By combining methods from the fields of information technology and operations research, production processes can be designed to be more efficient. The application of algorithms can be developed and tested in our own laboratory through the use of demonstrators.

We can simulate sequence planning and the optimisation of set-up times, as well as maintenance plans or resource allocation. The use of autonomous robots and the development of efficient planning strategies for vehicles can also be evaluated through simulations. Parameter studies and sensitivity analyses are also possible thanks to a range of interfaces.

Machine learning methods such as Gaussian processes & neural networks can predict figures based on system utilisation. Among other things, this enables the dynamic selection of control rules. What’s more, this also enables the evaluation of cause-effect relationships within processes, as well as an evaluation of the correlations between (input) parameters and their effects on the process.

Some examples of typical problems include optimising the installation and maintenance of wind turbines, optimising how high-priority tasks are dealt with in production operations, optimising intralogistics using the example of goods provision in the retail industry, dynamic rule selection in sequence planning and much more.