Bayesian Regularizers of Artificial Neural Networks applied to the reliability forecast of internal combustion machines in the short-term

Ítalo Rodrigo Soares Silva; Manoel Henrique Reis  Nascimento; Milton Fonseca  Júnior; Ricardo Silva  Parente; Paulo Oliveira Siqueira  Júnior; Jandecy Cabral  Leite

doi:10.31686/ijier.vol9.iss5.3111

Authors

Ítalo Rodrigo Soares Silva

Institute of Technology and Education Galileo da Amazônia - ITEGAM

https://orcid.org/0000-0002-2827-1078
Manoel Henrique Reis Nascimento

Institute of Technology and Education Galileo da Amazônia - ITEGAM

http://orcid.org/0000-0003-4688-6751
Milton Fonseca Júnior

Institute of Technology and Education Galileo da Amazônia - ITEGAM

http://orcid.org/0000-0001-6001-3098
Ricardo Silva Parente

Institute of Technology and Education Galileo da Amazônia - ITEGAM

http://orcid.org/0000-0003-3096-9069
Paulo Oliveira Siqueira Júnior

Institute of Technology and Education Galileo da Amazônia - ITEGAM

http://orcid.org/0000-0001-8071-3972
Jandecy Cabral Leite

Institute of Technology and Education Galileo da Amazônia - ITEGAM

http://orcid.org/0000-0002-1337-3549

DOI:

https://doi.org/10.31686/ijier.vol9.iss5.3111

Keywords:

Reliability, RNA, Bayesian Regularizers, UTE

Abstract

Predictive as well as preventive maintenance are tools of maintenance programs that aim to increase or maintain the life expectancy of an equipment through computational techniques and tools. Bearing in mind that the power generation industry has a high maintenance rate with machines and / or electric generators stopped, this research aims to develop a computational model for predicting the Reliability Key Performance Indicator (KPI) to identify how available the equipment will be in a time span of 22 days, for this the methodology to be used will be based on analyzes and tests of artificial neural network (ANN) architectures using the Bayesian Regularizers training algorithm, alternating the transfer functions in the layers hidden to find the best state of convergence and the minimum Root Mean Square Error (RMSE) value calculated between the real and simulated outputs. According to the results obtained by the training, validation and test steps, the algorithm presented a RMSE rate of 0.0000104202 and a 99.9% correlation between the real and simulated values, thus the model is able to identify which machine will have the greatest efficiency and less efficiency within the defined time span.

Author Biographies

Ítalo Rodrigo Soares Silva, Institute of Technology and Education Galileo da Amazônia - ITEGAM

Student of the Graduate Program in Engineering, Process, Systems and Environmental Management
Manoel Henrique Reis Nascimento, Institute of Technology and Education Galileo da Amazônia - ITEGAM

PhD in Electrical Engineering from the Graduate Program in Engineering, Process, Systems and Environmental Management
Milton Fonseca Júnior, Institute of Technology and Education Galileo da Amazônia - ITEGAM

PhD in Electrical Engineering from the Graduate Program in Engineering, Process, Systems and Environmental Management
Ricardo Silva Parente, Institute of Technology and Education Galileo da Amazônia - ITEGAM

Student of the Graduate Program in Engineering, Process, Systems and Environmental Management
Paulo Oliveira Siqueira Júnior, Institute of Technology and Education Galileo da Amazônia - ITEGAM

Student of the Graduate Program in Engineering, Process, Systems and Environmental Management
Jandecy Cabral Leite, Institute of Technology and Education Galileo da Amazônia - ITEGAM

PhD in Electrical Engineering from the Graduate Program in Engineering, Process, Systems and Environmental Management

References

ABDULRAHMAN, Shaymaa Adnan et al. Comparative study for 8 computational intelligence algorithms for human identification. Computer Science Review, v. 36, p. 100237, 2020. DOI: https://doi.org/10.1016/j.cosrev.2020.100237

AGNESE, Marco Antônio Dall. Análise da confiabilidade da manutenção em tratores de uma empresa de produção agrícola. 2020.

ARABI BULAGHI, Zohre et al. World competitive contest-based artificial neural network: A new class-specific method for classification of clinical and biological datasets. 2020. DOI: https://doi.org/10.1016/j.ygeno.2020.09.047

ARUNTHAVANATHAN, Rajeevan et al. Fault detection and diagnosis in process system using artificial intelligence-based cognitive technique. Computers & Chemical Engineering, v. 134, p. 106697, 2020. DOI: https://doi.org/10.1016/j.compchemeng.2019.106697

ASSOCIAÇÃO BRASILEIRA DE NORMAS TÉCNICAS (ABNT). NBR 5462: confiabilidade e mantenabilidade - terminologia. Rio de Janeiro, 1994.

