen. Chapter 21 - wavelet analysis: Time domain properties. In Wim van Drongelen, editor, Signal Processing for Neuroscientists (Second Edition), pages 401 – 423. Academic Press, second edition edition, 2018.spa
dc.relation.referencesAmani Yahyaoui’s, Imene Yahyaoui, and Nejat Yumu ̧sak. 13 - machine learning techni- ques for data classification. In Imene Yahyaoui, editor, Advances in Renewable Energies and Power Technologies, pages 441 – 450. Elsevier, 2018.spa
dc.relation.referencesMatthias Mauch and Simon Dixon. Pyin: A fundamental frequency estimator using pro- babilistic threshold distributions. In 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 659–663, 2014.spa
dc.relation.referencesMarshall Long. 7 - sound and solid surfaces. In Marshall Long, editor, Architectural Acoustics (Second Edition), pages 259–312. Academic Press, Boston, second edition edition, 2014.spa
dc.relation.referencesLeo Breiman. Random forests. Machine Learning, 45(1):5–32, 2001.spa
dc.relation.referencesF. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blon- del, P. Prettenhofer, R. Weiss, V. Dubourg, J. Vanderplas, A. Passos, D. Cournapeau, M. Brucher, M. Perrot, and E. Duchesnay. Scikit-learn: Machine learning in Python. Journal of Machine Learning Research, 12:2825–2830, 2011.spa
dc.relation.referencesMarco Jeub, Christian Herglotz, Christoph Nelke, Christophe Beaugeant, and Peter Vary. Noise reduction for dual-microphone mobile phones exploiting power level diffe- rences. In 2012 IEEE International Conference on Acoustics, Speech and Signal Pro- cessing (ICASSP), pages 1693–1696, 2012.spa
dc.rights.accessrightsinfo:eu-repo/semantics/openAccessspa
dc.rights.licenseAtribución-NoComercial-SinDerivadas 4.0 Internacionalspa
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/4.0/spa
dc.subject.ddc000 - Ciencias de la computación, información y obras generales::005 - Programación, programas, datos de computaciónspa
dc.subject.lembElectrodomésticosspa
dc.subject.lembHousehold appliances, electriceng
dc.subject.lembElectricidad-aparatos e instrumentosspa
dc.subject.lembElectric apparatus and applianceseng
dc.subject.lembMotores eléctricosspa
dc.subject.lembElectric motorseng
dc.subject.proposalFallaspa
dc.subject.proposalDiagnósticospa
dc.subject.proposalacústicospa
dc.subject.proposalFaulteng
dc.subject.proposalDiagnosiseng
dc.subject.proposalAcousticeng
dc.subject.proposalAudioeng
dc.titleDiseño, implementación y validación de herramienta de diagnóstico temprano de motores eléctricos basado en audio.spa
dc.title.translatedDesign, implementation, and validation of an early diagnosis tool for electric motors based on audio.eng
dc.typeTrabajo de grado - Maestríaspa
dc.type.coarhttp://purl.org/coar/resource_type/c_bdccspa
dc.type.coarversionhttp://purl.org/coar/version/c_ab4af688f83e57aaspa
dc.type.contentTextspa
dc.type.driverinfo:eu-repo/semantics/masterThesisspa
dc.type.redcolhttp://purl.org/redcol/resource_type/TMspa
dc.type.versioninfo:eu-repo/semantics/acceptedVersionspa
dcterms.audience.professionaldevelopmentEstudiantesspa
dcterms.audience.professionaldevelopmentInvestigadoresspa
dcterms.audience.professionaldevelopmentMaestrosspa
oaire.accessrightshttp://purl.org/coar/access_right/c_abf2spa
oaire.awardtitleDiseño, implementación y validación de herramienta de diagnóstico temprano de motores eléctricos basado en audiospa
oaire.fundernameLennin Edmundo Escobar Maflaspa

Archivos

Bloque original

Mostrando 1 - 1 de 1
Cargando...
Miniatura
Nombre:
1085254913.2023.pdf
Tamaño:
14.65 MB
Formato:
Adobe Portable Document Format
Descripción:
Tesis de Maestría en Ingeniería - Ingeniería Electrónica

Bloque de licencias

Mostrando 1 - 1 de 1
Cargando...
Miniatura
Nombre:
license.txt
Tamaño:
5.74 KB
Formato:
Item-specific license agreed upon to submission
Descripción: