Process Mining—Discovery, Conformance, and Enhancement of Manufacturing Processes

Abstract

Process-orientation has gained significant momentum in manufacturing as enabler for the integration of machines, sensors, systems, and human workers across all levels of the automation pyramid. With process orientation comes the opportunity to collect manufacturing data in a contextualized and integrated way in the form of process event logs (no data silos) and with that data, in turn, the opportunity to exploit the full range of process mining techniques. Process mining techniques serve three tasks, i.e., (i) the discovery of process models based on process event logs, (ii) checking the conformance between a process model and process event logs, and (iii) enhancing process models. Recent studies show that particularly, (ii) and (iii) have become increasingly important. Conformance checking during run-time can help to detect deviations and errors in manufacturing processes and related data (e.g., sensor data) when they actually happen. This facilitates an instant reaction to these deviations and errors, e.g., by adapting the processes accordingly (process enhancement), and can be taken as input for predicting deviations and errorsfor future process executions. This chapter discusses process mining in the context of manufacturing processes along the phases of an analysis project, i.e., preparation and analysis of manufacturing data during design and run-time and the visualization and interpretation of process mining results. In particular, this chapter features recommendations on how to employ which process mining technique for different analysis goals in manufacturing.