Davorin Kramar

Modelling of tool life and surface roughness in hard turning using soft computing techniques: a comparative study

In this paper the potential of soft computing techniques for tool wear and surface roughness prediction in hard turning operations under high pressure cooling conditions using coated carbide tools was investigated. An experimental investigation was conducted to analyse the effects of various cutting conditions on these two parameters analysed in the hard turning of the 100Cr6 steel (62 HRC). On the basis of experimental results two different methods, namely, artificial neural network (ANN) and adaptive neuro-fuzzy inference system (ANFIS) are developed for tool wear and surface roughness prediction. The estimation results obtained by both models are compared with experimental results and very good agreement is observed.

Design of fuzzy expert system for predicting of surface roughness in high-pressure jet assisted turning using bioinspired algorithms

Abstract The surface roughness of the machined parts is one of the most important factors that have considerable influence on the quality and functional properties of products. The objective of this study is development of a surface roughness prediction model for machining Inconel 718 in high-pressure jet assisted turning using the fuzzy expert system, where the fuzzy system is optimized using two bioinspired algorithms: genetic algorithm and particle swarm optimization. The effect of various influential machining parameters, such as diameter of the nozzle, pressure of the jet, cutting speed, feed rate, and distance between the impact point of the jet and cutting edge were taken into consideration in this study. The predicted surface roughness values obtained from developed fuzzy expert systems were compared with the experimental data, and the results indicate that proposed systems can be effectively used to estimate the surface roughness in high-pressure jet assisted turning.

Modeling of the Cutting Forces in Turning Process Using Various Methods of Cooling and Lubricating: An Artificial Intelligence Approach

Cutting forces are one of the inherent phenomena and a very significant indicator of the metal cutting process. The work presented in this paper is an investigation of the prediction of these parameters in turning using soft computing techniques. During the experimental research focus is placed on the application of various methods of cooling and lubricating of the cutting zone. On this occasion were used the conventional method of cooling and lubricating, high pressure jet assisted machining, and minimal quantity lubrication technique. The data obtained by experiment are used to create two different models, namely, artificial neural network and adaptive networks based fuzzy inference systems for prediction of cutting forces. Furthermore, both models are compared with the experimental data and results are indicated.

High pressure jet assisted turning of surface hardened piston rods

An experimental study has been performed to investigate the capabilities of dry, conventional and high pressure jet assisted turning of surface hardened piston rods used in high pressure fluid power applications. The capabilities of different hard turning procedures are compared by means of chip breakability, cooling efficiency, tool wear, tool life, cutting forces and process regions of operability, i.e., technological windows. All machining experiments are performed under conventional cutting speeds using coated carbide tools.

Intelligent Process Modeling and Optimization of Porosity Formation in High-Pressure Die Casting

In this paper, are presented design and implementation issues of predictive models developed for improving the quality of aluminum die castings by minimizing scrap due to porosity. A predictive model for porosity of casting parts is created using fuzzy systems optimized by genetic algorithm and simulated annealing. High-pressure die casting is a complex process that is affected by a large number of process parameters with influence on casting defects such as porosity. In this study, porosity of casting parts is expressed as a function of counter-pressure, first phase velocity, first phase length, second phase velocity, first cooling period, and second cooling period. It was found that the developed GA- and SA-based fuzzy systems have great predictive capability of porosity in die castings. The second objective of this work was to obtain a group of optimal process parameters leading to minimum porosity in high-pressure die casting using genetic algorithm and simulated annealing as optimal solution finders. The optimal parameters were validated experimentally, and the castings with minimum percentage of porosity were achieved.

Study on the Machinability Characteristics of Inconel 718 Super Alloy During Micro-Milling

The increase of demands for products miniaturization has led to a need to research and explore the possibilities of micro-machining of special alloys. This paper presents the experimental study on the micro-milling of Inconel 718 super alloy. It is austenitic nickel-chromium based material which is oxidation resistant. Inconel 718 super alloy is used in the aerospace, automotive and energetic device industry. It applies for extreme environments subjected to high pressure and high temperatures. In this study, mentioned super alloy is machined with long neck micro-end-mill with diameter 0.6 mm, which is intended for side and channel milling of high aspect ratio features. The effects of cutting parameters on output machinability parameters were monitored. During experimental research, there are made conclusions about surface roughness, build-up on edges, cutting forces and etc. For purposes of practical application, general indicative data, area of cutting parameter values, and guidelines for micro-machining of Inconel 718 are given.

An Integration of Bio-inspired Algorithms and Fuzzy Logic for Tool Wear Estimation in Hard Turning

One of the most important factors in hard turning is tool wear, since tool condition affects the quality of the product, tool life, and, consequently, the efficiency of the machining process. Modern methods of cooling and lubricating such is high pressure cooling provides possibility to reduce intensive wear of cutting tool due to better penetration of the fluid into the chip-tool and workpiece-tool interfaces. This paper investigates the potential of fuzzy expert system, where the fuzzy system is optimized using two bio-inspired algorithms, namely genetic algorithm (GA) and particle swarm optimization (PSO), for tool wear prediction in hard turning. Experiments have been conducted on a 100Cr6 (AISI 52100) steel workpieces with 62 HRC hardness using inexpensive coated carbide tools under high pressure cooling conditions. The estimated values of tool wear obtained from developed GA and PSO based fuzzy expert systems were compared with the experimental data and very good agreement was observed.

Milling process optimization for the best surface coat adhesion of the rigid polyurethane foam

Abstract In this research, the influences of milling parameters on the surface quality and coat adhesion of rigid polyurethane (PU) foam are highlighted. Several surface texture parameters were correlated with the milling parameters. The correlation between the coat adhesion strength, as determined by the pull-off test, and the milling parameters was also established. The investigation revealed that traditional height distribution roughness parameters, such as Ra, Sa, Rz, and Sz, do not offer sufficient information for a proper surface adhesion evaluation. Shaping and bearing surface parameters, on the contrary, provide more information for the surface quality assessment, although the structure of the PU was found to be inhomogeneous. The evaluation of milling process effects on surface texture and coat adhesion and the determination of optimal machining conditions were derived based on response surface methodology. The goal was an adequate surface texture that provides the best coat adhesion strength.

Hybrid Machining Processes

In this paper a definition and classification of hybrid processes is given with the focus on assisted hybrid machining processes developed at the Faculty of Mechanical Engineering in Ljubljana. These processes include high-pressure jet assisted machining, cryogenic machining, laser assisted machining and ultrasonic assisted machining. The principles of each individual process are described, followed by the presentations of the results of machinability and productivity improvements. The results were obtained during the last eight years of research on machinability of different hard-to-machine materials at the Department for Management of Manufacturing Technologies.

Examination of Scanner Precision by Analysing Orthodontic Parameters

Summary Background: 3D modelling in orthodontics is becoming an increasingly widespread technique in practice. One of the significant questions already being asked is related to determining the precision of the scanner used for generating surfaces on a 3D model of the jaw. Materials and methods: This research was conducted by generating a set of identical 3D models on Atos optical 3D scanner and Lazak Scan laboratory scanner, which precision was established by measuring a set of orthodontic parameters (54 overall) in all three orthodontic planes. In this manner we explored their precision in space, since they are used for generating spatial models – 3D jaws. Results: There were significant differences between parameters scanned with Atos and Lazak Scan. The smallest difference was 0.017 mm, and the biggest 1.109 mm. Conclusion: This research reveals that both scanners (Atos and Lazak Scan), which belong to general purpose scanners, based on precision parameters can be used in orthodontics. Early analyses indicate that the reference scanner in terms of precision is Atos.