IIoT portable laser line profilometer powered by AI for gap and flush measurement in automotive

In automotive manufacturing, the final assembly of car body parts requires repeated measurements of gap and flush, which are essential not just for aesthetics but also for aerodynamics and noise reduction. This paper initially presents an innovative portable wireless laser line triangulation profilometer for human operators in assembly lines. It then describes how the wireless and ergonomic measurement device exploits embedded AI solutions to improve measurement accuracy. Two semantic segmentation approaches were tested (U-Net vs. LinkNet) to compare their performance in isolating the effective laser line from unwanted reflections, as well as inferring accurate segmentation with short inference times. These approaches were deployed at the edge, requiring pruning and quantization steps to comply with the computational capabilities of the System on Module (SoM) mounted on the device. The LinkNet demonstrated superior accuracy (Dice loss of 0.1127) and faster execution speed (166.77 ms). This approach, particularly with semantic segmentation algorithms implemented on the edge device, paves the way to improve the detection of laser line images on transparent surfaces even in the presence of low contrast and multiple reflections, ensuring precise and efficient measurement of gap and flush, even on front lights.