Nikolaos M. Vaxevanidis

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.

Single and Multi-objective Optimization Methodologies in CNC Machining

Aiming to optimize both productivity and quality in modern manufacturing industries, a wide range of optimization techniques and strategies has been presented by numerous researchers. Optimization modules such as Genetic Algorithms, Evolutionary Algorithms and Fuzzy systems are capable of exploiting manufacturing data with high efficiency and reliability, in order to provide optimal sets of solutions for machining processes. The main scope of this chapter is to present the fundamentals in formulating and developing optimization methodologies, which ultimately offer optimal cutting conditions for both prismatic and sculptured surface part machining and actually improve industrial practice.

Evaluation of Machinability in Turning of Engineering Alloys by Applying Artificial Neural Networks

The present paper investigates the influence of main cutting parameters on the machinability during turning process for three typical materials namely AISI D6 tool steel, Ti6Al4V ELI and CuZn39Pb3 brass, all three under dry cutting environment. Spindle speed, feed rate and depth of cut were selected for study whilst arithmetic surface roughness average (Ra) and main cutting force component (FC) were treated as quality objectives characterizing machinability. For the aforementioned materials a full factorial design of experiments was conducted to exploit main effects and interactions among parameters it terms of quality objectives. The results obtained from dry turning experiments were utilized as a data set to test, train and validate a feed-forward back propagation artificial neural network for machinability prediction regarding all three materials. The work presents the results obtained from the aforementioned experimental effort under an extensive state-of-the-art survey concerning neural network technology and implementation to machining optimization problems.

SURFACE ROUGHNESS ANALYSIS IN HIGH SPEED-DRY TURNING OF A TOOL STEEL

High-speed machining is widely applied for the processing of lightweight materials and also structural and tool steels. These materials are intensively used in the aerospace and the automotive industries. The advantages of high-speed machining lie not only in the speed of machining (lower costs and higher productivity) but also in attaining higher surface quality (prescribed surface roughness without surface defects). Based on this concept, in the present paper the high speed-dry turning of AISI O, (manganese-chromium-tungsten / W.-Nr. 1.2510) tool-steel specimens is reported. The influence of the main machining parameters i.e., cutting speed, feed rate and depth of cut on the resulted center-line average surface roughness (Ra ) is examined. Types of wear phenomena occurred during the course of the present experimental study as well as tool wear patterns were also monitored.Copyright

Electrical discharge drilling of carbon fibre reinforced composite materials

This work investigates the feasibility of applying die sinking electrical discharge machining (EDM) for blind hole drilling of carbon fibre reinforced composite (CFRC) materials. Both carbon fibre reinforced polymers as well as carbon-carbon composites were tested. Machining was performed with copper electrodes, at various currents, pulse durations and polarities. The machined surfaces are evaluated in terms of dimensional accuracy, material removal rate and surface roughness and are also examined by microscope. Research indicates that EDM is a feasible method for blind-hole drilling of CFRC materials however; proper selection of operational parameters is needed. Optimal results are, in general, obtained by low pulse currents and pulse durations and by using tool with positive polarity.

Prediction of Cutting Forces during Turning PA66 GF-30 Glass Fiber Reinforced Polyamide by Soft Computing Techniques

In the present paper the influence of the main cutting parameters on process performance during longitudinal turning of PA66 GF-30 Glass Fiber Reinforced Polyamide is investigated. The selected cutting parameters are cutting speed and feed-rate whilst depth of cut is kept constant. As outputs (responses), cutting force components Ft, FV and Fr were selected. Test specimens in the form of round bars and cemented carbide cutting tool were used during the experimental process. Fifteen experiments were conducted having all different combinations of cutting parameter values. Analysis of Variance (ANOVA), statistical approaches and soft computing techniques (artificial neural network) were applied in order to formulate stochastic models for relating the responses with main cutting parameters. The results obtained, indicate that the proposed soft computing techniques can be effectively used to predict the cutting force components (Ft, FV and Fr) thus; facilitating decision making during process planning since costly and time-consuming experimentation can be avoided.

