Camera-Based In-Process Quality Measurement of Hairpin Welding

Abstract

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.

Artificial intelligence methods for in-process high-speed image analysis in laser beam welding of hairpins

“…There is a high number of papers that use high-speed cameras to detect weld spatter. For example, You et al (2014) [10], Hartung et al (2021) [11,12], and Tan et al (2020) [14] use different high-speed cameras, each equipped with various filters such as UV [10,11] or bandpass filters [10,11,13,14], to examine laser-beam welded components. Hartung et al (2021) [11] analyze 18 mm long welds and conclude that the occurrence of spatter as well as the quality of the weld strongly depends on the welding factors.…”

“…Here, the spatters are detected by a proprietary CNN based on U-Net with an accuracy of 75%. In Hartung et al (2021) [12] this approach is followed up and optimized. The images from the camera already mounted on the laser beam welding system, which are taken from three different perspectives during the welding process of hairpin pairs, are superimposed and then evaluated by the modified U-Net.…”

“…Process light and spatters are considered as the main process deviations. Hartung et al (2021) [12] achieve a training accuracy of the CNN architecture of 98%. Furthermore, the spatter detection method of Tan et al (2020) [14] must be mentioned, as it consists of a combination of CNN and TNN.…”

Creepage Distance Estimation of Hairpin Stators Using 3D Feature Extraction

“…Due to a high number of wires that need to be connected, the welding process features an integral role in hairpin stator manufacturing [18]. In [19], an image-based approach using a neural network architecture was evaluated for in-process monitoring of laser-based weld seams of hairpin stators. Mayr et al [20] proposed a comparable approach for estimating the quality of the cross-section in contacting, and they used pre-trained neural network architectures to classify the images.…”

Prediction of electrical resistance of laser-welded copper pin-pairs with surface topographical information from inline post-process observation by optical coherence tomography

“…Inline cameras can give feedback on two-dimensional misalignments and can be used for the identification of spatter [2]. However, this approach is not able to detect axial height offsets between the pin-pairs.…”