A Tutorial on Data-Driven Petri Net Model Extraction and Simulation for Digital Twins in Smart Manufacturing

The adoption of data-driven Digital Twins in smart manufacturing systems necessitates robust, data-driven modeling techniques. Stochastic Petri nets offer a formal framework for capturing concurrency and synchronization in discrete-event systems, making them well-suited for modeling smart manufacturing systems. This tutorial provides a hands-on introduction to extracting stochastic Petri net models from system event logs. Using our Python-based stochastic Petri nets library (PySPN), participants will learn how to: (1) define ground-truth models using the Petri Net Markup Language (PNML), (2) generate event logs by simulating these models, and (3) apply process mining techniques to automatically reconstruct stochastic Petri net models from real or simulated data. Two case studies illustrate the end-to-end workflow,
from data generation to model validation, within the context of developing Digital Twins. By the end of the tutorial, participants will gain practical skills in data-driven stochastic Petri nets modeling for Digital Twins applications in manufacturing.