The technology of hairpin welding, which is frequently used in the automotive industry, entails high-quality requirements in the welding process. It can be difficult to trace the defect back to the affected weld if a non-functioning stator is detected during the final inspection. Often, a visual assessment of a cooled weld seam does not provide any information about its strength. However, based on the behavior during welding, especially about spattering, conclusions can be made about the quality of the weld. In addition, spatter on the component can have serious consequences. In this paper, we present in-process monitoring of laser-based hairpin welding. Using an in-process image analyzed by a neural network, we present a spatter detection method that allows conclusions to be drawn about the quality of the weld. In this way, faults caused by spattering can be detected at an early stage and the affected components sorted out. The implementation is based on a small data set and under consideration of a fast process time on hardware with limited computing power. With a network architecture that uses dilated convolutions, we obtain a large receptive field and can therefore consider feature interrelation in the image. As a result, we obtain a pixel-wise classifier, which allows us to infer the spatter areas directly on the production lines.

High-speed videos of the cut front and spectrometric measurements were applied to detect local vaporization on the cut front at high cutting speeds to show that with increasing feed rate, temporally short and intense flashes are generated by vaporization phenomena on the upper part of the cut front. The latter are accompanied by the emergence of an interrupted striation pattern on the surface of the cutting edge. The findings support the assumption that local vaporization at the cut front might be the cause for reduced quality of the cutting process at elevated cutting speeds. The observation of vaporization serves as a diagnostic method to anticipate a fail cut and the interrupted striation pattern.

The transition to high-energy-density lithium metal batteries (LMBs) is essential for advancing electric vehicle (EV) technologies beyond the limitations of conventional lithium-ion batteries. A key challenge in scaling LMB production is the precise, contamination-free separation of lithium metal (LiM) anodes, hindered by lithium’s strong adhesion to mechanical cutting tools. This study investigates high-speed, contactless laser cutting as a scalable alternative for shaping double-coated LiM anodes. The effects of pulse duration, pulse energy, repetition frequency, and scanning speed were systematically evaluated using a nanosecond pulsed laser system on 30 µm LiM foils laminated on both sides of an 8 µm copper current collector. A maximum single-pass cutting speed of 3.0 m/s was achieved at a line energy of 0.06667 J/mm, with successful kerf formation requiring both a minimum pulse energy (>0.4 mJ) and peak power (>2.4 kW). Cut edge analysis showed that shorter pulse durations (72 ns) significantly reduced kerf width, the heat-affected zone (HAZ), and bulge height, indicating a shift to vapor-dominated ablation, though with increased spatter due to recoil pressure. Optimal edge quality was achieved with moderate pulse durations (261–508 ns), balancing energy delivery and thermal control. These findings define critical laser parameter thresholds and process windows for the high-speed, high-fidelity cutting of double-coated LiM battery anodes, supporting the industrial adoption of nanosecond laser systems in scalable LMB electrode manufacturing.