A new operator training system that trains both control room and field operators by coupling dynamic processes and accident simulations, thereby preventing potential hazards in a chemical plant, is proposed. The two types of operators were trained in different training environments . a conventional distributed control system interface for the control room operators and an augmented virtual reality-based system for the field operators. To provide quantitative process changes and accident information driven by the actions of the trainees in real time, two types of simulation, dynamic processes and accidents, were implemented. The former was accomplished through a real-time dynamic process simulation using Aspen HYSYS; the latter was achieved by replacing the high-accuracy accident simulation model based on computational fluid dynamics with a variational autoencoder with deep convolutional layers and a deep neural network surrogate model. The resulting two types of outcomes were transferred across each training environment in a platform called the process and accident interactive simulation engine using object linking and embedding technology. In the last step, an augmented virtual reality-based platform was attached to the process and accident interactive simulation engine, making communication between the control room and field operators possible in the proposed operator training system platform.

Potential Hazards Operator Training System Dynamic Process Simulation Computational Fluid Dynamics Variational Autoencoder with Deep Convolutional Neural Layers Augmented Virtual Reality

Maresh MM, The aftermath of a deadly explosion: A rhetorical analysis of crisis communication as employed by British Petroleum and Phillips Petroleum, in, Texas Tech University (2006).
Antonovsky A, Pollock C, Straker L, Human Factors, 56, 306 (2014)
Kletz TA, Process Saf. Prog., 17(3), 196 (1998)
Naqvi SAM, Raza M, Ghazal S, Salehi S, Kang Z, Teodoriu C, Process Saf. Environ. Prot., 138, 220 (2020)
Ahmad Z, Patle DS, Rangaiah GP, Process Saf. Environ. Protect., 99, 55 (2016)
Marcano L, Haugen FA, Sannerud R, Komulainen T, Saf. Sci., 115, 414 (2019)
Morgan S, Sendelbach S, Stewart W, Hydrocarbon processing, United States (1994).
Rutherford P, Persad W, Lauritsen M, Hydrocarbon processing, United Sates (2003).
Siminovich C, Joao S, Procedia Eng., 83, 215 (2014)
Yang SH, Yang L, He CH, Process Saf. Environ. Prot., 79, 329 (2001)
Carvalho PV, et al., Human Factors and Ergonomics in Manufacturing & Service Industries, 17, 43 (2007).
Cha M, Han S, Lee J, Choi B, Fire Saf. J., 50, 12 (2012)
Cibulka J, et al., Virtual Reality Simulators in the Process Industry, Linkoping University Electronic Press, pp.495 2018.
Manca D, Brambilla S, Colombo S, Adv. Eng. Software, 55, 1 (2013)
Hanna SR, Brown MJ, Camelli FE, Chan ST, Coirier WJ, et al., Bull. Am. Meteorol. Soc., 87, 1713 (2006)
Hanna SR, Hansen OR, Dharmavaram S, Atmos. Environ., 38, 4675 (2004)
Long KJ, Zajaczkowski FJ, Haupt SE, Peltier LJ, JCP, 4, 881 (2009)
Middha P, Hansen OR, Grune J, Kotchourko A, J. Hazard. Mater., 179(1-3), 84 (2010)
Palmer K, Realff M, Chem. Eng. Res. Des., 80(7), 773 (2002)
Chen T, Hadinoto K, Yan WJ, Ma YF, Comput. Chem. Eng., 35(3), 502 (2011)
Widodo A, Yang BS, Mechanical Systems and Signal Processing, 21, 2560 (2007).
Fauvel M, Chanussot J, Benediktsson JA, Pattern Recognition, 45, 381 (2012)
Udugama IA, Gargalo CL, Yamashita Y, Taube MA, Palazoglu A, Young BR, Gernaey KV, Kulahci M, Bayer C, Ind. Eng. Chem. Res., 59(34), 15283 (2020)
Kajero OT, Chen T, Yao Y, Chuang YC, Wong DSH, J. Taiwan Inst. Chem. Engineers, 73, 135 (2017)
Masci J, et al., Stacked convolutional auto-encoders for hierarchical feature extraction, in: International Conference on Artificial Neural Networks, Springer, 52 (2011).
Geng J, Fan J, Wang H, Ma X, Li B, Chen F, IEEE Geoscience and Remote Sensing Letters, 12, 2351 (2015).
Kingma DP, Welling M, Auto-encoding variational bayes, arXiv preprint arXiv:1312.6114 (2013).
Na J, Jeon K, Lee WB, Chem. Eng. Sci., 181, 68 (2018)
Geron A, Hands-on machine learning with Scikit-Learn and TensorFlow: concepts, tools, and techniques to build intelligent systems, O'Reilly, United States (2017).
Ioffe S, Szegedy C, Batch normalization: Accelerating deep network training by reducing internal covariate shift, arXiv preprint arXiv:1502.03167 (2015).
Kingma DP, Ba J, Adam: A method for stochastic optimization, arXiv preprint arXiv:1412.6980 (2014).
Yun DY, Seo SK, Zahid U, Lee CJ, Appl. Sci., 10, 4005 (2020)
Melhem GA, Saini R, Goodwin BM, Fluid Phase Equilib., 47, 189 (1989)
Stein M, Technometrics, 29, 143 (1987)
Maltby J, Phipps S, Singleton V, US Patent, 6,202,100 B1 (2001).
Witlox HW, Fernandez M, Harper M, Oke A, Stene J, Xu Y, J. Loss Prevent. Proc. Ind., 55, 457 (2018)
Geron A, Hands-on machine learning with Scikit-Learn, Keras, and TensorFlow: Concepts, tools, and techniques to build intelligent systems, O'Reilly, United States (2019).
Ko C, Risk Management of Chemical Processes Using Dynamic Simulation and CFD-based Surrogate Model Approach, in, Seoul National University (2020).