Wire Electrical Discharge Machining (WEDM) is aspecialized thermal machining process capable of accurately machining parts ofhard materials with complex shapes. Parts having sharp edges that posedifficulties to be machined by the main stream machining processes can be easilymachined by WEDM process. However, selection of process parameters forobtaining higher cutting efficiency or accuracy in wire EDM is still not fullysolved, even with the most up-to-date CNC wire-EDM machine. This is mainly dueto the complicated stochastic process mechanisms in wire-EDM. One of the mainresearch fields in WEDM is related to the improvement of the processproductivity by avoiding wire breakage. Different factors can lead to wirebreakage such as a decrease in flushing pressure, inefficient removal oferosion debris, as well as other types of stochastic phenomena that appearduring the cutting process.
In such a case, the cutting process is stopped andthe wire has to be threaded again, involving an undesired waste of time.Therefore, it would be desirable to diagnose in advance low quality cuttingregimes and consequently predict wire breakage, in order to perform an on-linereadjust of the machine parameter before it happens.Recently,vision systems are being exploited for such application mainly due to theirhigh resolution, reliability and ease of automatic processing of data. Machinevision (MV) is the technology and method used to provide imaging-basedautomatic inspection and analysis for such applications as automatic inspection,process control and robot guidance in industry.
The first step in the MVsequence of operation is acquisition of an image, typically using cameras,lenses, and lighting that has been designed to provide the differentiationrequired by subsequent processing. MV software packages then employ variousdigital image processing techniques to extract the required information andoften make decisions (such as pass/fail) based on the extracted information.Inspite of the large amount of work worldwide on the application of machinevision for tool status monitoring, such system have not been implemented onWEDM. Machine vision system can be used to park and align the electrodeprecisely under the field of view of the camera for electrode statusmeasurement.
By monitoring the electrode status, helps in avoiding unnecessaryoverhauls of machines in good working orders, to detect the problem in time forplanned replacements and repairs, avoiding the breakdowns in production. Theelectrode is the only element in a wire-EDM that requires frequent changes dueto failure, either by wear or breakage. Hence, there is an imperative need tokeep a watch on the condition of the electrode during the machining process, sothat the electrode can be replaced in time.Wornelectrode state dramatically affects the texture of the machined surface.Analyzing the texture of machined surfaces has been shown to be promising forelectrode status monitoring. However, most methods have their limitations whenapplied to real environments, where the geometric features of machined surfacedepend on the machining operation and where image quality is affected byillumination and other factors.
Problems of non-uniform illumination and imagenoise can be reduced by applying image segmentation and image enhancementtechniques. Inthe past, many researchers have investigated the effect of the WEDM processparameters on surface roughness and electrode wear. Cabanes, et al., 1investigates on avoiding wire breakage and unstable situations in WEDM, as bothphenomena reduce process performance and can cause low quality components. Thiswork proposes a methodology that guarantees an early detection of instabilitythat can be used to avoid the detrimental effects associated to both unstablemachining and wire breakage. The proposed methodology establishes theprocedures to follow in order to understand the causes of wire breakage andinstability.
In order to quantify the trend to instability of a given machiningsituation, a set of indicators related to discharge energy, ignition delaytime, and peak current has been defined. Wire breakage risk associated to eachsituation is evaluated comparing the evolution of those indicators with somepreviously defined threshold values. Srinagalakshmi Nammi and Ramamoorthy, 2have discussed on effect of surface lay in the surface roughness evaluationusing machine vision.
This work explores the influence of orientation ofsurface lay pattern of the machined components, while quantifying the surfaceroughness using machine vision approach. The surface images are captured frommilled low carbon steel specimens with different roughness values using avision system with coaxial lighting arrangement at different angularorientations of the work pieces. The captured images are subjected topreprocessing in order to retain the frequency components that attribute toroughness using a Gaussian filter by adapting the filtering proceduresspecified in ISO 4288. Numerous image based parameters are computed from thesurface images captured at different angular positions of the work piece. Thecomputed vision based parameters are compared and correlated with the roughnessaverage (Ra) obtained using a stylus instrument and the results are analyzed.
The results clearly indicated that it is important to consider the orientationof the work piece when the machine vision approach is used to quantify thesurface texture parameters.OssamaB. Abouelatta 3 has discussed on a new approach to measure surface roughnessin three dimensions by combining a light sectioning microscope and a computervision system. This approach has the advantages of being non-contact, fast andcheep. A prototype version of a user interface program, currently namedSR3DVision, has been developed to manage three dimensional surface roughnessmeasurements. A light sectioning microscope is used to view roughness profilesof the specimens to be measured and the vision system is used to capture imagesfor successive profiles. This program has been totally developed in-house usingMatlab™ software to analyze the captured images through four main modules:(Measurement controller, Profile or surface extraction, 2D roughness parameterscalculation and 3D roughness parameters calculation). The system has beencalibrated for metric units and verified using standard specimens.
In addition,the system was used to measure various samples machined by different operationsand the results were compared with commercial software and a web-based surfacemetrology algorithm testing system. The accuracy of the system was verified andproved to be within ±4.8% compared with these systems.
Ghassan A., et al, 4have discussed about a methodology for using machine vision data to acquirereliable surface roughness parameter measurement. Stylus-based measurementswere acquired and compared to vision-based measurements using standard andnon-standard roughness parameters. Two light reflection models namelyIntensity-Topography Compatible (ITC) model and Light-Diffuse model wereadopted and applied to interpret acquired vision data and to enable suitablecomputation of roughness parameters.
P.M.George et al 5 EDM machining of carbon–carbon composite. Experiments havebeen carried out to determine the optimal setting of the process parameters onthe electro-discharge machining (EDM) machine while machining carbon–carboncomposites. The parameters considered are pulse current, gap voltage andpulse-on-time; whereas the responses are electrode wear rate (EWR) and materialremoval rate (MRR).
The optimal setting of the parameters are determinedthrough experiments planned, conducted and analysed using the Taguchi method.It is found that the electrode wear rate reduces substantially, within theregion of experimentation, if the parameters are set at their lowest values,while the parameters set at their highest values increase the MRR drastically. This paperdiscuss research work that analyzes images of work piece surface roughness andelectrode that have been subjected to WEDM operations and investigates thecorrelation between electrode status and quality characterizing machinedsurfaces. Results clearly indicate that tool status monitoring can besuccessfully accomplished by analyzing surface image data.