Learning Actionable World Models for Industrial Process Control

2025-03-03

AI Summary

Digital twin modeling for industrial processes faces challenges under data scarcity, hindering proactive control. Method: This paper proposes a lightweight, actionable world model that employs disentangled latent representations, integrating joint embedding prediction with contrastive learning to ensure bidirectional predictability among process inputs, latent space, and outputs—thereby preserving causal interpretability of control actions. Crucially, the method reduces reliance on large-scale labeled datasets. Contribution/Results: Evaluated on highly dynamic, strongly nonlinear injection molding, the model generates concrete, executable control policies. Experiments demonstrate significant improvements in process stability and operational boundary preservation, enabling a paradigm shift in industrial process monitoring—from passive observation to active intervention.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Cognitive Modeling & Cognitive Systems: Computational Creativity
• Planning, Routing, and Scheduling: Model-Based Reasoning

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

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 in- 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 that influence 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.

Problem

• Develop AI for active industrial process control from limited data
• Learn disentangled latent representations for fine-grained process control
• Validate method on unstable processes like plastic injection molding

Innovation

• Learning world models for industrial control
• Disentangling process parameters in latent space
• Contrastive learning in joint embedding architecture