HVL Ci2Lab Team combines AI and Causal Inference for Predictive Maintenance in Complex Systems

Many real-world complex systems ranging from living organisms to electricity, transportation, and the internet of things operate through multiple types of interactions between their components to perform their functions. Therefore, these complex systems can be treated as multi-layer networks or networks of networks.

Despite advancements in network science, the vast majority of studies only deal with simplified models that are undirected, non-temporal, and those network models rarely take into account causal relationships and nonlinear structures.

This project’s objective is to develope a novel framework called the Causal Machine Learning for IoT Networks (CINet).

CINet outcomes will lead to an innovative toolset for understanding complex system (such as IoT systems) behaviors and performing predictive maintenance. The project leader at HVL is professor Reza Argandeh, director of the Connectivity, Information & Intelligence Lab (Ci2lab.com). This project is a collaboration with the Energy Advice company in Lithuania. Energy Advice provides the knowledge and IT systems to solve complex engineering challenges for various industries. 

For the implementation of project activities, the University intends to appoint university researchers with the necessary competence and experience in the implementation of similar projects.

Funding

This three-year-long project is financed by the Norwegian Financial Mechanism and by State budget funds of the Republic of Lithuania. The funds are granted under the Norwegian Financial Mechanism 2014-2021 Programme Business Development, Innovation and SMEs.

The total budget for the project is EUR 1,142,621.04, of which EUR 833,838.01 is funded by the EEA (Norway Grants). 

The project starts in September, 2021 and the project activities are planned to end at the 30th of April, 2024.