Generative Model Predictive Control in Manufacturing Processes: A Review

2025-11-21

AI Summary

Manufacturing processes exhibit strong dynamics, nonlinearity, and multiple sources of uncertainty, rendering conventional control methods insufficiently robust; meanwhile, existing model predictive control (MPC) approaches are constrained by low-fidelity simplified models and the inability of deterministic machine learning (ML) to adequately characterize uncertainty. This paper proposes a generative ML-enhanced MPC paradigm that integrates generative modeling, nonlinear dynamical representation, uncertainty propagation estimation, and data distribution learning into a unified enhancement framework. The method overcomes the dual limitations of traditional MPC—model simplification and deterministic ML assumptions—achieving synergistic improvements in state estimation, predictive modeling, and receding-horizon optimization. Through systematic analysis of five representative approaches and extensive multi-scenario validation, the framework demonstrates significant gains in control accuracy and robustness under complex operating conditions. It establishes a scalable theoretical foundation and practical methodology for intelligent manufacturing control.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Intelligent Robots: State Estimation
• Planning, Routing, and Scheduling: Planning with Markov Models (MDPs, POMDPs)

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• User Modeling, Personalization and Recommendation: ML for personalized search and recommendations
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Manufacturing processes are inherently dynamic and uncertain, with varying parameters and nonlinear behaviors, making robust control essential for maintaining quality and reliability. Traditional control methods often fail under these conditions due to their reactive nature. Model Predictive Control (MPC) has emerged as a more advanced framework, leveraging process models to predict future states and optimize control actions. However, MPC relies on simplified models that often fail to capture complex dynamics, and it struggles with accurate state estimation and handling the propagation of uncertainty in manufacturing environments. Machine learning (ML) has been introduced to enhance MPC by modeling nonlinear dynamics and learning latent representations that support predictive modeling, state estimation, and optimization. Yet existing ML-driven MPC approaches remain deterministic and correlation-focused, motivating the exploration of generative. Generative ML offers new opportunities by learning data distributions, capturing hidden patterns, and inherently managing uncertainty, thereby complementing MPC. This review highlights five representative methods and examines how each has been integrated into MPC components, including predictive modeling, state estimation, and optimization. By synthesizing these cases, we outline the common ways generative ML can systematically enhance MPC and provide a framework for understanding its potential in diverse manufacturing processes. We identify key research gaps, propose future directions, and use a representative case to illustrate how generative ML-driven MPC can extend broadly across manufacturing. Taken together, this review positions generative ML not as an incremental add-on but as a transformative approach to reshape predictive control for next-generation manufacturing systems.

Problem

• Addressing dynamic uncertainties in manufacturing through generative model predictive control
• Overcoming simplified model limitations in traditional predictive control methods
• Integrating generative machine learning to enhance predictive modeling and uncertainty management

Innovation

• Generative ML learns data distributions and captures hidden patterns
• Generative ML enhances MPC by inherently managing uncertainty
• Generative ML transforms predictive control for next-generation manufacturing