Korean Journal of Chemical Engineering, Vol.40, No.1, 37-45, January, 2023
Exploring advanced process equipment visualization as a step towards digital twins development in the chemical industry: A CFD-DNN approach
Several studies involving the implementation of artificial neural network (ANN) technology for process design, monitoring, and control are under active research. This new technology has shown great potential in advancing chemical processes through the development of digital twins and smart factories. In joining this race, the current study explores the capability of physics-based modeling (CFD) and artificial neural networks for advanced process data visualization. Here, 20 CFD simulations of a multi-tubular reactor equipped with a Zn-Fe-Cr catalyst for synthesizing butadiene were executed. The simulation result was extracted as 3-D data with XYZ coordinates and imported into a python-based DNN model for training and cross-validation. An accuracy of 99.2% was obtained from the ANN surrogate model. The trained model was used to predict 3D data in terms of the process temperature, concentration, etc. The 3D data was then imported into a Paraview® VTK for detailed virtualization. Cross-sectional, longitudinal, and radial distribution of the various process variables, such as concentration profiles and pressure contour, were effectively visualized. A graphic user interface was further developed using Python for real-time visualization of the equipment. This implementation is analogous to the digital twin and is employable for online system optimization, high accuracy, low computational cost, and seamlessly integrable 3D real-time visualization system design for efficient, quick, and easy plant decision-making.
Keywords:Digital Twins;CFD;Artificial Intelligence;Deep Neural Networks;Optimization;Chemical Industry
- Fuller A, Fan Z, Day C, Barlow C, IEEE Access, 8, 108952 (2020)
- Vrabič R, Erkoyuncu JA, Butala P, Roy R, Procedia Manuf., 16, 139 (2018)
- Fei X, Shah N, Verba N, Chao KM, Sanchez-Anguix V, Lewandowski J, James A, Usman Z, Future Generation Computer Syst., 90, 435 (2019)
- Qi Q, Tao F, IEEE Access, 6, 3585 (2018)
- Mandolla C, Petruzzelli AM, Percoco G, Urbinati A, Comput. Ind., 109, 134 (2019)
- Chhetri SR, Faezi S, Canedo A, Al Faruque MA, Proceedings of the International Conference on Internet of Things Design and Implementation (2019).
- He Y, Guo J, Zheng X, IEEE Signal Process. Mag., 35, 120 (2018)
- Chen X, Kang E, Shiraishi S, Preciado VM, Jiang Z, Proceedings - 21st ACM/IEEE International Conference on Model Driven Engineering Languages and Systems, MODELS 2018 144 (2018).
- Magargle R, Johnson L, Mandloi P, Davoudabadi P, Kesarkar O, Krishnaswamy S, Batteh J, Pitchaikani A, Proceedings of the 12th International Modelica Conference, May 15-17, 2017 132, 35 (2017).
- Karadeniz AM, Arif I, Kanak A, Ergün S, Proceedings - IEEE International Symposium on Circuits and Systems, 2019-May (2019).
- Coraddu A, Oneto L, Baldi F, Cipollini F, Atlar M, Savio S, Ocean Eng., 186, 106063 (2019)
- Madni AM, Madni CC, Lucero SD, Systems, 7, 7 (2019)
- Bilberg A, Malik AA, CIRP Annals, 68, 499 (2019)
- Glaessgen EH, Stargel DS, Collection of Technical Papers - AIAA/ASME/ASCE/AHS/ASC Structures, Structural Dynamics and Materials Conference (2012).
- Petrik D, Herzwurm G, IWSiB 2019 - Proceedings of the 2nd ACM SIGSOFT International Workshop on Software-Intensive Business: Start-Ups, (2019).
- Zheng Y, Yang S, Cheng H, J. Am. Intelligence Humanized Computing, 10, 1141 (2019)
- Gbadago DQ, Moon J, Kim M, Hwang S, Chem. Eng. J., 409, 128163 (2021)
- Kim H, Park M, Kim CW, Shin D, Comput. Chem. Eng., 125, 476 (2019)
- Sterrett JS, Mcllvried HG, Ind. Eng. Chem. Process Des. Dev., 13, 54 (1974)