Learning Actionable World Models for Industrial Process Control

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Yan, Peng, Abdulkadir, Ahmed, Schatte, Gerrit A., Aguzzi, Giulia, Gha, Joonsu, Pascher, Nikola, Rosenthal, Matthias, Gao, Yunlong, Grewe, Benjamin F., Stadelmann, Thilo
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912346136379392
author Yan, Peng
Abdulkadir, Ahmed
Schatte, Gerrit A.
Aguzzi, Giulia
Gha, Joonsu
Pascher, Nikola
Rosenthal, Matthias
Gao, Yunlong
Grewe, Benjamin F.
Stadelmann, Thilo
author_facet Yan, Peng
Abdulkadir, Ahmed
Schatte, Gerrit A.
Aguzzi, Giulia
Gha, Joonsu
Pascher, Nikola
Rosenthal, Matthias
Gao, Yunlong
Grewe, Benjamin F.
Stadelmann, Thilo
contents To go from (passive) process monitoring to active process control, an effective AI system must learn about the behavior of the complex system from very limited training data, forming an ad-hoc digital twin with respect to process inputs and outputs that captures the consequences of actions on the process's world. We propose a novel methodology based on learning world models that disentangles process parameters in the learned latent representation, allowing for fine-grained control. Representation learning is driven by the latent factors influencing the processes through contrastive learning within a joint embedding predictive architecture. This makes changes in representations predictable from changes in inputs and vice versa, facilitating interpretability of key factors responsible for process variations, paving the way for effective control actions to keep the process within operational bounds. The effectiveness of our method is validated on the example of plastic injection molding, demonstrating practical relevance in proposing specific control actions for a notoriously unstable process.
format Preprint
id arxiv_https___arxiv_org_abs_2503_01411
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Learning Actionable World Models for Industrial Process Control
Yan, Peng
Abdulkadir, Ahmed
Schatte, Gerrit A.
Aguzzi, Giulia
Gha, Joonsu
Pascher, Nikola
Rosenthal, Matthias
Gao, Yunlong
Grewe, Benjamin F.
Stadelmann, Thilo
Machine Learning
Artificial Intelligence
Systems and Control
I.2.0; I.2.4
To go from (passive) process monitoring to active process control, an effective AI system must learn about the behavior of the complex system from very limited training data, forming an ad-hoc digital twin with respect to process inputs and outputs that captures the consequences of actions on the process's world. We propose a novel methodology based on learning world models that disentangles process parameters in the learned latent representation, allowing for fine-grained control. Representation learning is driven by the latent factors influencing the processes through contrastive learning within a joint embedding predictive architecture. This makes changes in representations predictable from changes in inputs and vice versa, facilitating interpretability of key factors responsible for process variations, paving the way for effective control actions to keep the process within operational bounds. The effectiveness of our method is validated on the example of plastic injection molding, demonstrating practical relevance in proposing specific control actions for a notoriously unstable process.
title Learning Actionable World Models for Industrial Process Control
topic Machine Learning
Artificial Intelligence
Systems and Control
I.2.0; I.2.4
url https://arxiv.org/abs/2503.01411