With increased automation, electrification and conversion to renewable energy supply, high costs arise in connection with downtimes and unplanned maintenance of systems and their components. Against this background, this project will develop new methods to minimize the costs of planned maintenance of a system or component, under conditions regarding the system's ability to function properly.
Facts about the project
Project manager Karl-Olof Lindahl Other project members Björn Lindenberg, Jonas Nordqvist, Magnus Perninge, Roger Pettersson Participating organizations Linnaeus University Financier Linnaeus University Timetable 2020– Subject Mathematics (Department of Mathematics, Faculty of Technology) Electrical engineering (Department of Physics and Electrical Engineering, Faculty of Technology)
More about the project
The reliability of a system is basically about a system's ability to function without failure. An important way to increase the reliability of a system (or equipment) is to perform scheduled maintenance. This in itself can be costly.
In this project, we focus in particular on developing algorithms in reinforcement learning with the aim of scheduling planned maintenance at a minimal cost, under the condition that systems meet given requirements for reliability.
In the project, we develop:
Models for reliability
Tailor-made algorithms for optimal scheduling of maintenance