Hennebold, ChristophChristophHenneboldIslam, Muhammad MomotazulMuhammad MomotazulIslamKrauß, JonasJonasKraußHuber, MarcoMarcoHuber2025-04-022025-04-022024https://publica.fraunhofer.de/handle/publica/48604910.1016/j.procir.2024.10.2422-s2.0-852150039112-s2.0-85213003094The extraction of process knowledge and its use for modeling and subsequent analysis is a very valuable approach to optimizing processes. Process Mining (PM) methods are widely used knowledge extraction techniques based on process knowledge recorded in event logs. One shortcoming is that PM approaches cannot easily access data in non-event log format, and secondly, that models are generated using directly-follows relations, which in the case of processes with concurrent activities means that process transitions may not be modeled correctly, and the resulting models do not correspond to reality as well as being unnecessarily complex. In addition, increasing digitization in manufacturing enables an ever greater collection of various data sources throughout the process with varying levels of information. Besides PM, in recent years great progress has been made in learning causal structures via causal discovery (CD) as well as in explicitly using additional expert knowledge. We argue that CD and expert knowledge are valuable additions to existing PM based approaches, as they allow knowledge extraction and modeling on different process levels. To combine these levels of information, this paper uses a manufacturing use case to show heterogeneous data sources and expert knowledge are used to create hybrid models. The results show that the combination of data-driven modeling methods with expert knowledge help to compensate for the weaknesses of the individual methods and achieve better overall results.entrueCausal DiscoveryDomain KnowledgeHybrid ModelingProcess Mining600 Technik, Medizin, angewandte Wissenschaftenjournal article