There has been a noticeable trend in intralogistics towards driverless transport systems that navigate their own way around the warehouse. However, these transport systems lack the human ability to detect faults as they occur and to take appropriate remedial action.
In the AiF project proSVIFT, the Information Visualization and Visual Analytics department is working together with the Fraunhofer LBF on an approach for automated self-protection against critical component and function failures within a vehicle. This is based on systematic condition monitoring, fault detection and development of safeguarding measures using sensory detection and probability-based analytics. The focus is on optimizing the trade-off between availability and of the transportation system.
Development of a visual-interactive editor
In this project, we are developing a visual-interactive editor that not only supports the creation of a likelihood- and risk-based knowledge model but also facilitates the appropriate evaluation and interpretation of the modeled failure modes and their impact on system reliability and safety.
To ensure right from the start the practical applicability of its results, the project is being supervised by a committee whose members are drawn from industry.