Joint Parameter and State-Space Bayesian Optimization: Using Process Expertise to Accelerate Manufacturing Optimization

2026-02-04

arXiv.org

AI Summary

This work addresses the inefficiency of conventional Bayesian optimization in high-dimensional multistage manufacturing processes, where intermediate observations and process structure are typically ignored. To overcome this limitation, the authors propose a novel framework that integrates expert knowledge with structured probabilistic modeling. Specifically, expert-guided low-dimensional feature extraction is combined with a partially observable Gaussian process network (POGPN) and joint parameter–state space (JPSS) modeling to effectively leverage high-dimensional temporal intermediate observations within Bayesian optimization. The process structure is explicitly encoded using a directed acyclic graph (DAG). Evaluated on a multistage bioethanol production simulation, the proposed method doubles optimization speed, achieves target performance thresholds more reliably, and substantially reduces time and resource consumption.

Abstract

Bayesian optimization (BO) is a powerful method for optimizing black-box manufacturing processes, but its performance is often limited when dealing with high-dimensional multi-stage systems, where we can observe intermediate outputs. Standard BO models the process as a black box and ignores the intermediate observations and the underlying process structure. Partially Observable Gaussian Process Networks (POGPN) model the process as a Directed Acyclic Graph (DAG). However, using intermediate observations is challenging when the observations are high-dimensional state-space time series. Process-expert knowledge can be used to extract low-dimensional latent features from the high-dimensional state-space data. We propose POGPN-JPSS, a framework that combines POGPN with Joint Parameter and State-Space (JPSS) modeling to use intermediate extracted information. We demonstrate the effectiveness of POGPN-JPSS on a challenging, high-dimensional simulation of a multi-stage bioethanol production process. Our results show that POGPN-JPSS significantly outperforms state-of-the-art methods by achieving the desired performance threshold twice as fast and with greater reliability. The fast optimization directly translates to substantial savings in time and resources. This highlights the importance of combining expert knowledge with structured probabilistic models for rapid process maturation.

Problem

• Bayesian optimization
• high-dimensional multi-stage systems
• intermediate observations
• state-space time series
• process structure

Innovation

• Bayesian optimization
• Joint Parameter and State-Space modeling
• Partially Observable Gaussian Process Networks
• process expert knowledge
• multi-stage manufacturing