AYVAZ, Serkan; ALPAY, Koray. Predictive maintenance system for production lines in manufacturing: A machine learning approach using IoT data in real-time. Expert Systems with Applications, v. 173, p. 114598, 2021. DOI: https://doi.org/10.1016/j.eswa.2021.114598

BAI, Bin et al. Fault data screening and failure rate prediction framework-based bathtub curve on industrial robots. Industrial Robot: the international journal of robotics research and application, 2020. DOI: https://doi.org/10.1108/IR-02-2020-0031

BARBOSA, Douglas AM; FERREIRA, Vitor H. Inferência Bayesiana Aplicada a MLPs para Previsão Probabilística de Carga Semanal. Simpósio Brasileiro de Sistemas Elétricos-SBSE, v. 1, n. 1, 2020.

BAROROH, Dawi Karomati; CHU, Chih-Hsing; WANG, Lihui. Systematic literature review on augmented reality in smart manufacturing: Collaboration between human and computational intelligence. Journal of Manufacturing Systems, 2020. DOI: https://doi.org/10.1016/j.jmsy.2020.10.017

CABEZA, R. Torres et al. Faults Diagnostic using Hopfield Artificial Neural Network in front of Incomplete Data. Journal of Engineering and Technology for Industrial Applications-JETIA, v. 4, n. 13, p. 6, 2018. DOI: https://doi.org/10.5935/2447-0228.20180011

CARDOSO, Diogo Emanuel Da Rocha. Aplicação de conceitos de manutenção preditiva com aplicação de ferramentas de Inteligência Artificial. 2020.

CHEN, Xiang et al. On the role of crack tip creep deformation in hot compressive dwell fatigue crack growth acceleration in aluminum and nickel engine alloys. International Journal of Fatigue, v. 145, p. 106082, 2021. DOI: https://doi.org/10.1016/j.ijfatigue.2020.106082

CHINI, Christopher M.; LOGAN, Lauren H.; STILLWELL, Ashlynn S. Grey water footprints of US thermoelectric power plants from 2010–2016. Advances in Water Resources, v. 145, p. 103733, 2020. DOI: https://doi.org/10.1016/j.advwatres.2020.103733

CORRÊA, Rafaela Gomide. Estudo numérico do escoamento de ar em um motor de combustão interna. 2020.

EL-ADAWY, Mohammed et al. Stereoscopic particle image velocimetry for engine flow measurements: Principles and applications. Alexandria Engineering Journal, v. 60, n. 3, p. 3327-3344, 2021. DOI: https://doi.org/10.1016/j.aej.2021.01.060

FERREIRA, Vitor Hugo; DE SOUZA, Julio Cesar Stacchini; DO COUTTO FILHO, Milton Brown. Inferência Bayesiana Aplicada ao Desenvolvimento de Modelos Neurais para Tratamento de Alarmes em Subestações, 2020.

FONSECA-JUNIOR, M. et al. Programa de gestión de mantenimiento a través de la implementación de herramientas predictivas y de TPM como contribución a la mejora de la eficiencia energética en plantas termoeléctricas. Dyna, v. 82, n. 194, p. 139-149, 2015.

HAN, Xiao et al. Remaining useful life prediction and predictive maintenance strategies for multi-state manufacturing systems considering functional dependence. Reliability Engineering & System Safety, v. 210, p. 107560, 2021. DOI: https://doi.org/10.1016/j.ress.2021.107560

Koçak, Y., & Üstündağ Şiray, G. New activation functions for single layer feedforward neural network. Expert Systems with Applications, 164, 113977. doi:10.1016/j.eswa.2020.113977. 2021. DOI: https://doi.org/10.1016/j.eswa.2020.113977

LEOCÁDIO, Caio Monteiro; FERREIRA, Vitor Hugo. Inferência Bayesiana no desenvolvimento de previsores neurais de vazão diária utilizando informações de precipitação. Journal of the Brazilian Neural Network Society, v. 10, n. 3, p. 157-165, 2012. DOI: https://doi.org/10.21528/LNLM-vol10-no3-art2

LU, Xue-Qin et al. Metaheuristics for homogeneous and heterogeneous machine utilization planning under reliability-centered maintenance. Computers & Industrial Engineering, v. 151, p. 106934, 2021. DOI: https://doi.org/10.1016/j.cie.2020.106934

LUGHOFER, Edwin; SAYED-MOUCHAWEH, Moamar. Predictive maintenance in dynamic systems: advanced methods, decision support tools and real-world applications. Springer, 2019. DOI: https://doi.org/10.1007/978-3-030-05645-2

MANHERTZ, Gabor; BERECZKY, Akos. STFT spectrogram based hybrid evaluation method for rotating machine transient vibration analysis. Mechanical Systems and Signal Processing, v. 154, p. 107583, 2021. DOI: https://doi.org/10.1016/j.ymssp.2020.107583

MEIßNER, Christian et al. Investigation on wall and gas temperatures inside a swirled oxy-fuel combustion chamber using thermographic phosphors, O2 rotational and vibrational CARS. Fuel, v. 289, p. 119787, 2021. DOI: https://doi.org/10.1016/j.fuel.2020.119787

MORO, Giancarlo Dal. Efficient Joint Analysis of Surface Waves and Introduction to Vibration Analysis: Beyond the Clichés. Springer Nature, 2020.

