Abstract
Refrigeration cycles employed for process cooling in industrial settings are known to be very energy-intensive. With the rise in energy demand across the globe, it is imperative that these systems are monitored and optimised to improve thermal efficiency and minimise energy consumption. While process simulators have been widely employed for process monitoring of refrigeration systems for optimisation and “what-if” scenarios, it is generally not suitable for remote monitoring due to their high computational cost. This is where machine learning (ML) models stand out, as they can be executed up to several orders of magnitude quicker than their corresponding first principle simulation model. In this paper, a case study is presented for a two-stage refrigeration system that covers data management, hybrid modelling (combining process simulation and ML), optimisation and online deployment. This case study demonstrates the workflow for constructing a refrigeration system ML model and deploying it to an online monitoring and prediction dashboard. Five different ML algorithms, namely multivariate linear regression (MLR), regression trees (RTs), random forests (RFs), extreme gradient boosting (XGBoost) and artificial neural networks (ANNs) were tested and evaluated to determine the most suitable algorithm to represent the behaviour of the refrigeration system. The results have shown that the XGBoost algorithm outperformed the other four algorithms as demonstrated by the lowest mean absolute error (MAE) and root mean squared error (RMSE). A significant improvement in performance was achieved after the XGBoost model was optimised via hyperparameter tuning and displayed an 86.40% and 82.35% improvement in terms of the MAE and RMSE. The results obtained from this study serve as a good benchmark for future modelling of refrigeration systems with XGBoost.
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs41660-023-00367-2/MediaObjects/41660_2023_367_Fig1_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs41660-023-00367-2/MediaObjects/41660_2023_367_Fig2_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs41660-023-00367-2/MediaObjects/41660_2023_367_Fig3_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs41660-023-00367-2/MediaObjects/41660_2023_367_Fig4_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs41660-023-00367-2/MediaObjects/41660_2023_367_Fig5_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs41660-023-00367-2/MediaObjects/41660_2023_367_Fig6_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs41660-023-00367-2/MediaObjects/41660_2023_367_Fig7_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs41660-023-00367-2/MediaObjects/41660_2023_367_Fig8_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs41660-023-00367-2/MediaObjects/41660_2023_367_Fig9a_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs41660-023-00367-2/MediaObjects/41660_2023_367_Fig9b_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs41660-023-00367-2/MediaObjects/41660_2023_367_Fig10_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs41660-023-00367-2/MediaObjects/41660_2023_367_Fig11_HTML.png)
Similar content being viewed by others
Data Availability
All data needed for the work are reported in this paper.
References
Ahmadi MA, Bahadori A (2016) Prediction performance of natural gas dehydration units for water removal efficiency using a least-square support vector machine. Int J Ambient Energy 37(5):486–494
Banerjee P (2020) A guide on XGBoost hyperparameters tuning≫. In: kaggle.com. http://www.kaggle.com/code/prashant111/a-guide-on-xgboost-hyperparameters-tuning/notebook. Accessed 12/04/2022
Barkanyi A, Chovan T, Nemeth S, Abonyi J (2021) Modelling for digital twins—potential role of surrogate models. Processes 9(3):476
Bradley W, Kim J, Kilwein Z, Blakely L, Eydenberg M, Jalvin J, Laird C, Boukouvala F (2022) Perspectives on the integration between first-principles and data-driven modeling. Comput Chem Eng 166:107898
Breiman L (2001) Random forests. Mach Learn 45(1):5–32
Breiman L (2017) Classification and regression trees. Routledge
Chakraborty S, Bhattacharya S (2021) Application of XGBoost algorithm as a predictive tool in a CNC turning process. Rep Mech Eng 2(1):190–201
Chen T, Guestrin C (2016) Xgboost: A scalable tree boosting system. In Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining, pp 785–794
Dincer I, Rosen MA, Ahmadi P (2017) Optimization of energy systems. John Wiley & Sons
Eberly LE (2007) Multiple linear regression. Topics in Biostatistics 165–187
Egorov VV, Novakovskii AD, Zdrachek EA (2017) Modeling of the effect of diffusion processes on the response of ion-selective electrodes by the finite difference technique: Comparison of theory with experiment and critical evaluation. J Anal Chem 72:793–802
ExxonMobil (2022) Energy demand: three drivers. In: corporate.exxonmobil. url: https://corporate.exxonmobil.com/energy-and-innovation/outlook-for-energy/energy-demand (visited on 10/05/2022)
Hamid A, Hasan AH, Azhari SN, Harun Z, Putra ZA (2022) Hybrid modelling for remote process monitoring and optimisation. Digital Chemical Engineering 4:100044
IEA (2021) Net zero by 2050, IEA, Paris. https://www.iea.org/reports/net-zero-by-2050, License: CC BY 4.0
Karniadakis GE, Kevrekidis IG, Lu L, Perdikaris P, Wang S, Yang L (2021) Physics-informed machine learning. Nat Rev Phys 3(6):422–440
Kuhn M, Johnson K (2013) Applied predictive modeling, vol 26. Springer, New York, NY, p 13
Li F, Zhang J, Oko E, Wang M (2015) Modelling of a post-combustion CO2 capture process using neural networks. Fuel 151:156–163
McBride K, Sundmacher K (2019) Overview of surrogate modeling in chemical process engineering. Chemie Ingenieur Technik 91(3):228–239
Moghadasi M, Ozgoli HA, Farhani F (2021) A machine learning-based operational control framework for reducing energy consumption of an amine-based gas sweetening process. Int J Energy Res 45(1):1055–1068
Nawi NM, Atomi WH, Rehman MZ (2013) The effect of data pre-processing on optimized training of artificial neural networks. Procedia Technol 11:32–39
Olof SS (2018) A comparative study of black-box optimization algorithms for tuning of hyper- parameters in deep neural networks. Luleå University of Technology
Rathakrishnan V, Bt. Beddu, S. and Ahmed, A.N. (2022) Predicting compressive strength of high-performance concrete with high volume ground granulated blast-furnace slag replacement using boosting machine learning algorithms. Sci Rep 12(1):9539
Song W, Mahalec V, Long J, Yang M, Qian F (2020) Modeling the hydrocracking process with deep neural networks. Ind Eng Chem Res 59(7):3077–3090
Stump J (2021) Industry advancing unmanned platforms, remote operations. In: Offshore Magazine. www.offshore-mag.com. Accessed 10/31/2022
Timofeev R (2004) Classification and regression trees (CART) theory and applications. Humboldt University, Berlin, p 54
Venkatasubramanian V (2019) The promise of artificial intelligence in chemical engineering: is it here, finally? AIChE Journal 65(2):466–478
Yang L, Shami A (2020) On hyperparameter optimization of machine learning algorithms: theory and practice. Neurocomputing 415:295–316
Author information
Authors and Affiliations
Contributions
Conceptualization: Zulfan; data curation: Zulfan; formal analysis: Liew; investigation: Liew; methodology: Liew and Foo; project administration: Foo; software: Liew; supervision: Foo; validation: Liew; visualisation: Liew; writing—original draft: Liew; writing—review and editing: Foo and Zulfan.
Corresponding author
Ethics declarations
Competing Interests
One of the authors (DCY Foo) is the editor of this journal.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary Information
Below is the link to the electronic supplementary material.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Liew, J.Y.L., Foo, D.C.Y. & Putra, Z.A. Hybrid Modelling of a Two-Stage Refrigeration System. Process Integr Optim Sustain 8, 309–328 (2024). https://doi.org/10.1007/s41660-023-00367-2
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s41660-023-00367-2