Thermodynamics-based neural network and the optimization of ethylbenzene production process. (10th May 2021)

• Record Type: Journal Article
• Authors: Hang, Peng; Zhou, Leihao; Liu, Guilian
• Is Part Of: Journal of cleaner production. Volume 296(2021)
• Publication Date: 2021-05-10
• Subjects: BP neural Network -- Chemical potential -- Equilibrium constant -- Ethylbenzene -- Simulation -- Optimization; 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.2021.126615
• Languages: English
• ISSNs: 0959-6526

Abstract

Abstract: Thermodynamics is significantly important for analyzing properties and establishing mechanism models of chemical process. Based on the characteristics of the reaction and distillation process and their similarity with back-propagation process, improved BP neural network models are built for reactor and distillation column. In the reactor model, the chemical potential is used to adjust the errors of output nodes. For distillation column, the errors of output nodes corresponding components are adjusted according to their gas-liquid equilibrium constant. The models have improved predictive capability and convergence. An ethylbenzene unit is simulated and optimized by the proposed method, and its heating utility consumption is reduced by 55.2%. Highlights: Chemical potential and equilibrium constants are introduced into neural network model. An analogy is drawn between hypothetical chemical and back-propagation processes. The interpretability of neural networks is improved. An ethylbenzene process is optimized based on the improved neural network.