Accurate departure from nucleate boiling ratio (DNBR) prediction using SIMCA’s partial least squares regression and clustering

Mohamed Y.M. Mohsen; Mohy Sabry; Wassim I. Shalaby; Tarek F. Nagla; A. Abdelghafar Galahom; Mohamed A.E. Abdel-Rahman

doi:10.1515/kern-2025-0015

Article

Accurate departure from nucleate boiling ratio (DNBR) prediction using SIMCA’s partial least squares regression and clustering

Mohamed Y.M. Mohsen , Mohy Sabry , Wassim I. Shalaby , Tarek F. Nagla , A. Abdelghafar Galahom and Mohamed A.E. Abdel-Rahman

Published/Copyright: April 10, 2025

Published by

Become an author with De Gruyter Brill

Submit Manuscript Author Information

From the journal Kerntechnik Volume 90 Issue 3

Abstract

Data prediction and classification are the cornerstones of modern data analysis, especially when it comes to enhancing operational safety in critical systems. The SIMCA software offers robust, scalable tools for these tasks, leveraging the partial least squares (PLS) method for both classification and regression. This study applied regression and classification analyses to a thermal-hydraulic dataset generated using the COBRA-IV code, focusing on the calculation of the Departure from Nucleate Boiling Ratio (DNBR). The dataset was categorized into two subsets: a steady-state random dataset and a transient dataset, incorporating scenarios such as Rod Cluster Control Assembly (RCCA) operations and Loss of Flow Rate Accidents (LOFA). The steady-state dataset was developed through the variation of five key features – power, flow rate, enthalpy rise peaking factor (F_ΔH), temperature, and pressure – and computing the corresponding DNBR for each case. Hyper parameter optimization was conducted to identify the optimal number of PLS components, ensuring comprehensive information retention across datasets. For each dataset, the PLS regression metrics, including variable importance in projection (VIP), R²X, R²Y, Q²Y, and PLS coefficients, were analyzed to evaluate the predictive accuracy and interpretability of the model. The results demonstrated a strong similarity with COBRA-IV outputs and confirmed the findings of prior work which employed artificial neural networks (ANNs). These outcomes highlight the reliability of PLS as a predictive tool and its potential for advancing the analysis of thermal-hydraulic datasets.

Keywords: SIMCA; DNBR; LOFA; RCCA; PLS; artificial neural network (ANN) technique

Corresponding author: Mohamed A.E. Abdel-Rahman, Nuclear Engineering Department, Military Technical College, Kobry El-kobbah, Cairo, Egypt; and Arab Academy of Science, Technology and Maritime Transport, College of Engineering and Technology, Smart Village, Giza, Egypt, E-mail: mabdelrahman@mtc.edu.eg

Research ethics: Not applicable.
Informed consent: Not applicable.
Author contributions: All authors have accepted responsibility for the entire content of this manuscript and approved its submission.
Use of Large Language Models, AI and Machine Learning Tools: None declared.
Conflict of interest: The authors state no conflict of interest.
Research funding: None declared.
Data availability: Not applicable.

Nomenclature

ANN: Artificial neural network
CHF: Critical heat flux
DNBR: Departure from nucleate boiling
F_ΔH: Enthalpy rise peaking factor
LOFA: Loss of flow accident
PLS: Partial least squar
RCCA: Rod cluster control assembly
VIP: variable importance in projection

Regression and classification metrics

R²X: Explained variance fraction for predictors
R²Y: Explained variance fraction for output
Q²Y: Predictive variance fraction

Principal component scores

t[1]: 1st principal component score
t[2]: 2nd principal component score
tPS [1]: 1st principal component predicted score
tPS [2]: 2nd principal component predicted score
W*c[1]: Variable loading on the 1st principal component
W*c[2]: Variable loading on the 2nd principal component

References

Ayodeji, A., Amidu, M.A., Olatubosun, S.A., Addad, Y., and Ahmed, H. (2022). Deep learning for safety assessment of nuclear power reactors: reliability, explainability, and research opportunities. Prog. Nucl. Energy 151: 104339, https://doi.org/10.1016/j.pnucene.2022.104339.Search in Google Scholar

Baek, W.-P., Kim, H.-C., and Chang, S.H. (1997). An independent assessment of Groeneveld et al.’s 1995 CHF look-up table. Nucl. Eng. Des. 178: 331–337, https://doi.org/10.1016/S0029-5493(97)00236-7.Search in Google Scholar

