Reliability and controllability of selective removal of multiple paint layers from the surface of aircraft skin depend on effective online monitoring technology. An analysis was performed on the multi-pulse laser-induced breakdown spectroscopy (LIBS) on the surface of the aluminum alloy substrate, primer, and topcoat. Based on that, an exploration was conducted on the changes of the characteristic peaks corresponding to the characteristic elements that are contained in the topcoat, primer, and substrate with different layers of a laser action, in combination with analysis of microscopic morphology, composition, and depth of laser multi-pulse pits. The results show that the appearance and increase of the characteristic peak intensity of the Ca I at the wavelength of 422.7 nm can be regarded as the basis for the complete removal of the topcoat; the decrease or disappearance of the characteristic peak intensity can be regarded as the basis for the complete removal of the primer. Al I spectrum at the wavelength of 394.5 nm and 396.2 nm can be adopted to characterize the degree of damage to the aluminum alloy substrate. The feasibility and accuracy of the LIBS technology for the laser selective paint removal process and effect monitoring of aircraft skin were verified. Demonstrating that under the premise of not damaging the substrate, laser-based layered controlled paint removal (LLCPR) from aircraft skin can be achieved by monitoring the spectrum and composition change law of specified wavelength position corresponding tothe characteristic elements that are contained in the specific paint layer.

Laser-induced breakdown spectroscopy (LIBS) is expected to be used for real-time monitoring and closed-loop control of laser-based layered controlled paint removal (LLCPR) from aircraft skin. However, the LIBS spectrum must be rapidly and accurately analyzed, and the monitoring criteria should be established based on machine learning algorithms. Hence, this study develops a self-built LIBS monitoring platform for the paint removal process utilizing a high-frequency (kilohertz-level) nanosecond infrared pulsed laser and collects the LIBS spectrum during the laser removal process of the top coating (TC), primer (PR), and aluminum substrate (AS). After subtracting the spectrum’s continuous background and screening the key features, we construct a classification model of three types of spectra (TC, PR, and AS) based on a random forest algorithm, and the real-time monitoring criterion based on the classification model and multiple LIBS spectra was established and verified experimentally. The results show that the classification accuracy is 98.89%, the time-consuming classification is about 0.03 ms per spectrum, and the monitoring results of the paint removal process are consistent with the macroscopic observation and microscopic profile analysis results of the samples. Overall, this research provides core technical support for the real-time monitoring and closed-loop control of LLCPR from aircraft skin.