grit size. After the experimental work theyhave conclude that traverse speed and abrasive gritsize is most significant factor on MRR and surfaceroughness respectively.
Rama rao et al. 
they have studied the effect of various electro chemical machining parameters suchas voltage, feed rate and electrolyte concentration onthe material removal rate of the AL Sic material.The settings of process parameters were determine
by using Taguchi’
s experimental design method.Orthogonal array of Taguchi, the signal to noiseratio, the analysis of variance and regressionanalysis are employed to find the optimal processparameter levels and to analyze the effect of theseparameters on material removal rate values.Confirmation test with the optimal level of machining parameters was carried out in order toillustrate the effectiveness of the Taguchioptimization method. After the data analysis they
have found that ANOVA and Taguchi’s S/N ratio
for data analysis drew similar conclusion. After theexperimental work statistical result shows that thevoltage, feed rate and electrolyte concentrationaffects the metal removal rate by 34.04 %, 58.09 %and 7.57 % in ECM respectively. At lastthe analysisof the confirmation experiment for metal removalrate has shown that Taguchi parameter design cansuccessfully verify the optimum cutting parameters.
Srinivasathreya et al. 
they have study toillustrate the procedure adopted in using TaguchiMethod to a lathe facing operation. The orthogonalarray, signal-to-noise ratio, and the analysis of variance are employed to study the performancecharacteristics on facing operation. In this analysis,three factors namely speed; feed and depth of cutwere considered. Accordingly, a suitable orthogonalarray was selected and experiments were conducted.After conducting the experiments the surfaceroughness was measured and Signal to Noise ratiowas calculated.With the help of graphs, optimumparameter values were obtained and theconfirmation experiments were carried out.Theseresults were compared with the results of fullfactorial method. After the comparison they haveconclude that the Tag
uchi’s Method of parameter
design can be performed with lesser number of experimentations as compared to that of fullfactorial analysis and yields similar results.It isfound that the parameter design of the Taguchimethod provides a simple, systematic, and efficientmethodology for optimizing the process parameters.
Application OfArtificial Neural Network
Ramezan Ali et al. 
They have conductexperimentsto optimize the surface roughness andmaterial removal rate of electro dischargemachining of Sic parameters simultaneously.Effectsof three important input parameters of process viz.,discharge current, pulse on time (Ton), pulse off time (Toff) on electric discharge machining of Sicare considered.Artificial neural network (ANN) withback propagation algorithm is used to model theprocess. A multi-objective optimization method,non-dominating sorting genetic algorithm-II is usedto optimize the process.Experiments have beenconducted over a wide range of considered inputparameters for training and verification of themodel.The MRR and surface roughness have beenmeasured for each setting of pulse on time and pulseoff time and current.ANN model has been trainedwithin the experimental data which both are close toeach other that demonstrate that the model issuitable for predicting the response parameters.
Mr.Ch.Madhu et al. 
They have doneexperiments in order to find out effect of turningparameters on surface roughness of titanium work piece. Three important turning parameters such ascutting speed, feed rate and depth of cut are selectedto study for this purpose. They have employeddesign of experiments in order to conduct theexperiments. The model for the surface roughness,as a function of cutting parameters, is obtained usingANN in MATLAB7. After the experimental work comparison was carried out between experimentaldata and ANN value which was found similar. Theresults obtained conclude that ANN is reliablemethod and it can be readily applied to differentmetal cutting processes with greater confidence.
ShenChangyu et al. 
they haveproposed acombining artificial neural network and geneticalgorithm method to optimize injection moldingprocess. The back propagation neural model wasdeveloped to build nonlinear relationship betweenprocess conditions and quality indexes of theinjection molded parts. The genetic algorithm wasused for process condition optimization. Thecombine ANN/GA method is used in the processoptimization for industrial parts in order to improvethe quality of volumetric shrinkage variation in theparts. After the results they have conclude thatTheANNtechniquehasbeenshownasaneffectivemethodtomodelthecomplexrelationshipbetweentheprocessconditionsandthequalityindexofinjectionmoldingparts.TheGAisespeciallyappropriatetoobtaintheglobal