Optimisation of laser cutting parameters of oil palm wood / Harizam Mohd Zin

• Main Author: Harizam, Mohd Zin
• Format: Thesis
• Published: 2013
• Subjects: T Technology (General); TJ Mechanical engineering and machinery
• Online Access: http://studentsrepo.um.edu.my/8122/4/harizam.pdf; http://studentsrepo.um.edu.my/8122/

Materials derived from Oil palm wood are still not widely used in furniture industry. There are many machining operations that can be implemented to process the oil palm wood into the final product. This project experimentally investigates the cutting quality of oil palm wood produced/processed using a CO2 laser cutting machine. The quality of the cut has been monitored by measuring the upper kerf width. Another aim of this project is to evaluate the effect of processing parameters of CO2 laser cutting such as laser power, inert gas pressure, cutting speed and focal point position on the cutting quality of the oil palm wood. A statistical analysis of the result has been conducted in order to determine the effect of each parameter on the cut quality. From the analysis for dried sample (Sample X), laser power has a very big effect on upper kerf width (34.08%). Simulation and prediction of CO2 laser cutting of oil palm wood have been done by feed forward back propagation Artificial Neural Network (ANN). Experimental data of Taguchi orthogonal array L9 was used to train the ANN model. The simulation results were evaluated and verified with the experiment. In some cases, the prediction errors of Taguchi ANN model was found larger than 10% even using a Levenberg Marquardt training algorithm. To overcome the problem, a hybrid genetic algorithm-based Taguchi ANN (GA-Taguchi ANN) has been developed. The potential of genetic algorithm in optimization was utilized in the proposed hybrid model to minimize the error prediction for regions of cutting conditions away from the Taguchi based factor level points. The hybrid model was constructed in such a way to realize mutual input output between ANN and GA. The simulation results showed that the developed GA-Taguchi ANN model managed to reduce the maximum prediction error below 10%. The model has significant benefits in many manufacturing processes.