Combining maximum likelihood estimation and LSTM neural network to forecast reliability distributions: a study based on real data from the sugar-energy sector



Reliability, RCM, engineering, Maintenance, MLE, maximum likelihood estimation, neural network, KERAS, tensorflow, LSTM, ASSET, industry, management


The recent advances in reliability engineering and assets management allow industries to use advanced mathematical and statistical techniques to improve their maintenance strategies. Conversely, many of these methods requires the previous knowledge of the failure history for the assets, which are not always available. This study shows that is possible to support maintenance management decisions providing the distributions for assets with known and unknown failures history. The approach combines maximum likelihood estimation with a LSTM neural network to find and predict optimal reliability and failure distributions for data actual assets data and failures history. It is shown as an efficient and probably useful approach for practical business situations in the results section.


Download data is not yet available.

Author Biographies

Guilherme Hering Scavariello, Faculdade de Ciências Aplicadas da UNICAMP - Universidade de Campinas. São Paulo, Brasi

Possui graduação em Engenharia de Manufatura pela UNICAMP (2015) e MBA em Gerenciamento de Projetos pela Fundação Getúlio Vargas (2017). Atualmente exerce a função de engenheiro de manutenção sênior no setor sucroenergético e cursa o mestrado no programa de Engenharia de Produção e Manufatura, na área de Pesquisa Operacional, da UNICAMP - Universidade Estadual de Campinas. Lattes:

Ailson Renan Santos Picanço, ITA - UNIFESP. São Paulo, Brasil

Graduado em Engenharia de Produção pela UEPA, Mestre em Engenharia de Produção e de Manufatura, na área de Pesquisa Operacional, pela Universidade Estadual de Campinas e Doutor em Pesquisa Operacional pelo Programa ITA/Unifesp. Possui experiência em modelagem matemática, métodos quantitativos de apoio à decisão, programação linear e programação inteira-mista. Desenvolve pesquisas na área de engenharia de confiabilidade, simulação de eventos discretos, modelagem matemática e Lean Manufacturing. Lattes:

Cristiano Torezzan, Faculdade de Ciências Aplicadas da UNICAMP - Universidade de Campinas.

Doutor em Matemática Aplicada pela Unicamp e atua como docente na Faculdade de Ciências Aplicadas da mesma Universidade. É membro fundador do Centro de Pesquisa Operacional da Unicamp e seus temas de pesquisa concentram-se nas áreas de Pesquisa Operacional e Teoria de Informação, com ênfase em modelagem matemática, análise de dados, apoio à decisão multicritério e métodos matemáticos para inteligência artificial. Lattes:


M. Lopes and R. Martins, “Mapping the impacts of industry 4.0 on performance measurement systems,” IEEE Latin America Transactions, vol. 1000, no. 4807, pp. 1912–1923, 2021.

M. Rodrigues and K. Hatakeyama, “Analysis of the fall of tpm in companies,” Journal of Materials Processing Technology, vol. 179, p. 276–279, 10 2006.

K.-A. Nguyen, P. Do, and A. Grall, “Joint predictive maintenance and inventory strategy for multi-component systems using birnbaum’s structural importance,” Reliability Engineering System Safety, vol. 168, pp. 249–261, 2017. Maintenance Modelling.

E. Ruschel, E. A. P. Santos, and E. de Freitas Rocha Loures, “Industrial maintenance decision-making: A systematic literature review,” Journal of Manufacturing Systems, vol. 45, pp. 180–194, 2017.

G. Gupta and R. Mishra, “A swot analysis of reliability centered maintenance framework,” Journal of Quality in Maintenance Engineering, vol. 22, pp. 130–145, 05 2016.

J. Igba, K. Alemzadeh, I. Anyanwu-Ebo, P. Gibbons, and J. Friis, “A systems approach towards reliability-centred maintenance (rcm) of wind turbines,” Procedia Computer Science, vol. 16, pp. 814–823, 2013. 2013 Conference on Systems Engineering Research.

J. Izquierdo, A. C. Márquez, J. Uribetxebarria, and A. Erguido, “On the importance of assessing the operational context impact on maintenance management for life cycle cost of wind energy projects,” Renewable Energy, vol. 153, pp. 1100–1110, 2020.

M. Abbas and M. Shafiee, “An overview of maintenance management strategies for corroded steel structures in extreme marine environments,” Marine Structures, vol. 71, p. 102718, 2020.

