Determining optimal machine part replacement time using a hybrid ANN- GA model

Document Type : Article


Department of Industrial Engineering, Sakarya University, Sakarya, 54050, Turkey


Companies must determine the replacement time of machine parts correctly since it affects their production costs and efficiencies. For this, it is aimed to determine the most appropriate replacement time to minimize cost per unit. In this study, it is proposed to develop a hybrid Artificial Neural Network (ANN)-Genetic Algorithm (GA) model to predict replacement time without using a cost model. At first, a replacement cost model is developed to calculate replacement times to use in training the neural network. Nevertheless, the cost model needs complex mathematical calculations. GA is used instead of the cost model to determine replacement time, and thus, to achieve fast learning for the neural network. The hybrid ANN-GA model was applied to predict replacement time of bladder in tire manufacturing. Furthermore, ANN and GA models, which were developed to increase the prediction accuracy of the hybrid model, were used. The hybrid ANN-GA model showed better performance with higher R^2 (0.943) and lower RMSE (9.124) and MAPE (2.528) values than the other ANN and GA models. The values indicate that the hybrid model is in good agreement with the cost model. Thus, it is recommended that the hybrid model is used instead of the cost model.


 [1] Jeang, A. “Reliable tool replacement policy for quality and cost”, Eur J Oper Res., 108 (2), pp. 334-344 (1998).
[2] Nakagawa, T. and Yasui, K. “Calculation of age-replacement with Weibull failure
times”, IEEE Trans Reliab., 30(2), pp. 163–164 (1981).
[3] Jonge, B. Klingenberg, W. Teunter,  R. et al. “Optimum maintenance strategy under uncertainty in the lifetime distribution”, Reliab Eng Syst Safe., 133, pp. 59–67 (2015).
[4] Lewis, E.E. “Introduction to reliability engineering”, John Wiley&Sons Press,  Singapore. (1987).
[5] Mazzuchi, T.A. and Soyer, R. “A Bayesian perspective on some replacement strategies”, Reliab Eng Syst Safe., 51: pp. 295-303 (1996).
[6] Eryilmaz, S. “Computing optimal replacement time and mean residual life in reliability shock models.” CAIE., 103, pp. 40–45 (2017).
[7] Xu, W. and Cao, L.  “Optimal tool replacement with product quality deterioration and random tool failure”, Int J Prod Res., 53(6), pp. 1736-1745 (2015).
[8] Zaretalab, A. Haghighi, H.S.  Mansour, S. et al. “A mathematical model for the joint optimization of machining conditions and tool replacement policy with stochastic tool life in the milling process”, Int J Adv Manuf Technol., 96(5-8), pp. 2319–2339 (2018).
[9] Diaz, N. Pascual, R. Ruggeri, F. et al. “Modelling age replacement policy under multiple time scales and stochastic usage profiles”, Int J Prod Econ., 188: pp. 22-28 (2017).
[10] Chand, S. McClurg, T. and Ward, J. “A model for parallel machine replacement with capacity  expansion”, Eur J Oper Res., 121 (2000), pp. 519–531 (2000).
[11] Wang, K.S. Tsai, Y.T. and Lin, C.H. “A study of replacement policy for components in a mechanical system”, Reliab Eng Syst Safe., 58(3), pp. 191-199 (1997).
 [12] Sheikh, A. K. Raouf, A. Sekerdey, U.A. et al. “Optimal tool replacement and resetting strategies in automated manufacturing systems”, Int J Prod Res., 37(4), pp. 917- 937 (1999).
[13] Hashemi, S.T. Ebadati, O.M. Kaur, H. “A hybrid conceptual cost estimating model using ANN and GA for power plant projects”, Neural Comput & Applic., 31, pp.2143–2154  (2019).
[14] Seo, K. “A methodology for estimating the product life cycle cost using a hybrid GA and
