Mechanical Failures Detection by Vibration Analysis in Rotary Machines Using Wavelet and Artificial Neural Network in the Gera Maranhão Plant.

Érico Fernando da Costa Vale; Antonio Carlos Duarte Ricciotti; Viviane Barrozo da Silva

doi:10.31686/ijier.vol10.iss2.3663

Authors

Érico Fernando da Costa Vale Gerência de planejamento e controle Maranhão https://orcid.org/0000-0001-6924-276X
Antonio Carlos Duarte Ricciotti Federal University of Rondônia https://orcid.org/0000-0002-4986-6601
Viviane Barrozo da Silva Federal University of Rondônia https://orcid.org/0000-0002-1948-1532

DOI:

https://doi.org/10.31686/ijier.vol10.iss2.3663

Keywords:

Vibration analysis, Wavelets, Artificial neural networks, Maintenance

Abstract

This article presents aspects of a tool to assist in predictive maintenance based on vibration analysis in rotating machines using wavelet transform and artificial neural networks. The work analyzed the experimental results of applying a methodology based on the combination of the discrete wavelet transform using a Gaussian window with an artificial neural network for condition monitoring of three-phase induction motors. This approach consisted of simulating faulty and flawless signals using software developed in LabVIEW, their processing, appropriate choice of signals, establishing statistical measures of the chosen signs, and forming the input vectors presented to the artificial neural network. The input vectors are constituted based on statistical measures involving measures of central tendency (mean and centroid), measures of dispersion (RMS value and standard deviation), and a measure of asymmetry (Kurtosis). The most promising configuration was the Multiple Perceptron Layer (MPL) network with four hidden layers containing 256 neurons. Such network showed satisfactory performance for both mechanical failures, with a correct range of around 97%. These results proved to be very effective for detecting mechanical failures, thus being an auxiliary instrument in predictive maintenance.

Downloads

Download data is not yet available.

Author Biographies

Érico Fernando da Costa Vale, Gerência de planejamento e controle Maranhão

Engenheiro Eletricista, Usina Termelétrica Gera Maranhão
Antonio Carlos Duarte Ricciotti, Federal University of Rondônia

Professor, Department of Electrical Engineering
Viviane Barrozo da Silva, Federal University of Rondônia

Professor, Department of Electrical Engineering

References

Filho, G. B. A organização, o Planejamento e o Controle da

Manutenção.1.ed.Ciência Moderna, 2008.

ANHESINE, M., W.,. Uma abordagem sistêmica para diagnósticos em manutenção industrial. Tese de doutorado, apresentado à Escola de Engenharia de São Carlos-USP, São Carlos. 1999.

ABDESH, M.; KHAN, S.; RAHMAN, M. A. A new wavelet-based diagnosis and protection of faults in induction motor drives. In: IEEE. Power Electronics Specialists Conference, PESC 2008. IEEE. 2008. p. 1536–1541. DOI: https://doi.org/10.1109/PESC.2008.4592156

SILVA, K. et al. Haar wavelet-based method for fast fault classification in transmission lines. In: IEEE. Transmission & Distribution Conference and Exposition: Latin America. TDC’06. IEEE/PES. [S.l.], 2006. p. 1–5. DOI: https://doi.org/10.1109/TDCLA.2006.311465

JAWADEKAR, A. et al. Artificial neural network-based induction motor fault classifier using continuous wavelet transform. Syst. Sci. Control Eng. An Open Access J., v. 2, p. 684–690, 2014 DOI: https://doi.org/10.1080/21642583.2014.956266

OLIVEIRA, H. de. Análise de Fourier e Wavelets. [S.l.]: Editora Universitária da UFPE, 2007.

PINTO, S. C. D. Análise de Formas 3D usando Wavelets 1D, 2D e 3D. Tese

(Doutorado) —Universidade de Sao Paulo, 2005.

FANUCCHI, R. Z. A Detecção e a Localização de Faltas de Alta Impedância em Sistemas de Distribuição utilizando Transformadas Wavelets e Redes Neurais Artificiais. 176 p. Tese (Doutorado) — Universidade de São Carlos,

DINIZ, P. S.; SILVA, E. A. da; NETTO, S. L. Processamento Digital de Sinais-

: Projeto e Análise de Sistemas. [S.l.]: Bookman Editora, 2014.

BANDEIRA, G.; ABREU, G.; GIANELLI, R. Vibração e ruído em manutenção preditiva. UNESP, 2010.

SILVA, Derick Henrique de Jesus. Processamento de Sinais para

Monitoramento de Vibrações em Unidades Geradoras Hidrelétricas. UFMG,

Ho, D., Randall, R.B., 2000, Optimisation of bearing diagnostic techniques using simulated and actual bearing fault signals, Mechanical Systems and Signal Processing, 14/5: 763–788. DOI: https://doi.org/10.1006/mssp.2000.1304

SANTOS, F. M. d. C. Identificação de falhas em motores de indução trifásicos usando sistemas inteligentes. Tese (Doutorado) — Universidade de São Paulo, 2013.

MARTINS, J. F.; PIRES, V. F.; PIRES, A. Unsupervised neural-network- based algorithm for na on-line diagnosis of three-phase induction motor stator fault. IEEE Transactions on Industrial Electronics, v. 54, n. 1, p. 259–264, 2007. ISSN 02780046. DOI: https://doi.org/10.1109/TIE.2006.888790

YANG, B.-S. et al. Fault diagnosis of induction motor based on decision trees and adaptive neuro-fuzzy inference. Expert Systems with Applications, Elsevier, v. 36, n. 2, p. 1840–1849,2009. DOI: https://doi.org/10.1016/j.eswa.2007.12.010

HOLANDA, S. M. Aplicação da manutenção preditiva por análise de vibrações em equipamentos de trens urbanos com plano de manutenção proposto. 2016. 7 f. Dissertação (Mestrado em Engenharia Mecânica) – Universidade Federal de Pernambuco, Recife, 2016.

SILVA, Derick Henrique de Jesus. Processamento de Sinais para Monitoramento de Vibrações em Unidades Geradoras Hidrelétricas. UFMG, 2013.Disponível em: <https://www.ppgee.ufmg.br/defesas/1001M.PDF>. Acesso em: 02 julho 2021.

Hansford Sensors, Imbalance, misalignment, looseness: know the difference, UK. 2021. https://www.hansfordsensors.com/blog/2017/02/07/imbalance-misalignment-looseness-know-difference/