08-11-2012, 06:13 PM
A user-friendly fuzzy-based system for the selection of electro
discharge machining process parameters
A user-friendly fuzzy-based system.pdf (Size: 511.67 KB / Downloads: 55)
Introduction
Electro discharge machining (EDM) is a thermal removal
process extensively used for die manufacturing in industry. It is
the most common process together with the CNC milling in the
manufacture on plastic injection moulds. Mould-dies are usually
machined on CNC machining centers. If CNC machining is
not capable of generating certain geometries and accuracies then
EDMis applied. It removes metal by discharging an electric current
across a narrowdielectric filled gap between the tool and the
workpiece. It uses heat to produce a tiny crater by melting and
vaporization. Literally thousands of sparks per second are produced
to erode the shape of the tool into the workpiece. EDM is
applicable to all electrically conductive materials [1]. Additionally,
EDM is widely used in two particular applications: shaping
very tough metals such as the heat-resistant alloys of gas turbine
blades, which cause severe tool-wear in conventional machining
Experimental work
The experiments were performed to investigate the relationships and effects
of EDM machining parameters between each other. For this purpose, 8mm
diameter copper electrodes were prepared. AISI 4340 tool steel test-part with
a blind hole was selected as a machining feature type. The machine tool was a
conventional HIZAL EDM S300 model. The S300 model enables to set current
intensity levels and the current voltage and frequency at each level are automatically
adjusted by the machine. Fig. 2 shows the picture of electrodes and
machined surfaces of test-part at each intensity level.
Fuzzy model for the EDM parameters selection
In this paper, the fuzzy model has been designed for selecting
the parameters for EDM machining operations. There are three
main stages during the development of the model: formation
of membership functions (fuzzification), selecting the proper
shape, definition of the expert rules and selecting defuzzification
method. Discharge current, pulse duration and pulse interval are
chosen as inputs while erosion rate, electrode wear and surface
roughness are chosen as outputs in the system. Fuzzy expressions
for discharge current, pulse duration and pulse interval;
electrode wear, surface roughness and erosition rate are shown
in Table 2.
Fuzzy-expert rules
The relationship between the inputs and the outputs in a fuzzy
model is characterized by a set of linguistic statements called
as fuzzy rules. They are defined based on experimental work,
expert and engineering knowledge. The number of fuzzy rules
in a fuzzy system is related to the number of fuzzy sets for
each input variable. In this study, there are three input variables
each of which is classified into five fuzzy sets. Therefore, the
maximum number of rules for this model is set to 125 (Table 3).
On the other hand, fuzzy sets and fuzzy operators are the subjects
and the verbs of fuzzy logic. But in order to say anything