Multi-criteria optimization of quartz glass laser cutting parameters using neural network simulation and genetic algorithm

Using neural network modeling and a genetic algorithm, the values of technological parameters were determined that ensure efficient laser cutting of quartz glass when the workpiece is exposed to a laser beam with a wavelength of 10,6 $\mu$m and a coolant. The multi-criteria optimization of laser cutting of quartz plates was performed according to the criteria of maximum tensile stresses and maximum processing speed. The algorithms for choosing the optimal architecture of neural networks are described.