FUZZY EXPERT SYSTEM FOR PREDICTION OF KERF QUALITIES IN PULSED LASER CUTTING OF TITANIUM ALLOY SHEET

Laser cutting is an advanced thermal cutting process of complex nature. It's process behavior drastically changes with slight variation in processing conditions. The prediction of process performance becomes more difficult if cutting materials have non-favorable optical and thermal properties. Titanium (Ti) alloys are characterized by their low thermal conductivity and high chemical reactivity at elevated temperature and hence difficult to cut by laser. It has been found that complex and nonlinear behavior of manufacturing process can better be dealt with the application of artificial intelligence (AI) tools. The aim of present research is to develop a fuzzy expert system for prediction of the laser cutting process behavior of Ti alloy (Ti-6Al-4V) sheet. A hybrid approach of neural network and fuzzy logic theory has been applied to develop the fuzzy expert system to predict the kerf widths and kerf deviation. The predicted results have been compared with the experimental data and found appropriate. The effects of significant process parameters on the different quality characteristics such as kerf widths and kerf deviation have been discussed.