In this study, eight different painted stainless steel 304L specimens were laser-cleaned using different process parameters, such as laser power, scan speed, and the number of repetitions. Laser-induced breakdown spectroscopy (LIBS) was adopted as the monitoring tool for laser cleaning. Identification of LIBS spectra with similar chemical compositions is challenging. A convolutional neural network (CNN)-based deep learning method was developed for accurate and rapid analysis of LIBS spectra. By applying the LIBS-coupled CNN method, the classification CNN model accuracy of laser-cleaned specimens was 94.55%. Moreover, the LIBS spectrum analysis time was 0.09 s. The results verified the possibility of using the LIBS-coupled CNN method as an in-line tool for the laser cleaning process.

Electric vehicles are gaining popularity as an effective alternative for reducing carbon dioxide emissions and achieving carbon neutrality. Welding copper (Cu) and aluminum (Al) is applied to electric vehicle batteries due to their high conductivity and lightweight properties. However, welding Cu and Al may lead to the formation of intermetallic compounds (IMCs) within the weld zone, which deteriorates mechanical properties. This study analyses the tendency for cracks to occur and the causes of crack formation by welding Al and Cu materials based on nickel (Ni) coating thicknesses (0, 7, 25, and 50 µm) using a green laser. Observations of cracks in the weld zone and the corresponding Ni content, performed using an optical microscope and an electron probe micro-analyser, revealed that increased Ni coating thickness led to higher Ni content in the weld zone and a corresponding decrease in crack occurrence. In addition, micro-structural analysis of the weld zone using a scanning electron microscope revealed that cracks began to occur with the formation of Cu-Al IMCs and propagated in regions where CuAl and CuAl ₂ phases were present. The formation of the NiAl phase, due to the increased Ni content in the weld zone, inhibited the reaction between Cu and Al, thereby suppressing the formation of these brittle IMCs. Consequently, crack initiation and propagation were effectively reduced. A shear test was conducted to evaluate mechanical performance. The results showed that the shear strength of the weld with a Ni coating thickness of 25 µm improved by approximately 203% compared to the weld without Ni coating. The shear strength of the weld with a 50 µm Ni coating thickness decreased compared the 25 µm sample due to the non-uniform formation of equiaxed and columnar grain structures.