In the present study, artificial neural network (ANN) along with heuristic algorithms, namely particle swarm optimization (PSO) and simulated annealing (SA), has been employed to carry out the modeling and optimization procedure of electrical discharge machining (EDM) process on AISI2312 hot worked steel parts. Surface roughness (SR), tool wear rate (TWR) and material removal rate (MRR) are the process quality measures considered as process output characteristics. Determination of a process variables (pulse on and off time, current, voltage and duty factor) combination to minimize TWR and SR and maximize MRR independently (as single objective) and also simultaneously (as multi-criteria) optimization is the main objective of this study. The experimental data are gathered using Taguchi L 36 orthogonal array based on design of experiments approach. Next, the output measures are used to develop the ANN model. Furthermore, the architecture of the ANN has been modified using PSO algorithm. At the last step, in order to determine the best set of process output variables values for a desired set of process quality measures, the developed ANN model is embedded into proposed heuristic algorithms (SA and PSO) with which their derived results have been compared. It is evident that the proposed optimization procedure is quite efficient in modeling (with less than 1% error) and optimization (less than 4 and 7 percent error for single-and multiobjective optimizations, respectively) of EDM process variables.

No abstract

Face milling is an important and common machining operation because of its versatility and capability to produce various surfaces. Face milling is a machining process of removing material by the relative motion between a work piece and rotating cutter with multiple cutting edges. It is an interrupted cutting operation in which the teeth of the milling cutter enter and exit the work piece during each revolution. This paper is concerned with the experimental and numerical study of face milling of AISI1045. The proposed approach is based on statistical analysis on the experimental data gathered using Taguchi design matrix. Surface roughness is the most important performance characteristics of the face milling process. In this study the effect of input face milling process parameters on surface roughness of AISI1045 steel milled parts have been studied. The input parameters are cutting speed (v), feed rate (f z) and depth of cut (a p). The experimental data are gathered using Taguchi L 9 design matrix. In order to establish the relations between the input and the output parameters, various regression functions have been fitted on the data based on output characteristics. The significance of the process parameters on the quality characteristics of the process was also evaluated quantitatively using the analysis of variance method. Then, statistical analysis and validation experiments have been carried out to compare and select the best and most fitted models. In the last section of this research, mathematical model has been developed for surface roughness prediction using particle swarm optimization (PSO) on the basis of experimental results. The model developed for optimization has been validated by confirmation experiments. It has been found that the predicted roughness using PSO is in good agreement with the actual surface roughness.

No abstract

Multi objective optimizing of machining processes is used to simultaneously achieve several goals such as increased product quality, reduced production time and improved production efficiency. This article presents an approach that combines grey relational analysis and regression modeling to convert the values of multi responses obtained from Taguchi method design of experiments into a multi objective model. The proposed approach is implemented on turning process of St 50.2 Steel. After model development, Analysis of Variance (ANOVA) is performed to determine the adequacy of the proposed model. The developed multi objective model is then optimized by simulated annealing algorithm (SA) in order to determine the best set of parameter values. This study illustrates that regression analysis can be used for high precision modeling and estimation of process variables.