Maintenance

In-orbit servicing of satellites presents several challenges as the satellite hardware is exposed to external influences throughout its life cycle. These factors wear down the components and cause changes to their physical structure. In such cases, the limits of simple dis- and reassembly steps may be reached, as the gripping surfaces are no longer present or suitable. This paper proposes an approach of an adaptive grip position estimation in a CubeSat disassembly process. The relevant components are identified using CAD models and a 3D camera. The gripping positions are determined based on the geometry of the gripper and the point cloud of the component.

The paper specifies the genAI support needs for industrial maintenance against the background of a sociotechnical systems perspective. Emphasizing two needs, accessing implicit operator knowledge and prioritizing complex regulatory knowledge, a multi-layer architecture is outlined for an AI-based context-sensitive maintenance assistance system (MAS). The main purpose is to bridge knowledge gaps with genAI if human expertise and human implicit knowledge are not available and to cope with sub-process-specific challenges of multiple regulations. The MAS facilitates access to technical knowledge, distributes expertise, and shares implicit knowledge of experienced operators across different layers of information processing. The approach goes beyond standardization and has a high potential to enhance organizational as well as individual resilience.

Traditional quality control often falls short in high-mix, low-volume production environments due to variability and complexity. This project introduces an advanced workstation to boost industrial productivity and quality, developed with Axiomatic Design to ensure a clear link between customer needs, functional requirements, and design solutions. Combining polarization cameras, high-resolution imaging, adaptive lighting, and deep learning-based computer vision, the system performs high-accuracy inspection on quantity, quality, and compliance. A digital assistance system offers real-time feedback via an intuitive interface. Validation in a controlled environment confirmed both the system’s practical benefits and its scalability.

Personnel deployment planning in industrial maintenance is a complex challenge, as dispatchers often have to match incomplete customer requests with the appropriate employee skills. An AI-based assistance system can help by automatically analyzing relevant data and providing well-founded suggestions for employee selection. This article describes the user-centered development and introduction of such a system as part of a pilot project at a medium-sized service provider. The user-centered design ensures that dispatchers retain their autonomy. Involving employees from the outset creates acceptance and promotes a deeper understanding of the system’s advantages.

The decarbonization of the energy sector is crucial for a climate-neutral EU, as a large proportion of greenhouse gas emissions come from energy use. Especially the wind energy sector, with its high material costs, faces major challenges. The rapid expansion of wind energy requires innovative solutions to establish sustainable End-of-Life (EoL) management practices. A digital decision-making framework for sustainable EoL strategies is therefore extremely useful.

This article describes a predictive maintenance approach in which a flexible sensor toolkit records and a prediction model monitors the component wear within technical systems. The condition of the components is not determined continuously, but based on time-discrete measurements. The prediction model predicts the presumable remaining useful life of the components based on the recorded data. A machine learning tool is trained with historical wear curves and used to generate the prediction. The training data is collected through statistical tests in which the influencing variables and characteristic curves of different types of wear are identified.