CrystalGPT: Enhancing system-to-system transferability in crystallization prediction and control using time-series-transformers
This addresses the challenge of custom-designed models in chemical process control, enabling more efficient and adaptable digital twins for industrial applications.
The paper tackled the problem of poor system-to-system transferability in machine-learning-based digital twins for crystallization prediction and control, achieving an eight times lower cumulative error compared to existing models and reducing setpoint tracking variance to 1% when coupled with a predictive controller.
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%.