Process Prediction with Digital Twins

Abstract

Process discovery from event logs as well as process prediction using process models at runtime are increasingly important aspects to improve the operation of digital twins of complex systems. The integration of process mining functionalities with model-driven digital twin architectures raises the question which models are important for the model-driven engineering of digital twins at designtime and at runtime. Currently, research on process mining and model-driven digital twins is conducted in different research communities. Within this position paper, we motivate the need for the holistic combination of both research directions to facilitate harnessing the data and the models of the systems of the future at runtime. The presented position is based upon continuous discussions, workshops, and joint research between process mining experts and software engineering experts in the Internet of Production excellence cluster. We aim to motivate further joint research into the combination of process mining techniques with model-driven digital twins to efficiently combine data and models at runtime.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 64 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.