Combing metaheuristics and process mining: Improving cobot placement in a combined cobot assignment and job shop scheduling problem

Human workers can share a workspace with modern collaborative robots (cobots). The main differences to traditional robots are, that workers do not need a safety distance when interacting with cobots, as they move slower than typical industrial robots. Cobots also have fast setup times compared to traditional resources. The hybridization is based on a previous work of the authors, where a job shop scheduling problem that is extended with a robot to workstation assignment with a hybrid genetic algorithm is solved. In this paper, the potential of hybridizing an optimization algorithm with process mining techniques to improve the solution quality by gaining information on the solution structure is analyzed. This additional information should help to guide the search process. Process mining techniques are presented to analyze the solutions and learn from them. The idea of this work is to understand the solutions generated by the genetic algorithms as process executions, e.g., the production of a part as a process instance executed across the selected work stations. Then, by generating process event log data out of selected solutions, state-of-the-art process mining techniques can be used as visualization and scanning tools for the underlying processes. This way, for example, bottleneck workstations in the production process can be highlighted. Based on created scenarios, this paper demonstrates how genetic algorithms and process mining techniques can be combined. In the future, it is planned that information that is mined from generated logs of an evaluation framework is used to improve the performance of hybrid genetic algorithms by using this information in a feedback loop. Generated insight in cobot placement can also be used for prescriptive analytics in real-world manufacturing companies that want to utilize cobots. The focus of this paper lies in the discussion of the usage of potential information extracted from process mining.