Electrical discharge machine using fuzzy for fitness evolutionary strategies optimization (EDiMƒESO)

  • Authors:

  • Noor Elaiza Abd Khalid;Nordin Abu Bakar;Faridah Sh. Ismail;Noor Sheera Mohd Dout

  • Affiliations:

  • Faculty of Computer & Mathematical Sciences, Universiti Teknologi MARA Malaysia, Shah Alam, Selangor, Malaysia;Faculty of Computer & Mathematical Sciences, Universiti Teknologi MARA Malaysia, Shah Alam, Selangor, Malaysia;Faculty of Computer & Mathematical Sciences, Universiti Teknologi MARA Malaysia, Shah Alam, Selangor, Malaysia;Faculty of Computer & Mathematical Sciences, Universiti Teknologi MARA Malaysia, Shah Alam, Selangor, Malaysia

  • Venue:
  • Proceedings of the 15th WSEAS international conference on Computers
  • Year:
  • 2011

Quantified Score

Hi-index 0.00

Visualization

Abstract

Electrical Discharge Machine (EDM) is one of the engineering machineries which is widely used in manufacturing mould, die, automotive, aerospace and surgery components. EDM performance was measured in the output performance using factors such as Material Removal Rate (MRR), Tool Wear Rate (TWR) and Surface Roughness (SR). The process also depends on the shape of the current pulses and parameter setup. A complex machine needs a complex control; for example, EDM requires a complex parameter setting such as current (I), pulse time (ti), duty cycle (η), open-circuit voltage (U) and dielectric flushing pressure (P) to be taken into account as design factors. This paper proposes EDiMfESO (Electrical Discharge Machine using Fuzzy Fitness Evolutionary Strategies Optimization). EDiMfESO learning rate is calculated based on performance of the input parameter setting which involves calculating the current (A), pulse time on (µs) and pulse time off (µs) while other parameters are constant. It employs Evolutionary Strategies (ES) technique and Dynamic Fuzzy to predict the most appropriate multi-objective optimization parameter setting for creating various shape template holes on various types of work piece (example: alloy, graphite, copper, etc). EDiMfESO multi-objective performance testing has shown that this model has a huge potential in achieving multi - objective optimization. The introduction of Dynamic Fuzzy is very useful to give the optimum weight for ES fitness evaluation in this multi - objective optimization. The results have been compared with Mandal's and proved to be better.