In this research work, the application of Cylindrical Wire Electrical Discharge Machining (CWEDM) for machining of precise conical-cylindrical forms on hard and difficult-to-machine materials is presented. The material chosen in this case was AISI D3 tool steel due to its growing range of applications in the field of manufacturing tools, dies and molds as punch, tapping, reaming and so on. Results of surface roughness (Ra), roundness and material removal rate (MRR) on the cylindrical wire electrical discharge turning (CWEDT) has been presented. This study has been carried out on the influence of five design factors: power, voltage, pulse off time, spindle rotational speed and conical angle, over the three previous mentioned response variables by using of statistical design of experiment (DOE) method. Three levels Fractional factorial method was used for studying selected factors. All experiments are conducted on ONA R250 wire EDM machine. Analysis of Variance (ANOVA) has been used for acquiring optimal conditions of machining on AISI D3 cold worked steel parts. Also an equation based on data regression has been presented for each of three responses. Results demonstrate that power, voltage, time off and form factor are the most affective parameters on MMR and Surface Roughness (Ra). Power, time off and RPM are the most affective parameters on Roundness. Surfaces of the cylindrical WEDT parts were examined using Scanning Electron Microscopy (SEM) to identify the micro ridges and craters on the surface. Cross-sections of the EDM parts are examined using the SEM to quantify the recast layer and heat-affected zone under various process parameters. The undesired recast layer, which has poor mechanical properties and irregular features, must eventually be removed. In other hand one of the most important problems in wire electrical discharge machining is related to wire breakage so effect of input parameters such as power and voltage on wire (as electrode) has been investigated. The results of this work will be used for increasing the performance of the CWEDM process.