predictive maintenance

In today’s manufacturing industry, digital twins are a key enabler for optimizing production processes and efficient resource use. However, creating digital twins is often associated with high or difficult-to-estimate costs and typically requires unknown characteristic values, such as material parameters, making practical implementation challenging. With RAPIDZ, we present a tool for creating and using digital twins that overcomes these barriers through its modular structure. The virtual modeling of physical systems enables comprehensive analysis and real-time forecasting of material flows, energy consumption and machine performance. The use of RAPIDZ increases production line efficiency, enhances flexibility and response time, and enables proactive maintenance to minimize downtime.

The combination of product service systems and big data requires a change in the existing, traditional business models and a repositioning of the companies. Since these changes are often a challenge, this article uses the example of predictive maintenance to present the influences of big data and product service systems on the business models of medium-sized companies in mechanical and plant engineering. Based on a systematic literature review in combination with expert interviews, numerous practical business model implications were obtained, providing sound guidance for industry representatives.

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.