A machining center selection study using neural networks

Abstract Machining centers (MCs) are crucial high-technology machine tools that are widely used in the manufacturing industry. Since their high investment necessities, the selection of the appropriate MC for a company is an important task so that the company’s competitive advantages can be continued in the future. In the literature, there are many studies for MC selection using multi-criteria decision-making (MCDM) models and their fuzzy versions. This type of selection model must use selection criteria weighting procedures that are mainly based on subjective preferences. On the other hand, some attempts are provided in the literature to set objective decision-making models, such as the design of an experiment (DoE)-based Technique for Order Preferences by Similarity to the Ideal Solution (TOPSIS) model. In this study, we improved the DoE-based TOPSIS approach using neural network-based solutions and compared their capability of the MC selection studies against the classical MCDM and DoE-TOPSIS models. The proposed model can handle the newly generated scenarios using the Neural Networks. The feedforward neural network (FFNN)-based model utilizes machine learning techniques to overcome some of the challenges by modeling the complex relationships among various decision criteria without relying on human judgment for weighting. As a form of artificial neural network, FFNNs learned from large datasets and captured non-linear patterns, making them well-suited for the MC selection problem. Their capability to process high-dimensional inputs with numerous variables and interactions aligns effectively with the complexities of the MC selection problem. Therefore, the proposed FFNN model is very competitive against the DoE-TOPSIS and classical TOPSIS models.