The monitoring of aircraft paint cleaning based on Laser-induced breakdown spectroscopy (LIBS) technology requires limiting the peak power density range to ensure the stability of plasma excitation and paint cleaning. However, for the widely used high-frequency (kHz-level) pulsed laser paint removal technique, the peak power density is relatively low, which limits the plasma excitation during the paint removal process, and the strong continuous background spectra generated by the high-frequency laser ablation of the material interferes with the plasma spectral acquisition. Based on the demand for controllable cleaning of the functional paint layer of the skin, the thesis designs a LIBS monitoring platform for high-frequency laser paint removal based on the writing of the control software of LabVIEW embedded development system and the integration of laser cleaning, spectral acquisition, control and display modules. The 2024-T3 aluminum alloy double-paint layer specimen was selected as the research object, and the spectra of the paint layer/substrate system with wavelengths in the range of 360~700 nm were collected (top paint layer: TC; bottom paint layer: PR; substrate: AS). The original spectra were preprocessed by smoothing filter, baseline correction, and normalization, and 12 characteristic spectral lines were selected for principal component analysis (PCA), and their dimensionality reduction data were used as the input variables for linear discriminant analysis (LDA), to establish the PCA-LDA discriminant model. Finally, the model was imported into the LIBS monitoring platform, and the classification accuracy of the high-frequency laser paint removal LIBS monitoring platform was verified through experiments. The results show that: only the cumulative variance explanation rate is greater than 85% as the principle of principal component selection, which can not meet the classification needs of LDA in the paint removal process; by optimizing the number of principal components of LDA, and ultimately selecting the first 9 principal components as the input of LDA, the detection accuracy of the LIBS platform is significantly improved. At this time, the classification accuracy of the PCA-LDA model based on LIBS spectra reaches 92.5%. It can be seen that the designed high-frequency laser paint removal LIBS monitoring platform can complete the material identification of different structural layers of the paint layer/substrate system, thus realizing the effective monitoring of high-frequency pulsed laser controllable paint removal.