A. Dhar and V. Minin, “Maximum likelihood phylogenetic inference,” Encyclopedia of Evolutionary Biology, 12 2016.

E. A. Mohammed, C. Naugler, and B. H. Far, “Chapter 32 - emerging business intelligence framework for a clinical laboratory through big data analytics,” in Emerging Trends in Computational Biology, Bioinformatics, and Systems Biology, pp. 577–602, Elsevier Inc, 2015.

NIST/SEMATECH, e-Handbook of Statistical Methods, 2013.

M. Abbas and M. Shafiee, “An overview of maintenance management strategies for corroded steel structures in extreme marine environments,” Marine Structures, vol. 71, 5 2020.

M. Paolanti, L. Romeo, A. Felicetti, A. Mancini, E. Frontoni, and J. Loncarski, “Machine learning approach for predictive maintenance in industry 4.0,” Institute of Electrical and Electronics Engineers Inc., 8 2018.

G. S. Sampaio, A. R. de Aguiar Vallim Filho, L. S. da Silva, and L. A. da Silva, “Prediction of motor failure time using an artificial neural network,” Sensors, vol. 19, p. 4342, Oct. 2019.

D. Chan and J. Mo, “Life cycle reliability and maintenance analyses of wind turbines,” Energy Procedia, vol. 110, pp. 328–333, 2017. 1st International Conference on Energy and Power, ICEP2016, 14-16 December 2016, RMIT University, Melbourne, Australia.

P. Tchakoua, R. Wamkeue, M. Ouhrouche, F. Hasnaoui, T. A. Theu bou Tameghe, and G. Ekemb, “Wind turbine condition monitoring: State-of-the-art review, new trends, and future challenges,” Energies, vol. 7, pp. 2595–2630, 04 2014.

M. Wiseman, “Real meaning of the six rcm curves.” https://www., 2011.

S. Hochreiter and J. Schmidhuber, “Long short-term memory,” Neural computation, vol. 9, pp. 1735–80, 12 1997.

K. Schenkelberg, U. Seidenberg, and F. Ansari, “Analyzing the impact of maintenance on profitability using dynamic bayesian networks,” Procedia CIRP, vol. 88, pp. 42–47, 2020.

J. Kang and C. G. Soares, “An opportunistic maintenance policy for offshore wind farms,” Ocean Engineering, vol. 216, p. 108075, Nov. 2020.

E. Amrina, I. Kamil, and D. Aridharma, “Fuzzy multi criteria approach for sustainable maintenance performance evaluation in cement industry,” Procedia Manufacturing, vol. 43, pp. 674–681, 2020.

A. Syamsundar, V. Naikan, and S. Wu, “Estimating maintenance effecti veness of a repairable system under time-based preventive maintenance,” Computers & Industrial Engineering, vol. 156, p. 107278, June 2021.

M. H. Nili, H. Taghaddos, and B. Zahraie, “Integrating discrete event simulation and genetic algorithm optimization for bridge maintenance planning,” Automation in Construction, vol. 122, p. 103513, Feb. 2021.

R. Mena, P. Viveros, E. Zio, and S. Campos, “An optimization fra mework for opportunistic planning of preventive maintenance activities,” Reliability Engineering & System Safety, vol. 215, p. 107801, Nov. 2021

J. Wang and Y. Miao, “Optimal preventive maintenance policy of the balanced system under the semi-markov model,” Reliability Engineering & System Safety, vol. 213, p. 107690, Sept. 2021.

O. Yorkinov, “Multioutput regression example with keras lstm network in python.” multi-output-regression-example-with_24.html, 2019.

E. Paiva, A. Paim, and N. Ebecken, “Convolutional neural networks and long short-term memory networks for textual classification of information access requests,” IEEE Latin America Transactions, 2021.

S. Sugiyam, Human Behavior and Another Kind in Consciousness. IGI Global, 2019.

J. Schmidhuber, “Deep learning in neural networks: an overview,” Neural Netw, vol. 61, pp. 85–117, Jan 2015.

M. Reid, “Reliability - a python library for reliability engineering.” https: //, 2020.

G. Scavariello, “Repositório: Combinação da estimativa por máxima verossimilhança com uma rede neural profunda.” GitLab Project ID: 25750333, 2021.

G. Singh Jamnal, A Cognitive IoE (Internet of Everything) Approach to Ambient-Intelligent Smart Space. PhD thesis, 2019



How to Cite

Scavariello, G. H., Picanço, A. R. S., & Torezzan, C. (2021). Combining maximum likelihood estimation and LSTM neural network to forecast reliability distributions: a study based on real data from the sugar-energy sector. IEEE Latin America Transactions, 100(XXX). Retrieved from