| Abstract [eng] |
Laser cutting is one of the non-traditional methods used for material machining. The latest laser cutting technology is fiber lasers, which are notable for their high process efficiency, cutting precision and high cutting quality for thin materials. However, the quality of the cut is significantly decreased when machining thicker materials, which makes the input parameters of the cutting process very important. For this reason, the influence of laser power, cutting speed and assisted gas pressure on the cutting quality of the fibre laser was investigated in this project. Firstly, 4 mm and 6 mm thick specimens of low carbon steel S355JR were cut by changing the cutting parameters. In order to evaluate the influence of the cutting parameters on the cut quality, the surface roughness, dimensional accuracy and kerf taper were measured. Furthermore, to evaluate the thermal effect of the laser, microscopic analysis of the microstructure was carried out by comparing the heat-affected zone with the remaining bulk of the material not affected by the high temperature. The results of the investigations show that laser cutting is a complex process, which performance and the final quality of the cut are strongly influenced by the correct choice of cutting parameters. For this reason, in order to achieve optimum cutting quality, an artificial neural network was created and trained using the results received from the measurement of the quality characteristics. To evaluate the accuracy of the optimisation model, new specimens were cut using the calculated optimum parameters values and quality measurements were made. The results of these measurements were compared with the values predicted by the artificial neural network. Such investigations of the laser cutting process on purpose to achieve optimum quality are very important not only for increasing the efficiency of the process, reducing the number of low-quality products, but also for ensuring the longevity of laser cut parts and implementation of sustainable manufacturing ideas. |
