Abstract
Process models are getting more detailed, thus computational costs are rising. For this reason, the main aim of process engineering is to provide effective and cost-efficient production processes. Computational methods are important for composing the field of process systems engineering. They are used in process design and simulation with the capability of modeling, prediction, and optimizing processes. Also, machine learning (ML) emerges for enhancing this capability with providing a solution by performing as surrogate models of complex relationships in processes. By this way, accurate and efficient process optimization is presented. In the paper, machine learning algorithms were used on data which is generated through the sampling of varied parts of an ethylene oxide (EO) process plant in Pyomo. The physical system being surrogate modeled is an ethylene oxide plug flow reactor. Also, it is evaluated for accuracy and speed of surrogate modeling for various ML algorithms and various sampling techniques which are random, stratified, latin hypercube.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Forrester, S., Sobester, A., Keane, A.: Engineering design optimization using surrogate modelling: a comparative study. Proc. Roy. Soc. A Math. Phys. Eng. Sci. 463, 3251–3269 (2007)
Sacks, J., Welch, W.J., Mitchell, T.J., Wynn, H.P.: Design and analysis of computer experiments. Stat. Sci. 4, 409–423 (1989)
Regis, K.R., Shoemaker, C.A.: Constrained global optimization of expensive black box functions using radial basis functions. J. Glob. Optim. 31, 153–171 (2005). https://doi.org/10.1007/s10898-004-0570-0
Forrester, A., Sobester, A., Keane, A.: A review of surrogate modeling and its applications in engineering. Proc. Roy. Soc. A Math. Phys. Eng. Sci. 463, 3257–3281 (2008)
Moghaddam, M., Behzadi, S., Yazdi, M.: A novel multi-objective mathematical model for optimizing the casting process. J. Manuf. Process. 46, 44–59 (2019)
Choudhary, A.K., Shankar, R.: Supply chain optimization: a literature review and future research directions. Int. J. Logist. Syst. Manag. 22(2), 139–164 (2015)
Suebnukarn, S., Rungreunganun, N., Khunnawutmanotham, N.: A conceptual model for enhancing service quality by operational optimization in the healthcare system. TQM J. 30(2), 170–185 (2018)
Nizami, A.S., et al.: Optimization of production of biogas from livestock manure for vehicular fuel in developing countries. Renew. Sustain. Energy Rev. 53, 51–57 (2016)
Haftka, R., Gurdal, Z.: Surrogate Modeling in Engineering Design: A Practical Guide. Wiley, Hoboken (1999)
Bandyopadhyay, S., Mahapatra, S.S., Ghosh, S.: Optimization of manufacturing processes: a review. Int. J. Adv. Manuf. Technol. (2011)
Rajkumar, R., Lui, J.C.S.: Machine learning applications in manufacturing. Proc. IEEE (2018)
Chen, X., Chen, Y., Wang, Y.: Predictive maintenance in manufacturing industry: a review of recent developments. IEEE Access (2020)
Raut, N.K., Bodhe, S.H.: Quality control in manufacturing using machine learning techniques: a review. Int. J. Mech. Prod. Eng. Res. Dev. (2019)
Krishnan, R., Kumar, K.: Machine learning for production process optimization: a review. IEEE Trans. Semicond. Manuf. (2020)
Rangaiah, G.P., Srinivasan, R.: Optimization in Chemical Engineering. Wiley, Hoboken (2014)
Edgar, T.F., Himmelblau, D.M., Lasdon, L.S.: Optimization of Chemical Processes. McGraw Hill Education (2019)
Bonilla, L.F., Grossmann, I.E.: Handbook of Optimization in the Chemical Industry. Springer, Heidelberg (2019)
Sundaramoorthy, R., Saravanan, S.: Role of machine learning and artificial intelligence in chemical engineering. Artificial Intelligence and Machine Learning in Industry 4.0, pp. 263–285 (2020)
Mohan, S., Srinivasan, R.: Applications of machine learning in chemical engineering. Chem. Eng. Sci. 214, 115462 (2020)
Mustapa, R.F., et al.: Educational building’s energy consumption independent variables analysis using linear regression model: a comparative study. In: 2023 IEEE 3rd International Conference in Power Engineering Applications (ICPEA), Putrajaya, Malaysia, pp. 202–207. IEEE (2023)
Sidabutar, M.M., Firmansyah, G.: Comparison of linear regression, neural net, and arima methods for sales prediction of instrumentation and control products in PT. Sarana instrument. J. Res. Soc. Sci. Econ. Manag. 2(08), 1694–1705 (2023)
Han, B., Zhang, S., Qin, L., Wang, X., Liu, Y., Li, Z.: Comparison of support vector machine, Gaussian process regression and decision tree models for energy consumption prediction of campus buildings. In: 8th International Conference on Hydraulic and Civil Engineering: Deep Space Intelligent Development and Utilization Forum (ICHCE), Xi’an, China, pp. 689–693 (2022)
Pallavi, M., Valsan, A.S., Thoufi, K.U.: Toxicity prediction in peptides and proteins using random forest, decision tree and logistic regression. In: International Conference on Futuristic Technologies (INCOFT), Belgaum, India, pp. 1–6 (2022)
Lahiri, S.K., Khalfe, N.: Process modeling and optimization of industrial ethylene oxide reactor by integrating support vector regression and genetic algorithm. Can. J. Chem. Eng. 87, 118–128 (2009)
Huang, B.M.: Surrogate modelling for process simulation and optimisation. Master thesis, Department of Chemical Engineering and Biotechnology, University of Cambridge, 14 May 2021
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Keremer, O., Malay, F.C., Deveci, B., Kirci, P., Unal, P. (2023). Optimisation of a Chemical Process by Using Machine Learning Algorithms with Surrogate Modeling. In: Younas, M., Awan, I., Grønli, TM. (eds) Mobile Web and Intelligent Information Systems. MobiWIS 2023. Lecture Notes in Computer Science, vol 13977. Springer, Cham. https://doi.org/10.1007/978-3-031-39764-6_13
Download citation
DOI: https://doi.org/10.1007/978-3-031-39764-6_13
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-39763-9
Online ISBN: 978-3-031-39764-6
eBook Packages: Computer ScienceComputer Science (R0)