Sezan Orak

A hybrid decision making approach to prevent chatter vibrations

MCDM study has been performed to determine optimum cutting conditions without chatter.Different cutting, tool-working material and modal parameters have been used in the models to maximize stable cutting depth.Hybrid decision making models have produced successful results. In this paper, the optimum cutting conditions without chatter vibrations have been determined during turning operations. Chatter vibrations are detrimental and cause poor surface properties. In this study, chatter vibration prevention has been discussed in a different way using a multi-criteria decision making approach. Regression-multi-criteria decision making hybrid models have been developed and applied to the problem of chatter vibrations. First, regression models have been used to determine the criteria weights for TOPSIS (technique for order preference by similarity to ideal solution) model. Then, TOPSIS models have been developed. Three different hybrid models have been studied. The results of these three models are the same. It has been seen from the results that the number of revolutions and the workpiece hardness are the most effective parameters. The models are developed to help operators in different manufacturing environments.

Prediction of stable cutting depths in turning operation using soft computing methods

Different soft computing methods were used to predict stable cutting depths.Different experiments were used in the models to predict stable cutting depth.ANN model produced successful results. This article suggests soft computing methods to predict stable cutting depths in turning operations without chatter vibrations. Chatter vibrations cause poor surface finish. Therefore, preventing these vibrations is an important area of research. Predicting stable cutting depths is vital to determine the stable cutting region. In this study, a set of cutting experiments has been used and the stable cutting depths are predicted as a function of cutting, modal and tool-working material parameters. Regression analyses, artificial neural networks (ANN) decision trees and heuristic optimization models are used to develop the generalization models. The purpose of the models is to estimate stable cutting depths with minimum error. ANN produces better results compared to the other models. This study helps operators and engineers to perform turning operations in an appropriate cutting region without chatter vibrations. It also helps to take precautions against chatter.

Development of an ANN-based decision-making method for determining optimum parameters in turning operation

Chatter vibration is a condition which hinders effective performance of material removal in machining operations. This kind of vibration is dangerous and leads to over-vibration between workpiece and tool. Additionally, it results in low surface quality, loudness and excessive tool wear. In order to prevent the chatter vibration, there are different methods in the literature by which vibration can be effectively controlled. The aim of this study is to determine the optimum parameters of chatter vibrations in turning process and develop a hybrid decision-making algorithm which consists of artificial neural networks–TOPSIS methods for the optimization of machining parameters. First, stable cutting depths, chatter frequencies and other modal parameters are determined by an empirical study. Then, a new hybrid decision-making model is developed and optimum machining parameters are determined. It is observed that the hybrid decision-making model produces successful results and chatter vibrations are prevented.