ANN model”, Artificial Neural Networks – ICANN 2006 The Series Lecture Notes in Computer Science, 4131 (Eds. Kollias et al.), pp. 386-395 (2006).
 [15] Firouzi, A. and Rahai, A. “An integrated ANN-GA for reliability based inspection of concrete bridge decks considering extent of corrosion-induced cracks and life cycle costs”, Scientia Iranica, 19(4), pp.974-981 (2012).
 [16] Al-Chalabi, H. S. Lundberg, J. Al-Gburi, M. et al. “ Model for economic replacement time of mining production rigs including redundant rig costs”, J Qual Maint Eng.,  21(2), pp.207-226 (2015).
[17] Aldhubaib, H.A. and Salama, M.A. “A novel approach to investigate the effect of maintenance on the replacement time for transformers”, IEEE T Power Deliver., 29(4), pp. 1603-1612 (2014).
[18] Liu,  Y. Li, Y. Huang,  H. et al. “Optimal preventive maintenance policy under fuzzy Bayesian reliability assessment environments”, IIE Trans., 42(10), pp. 734-745 (2010).
[19] Fukuda, T. and Shibata, T. “Theory and applications of neural networks for industrial control system”, IEEE T Ind Electron 39(6), pp.472-489 (1992).
[20] Holland J.H. “Adaptation in Natural and Artificial Systems: an Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence”, University of Michigan Press, Ann Arbor, Mich, USA, (1975).
[21] Holland, J.H. “Genetic algorithms”, Sci Am., 267, pp. 44–50 (1992).
[22] Barlow, R.E. and Hunter, L. “Optimal preventive maintenance policies”, Operat Res., 8, pp. 90-100 (1960).
[23] Handlarski, J. “Mathematical analysis of preventive maintenance schemes”, J Oper Res Soc., 31(3), pp. 227-237 (1980).
[24] Ahmad, R. and Kamaruddin, S. “An overview of time-based and condition-based maintenance in industrial application”, Comput Ind Eng., 63(1), pp. 135-149 (2012).
[25] Zhang, J. Tan, J. Liu, X. et al. “Energy saving curing and precision manufacturing technology of tires”, AIP Conference Proceedings., 1713, pp. 130002-130004 (2016).
[26] Angelova, M. and Pencheva, T. “Tuning genetic algorithm parameters to improve convergence time”,  IJChER, Article ID 646917 (2011).
[27] Tian, X. and Yuan, S. “Genetic algorithm parameters tuning for resource-constrained project scheduling problem” AIP Conf Proc., 1955(040059), pp. 1-9 (2018).
[28] Leung, Y.W. and Wang, Y. “An orthogonal genetic algorithm with quantization for global numerical optimization”, IEEE Trans. Evol. Comput., 5(1), pp. 41–53 (2001).
[29] Rad, M.A.A. and Rad, M.S.A. “Comparison of articial neural network and coupled simulated annealing based least square support vector regression models for prediction of compressive strength of high-performance concrete”, Sci Iran., 24(2), pp. 487-496 (2017).
[30] Timothy, M. “Practical neural network recipes in C++”, Academic Press, p 174, Toronto (1993).
[31] Pontes, F.J. Amorim,  G.F. Balestrassi, P.P. et al. “Design of experiments and focused grid search for neural network parameter optimization”, Neurocomputing., 186, pp. 22–34 (2016).
[32] Lahiri, S.K. and Ghanta, K.C. “Artificial neural network model with the parameter tuning assisted by a differential evoluation technique:  the study of the holdup of the
slurry flow in a pipeline”, Chem Ind Chem Eng Q., 15 (2), pp. 103-117 (2009).
[33] Jeong, C. Min, J.M. and Kim, M.S. “A tuning method for the architecture of neural network models incorporating GAM and GA as applied to bankruptcy prediction”, Expert Syst Appl., 39, pp. 3650–3658 (2012).
[34] Monks, J.G. “Operations management: theory and problems” Ed., 3th Edn., McGraw-Hill, New York (1987).
[35] Witt, S.F. and Witt, C.A. “Modeling and forecasting demand in tourism” Academic Press, Londra (2000).
[36] Lewis, C.D. “Industrial and business forecasting methods” Butterworths Publishing, Londra (1982).