RIGHETTO, Sophia Boing et al. Manutenção Preditiva 4.0: Conceito, Arquitetura e Estratégias de Implementação. 2020.

ROCHA, Márcio Andrade et al. Aplicação da análise de vibração na determinação do atraso de ignição em um motor de combustão interna por compressão. Brazilian Journal of Development, v. 6, n. 12, p. 99947-99952, 2020. DOI: https://doi.org/10.34117/bjdv6n12-472

RUIZ-HERNÁNDEZ, Diego; PINAR-PÉREZ, Jesús M.; DELGADO-GÓMEZ, David. Multi-machine preventive maintenance scheduling with imperfect interventions: A restless bandit approach. Computers & Operations Research, v. 119, p. 104927, 2020. DOI: https://doi.org/10.1016/j.cor.2020.104927

SALLES, Gisele Maria de Oliveira et al. Estimação de intervalos de tempo ótimos para a inspeção e manutenção de escovas em unidades geradoras da copel. 2020. Dissertação de Mestrado. Universidade Tecnológica Federal do Paraná.

SÁNCHEZ, D. et al. Experimental enhancement of a CO2 transcritical refrigerating plant including thermoelectric subcooling. International Journal of Refrigeration, v. 120, p. 178-187, 2020. DOI: https://doi.org/10.1016/j.ijrefrig.2020.08.031

SCHWENDEMANN, Sebastian; AMJAD, Zubair; SIKORA, Axel. A survey of machine-learning techniques for condition monitoring and predictive maintenance of bearings in grinding machines. Computers in Industry, v. 125, p. 103380, 2021. DOI: https://doi.org/10.1016/j.compind.2020.103380

SILVA, Jean da Silva de Abreu et al. PROPOSTA DE IMPLANTAÇÃO DE SISTEMA DE PROTEÇÃO CONTRA POTENCIAL DE FALHA DO MOTOR À DIESEL (DISPARO DO MOTOR). ITEGAM-JETIA, v. 5, n. 19, p. 06-11, 2019.

SOLTANALI, Hamzeh et al. A comparative study of statistical and soft computing techniques for reliability prediction of automotive manufacturing. Applied Soft Computing, v. 98, p. 106738, 2021. DOI: https://doi.org/10.1016/j.asoc.2020.106738

SOUZA, Arthur Gabriel. REDESIGN DE MÁQUINA EMBALADORA TERMOENCOLHIVEL COM BASE NA METODOLOGIA TOOLBOX PARA INDUSTRIA 4.0. Engenharia de Produção-Pedra Branca, 2020.

TIAN, Hua; LIU, Peng; SHU, Gequn. Challenges and opportunities of Rankine cycle for waste heat recovery from internal combustion engine. Progress in Energy and Combustion Science, v. 84, p. 100906, 2021. DOI: https://doi.org/10.1016/j.pecs.2021.100906

YU, Xinnan; FENG, Zhipeng; LIANG, Ming. Analytical vibration signal model and signature analysis in resonance region for planetary gearbox fault diagnosis. Journal of Sound and Vibration, v. 498, p. 115962, 202. DOI: https://doi.org/10.1016/j.jsv.2021.115962

ZINGONI, Alphose. Use of symmetry groups for generation of complex space grids and group-theoretic vibration analysis of triple-layer grids. Engineering Structures, v. 223, p. 111177, 2020. DOI: https://doi.org/10.1016/j.engstruct.2020.111177

ZOU, Guang et al. Fatigue inspection and maintenance optimization: A comparison of information value, life cycle cost and reliability based approaches. Ocean Engineering, v. 220, p. 108286, 2021. DOI: https://doi.org/10.1016/j.oceaneng.2020.108286

Submission

Share

Bayesian Regularizers of Artificial Neural Networks applied to the reliability forecast of internal combustion machines in the short-term

Authors

Ítalo Rodrigo Soares Silva

Manoel Henrique Reis Nascimento

Milton Fonseca Júnior

Ricardo Silva Parente

Paulo Oliveira Siqueira Júnior

Jandecy Cabral Leite

DOI:

Keywords:

Abstract

Author Biographies

Ítalo Rodrigo Soares Silva, Institute of Technology and Education Galileo da Amazônia - ITEGAM

Manoel Henrique Reis Nascimento, Institute of Technology and Education Galileo da Amazônia - ITEGAM

Milton Fonseca Júnior, Institute of Technology and Education Galileo da Amazônia - ITEGAM

Ricardo Silva Parente, Institute of Technology and Education Galileo da Amazônia - ITEGAM

Paulo Oliveira Siqueira Júnior, Institute of Technology and Education Galileo da Amazônia - ITEGAM

Jandecy Cabral Leite, Institute of Technology and Education Galileo da Amazônia - ITEGAM

References

Downloads

Published

Issue

Section

License

How to Cite

Most read articles by the same author(s)