Groeneveld, D.C., Shan, J.Q., Vasić, A.Z., Leung, L.K.H., Durmayaz, A., Yang, J., Cheng, S.C., and Tanase, A. (2007). The 2006 CHF look-up table. Nucl. Eng. Des. 237: 1909–1922, https://doi.org/10.1016/j.nucengdes.2007.02.014.Search in Google Scholar

Jiang, B.T. and Zhao, F.Y. (2013). Particle swarm optimization-based least squares support vector regression for critical heat flux prediction. Ann. Nucl. Energy 53: 69–81, https://doi.org/10.1016/j.anucene.2012.09.020.Search in Google Scholar

Jiang, B.T., Zhou, J., Huang, X.B., and Wang, P.F. (2020). Prediction of critical heat flux using Gaussian process regression and ant colony optimization. Ann. Nucl. Energy 149: 107765, https://doi.org/10.1016/j.anucene.2020.107765.Search in Google Scholar

Jollife, I.T. and Cadima, J. (2016). Principal component analysis: a review and recent developments. Phil. Trans. R. Soc. A: Math. Phys. Eng. Sci. 374: 20150202, https://doi.org/10.1098/rsta.2015.0202.Search in Google Scholar PubMed PubMed Central

Kharbach, M., Mansouri, M.A., Taabouz, M., and Yu, H. (2023). Current application of advancing spectroscopy techniques in food analysis: data handling with chemometric approaches. Foods 12: 2753, https://doi.org/10.3390/foods12142753.Search in Google Scholar PubMed PubMed Central

Kim, H.-K., Lee, S.-H., and Chang, S.-H. (1993). Neural network model for estimating departure from nucleate boiling performance of a pressurized water reactor core. Nucl. Technol. 101: 111–122, https://doi.org/10.13182/nt93-a34773.Search in Google Scholar

Kim, D.S., Lee, S.W., and Na, M.G. (2011). Prediction of axial DNBR distribution in a hot fuel rod using support vector regression models. IEEE Trans. Nucl. Sci. 58: 2084–2090, https://doi.org/10.1109/tns.2011.2159738.Search in Google Scholar

Kirdar, A.O., Green, K.D., and Rathore, A.S. (2008). Application of multivariate data analysis for identification and successful resolution of a root cause for a bioprocessing application. Biotechnol. Prog. 24: 720–726, https://doi.org/10.1021/bp070384.Search in Google Scholar

Li, J., Huang, Y., Qiu, Y., Wang, S., Yang, Q., Wang, K., and Zhu, Y. (2025). Prediction of critical heat flux using different methods: a review from empirical correlations to the cutting-edge machine learning. Int. Commun. Heat Mass Tran. 160: 108362, https://doi.org/10.1016/j.icheatmasstransfer.2024.108362.Search in Google Scholar

Mohsen, M.Y.M. and Abdel-Rahman, M.A.E. (2021). Neutronics and both analytical and numerical solutions for the rod centered subchannel thermal-hydraulic model. Kerntechnik 86: 312–320, https://doi.org/10.1515/kern-2020-0040.Search in Google Scholar

Mohsen, M.Y.M., Soliman, A.Y., and Abdel-Rahman, M.A.E. (2020). Thermal-hydraulic and solid mechanics safety analysis for VVER-1000 reactor using analytical and CFD approaches. Prog. Nucl. Energy 130: 103568, https://doi.org/10.1016/j.pnucene.2020.103568.Search in Google Scholar

Mohsen, M.Y.M., Abdel-Rahman, M.A.E., and Galahom, A.A. (2021). Integrated analysis of VVER-1000 fuel assembly fueled with accident tolerant fuel (ATF) materials. Ann. Nucl. Energy 159: 108330, https://doi.org/10.1016/j.anucene.2021.108330.Search in Google Scholar

Mohsen, M.Y.M., Abdel-Rahman, M.A.E., Saffaa Hassan, M., and Abdelghafar Galahom, A. (2022). Searching for the most optimum burnable absorbers (BAs) for AP-1000 from the neutronic, thermal-hydraulic, and solid mechanics points of view. Nucl. Eng. Des. 391: 111728, https://doi.org/10.1016/j.nucengdes.2022.111728.Search in Google Scholar

Mohsen, M.Y.M., Nagla, T.F., Elsamahy, M., and Abdel-Rahman, M.A.E. (2023). Multivariate image analysis for core monitoring in PWRs. J. Phys.: Conf. Ser. 2616: 012059, https://doi.org/10.1088/1742-6596/2616/1/012059.Search in Google Scholar

