Project information
Project manager
Michael Dorn, Jaume Nualart Vilaplana
Other project members
Rafael Messias Martins, Osama Abdeljaber, Carl Larsson
Participating organizations
Linnaeus University, the InfraVis node at Linnaeus University
Financier
InfraVis, own funding
Timetable
Mar–Dec 2023
Subject
Building technology (Department of Building Technology, Faculty of Technology)
Computer science (Department of Computer Science and Media Technology, Faculty of Technology)
More about the project
During the last years, numerous projects have been realized within the research group Structural Health Monitoring as part of the Department of Building Technology’s research. Those projects often run over multiple years and collect information from a vast number of sensors at very tight time intervals. Hence, proper data handling, visualization, exploration and analysis are required to make the data understandable and interpretable by deploying big data approaches.
InfraVis is a national infrastructure, funded by the Swedish Research Council (Vetenskapsrådet) and nine partner universities, supporting researchers from all scientific fields to maintain their data and make it easily accessible. The collaboration with the Linnaeus University node of InfraVis (led by Andreas Kerren at the Department of Computer Science and Media Technology) has the goal to create a visualization dashboard which can be used by researchers in building technology and their collaboration partners.
The visualization approach chosen is based on software and libraries with open-source and free licenses and requires low hardware specifications. The distribution of the system can hence be done easily, and it will be able to run out of the box on basically any computer with low maintenance efforts. The visualization methods are based on modular elements which are easily adaptable and can be modified and extended later on.
The low-level approach allows to interpret the collected data quickly and at the same time thoroughly. Trends and predictions can be derived easily while keeping the overview. The graphs and plots are also helpful in presenting the long-term data for collaboration partners or scientific audiences, e.g., at conferences.
In an upcoming extension, trend predictions are planned where the previous data is extrapolated into the near future. This allows to detect deviations which can be signals for problems. These can be followed up so that damage can be prevented early. A second addition will be to add functionalities for derived values, e.g., cases where two signals have to be interpreted simultaneously.
The project is part of the research in the Structural Health Monitoring and Information and Software Visualization (ISOVIS) research group and the Linnaeus Knowledge Environments Green Sustainable Development and Digital Transformations.
Staff