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

Abstract

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.