Digitalisation trends of Industry 4.0 and Internet of Things led to an unprecedented growth of manufacturing data. This opens new horizons for data-driven methods, such as Machine Learning (ML), in monitoring of manufacturing processes. In this work, we propose ML pipelines for quality monitoring in Resistance Spot Welding. Previous approaches mostly focused on estimating quality of welding based on data collected from laboratory or experimental settings. Then, they mostly treated welding operations as independent events while welding is a continuous process with a systematic dynamics and production cycles caused by maintenance. Besides, model interpretation based on engineering know-how, which is an important and common practice in manufacturing industry, has mostly been ignored. In this work, we address these three issues by developing a novel feature-engineering based ML approach. Our method was developed on top of real production data. It allows to analyse sequences of welding instances collected from running manufacturing lines. By capturing dependencies across sequences of welding instances, our method allows to predict quality of upcoming welding operations before they happen. Furthermore, in our work we strive to combine the view of engineering and data science by discussing characteristics of welding data that have been little discussed in the literature, by designing sophisticated feature engineering strategies with support of domain knowledge, and by interpreting the results of ML analysis intensively to provide insights for engineering. We developed 12 ML pipelines in two dimensions: settings of feature engineering and ML methods, where we considered 4 feature settings and 3 ML methods (linear regression, multi-layer perception and support vector regression). We extensively evaluated our ML pipelines on data from two running industrial production lines of 27 welding machines with promising results.

No abstract

No abstract

This paper presents results from an extensive experimental study on the rubbing behavior of labyrinth seal fins (SFs) and a honeycomb liner. The objective of the present work is to improve the understanding of the rub behavior of labyrinth seals by quantifying the effects and interactions of sliding speed, incursion rate, seal geometry, and SF rub position on the honeycomb liner. In order to reduce the complexity of the friction system studied, this work focuses on the contact between a single SF and a single metal foil. The metal foil is positioned in parallel to the SF to represent contact between the SF and the honeycomb double foil section. A special test rig was set up enabling the radial incursion of a metal foil into a rotating labyrinth SF at a defined incursion rate of up to 0.65 mm/s and friction velocities up to 165 m/s. Contact forces, friction temperatures, and wear were measured during or after the rub event. In total, 88 rub tests including several repetitions of each rub scenario have been conducted to obtain a solid data base. The results show that rub forces are mainly a function of the rub parameters incursion rate and friction velocity. Overall, the results demonstrate a strong interaction between contact forces, friction temperature, and wear behavior of the rub system. The presented tests confirm basic qualitative observations regarding blade rubbing provided in literature.

Labyrinth seals are a state-of-the-art sealing technology to prevent and control leakage flows at rotor-stator interfaces in turbomachinery. Higher pressure ratios and the economical use of cooling air require small clearances, which lead to potential rubbing events. The use of honeycomb liners allows for minimal leakage by tolerating rub events to a certain extent. A previous study within an EU project investigated the complex contact conditions of honeycomb liners, with the idealized contact of a seal fin and a single parallel metal foil representing the honeycomb double foil section. In the present work, the results for the slanted foil position are shown and compared to the previous results. The variation of rub velocity, incursion speed, incursion rate, and seal geometry in a test rig allows for the identification of the influence on contact forces, temperatures, and wear. For the slanted position, significantly lower friction temperatures are observed, leading to a higher ratio of abrasive wear. Overall, the rub test results demonstrate strong interactions between the contact forces, friction temperatures, and wear.