A simple coupled ANNs‐RSM approach in modeling product distribution of Fischer‐Tropsch synthesis using a microchannel reactor with Ru‐promoted Co/Al2O3 catalyst. (22nd November 2019)

• Record Type: Journal Article
• Authors: Sun, Yong; Yang, Gang; Xu, Mengxia; Xu, Jian; Sun, Zhi
• Is Part Of: International journal of energy research. Volume 44:Number 2(2020)
• Page Start: 1046
• Page End: 1061
• Publication Date: 2019-11-22
• Subjects: ANNs‐RSM -- cobalt catalyst -- comprehensive kinetics -- Fischer‐Tropsch synthesis -- microchannel reactor; Power resources -- Periodicals; Power (Mechanics) -- Periodicals; Power resources -- Research -- Periodicals; 621.042
• DOI: 10.1002/er.4990
• Languages: English
• ISSNs: 0363-907X

Abstract

Summary: A simple approach using hybrid artificial neural networks (ANNs)‐response surface methodology (RSM) was developed to model the detailed product distribution using Ru‐promoted cobalt‐based catalyst with Al2 O3 as the support in a microchannel reactor for Fischer‐Tropsch (FT) synthesis. Using the independent process parameters for training, the established model is capable of predicting hydrocarbon production distributions, ie, paraffin formation rate (C2 ‐C15 ) and olefin to paraffin ratio (OPR C2 ‐C15 ) within acceptable uncertainties. The ANNs‐RSM model and comprehensive mechanistic model using the Langmuir‐Hinshelwood‐Hougen‐Watson (LHHW) approach were compared to identify a few inherent advantages of the proposed model in modeling complex FT synthesis. The proposed ANNs‐RSM model shows its appealing merits, ie, faster converge and higher accuracy (less than ±10% uncertainties was achieved from ANNs‐RSM model, while LHHW model achieved less than ±15% uncertainties except a few exceptional high errors uncertainties at certain experimental conditions). The statistical significances to the product distributions and hydrocarbon formation rate during FT synthesis could be easily identified and quantitatively analyzed by the established ANNs‐RSM model. The future effective alternative of kinetic study of the complex system such as FT synthesis in the microstructured reactor might follow the methods of using empirical reliable approach for process optimization together with mechanistic kinetic study for detailed reaction pathway discrimination. Abstract : A novel simple approach of coupling AANs (artificial neuron networks) with RSM (response surface methodology) was developed to model the detailed product distribution of Fischer‐Tropsch (FT) synthesis in a microchannel reactor using Ru‐promoted Co/Al2 O3 catalyst. With experimental data as the training data set, the setup model is able to present a very good result in predicting hydrocarbon product distributions and olefin to paraffin ratio with different carbon numbers (C2 ‐C15 ) during FT synthesis. The proposed ANNs‐RSM model shows its appealing advantages of fast converge and higher accuracy. The established model is also able to evaluate the effect of process parameters upon the significances of product distributions and hydrocarbon formation rate during FT synthesis.