16 Million NOK to R&D project on AI -supported scheduling
We are pleased to announce that Visavi has been awarded a major grant (16 MNOK) from the Research Council of Norway in support of our “OptiPlan” initiative. This project will turn our solution into a game-changing enabler of more efficient maintenance planning and execution by using powerful algorithms for automated work scheduling. It will also develop new work processes that will enable industry users to fully rely on and gain full value from such intelligent decision support. The work will be done in collaboration with a consortium of research and industry partners that already include the Institute for Energy Technology (IFE) and Borregaard.
Maintenance is an essential activity to ensure safety and productivity in all major industries. Maintenance tasks in such industries are very complex due to the sheer number of tasks and resources and constraints involved. Scheduling maintenance work is therefore a very complex problem. Manually finding solutions to the scheduling problem is not only time-consuming but highly inefficient both for the maintenance companies and their customers, and inefficient solutions are costly because they lead to increase downtime as well as poor utilisation of personell and other costly resources. Still, scheduling is today largely a manual processes because existing tools in this area suffer from some major shortcomings: They are complex specialist tools, yet no single tool takes into account the full range of dimensions in the complex “puzzle” to be solved, and they are not well suited to handle the highly dynamic nature of the problem. Rapid changes in weather conditions, delays and missing personell or part arrivals call for plans to adapt rapidly, but current tools and manual practices are nowhere near being able to completely and rapidly reassess the totality of the schedule.
OptiPlan will make VISAVI a game changer with the potential to become a key international player in the growing maintenance market through an innovative optimisation-based maintenance planning engine that will significantly reduce costs by increasing the effectiveness and efficiency of maintenance. The new solution will employ multivariable optimization to automate scheduling and also use machine learning to add further automation and robustness. The project will also be highly mindful of the human and organizational factors and challenges of attempting such a radical transformation of well-established, critical work processes. An interdisciplinary approach will be adopted to ensure a holistic solution with proven customer value.