Selecting subsets of mutually unrelated ISO 13565-2: 1997 surface roughness parameters in turning operations

Due to the complexity of machined roughness profiles and the fact that different surface characteristics exist in view of function, a multi-parameter analysis of roughness is recommended by international surface metrology standards, as well as by recent research projects. A multi-parameter surface analysis according to ISO 13565-2:1997 standard is performed on longitudinally and face turned surfaces of Ck60 steel over a wide range of feed and cutting speed values in order to stablish subsets of mutually unrelated roughness parameters; each one of them would describe different features of the surfaces with the criterion for this purpose being insensitivity to cutting conditions. The correlation of each parameter considered is examined with the machining conditions; statistical regression models with varying correlation coefficients are developed. It is concluded further that a minimum concise set of independent parameters towards turning process control and research would incorporate Ra, Rsk, RRku, and RDelQ. [Received 3 November 2005, Accepted 7 January 2007]

Evaluation of 3-and 5-axis sculptured surface machining in CAM environment through design of experiments

Sculptured surface machining (SSM) is an operation widely applied to several industrial fields such as aerospace, automotive and mould/die. The number of the parameters and strategies involved to program such machining operations can be enormously large owing to surface complexity and advanced design features. This study focuses on the examination of machining strategies and related parameters for the assessment of roughing and finishing stages. A fractional factorial design implementing an L27 Taguchi orthogonal array (OA) was established to conduct machining experiments with the use of a computer-aided manufacturing (CAM) software. Fractional factorial design specifics involve the statistical elimination of unimportant parameters, thus reducing experimental runs without the loss of useful information. Two scenarios were considered to machine a sculptured part; one involving 3-axis roughing/3-axis finish machining experiments and the other one involving 3-axis roughing/5-axis finish machining experiments. Roughing operation was common for both scenarios. The problem was subjected to discrete technological constraints to reflect the actual industrial status. For each machining phase, two quality objectives reflecting productivity and part quality were determined. Roughing experiments were tested to minimise machining time and remaining volume, whilst finishing experiments were subjected to minimise machining time and surface deviation between the designed and the machined 3D model. Quality characteristics were properly weighted to formulate a single objective criterion for both machining phases. Results indicated that DOE applied to CAM software, enables NC programmers to have a clear understanding about the influence of process parameters for SSM operations, thus generating efficient toolpaths to improve productivity, part quality and process efficiency. Practically the work contributes to machining improvement by through the proposition of machining experimentation methods using safe and useful platforms such as CAM systems; the investigation of approaches to avoid problem oversimplification mainly when large number of machining parameters should be exploited and the evaluation of quality criteria which allow their assessment directly form CAM software.

Prediction of Surface Texture Characteristics in Turning of FRPs Using ANN

The objective of the present study is to develop an artificial neural network (ANN) in order to predict surface texture characteristics for the turning performance of a fiber reinforced polymer (FRP) composite. Full factorial design of experiments was designed and conducted. The process parameters considered in the experiments were cutting speed and feed rate, whilst the depth of cut has been held constant. The corresponding surface texture parameters that have been studied are the Ra and Rt. A feed forward back propagation neural network was fitted on the experimental results. It was found that accurate predictions of performance can be achieved through the feed forward back propagation (FFBP) neural network developed for the surface texture parameters.

A virus-evolutionary multi-objective intelligent tool path optimization methodology for 5-axis sculptured surface CNC machining

Sculptured surface machining is a material removal operation essentially adopted to manufacture complex products. Computing optimal tool paths with reference to ideally designed CAD models is indispensable to be able to suggest machining improvements in terms of high quality and productivity. The present paper proposes a new methodology based on a virus-evolutionary genetic algorithm for enhancing sculptured surface tool path planning through an automated selection of values for standard 5-axis end milling strategies’ machining parameters to be decided upon in the context of a simulation-based; software-integrated, multi-objective optimization problem. The problem involves surface machining error as the first quality objective represented via the mean value of chordal deviations that tool path interpolation yields and effective radius of inclined tools that affects scallop. Machining time is the second quality objective entering the problem to assess productivity; whereas the number of cutter location points created for each tool path evaluation is also considered. Tool type, tool axis inclination angles as well as longitudinal and transversal steps are considered as the independent parameters in the case of 5-axis machining. Results obtained by conducting evaluation experiments and simulation tests accompanied by an actual machining process provided significant insight concerning the methodology’s efficiency and ability of suggesting practically viable results.