Data-driven methods based on artificial intelligence (AI) are powerful yet flexible tools for gathering knowledge and automating complex tasks in many areas of science and practice. Despite the rapid development of the field, the existing potential of AI methods to solve recent industrial, corporate and social challenges has not yet been fully exploited. Research shows the insufficient practicality of AI in domain-specific contexts as one of the main application hurdles. Focusing on industrial demands, this publication introduces a new paradigm in terms of applicability of AI methods, called Usable AI (UAI). Aspects of easily accessible, domain-specific AI methods are derived, which address essential user-oriented AI services within the UAI paradigm: usability, suitability, integrability and interoperability. The relevance of UAI is clarified by describing challenges, hurdles and peculiarities of AI applications in the production area, whereby the following user roles have been abstracted: developers of cyber–physical production systems (CPPS), developers of processes and operators of processes. The analysis shows that target artifacts, motivation, knowledge horizon and challenges differ for the user roles. Therefore, UAI shall enable domain- and user-role-specific adaptation of affordances accompanied by adaptive support of vertical and horizontal integration across the domains and user roles.

This work addresses the fabrication of hydrophobic surface structures by means of direct laser interference patterning using an optical setup optimized for high throughput processing. The developed optical assembly is used to shape the laser beam intensity as well as to obtain the two sub beams required for creating the interference pattern. The resulting beam profile consists of an elongated rectangular laser spot with 5.0 mm × 0.1 mm size, which enables the optimized utilization of the laser fluence available from an ns-pulsed laser with a wavelength of 1064 nm. Depending on the pulse repetition rate applied, heating of the substrate volume generated by heat accumulation encouraged exceptionally high aspect ratios of the trench structures due to melt flow dynamic material deformation. Finally, water contact angle measurements of the produced structures permitted the demonstration of the capability of controlling the wetting angle, in which this effect does not only depend on the height of the generated surface structures but also on their morphology.

Multi-material jetting (CerAM MMJ, previously T3DP) enables the additive manufacturing of ceramics, metals, glass and hardmetals, demonstrating comparatively high solid contents of the processed materials. The material is applied drop by drop onto a substrate. The droplets can be adapted to the component to be produced by a large degree of freedom in parameterization. Thus, large volumes can be processed quickly and fine structures can be displayed in detail, based on the droplet size. Data-driven methods are applied to build process knowledge and to contribute to the optimization of CerAM MMJ manufacturing processes. As a basis for the computational exploitation of mass sensor data from the technological process chain for manufacturing a component with CerAM MMJ, a data management plan was developed with the help of an engineering workflow. Focusing on the process step of green part production, droplet structures as intermediate products of 3D generation were described by means of droplet height, droplet circularity, the number of ambient satellite particles, as well as the associated standard deviations. First of all, the weighting of the factors influencing the droplet geometry was determined by means of single factor preliminary tests, in order to be able to reduce the number of factors to be considered in the detailed test series. The identification of key influences (falling time, needle lift, rising time, air supply pressure) permitted an optimization of the droplet geometry according to the introduced target characteristics by means of a design of experiments.