Laser-induced breakdown spectroscopy (LIBS) has been widely used in the field of material detection due to its advantages such as no sample preparation, multi-element simultaneous analysis and rapid detection. Selecting appropriate parameters of the experimental device is an important prerequisite for achieving a good detection effect. Based on the single factor experiment, a multi-factor response surface model for optimizing the parameters of the laser-induced breakdown spectroscopy experimental device is established with laser energy, delay time and depth of focus as the influencing factors and with spectral signal-to-background ratio as the response factor. The influence of different influencing factors and their coupling effects on the spectral quality are studied and the obtained optimal experimental parameters are laser energy of 114 mJ, delay time of 1.86 μs, and depth of focus of 1.75 mm. Finally, the optimal experimental parameters obtained by the response surface methodology are verified by experiments. The mean value of the signal-to-background ratio of the spectral line is 7.45, which is 1.92% higher than that by the single factor method, and the relative standard deviation is 3.16%, which is 0.94% lower than that by the single factor method. The results show that the response surface methodology is more effective and reliable than the single factor method.