Angelos P. Markopoulos

Artificial neural network models for the prediction of surface roughness in electrical discharge machining

In the present paper Artificial Neural Networks (ANNs) models are proposed for the prediction of surface roughness in Electrical Discharge Machining (EDM). For this purpose two well-known programs, namely Matlab® with associated toolboxes, as well as Netlab®, were emplo- yed. Training of the models was performed with data from an extensive series of EDM experiments on steel grades; the proposed models use the pulse current, the pulse duration, and the processed material as input parameters. The reported results indicate that the proposed ANNs models can satisfactorily predict the surface roughness in EDM. Moreover, they can be considered as valuable tools for the process planning for EDMachining.

Finite element method in machining processes

Machining mechanics and orthogonal cutting model.- FEM and manufacturing technology.- Special features of modeling.- Advanced modeling.- Results and discussion.

Environmentally Friendly Precision Machining

ABSTRACT Material removal processing has been investigated both theoretically and experimentally to a certain extent. The demands for environmentally friendly processes impose new parameters such as the use of minimal quantity or even the complete omission of cutting fluids. Therefore, the related processes need to be newly studied in order to be optimized for specific cutting conditions. Cutting fluids are used in material removal processes mainly for lubrication, reduction of the temperature in the cutting region, and increase of tool life. However, cutting fluids are associated with skin and breathing problems of the machine operators. Furthermore, after their disposal and if, as in most cases, recycling is not possible, they may become polluting agents in soil and water when inappropriately handled. In this paper the case of hard cutting, a process that can be performed without the use of a cutting fluid, is investigated. A discussion on the technological parameters involved is given and experimental data are presented in order to point out the environmental as well as the economical benefits emerging from the use of such a technology.

Gamification in engineering education and professional training

The incorporation of game mechanics and dynamics in non-gaming applications is a subject of interest in various sectors such as education, marketing, medicine and military, in the last few years. It is believed that engineering education in a pre-graduate level and in professional practice will bring high pay-offs. The role of the academia is to develop new methodologies and tools to produce, apply and use digital games and gamification techniques in contemporary industry and present scientific evidence on the value and the benefits derived from this technology. In this paper, the relative literature is evaluated and a discussion on the gamification status today is given, by examining various aspects of this novel term. Furthermore, game techniques, gamification practices in education and e-learning are considered. Special discussion on engineering games, gamification platforms and empirical surveys is presented with focus on manufacturing.

Modelling and Optimization of Machining with the Use of Statistical Methods and Soft Computing

This book chapter pertains to the use of statistical methods and soft computing techniques that can be used in the modelling and optimization of machining processes. More specifically, the factorial design method, Taguchi method, response surface methodology (RSM), analysis of variance, grey relational analysis (GRA), statistical regression methods, artificial neural networks (ANN), fuzzy logic and genetic algorithms are thoroughly examined. As part of the design of experiments (DOE) the aforementioned methods and techniques have proven to be very powerful and reliable tools. Especially in machining, a plethora of works have already been published indicating the importance of these methods.

Cutting Mechanics and Analytical Modeling

Prior to the description of the most important modeling methods and their features, it would be helpful to introduce some questions that may come to mind of those who want to use modeling, and attempt to give answers. Although some answers are already given in the previous chapter, a more elaborated approach is presented in this section. The questions raised apply to all kinds of modeling; the answers mostly concern FEM, without excluding all the other methods. In the next chapter some more questions and answers, this time solely for FEM, will be presented.

Artificial Neural Networks Modeling of Surface Finish in Electro-Discharge Machining of Tool Steels

Electro-Discharge machining (EDM) is a thermal process with a complex metal removal mechanism that involves the formation of a plasma channel between the tool and the workpiece electrodes and the melting and evaporation of material resulted thus in the generation of a rough surface consisting of a large number of randomly overlapping craters and no preferential direction. EDM is considered especially suitable for machining complex contours, with high accuracy and for materials that are not amenable to conventional removal methods. However, certain phenomena negatively affecting the surface integrity of EDMed workpieces, constrain the expanded application of the technology. Accordingly, it has been difficult to establish models that correlate accurately the operational variables and the performance towards the optimization of the process. In recent years, artificial neural networks (ANN) have emerged as a novel modeling technique that is able to provide reliable results and it can be integrated into a great number of technological areas including various aspects of manufacturing. In this paper ANN models for the prediction of the surface roughness of electro-discharge machined surfaces are presented. A feed-forward artificial ANN trained with the Levenberg-Marquardt algorithm was finally selected. The proposed neural network takes into consideration the pulse current and the pulse-on time as EDM process variables, for three different tool steels in order to determine the center-line average (Ra ) and the maximum height of the profile (Rt ) surface roughness parameters.Copyright

3D Finite Element Modeling of High Speed Machining

This paper presents simulation of High Speed Machining of steel with coated carbide tools. More specifically, Third Wave Systems AdvantEdge commercial Finite Element Method code is employed in order to present turning models, under various machining conditions. As a novelty, the proposed models for High Speed Machining of steel are three-dimensional and are able to provide predictions on cutting forces, tool and workpiece temperatures, chip formation, and chip morphology. Model validation is achieved through experimental work carried out under the same conditions as the ones used in modeling. For the experimental work, the principles for design of experiment were used in order to minimize the required amount of experiments and obtain useful results at the same time. Furthermore, a Taguchi analysis is carried out based on the results. The analysis indicates that there is a good agreement between experiment and modeling, and the proposed models can be further employed for the prediction of a range of machining parameters, under similar conditions.

Thermotechnical modelling of hard turning: A computational fluid dynamics approach

Abstract During hard turning the original hardness of the surface layer changes, as does its texture structure and stress state. Even cracks and other defects may appear if the heat effect is too intense. As experimental investigations into heat effects are difficult and expensive, simulation investigation methods based on modelling are of great significance. In this paper an example of heat modelling of hard turning is presented. The layer thickness on the workpiece surface that reaches high temperature is determined. In that layer different modifications can occur due to heat. It was found that the thickness of the layer affected by heat depends primarily on the feed and only secondarily on other cutting parameters. The cooling gradient of the layer was determined, allowing conclusions to be drawn on the re-tempering of the heated layer. The computational fluid dynamics method and a commercial software was used for the modelling and proved to be suitable for the simulation analysis of the hard turning process.

Diamond grinding wheels production study with the use of the finite element method

Graphical abstract