Ulaş Çaydaş

An adaptive neuro-fuzzy inference system (ANFIS) model for wire-EDM

A wire electrical discharge machined (WEDM) surface is characterized by its roughness and metallographic properties. Surface roughness and white layer thickness (WLT) are the main indicators of quality of a component for WEDM. In this paper an adaptive neuro-fuzzy inference system (ANFIS) model has been developed for the prediction of the white layer thickness (WLT) and the average surface roughness achieved as a function of the process parameters. Pulse duration, open circuit voltage, dielectric flushing pressure and wire feed rate were taken as models input features. The model combined modeling function of fuzzy inference with the learning ability of artificial neural network; and a set of rules has been generated directly from the experimental data. The models predictions were compared with experimental results for verifying the approach.

Support vector machines models for surface roughness prediction in CNC turning of AISI 304 austenitic stainless steel

In the present investigation, three different type of support vector machines (SVMs) tools such as least square SVM (LS-SVM), Spider SVM and SVM-KM and an artificial neural network (ANN) model were developed to estimate the surface roughness values of AISI 304 austenitic stainless steel in CNC turning operation. In the development of predictive models, turning parameters of cutting speed, feed rate and depth of cut were considered as model variables. For this purpose, a three-level full factorial design of experiments (DOE) method was used to collect surface roughness values. A feedforward neural network based on backpropagation algorithm was a multilayered architecture made up of 15 hidden neurons placed between input and output layers. The prediction results showed that the all used SVMs results were better than ANN with high correlations between the prediction and experimentally measured values.

Effect of Traverse Speed on Abrasive Waterjet Machining of Age Hardened Inconel 718 Nickel-Based Superalloy

In this study, the effect of traverse speed on abrasive waterjet machining (AWJM) of Inconel 718 nickel-based superalloy was experimentally investigated. In the experiments, six different traverse speeds of 80, 130, 180, 230, 280, and 330 mm/min were employed. Following the tests, the surface roughness of the machined job, the kerf taper ratio, and kerf wideness were measured. The characteristics of machined surface were also investigated using scanning electron microscope (SEM) and atomic force microscope (AFM). As a consequence, it is observed that the surface roughness and kerf taper ratio tended to increase with traverse speed, while kerf wideness decreased.

Performance Evaluation of Different Twist Drills in Dry Drilling of AISI 304 Austenitic Stainless Steel

This article evaluates the performances of HSS, K20 solid carbide, and TiN-coated HSS tools in dry drilling of AISI 304 austenitic stainless steel. The roles of spindle speed, feed rate, drill point angle, and number of holes on the surface roughness, tool flank wear, exit burr height, and enlargement of the hole size were experimentally investigated. The structure of this analysis has been determined by means of the technique called the design of experiments (DOE), which allows us to perform a relatively small number of experiments. An L 9 orthogonal array was used to collect the experimental data. The experimental results demonstrated that the above mentioned drilling performances showed a tendency to increase in response to the cutting parameters. TiN-coated HSS drill showed the highest performance with longer tool life and higher hole quality, as well as lower surface roughness, followed by the K20 carbide and the HSS tools.

A Fuzzy Model for Predicting Surface Roughness in Plasma Arc Cutting of AISI 4140 Steel

In the present study, fuzzy logic (a tool in artificial intelligence) was used for the prediction of cutting parameters in plasma arc cutting (PAC) process of AISI 4140 steel. The parameters considered in this study were plasma arc current, cutting speed, and thickness of cut material. Fuzzy rule–based modeling was employed for prediction of surface roughness. These models can be effectively used to estimate the surface roughness. The experimental results were compared with fuzzy logic, and good agreement between them was observed. Analysis of the influence of the individual important machining parameters on the surface roughness have been carried out and presented. Statistically, cutting speed was found the most important factor on surface roughness, while the plasma arc current had the least. The characteristics of machined surfaces and microstructural changes are also studied.

Effect of Mg on Mechanical Properties of Al-Mg Alloys

Abstract In this study, the effect of Mg content on the mechanical properties of Al-Mg alloys was investigated. For this, five different alloys were produced by conventional casting method. Tension, Charpy and fatigue tests were carried out and hardness measurements were conducted on the alloys. Fatigue tests were performed using a rotational bending fatigue test machine and the fatigue strength has been analysed by drawing S-N curves and critically observing fatigue fracture surfaces of the tested samples. The microstructure of the alloys and fracture surfaces were examined by optical and scanning electron microscopy (SEM). The experimental results indicate that mechanical properties are significantly affected by the addition of Mg and the fatigue strength of samples increased due to solid solution strengthening with increasing Mg content in chosen conditions.