Employees at swa Netze lack an overview of the stock of usable spare parts and emergency materials. A tool for cross-departmental inventory management would be desirable, with which material stocks can be consolidated and sustainably reused in order to save money and resources. →
In collaboration with XITASO, we have developed a trade fair showcase that presents object recognition and segmentation using neural networks. By using RGB and infrared cameras, road users such as cyclists and pedestrians are recognised under different environmental conditions. Pre-trained models such as YOLOv8 and Mask R-CNN are used, which have been subsequently fine-tuned to infrared data to enable reliable detection even in poor lighting conditions. →
The increasing demand for components with tailored properties and functionally graded materials featuring adjustable interfaces is raising the requirements in gravity sand and die casting processes of aluminium. In response to these challenges, a novel controlled process based on injector casting is being developed. →
This paper presents a conceptual approach and a successful implementation guide for a digital twin of a modular manufacturing system. →
Predictive maintenance optimizes the maintenance of machines by preventing unplanned downtime and unnecessary repairs. The implementation is made possible by modern machine learning methods and a well-developed data infrastructure. In the research project PAS4PCM – in cooperation with Rational AG and on the basis of collected device data – the research group HSA_dsg of the Faculty of Computer Science at the Technical University of Augsburg is developing a concept and an implementation of such a system. →
Modern Industry 4.0 applications can be implemented with the Local-First Cooperation design principle. Proven methods of artificial intelligence (AI) can be used to solve problems. Distributed software agents communicate directly, coordinate themselves with others, and cooperate to solve local problems. Symbolic and sub-symbolic AI complement each other in problem solving. In this way, complex planning and optimization tasks can be implemented using resilient systems. These systems of the Industrial Internet of Things increasingly show self-x properties of organic computing. →
Manufacturing industries must address the needs of their human resources to maintain efficiency and profitability in the global markets. By fostering safe, psychologically supportive working conditions, companies can improve work performance and retain their workforce in the face of labor shortage. →
Workplaces in production contexts are subject to various changes due to automation and robotics. Apart from the expected positive effects on the safety and health of workers, there is also evidence that prolonged supervisory control can lead to increased cognitive workload as well as biomechanical stress. We present methods for an objective measurement of cognitive/emotional and biomechanical load, such as eye or motion tracking as well as subjective measures. →
As global markets increasingly demand sustainability and circular economy concepts are on the rise, products have to change as well. In this state of research paper, we discuss effects of circular economy concepts on production. →
The production industry has the potential to make a significant contribution to the transition towards a more sustainable future. Given the pressing nature and growing popularity of this topic, a considerable number of producing companies have already implemented sustainability goals. Nevertheless, at the operational level, decisions are still largely driven by economic considerations. →