Predictive maintenance services use AI and data analysis techniques to detect small deviations in the normal behavior of a device or system early, so that necessary maintenance can be scheduled before a major failure occurs. Maintenance can thus be performed efficiently, at lower cost, and with less inconvenience to the end user.
In our research we focus on the use of hybrid AI techniques to quickly detect and accurately classify problems with e.g. HVAC systems, suboptimal comfort, or deviations from normal living patterns.
We also investigate how this information can be efficiently and dynamically visualized in dashboards.