CrystalGPT: Enhancing system-to-system transferability in crystallization prediction and control using time-series-transformers

TL;DR

CrystalGPT leverages time-series-transformers to significantly improve transferability and accuracy in crystallization process prediction and control across multiple systems, outperforming existing models.

Contribution

We introduce CrystalGPT, a novel transformer-based framework that enhances system-to-system transferability in crystallization prediction and control tasks.

Findings

CrystalGPT achieves eight times lower cumulative error than existing ML models.

The model demonstrates successful transfer to unencountered systems.

Coupling CrystalGPT with a predictive controller reduces setpoint tracking variance to 1%.

Abstract

For prediction and real-time control tasks, machine-learning (ML)-based digital twins are frequently employed. However, while these models are typically accurate, they are custom-designed for individual systems, making system-to-system (S2S) transferability difficult. This occurs even when substantial similarities exist in the process dynamics across different chemical systems. To address this challenge, we developed a novel time-series-transformer (TST) framework that exploits the powerful transfer learning capabilities inherent in transformer algorithms. This was demonstrated using readily available process data obtained from different crystallizers operating under various operational scenarios. Using this extensive dataset, we trained a TST model (CrystalGPT) to exhibit remarkable S2S transferability not only across all pre-established systems, but also to an unencountered system. CrystalGPT achieved a cumulative error across all systems, which is eight times superior to that of existing ML models. Additionally, we coupled CrystalGPT with a predictive controller to reduce the variance in setpoint tracking to just 1%.