Machine-learned digital phase switch for sustainable chemical production. (1st January 2023)

• Record Type: Journal Article
• Authors: Teng, Sin Yong; Galvis, Leonardo; Blanco, Carlos Mendez; Özkan, Leyla; Barendse, Ruud; Postma, Geert; Jansen, Jeroen
• Is Part Of: Journal of cleaner production. Volume 382(2023)
• Publication Date: 2023-01-01
• Subjects: Chemical reaction analysis -- Machine learning -- Neural architecture search -- Process improvement -- Cleaner process operations; Factory and trade waste -- Management -- Periodicals; Manufactures -- Environmental aspects -- Periodicals; Déchets industriels -- Gestion -- Périodiques; Usines -- Aspect de l'environnement -- Périodiques; 628.5
• DOI: 10.1016/j.jclepro.2022.135168
• Languages: English
• ISSNs: 0959-6526

Abstract

Abstract: Batch or semi-batch chemical reaction units often requires multiple operational phases to convert reactants to valuable products. In various chemical production facilities, the switching decision of such operational phases has to be confirmed and registered by the operating personnel. Imprecise switching of phases can waste a significant amount of time and energy for the reaction unit, which gives negative plant sustainability and costs. Additionally, automation for phase switching is rarely used due to the challenges of batch-to-batch variance, sensor instability, and various process uncertainties. Here, we demonstrate that by using a machine learning approach which includes optimized noise removal methods and a neural network (that was neural architecture searched), the real-time reaction completion could be precisely tracked (R 2 > 0.98). Furthermore, we show that the latent space of the evolved neural network could be transferred from predicting reaction completion to classifying the reaction operational phase via optimal transfer learning. From the optimally transfer learned network, a novel phase switch index is proposed to act as a digital phase switch and is shown to be capable of reducing total reactor operation time, with the verification of an operator. These intelligent analytics was studied on a reactive distillation unit for a reaction of monomers and acids to polyester in the Netherlands. The combined analytics gave a potential of 5.4% reaction batch time saving, 10.6% reaction energy savings, and 10.5% carbon emissions reduction. For the operator, this method also saves up to 6 h during the end discharge of the reaction. Graphical abstract: Explainable machine learning as the basis for digital phase switch to improve operational time, energy and environmental impact. Image 1 Highlights: Explainable machine learning approach is used to track multi-step reaction systems. Evolving neural network with Hampel filter provide precise tracking (R 2 > 0.98). Optimal transfer learning provides optimal operational phase switch in the system. The system improved with 5.4% batch time, 10.5% energy consumption, 10.5% emissions. Prediction stabilizes after 800 min and saves 6 h of operator monitoring time.