PulseAugur
LIVE 08:16:39
research · [2 sources] ·
0
research

Gaussian Processes enable data-efficient control of nonlinear batch processes

By PulseAugur Editorial · Summary by gemini-2.5-flash-lite from 2 sources

Researchers have developed a new Gaussian Process-based Model Predictive Control (GP-MLMPC) scheme for nonlinear batch processes. This approach iteratively learns a dynamic model using data from initial batches, improving control performance over time without requiring prior mechanistic knowledge. The GP-MLMPC scheme incorporates uncertainty quantification for safe operation and has demonstrated significant improvements in tracking error and product yield in simulations. AI

Summary written by gemini-2.5-flash-lite from 2 sources. How we write summaries →

IMPACT Introduces a data-efficient method for controlling complex chemical processes, potentially reducing the need for extensive modeling and improving yields.

RANK_REASON This is a research paper detailing a new control scheme using Gaussian Processes.

Read on arXiv cs.LG →

COVERAGE [2]

  1. arXiv cs.LG TIER_1 · Tai Xuan Tan, Alexander Mitsos, Eike Cramer ·

    Iterative Model-Learning Scheme via Gaussian Processes for Nonlinear Model Predictive Control of (Semi-)Batch Processes

    arXiv:2604.22672v1 Announce Type: new Abstract: Batch processes are inherently transient and typically nonlinear, motivating nonlinear model predictive control (NMPC). However, adopting NMPC is hindered by the cost and unavailability of dynamic models. Thus, we propose to use Gau…

  2. arXiv cs.LG TIER_1 · Eike Cramer ·

    Iterative Model-Learning Scheme via Gaussian Processes for Nonlinear Model Predictive Control of (Semi-)Batch Processes

    Batch processes are inherently transient and typically nonlinear, motivating nonlinear model predictive control (NMPC). However, adopting NMPC is hindered by the cost and unavailability of dynamic models. Thus, we propose to use Gaussian Processes (GP) in a model-learning NMPC sc…

RELATED ENTITIES

RELATED TOPICS