Mohsen, M.Y.M., Al Meshari, M., Alzamil, Y., Alhammad, A., Alenazi, K., El-Taher, A., Nagla, T.F., and Abdel-Rahman, M.A.E. (2025). Leveraging machine learning for accurate DNBR prediction using python. Nucl. Eng. Technol. 57: 103532, https://doi.org/10.1016/j.net.2025.103532.Search in Google Scholar

Pomerantsev, A.L. and Rodionova, O.Y. (2020) 3.30 – Soft independent modeling by class analogy. In: Brown, S., Tauler, R., and Walczak, B. (Eds.). Comprehensive chemometrics, 2nd ed. Elsevier, Oxford.10.1016/B978-0-12-409547-2.14588-3Search in Google Scholar

Rohatgi, U., Godbole, C., Delipei, G., Wu, X., and Avramova, M. (2022) Machine learning-based prediction of departure from nucleate boiling power for the PSBT benchmark. In: Conference: Advances in thermal hydraulics (ATH 2022), Anaheim, CA, 6/12/2022 - 6/16/2022. Brookhaven National Lab. (BNL), Upton, NY (United States), United States.10.13182/T126-38128Search in Google Scholar

Sabry, M., Abed, N.S., Omar, A., El-Samrah, M.G., and Mohsen, M.Y.M. (2024). Feasibility of using mixed-oxide fuel for a pressurized water reactor instead of traditional UO2 fuel material. Nucl. Sci. Eng. 198: 1998–2012, https://doi.org/10.1080/00295639.2023.2284441.Search in Google Scholar

Su, G., Fukuda, K., Jia, D., and Morita, K. (2002). Application of an artificial neural network in reactor thermohydraulic problem: prediction of critical heat flux. J. Nucl. Sci. Technol. 39: 564–571, https://doi.org/10.1080/18811248.2002.9715235.Search in Google Scholar

Todreas, N.E. and Kazimi, M.S. (1990). Nuclear systems I: thermal hydraulic fundamentals. Hemisphere Publishing Co, New York.Search in Google Scholar

Tong, L.S. and Weisman, J. (1967). Heat transfer in water-cooled nuclear reactors. Nucl. Eng. Des. 6: 301–324, https://doi.org/10.1016/0029-5493(67)90111-2.Search in Google Scholar

Tong, L.S. and Weisman, J. (1972). Boiling crisis and critical heat flux (TID-25887). Technical Report, https://doi.org/10.2172/4629988.Search in Google Scholar

Tong, L.S. and Weisman, J. (1979). Thermal analysis of pressurized water reactors. American Nuclear Society, LaGrange Park, IL, United States.Search in Google Scholar

Wei, H., Su, G.H., Qiu, S.Z., Ni, W., and Yang, X. (2010). Applications of genetic neural network for prediction of critical heat flux. Int. J. Therm. Sci. 49: 143–152, https://doi.org/10.1016/j.ijthermalsci.2009.06.007.Search in Google Scholar

Wheeler, C.L., Stewart, C.W., Cena, R.J., Rowe, D.S., and Sutey, A.M. (1976). COBRA-IV-I: an interim version of COBRA for thermal-hydraulic analysis of rod bundle nuclear fuel elements and cores (BNWL-1962). Technical Report, Battelle Pacific Northwest Labs., Richland, WA (United States), https://doi.org/10.2172/7359476.Search in Google Scholar

Wheelock, Å.M. and Wheelock, C.E. (2013). Trials and tribulations of ‘omics data analysis: assessing quality of SIMCA-based multivariate models using examples from pulmonary medicine. Mol. BioSyst. 9: 2589–2596, https://doi.org/10.1039/c3mb70194h.Search in Google Scholar PubMed

Zhao, X., Shirvan, K., Salko, R.K., and Guo, F. (2020). On the prediction of critical heat flux using a physics-informed machine learning-aided framework. Appl. Therm. Eng. 164: 114540, https://doi.org/10.1016/j.applthermaleng.2019.114540.Search in Google Scholar

Zhao, X., Salko, R.K., and Shirvan, K. (2021). Improved departure from nucleate boiling prediction in rod bundles using a physics-informed machine learning-aided framework. Nucl. Eng. Des. 374: 111084, https://doi.org/10.1016/j.nucengdes.2021.111084.Search in Google Scholar

Received: 2025-02-10

Accepted: 2025-03-22

Published Online: 2025-04-10

Published in Print: 2025-06-26

You are currently not able to access this content.

Articles in the same Issue

https://doi.org/10.1515/kern-2025-0015

Keywords for this article

SIMCA; DNBR; LOFA; RCCA; PLS; artificial neural network (ANN) technique