Preventive maintenance optimization using a Hybrid Multi-Objective Evolutionary Algorithm

##plugins.themes.bootstrap3.article.main##

##plugins.themes.bootstrap3.article.sidebar##

Published Jul 5, 2016
Aitor Goti Ana I. Sanchez

Abstract

This paper is focused on the problem of preventive maintenance optimization in a manufacturing environment, to determine the optimal preventive maintenance frequencies for equipment under cost and profit criteria, considering production, quality and maintenance aspects. The paper is based on a previously developed maintenance model, to execute a benefit and cost optimization process using a Hybrid Multi-Objective Evolutionary Algorithm (Hybrid MOEA) that combines a global search method with a local one. The hybrid algorithm combines the capabilities of both worlds, using a global search technique to effectively explore wide parameter spaces, deal properly with function non-linearities and avoid falling into local optimal solutions, and combining it with the capacities of local search methods to efficiently converge into local optimal solutions. The hybridization is done according to two different schemes. Firstly, ‘a posteriori’ scheme has been implemented, where the MOEA runs for a number of generations obtaining an approximation of the Pareto front to apply then a local search from each non-dominated solution of the front. Secondly, an ‘on-line’ scheme has been developed, where in each generation (or after a reduced number of generations) of the evolutionary algorithm a local search is applied on each non-dominated solution to return then the improved solutions to the MOEA as the current population. Both hybrid schemes have been applied to an industrial manufacturing case where the benefit of implementing the hybrid optimization approach is shown, by comparing the hybrid schemes with the MOEA.

How to Cite

Goti, A., & Sanchez, A. I. (2016). Preventive maintenance optimization using a Hybrid Multi-Objective Evolutionary Algorithm. PHM Society European Conference, 3(1). https://doi.org/10.36001/phme.2016.v3i1.1660
Abstract 124 | PDF Downloads 116

##plugins.themes.bootstrap3.article.details##

Keywords

preventive maintenance, multi-objective optimization, hybrid algorithms

References
Ben-Daya, M., & Rahim, M. A. (2000). Effect of Maintenance on the economic design of x-control chart. European Journal of Operational Research, 120, 131–143.
de Almeida, A. T., Ferreira, R. J. P., & Cavalcante, C. A. V. (2015). A review of the use of multicriteria and multi-objective models in maintenance and reliability. IMA Journal of Management Mathematics, 26(3), 249–271.
Deb, K., Pratap, A., Agarwal, S., & Meyarivan, T. (2002). A fast and elitist multiobjective genetic algorithm: NSGA-II. IEEE Transactions on Evolutionary Computation, 6(2), 182–197.
Martorell, S., Sanchez, A., Carlos, S., & Serradell, V. (2004). Alternatives and challenges in optimizing industrial safety using genetic algorithms. Reliability Engineering and System Safety, 86(1), 25–38.
Martorell, S., Sanchez, A., & Serradell, V. (1998). Residual life management of safety-related equipment considering maintenance and working conditions. Esrel 1998 (2, 889–896). Trondheirn, Norway.
Nakajima, S. (Ed.). (1988). Introduction to TPM. Cambridge, MA: Productivity Press.
Nelder, J. A., & Mead, R. (1965). A simplex method for function minimization. The Computer Journal, 7, 308–313.
Sanchez, A., & Goti, A. (2006). Preventive maintenance optimization under cost and profit criteria for manufacturing equipment. ESREL 2006 (607–612). September 18-22. Estoril, Portugal.
Sharma, A., Yadava, G. S., & Deshmukh, S. G. (2011). A literature review and future perspectives on maintenance optimization. Journal of Quality in Maintenance Engineering, 17(1), 5–25.
Section
Technical Papers